system

Abstract

Provide a system. The present invention includes: a means for transmitting biometric data collected from a wearable device to a server; A means for creating and storing nutrition information in a database; Using a generative AI model that analyzes the collected biometric data and nutritional information to generate optimal meal plans for each individual user; a means for notifying a user of the generated meal menu on the user's terminal; A means of collecting user feedback and optimizing the generative AI model; and A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, improving the dietary habits of adults has become increasingly important, but optimizing one's own diet is difficult for many people who lead busy lives. In particular, the effort required to select nutritionally balanced meals according to an individual's health condition and physical activity level is a major obstacle. Therefore, there is a need to provide a system that suggests optimal meal menus based on an individual's health condition and physical activity. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: A system is provided that includes a means for transmitting biometric data collected from a wearable device to a server, a means for storing nutritional information in a database, a means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, a means for notifying the user of the generated meal menu on their device, and a means for collecting feedback from the user and optimizing the generative AI model. This makes it possible for even busy users to easily recommend nutritionally balanced meals that are suited to their health condition.

[0006] A "wearable device" is a device that is worn on the body and has the ability to measure and record biometric data (heart rate, number of steps, sleep time, etc.) in real time and transmit this data to an external server or device.

[0007] A "server" is a computer system that receives, stores, processes, and transmits data over a network. It is the central unit that stores and analyzes collected biometric and nutritional data.

[0008] "Biometric data" refers to data about the user's body that is collected by a wearable device, and includes information such as heart rate, number of steps, sleep time, and calorie consumption.

[0009] "Nutritional information" is data about the ingredients of a meal menu, and is detailed information including the values ​​of calories, protein, fat, carbohydrates, vitamins, and minerals.

[0010] "Database" means a system for storing and managing data in a structured format, allowing for the efficient storage, retrieval, and processing of nutritional and biological information.

[0011] A "generative AI model" is a model that uses machine learning and artificial intelligence techniques to analyze collected data and learn specific patterns and trends, and is used to suggest optimal meal menus to users.

[0012] "Feedback" refers to information about the user's impressions, satisfaction, and physical changes after actually using the proposed menu, and is data collected to improve the system's performance.

[0013] A "terminal" is an electronic device operated by a user, which acts as a relay point between the wearable terminal and the server, providing functions such as receiving notifications and inputting feedback. [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] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[0036] Program Overview

[0037] The system of the present invention consists of a wearable device, a server, and a user device. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and notifies the user's device of the results. It also collects feedback from users and optimizes the generative AI model.

[0038] Program processing

[0039] Data collection using wearable devices

[0040] The wearable device collects the following biometric data and transmits it to the server at regular intervals.

[0041] User steps

[0042] Heart rate

[0043] sleep time

[0044] Data storage and analysis by server

[0045] The server receives the biometric data sent from the wearable device and stores it in a database, and then compiles and stores the nutritional information of the buffet menu in a database.

[0046] Using generative AI models

[0047] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the model selects a nutritionally balanced buffet menu that is optimal for each user. For example, it suggests high-protein, low-calorie menus for active users.

[0048] Menu Notifications

[0049] The server notifies the user terminal of the generated optimal buffet menu, and the user can check and select the proposed menu on their own terminal.

[0050] Feedback collection and optimization

[0051] Users provide feedback on the proposed menu, including information such as satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback. This process further optimizes future menu suggestions.

[0052] Specific examples

[0053] Examples of data collection

[0054] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server.

[0055] Examples of data storage and analysis

[0056] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[0057] Menu notification example

[0058] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0059] Examples of feedback gathering and optimization

[0060] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server collects this feedback and tunes the generative AI model.

[0061] These processes allow users to have an efficient and healthy diet.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] While the user is wearing the device, it collects the following biometric data in real time: number of steps taken, heart rate, and sleep time, and stores the data in a buffer at regular intervals.

[0065] Step 2:

[0066] The device transmits the data stored in the buffer to the server at regular intervals. For example, all data is uploaded to the server at once at midnight every day.

[0067] Step 3:

[0068] The server receives the data sent from the device and stores it in a database for each user. The database stores biometric data in association with each user ID.

[0069] Step 4:

[0070] The server creates a database of nutritional information for the registered buffet menu items. Specifically, it inputs and stores detailed nutritional information for each menu item, such as calories, protein, fat, carbohydrates, vitamins, and minerals.

[0071] Step 5:

[0072] The server analyzes the collected biometric data and stored nutritional information using a generative AI model that incorporates the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over seven days) to select the optimal buffet menu.

[0073] Step 6:

[0074] Based on the analysis results, the server generates a buffet menu customized for each user, suggesting high-protein, low-calorie dishes for active users, for example.

[0075] Step 7:

[0076] The server notifies the user of the generated optimal buffet menu, and the user can check the proposed menu on their own device.

[0077] Step 8:

[0078] The user selects the suggested menu and eats the meal. After eating, the user enters feedback through the app, including information such as satisfaction level, taste rating, and physical reaction.

[0079] Step 9:

[0080] The server collects feedback from users and stores it in a database, whereby the collected feedback data is maintained as a feedback database.

[0081] Step 10:

[0082] The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be more personalized and better adapted to each individual's health status and preferences.

[0083] Example 1

[0084] 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."

[0085] In modern society, it is important to provide appropriate meal menus based on individual health conditions and lifestyle habits. However, existing systems mainly make suggestions based on general health indicators, and are limited in generating optimal meal menus based on individual lifestyles and biometric data. Furthermore, it is difficult to properly collect feedback from users and reflect it in future suggestions, and many systems currently cannot fully meet users' needs.

[0086] 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.

[0087] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, means for periodically transmitting biometric data acquired from the wearable device to the server, means for extracting and analyzing the biometric data and nutritional information stored in the database, and means for generating a nutritionally balanced meal menu based on the user's activity level. This allows for the provision of an optimal meal menu based on each user's biometric data and enables continuous menu optimization based on feedback.

[0088] A "wearable device" is an electronic device that has the function of collecting a user's biometric data and transmitting it to an external system.

[0089] "Biometric data" refers to information about the user's body, specifically data including the number of steps taken, heart rate, and sleep time.

[0090] A "server" is a centralized computer system that receives, stores, and analyzes data sent from outside.

[0091] A "database" is a system for efficiently storing, retrieving, and editing structured data.

[0092] "Nutrition information" refers to information about the ingredients, calories, and nutrient content of a particular meal menu.

[0093] A "generative AI model" is a model that uses machine learning algorithms to analyze data and generate optimal meal menus for individual users.

[0094] "Feedback" refers to information such as impressions, satisfaction, and physical changes provided by users after using the system.

[0095] A "user terminal" is an electronic device that can be directly operated by a user, and includes smartphones, tablets, etc.

[0096] "Analysis" is the process of processing collected data and extracting meaningful information and patterns.

[0097] "Notification" is the act of transmitting information from a server to a user terminal.

[0098] "Optimization" is the process of improving the performance of a generative AI model based on collected feedback.

[0099] MODE FOR CARRYING OUT THE INVENTION

[0100] The following describes in detail the mode for carrying out the present invention. The system of the present invention is mainly composed of a wearable device, a server, and a user terminal. Each device plays a specific role and provides an optimal meal menu for each user based on a generative AI model. The system also includes collecting feedback from users and optimizing the generative AI model.

[0101] Collecting biometric data using wearable devices

[0102] Wearable devices are equipped with numerous sensors that collect the user's biometric data (e.g., number of steps, heart rate, and sleep time) in real time. This data is automatically sent to a server at regular intervals. Specifically, wearable devices include a step sensor, a heart rate sensor, and a sleep monitoring sensor.

[0103] Data storage and analysis by server

[0104] The server receives the biometric data sent from the wearable device and stores it in a database. Examples of database management systems include MySQL (registered trademark) and PostgreSQL. The stored data is analyzed using a generative AI model. Machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch are used as generative AI models.

[0105] Menu generation using generative AI models

[0106] The server uses a generative AI model based on the stored biometric and nutritional data to generate a nutritionally balanced meal plan that is optimal for each user. For example, it suggests high-protein, low-calorie meals for active users.

[0107] Menu Notifications

[0108] The server then sends the generated optimal meal menu to the user's device (such as a smartphone or tablet). The notification is sent in the form of a push notification, and the user can check and select the suggested menu through the application.

[0109] Feedback collection and optimization

[0110] After eating, users provide feedback through the application, including information such as satisfaction with the meal, their thoughts, and changes in their body. The server analyzes this feedback and adjusts the parameters of the generative AI model, thereby optimizing future recommendations to be more personalized.

[0111] Specific examples

[0112] 1. Specific examples of data collection

[0113] The wearable device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server at midnight.

[0114] 2. Examples of Data Storage and Analysis

[0115] The server stores the received data in a database and analyzes the user data using a generative AI model. For example, the database contains the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.), and the generative AI model performs analysis based on this information.

[0116] 3. Example of menu notification

[0117] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details. The user checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0118] 4. Examples of Feedback Collection

[0119] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server uses this feedback to adjust the generative AI model and reflect it in the next menu suggestion.

[0120] Prompt Sentence Examples

[0121] Below are some example prompts that the system might use to make specific meal suggestions:

[0122] If a user walks 15,000 steps in a day, use that data to suggest a high-protein, low-calorie buffet menu.

[0123] As a result, the present invention provides a system that efficiently manages the user's health and provides optimal meal menus, thereby supporting the user in maintaining and improving their health.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] Data collection using wearable devices

[0127] Wearable devices collect biometric data from users. Specifically, a pedometer sensor measures the user's steps, a heart rate sensor measures the heart rate, and a sleep monitoring sensor measures the amount of sleep. The inputs are the user's movements and heart rate, and the wearable device records these data in real time. The output is the collected biometric data.

[0128] Step 2:

[0129] Sending data

[0130] The wearable device transmits the collected biometric data to a server at regular intervals. For example, a user's daily data is transmitted in batches at midnight every day. The input is the collected biometric data, which is transmitted to the server via network communication. The output is the biometric data received by the server.

[0131] Step 3:

[0132] Data storage by server

[0133] The server stores the received biometric data in a database. Specifically, it uses a database management system (e.g., MySQL or PostgreSQL). The received biometric data is input and recorded in the database. The output is the biometric data stored in the database.

[0134] Step 4:

[0135] Nutrition information database

[0136] The server stores the nutritional information of the buffet menu in a database. The input is the nutritional information of each menu item, which is registered in the database. The output is the nutritional information stored in the database.

[0137] Step 5:

[0138] Data analysis

[0139] The server retrieves the stored biometric and nutritional data and analyzes it using a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used here. The biometric and nutritional data are input, and these are combined and fed into the AI ​​model. The model performs the necessary calculations, and the output is the optimal meal plan for each user.

[0140] Step 6:

[0141] Menu generation

[0142] Based on the data analyzed by the generative AI model, a nutritionally balanced buffet menu optimal for each user is generated. For example, a high-protein, low-calorie menu is suggested for a user who exercises a lot. The input is the analysis results of the generative AI model, and specific menu suggestions are based on this. The output is the generated menu candidates.

[0143] Step 7:

[0144] Menu Notifications

[0145] The server notifies the user device of the generated optimal buffet menu. The input is the generated menu, and the server sends a push notification to the user device. The output is the menu information displayed on the user's smartphone or tablet.

[0146] Step 8:

[0147] Gathering feedback

[0148] The user provides feedback on the proposed menu. Specifically, after eating, the user submits feedback such as "The taste was good," "I was satisfied," and "The portion was large" through a form within the application. The input is the user's impressions and physical reactions, which are sent as feedback data. The output is the feedback data received by the server.

[0149] Step 9:

[0150] Model Optimization

[0151] The server analyzes the collected feedback data and optimizes the generative AI model. This allows menu suggestions to be further optimized individually from the next time onwards. The feedback data is used as input, and the parameters of the AI ​​model are adjusted based on this. The output is an optimized generative AI model.

[0152] Through these steps, the system can provide users with individually optimized buffet menus and support continuous health management.

[0153] (Application example 1)

[0154] 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."

[0155] Conventional food delivery services do not suggest meal menus based on the user's health status or exercise level, making it difficult for each user to select meals that take into account the optimal nutritional balance. Furthermore, they lack the functionality to quickly collect user feedback and reflect it in the next menu suggestion. This creates the issue of insufficient support for users to lead healthy lives while still being satisfied.

[0156] 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.

[0157] In this invention, the server includes a means for transmitting biometric data collected from the wearable device to the server, a means for creating and storing nutritional information in a database, a means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, a means for notifying the user of the generated meal menu to support delivery orders, and a means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to propose an optimal meal menu based on the user's health condition and exercise volume. Furthermore, by quickly incorporating feedback, a system can be provided that increases user satisfaction and supports continuous health management.

[0158] A "wearable device" is a device worn on the user's body that collects biometric data such as the number of steps taken, heart rate, and sleep time.

[0159] "Biometric data" refers to data obtained from the user's body, and primarily includes information such as the number of steps taken, heart rate, and sleep duration.

[0160] "Server" refers to a computer system for receiving, storing, and analyzing biometric data and nutritional information.

[0161] "Nutrition information" refers to data about the nutrients and calories contained in food or meal menus.

[0162] A "database" is an electronic information system that enables specific information to be systematically stored, managed, and searched.

[0163] "Generative AI model" refers to an artificial intelligence (AI) algorithm that analyzes biometric data and nutritional information to generate optimal meal plans for each individual user.

[0164] A "user terminal" is a device used by a user, such as a smartphone or personal computer, that notifies the user of the generated meal menu and places delivery orders.

[0165] "Notification" is the act of sending information or menu suggestions from the server to the user terminal.

[0166] "Delivery order" refers to the act of a user ordering a meal through a food delivery service based on a suggested meal menu.

[0167] "Feedback" refers to opinions and evaluations that users send to the server, such as their satisfaction with the meal menu, their impressions, and changes in their physical condition.

[0168] "Model optimization" refers to the process of improving the accuracy and performance of a generative AI model based on collected feedback.

[0169] MODE FOR CARRYING OUT THE INVENTION

[0170] Specific program processing and its explanation will be described below for an embodiment of the present invention. The system of the present invention is composed of a wearable terminal, a server, and a user terminal.

[0171] Data collection using wearable devices

[0172] Wearable devices collect biometric data from users. The main biometric data are the number of steps taken, heart rate, and sleep time. This data is sent to a server at regular intervals. Specific hardware used for this purpose includes smartwatches and fitness trackers.

[0173] Data storage and analysis by server

[0174] The server receives the biometric data sent from the wearable device and stores it in a database. It then compiles and stores the nutritional information in a database. To analyze the collected biometric data and nutritional information, the server uses a generative AI model. This model is a type of artificial intelligence (AI), and specific software such as TensorFlow and PyTorch are used.

[0175] Using generative AI models

[0176] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the generative AI model generates a nutritionally balanced meal menu that is optimal for each user. For example, it might suggest a high-protein, low-calorie menu for a user who exercises a lot. Below is an example of a prompt sentence.

[0177] Prompt Sentence Examples

[0178] User biometric data:

[0179] Steps: 12,000

[0180] Heart rate: 75 bpm

[0181] Sleep time: 6.5 hours

[0182] Use this information to create a nutritionally balanced menu.

[0183] Menu notifications and delivery orders

[0184] The server then notifies the user of the optimal meal menu that has been generated. The user can then check the proposed menu on their own device and place a delivery order. The user device can be a smartphone or personal computer.

[0185] Feedback collection and optimization

[0186] Users provide feedback on the proposed menu, including information such as their satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be further optimized and personalized.

[0187] For example, if a user walks 12,000 steps in a day, has an average heart rate of 75 bpm, and sleeps 6.5 hours, the generative AI model will use this information to suggest high-protein, low-calorie meals. For example, it might suggest "grilled chicken salad and a low-fat smoothie." The user can then review the suggestions on their smartphone and place a delivery order. After the meal, they can provide feedback, which will be reflected in future recommendations.

[0188] Through the above process, users are suggested optimal meal menus based on their health condition and exercise level, enabling them to live an efficient and healthy life.

[0189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0190] Step 1: Collecting biometric data using wearable devices

[0191] Wearable devices collect biometric data from users. Specifically, the device periodically measures data such as the number of steps taken, heart rate, and sleep time, and temporarily stores the data. The input is data related to the user's physical activity (number of steps taken, heart rate, and sleep time), and the output is a set of these data.

[0192] Step 2: Sending biometric data to the server

[0193] The device sends the collected biometric data to a server. Specifically, the device periodically uploads the data to the server via the Internet. At this time, the data is encrypted and transmitted securely. The input is the biometric data stored on the device, and the output is the data stored on the server.

[0194] Step 3: Data storage and analysis

[0195] The server stores the received biometric data in a database. It then creates a database of nutritional information and stores it in the same way. The input is biometric data and nutritional information, and the output is a database in which these data are stored. Specifically, a database management system such as "MySQL" or "PostgreSQL" is used.

[0196] Step 4: Generate the menu using a generative AI model

[0197] The server runs a generative AI model using biometric data and nutritional information stored in the database. This model generates an optimal meal plan based on the user's health status and activity level. The input is biometric data and nutritional information, and the output is a suggested meal plan. Specific operations include feeding data to the AI ​​model (e.g., using TensorFlow or PyTorch) and analyzing it.

[0198] Step 5: Creating and parsing prompt statements

[0199] The server creates a prompt based on the analysis results of the generative AI model and inputs it into the model. Specific examples of prompts are as follows:

[0200] Prompt Sentence Examples

[0201] User biometric data:

[0202] Steps: 12,000

[0203] Heart rate: 75 bpm

[0204] Sleep time: 6.5 hours

[0205] Use this information to create a nutritionally balanced menu.

[0206] The input is a prompt and the output is a generated meal menu, which the generative AI model analyzes and suggests the best meal options.

[0207] Step 6: Notification to user device and delivery order

[0208] The server notifies the user of the generated meal menu. The user receives the notification, checks the menu from the provided options, and places a delivery order. The input is the notification of the meal menu, and the output is the delivery order placed by the user. Specific operations include notification and order processing via a smartphone app or web app.

[0209] Step 7: Gather feedback

[0210] After eating, users provide feedback. Specifically, they use their device to send their satisfaction, impressions, physical reactions, etc. to the server. The input is the feedback provided by the user, and the output is the feedback data collected by the server.

[0211] Step 8: Optimizing the generative AI model

[0212] The server analyzes the collected feedback data and performs optimization to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model. Specific operations include adjusting the model parameters based on the feedback data to improve the accuracy of subsequent menu generation.

[0213] Through the above processing steps, the user is presented with an optimal meal menu based on their health condition and amount of exercise, enabling them to lead an efficient and healthy diet.

[0214] 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.

[0215] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[0216] Program Overview

[0217] The system of the present invention consists of a wearable device, a server, a user device, and an emotion engine. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and the emotion engine, and notifies the user's device of the results. In addition, by collecting feedback from users and optimizing the generative AI model, the system customizes the suggestions with even greater precision.

[0218] Program processing

[0219] Data collection using wearable devices

[0220] While the wearable device is worn by the user, it collects the following biometric data in real time and transmits it to a server at regular intervals.

[0221] User steps

[0222] Heart rate

[0223] sleep time

[0224] Data storage and analysis by server

[0225] The server receives the data sent from the wearable device and stores it in a database for each user. It then stores the nutritional information of the buffet menu in a database.

[0226] Using generative AI models

[0227] The server uses a generative AI model that analyzes the user's health indicators based on the stored biometric and nutritional data, and selects the optimal buffet menu based on the user's health indicators (e.g., daily activity, resting heart rate, average sleep time over seven days).

[0228] Using the Emotion Engine

[0229] The server uses an emotion engine that evaluates the user's emotional state through various emotion recognition technologies. The emotion engine analyzes the user's facial expressions, voice, and text, and recognizes and evaluates the user's emotional state in real time based on the results.

[0230] Menu generation and notification

[0231] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[0232] The user can view the proposed menu on their device and make their meal selection.

[0233] Feedback collection and optimization

[0234] After eating, users enter feedback through the app, including information such as satisfaction level, taste rating, changes in emotional state, and physical reactions.

[0235] The server collects user feedback and stores it in a database. Based on this feedback data, the generative AI model is optimized, and menu suggestions for future orders are further optimized individually.

[0236] Specific examples

[0237] Examples of data collection

[0238] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept for 7.5 hours, and sends this data to a server.

[0239] Examples of data storage and analysis

[0240] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[0241] Specific examples of using the Emotion Engine

[0242] The server uses an emotion engine to assess whether the user is feeling stressed based on collected facial expression data and voice tone. If the user is judged to be under high stress, the server suggests a menu containing foods that have a relaxing effect.

[0243] Menu notification example

[0244] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0245] Examples of feedback gathering and optimization

[0246] After eating, users provide feedback through the app, such as "It tasted good," "I was satisfied," "My stress was reduced," etc. The server collects this feedback and tunes the generative AI model and emotion engine.

[0247] These processes enable users to eat efficiently and healthily, and also provide meal suggestions tailored to individual emotional states.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] While the user is wearing the device, it collects real-time biometric data (number of steps, heart rate, and sleep time). Specifically, it measures data using an acceleration sensor and heart rate sensor and stores the data in a buffer at regular intervals.

[0251] Step 2:

[0252] The device sends the stored biometric data to the server at a set time each day, using Wi-Fi or Bluetooth to securely transfer the data.

[0253] Step 3:

[0254] The server receives the biometric data sent from the device and stores it in a database for each user. Specifically, it centrally manages each user's data using an SQL or NoSQL database.

[0255] Step 4:

[0256] The server stores the nutritional information of the buffet menu in a database. Detailed nutritional information such as calories, protein, fat, carbohydrates, vitamins, and minerals is recorded and saved for each menu item.

[0257] Step 5:

[0258] The server uses a generative AI model to analyze the stored biometric data and nutritional information. Specifically, it uses machine learning algorithms to select the optimal meal plan for each individual user. This process takes into account the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over a seven-day period).

[0259] Step 6:

[0260] The server uses an emotion engine to recognize and evaluate the user's emotional state. The emotion engine analyzes the user's facial expressions, voice, and text, and determines the user's emotional state in real time based on the results.

[0261] Step 7:

[0262] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[0263] Step 8:

[0264] The server then notifies the user of the optimal buffet menu, allowing them to view the proposed menu on their smartphone or computer.

[0265] Step 9:

[0266] The user selects the menu item for which they received a notification and provides feedback through the app after eating, including taste evaluation, satisfaction, and changes in emotional state (e.g., whether stress was reduced).

[0267] Step 10:

[0268] The server collects user feedback and stores it in a database. It then optimizes the generative AI model based on the collected feedback data, and further optimizes menu suggestions for future meals. During this process, the model is updated taking into account changes in the user's preferences and health status.

[0269] Example 2

[0270] 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."

[0271] In today's busy lifestyles, many people find it difficult to devote sufficient time to their own health and nutrition management. It is particularly challenging to provide customized meal recommendations based on individual biometric information and emotional state. It is also unrealistic to efficiently collect feedback on the extent to which the recommended meals contribute to the user's actual satisfaction and emotional state and reflect this feedback in future recommendations. Therefore, there is a need for a system that provides meal menus optimized for the user's health and emotional state.

[0272] 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.

[0273] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for using an emotion engine to analyze the user's emotional state, means for integrating the analysis results of the generative AI model and the emotion engine to generate an optimal meal menu, means for notifying the user's device of the generated meal menu, and means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to provide an optimal meal menu for each user based on the user's biometric data and emotion data, and to improve the accuracy of suggestions for future meals based on the feedback.

[0274] A "wearable terminal" is a device that can be worn by a user and has the function of collecting biometric data in real time and transmitting it to a server.

[0275] "Biometric data" refers to data for measuring the user's health condition, and examples include the number of steps taken, heart rate, and sleep time.

[0276] A "server" is a computer system for storing and analyzing collected biometric data.

[0277] "Nutritional information" refers to data about the nutrients contained in a meal menu, including, for example, calories, protein, and fat.

[0278] A "generative AI model" is an artificial intelligence model that analyzes a user's biometric data and nutritional information to generate the optimal meal menu for each individual user.

[0279] An "emotion engine" is a technology for analyzing a user's emotional state, and performs facial expression analysis, voice analysis, and text analysis.

[0280] A "database" is a system that systematically stores collected data and nutritional information so that it can be searched and retrieved as needed.

[0281] "Feedback" refers to the user evaluating the actual meal menu provided and providing information such as satisfaction and changes in emotional state.

[0282] "Optimization" refers to the process of improving the performance of the generative AI model based on feedback, thereby increasing the accuracy of meal menu suggestions from the next time onwards.

[0283] A "user terminal" is a device that can be operated by a user and that can check the meal menu notified by the server.

[0284] System configuration

[0285] The system of the present invention is composed of a wearable device, a server, a user device, and an emotion engine. These components work together to provide an optimal meal menu based on the user's health and emotional state.

[0286] Program processing flow

[0287] 1. Data Collection:

[0288] The wearable device collects biometric data such as the number of steps taken, heart rate, and sleep time of the user in real time, and periodically transmits this data to a server.

[0289] Example: A wearable device collects information such as the user's 15,000 steps in a day, their average heart rate is 72 bpm, and their sleep time is 7.5 hours, and sends this information to a server every 10 minutes.

[0290] 2. Data Retention:

[0291] The server stores the biometric data sent from the wearable device in a database for each user, and also registers the nutritional information of the buffet menu in the database.

[0292] Example: The server stores the biometric data described above in the record corresponding to the user ID and adds the nutritional information for "Grilled Chicken Salad" (250 kcal, 25 g protein, 10 g fat) to the database.

[0293] 3. Analysis of health indicators:

[0294] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators (daily activity, resting heart rate, and average sleep time over seven days).

[0295] Example: The server inputs data of the user's daily 15,000 steps, 72 bpm, and 7.5 hours into the generated AI model, and calculates health indicators based on this.

[0296] 4. Emotional state analysis:

[0297] The server uses an emotion engine to analyze the user's emotional state from facial expression data, voice tone, and text, and in particular evaluates whether the user is feeling stressed.

[0298] Example: The server determines from the user's facial expression data that the stress level is high because the user's brow is furrowed and the tone of the voice is low and unsettled.

[0299] 5. Generate the menu:

[0300] The server integrates the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user.

[0301] Example: If a generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and the emotion engine recognizes stress, it will also add relaxing herbal tea to the menu.

[0302] 6. Menu Notifications:

[0303] The server notifies the user terminal of the generated buffet menu, and the user can check the proposed menu on his or her own terminal.

[0304] Example: The server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea," and the user confirms this and makes a selection.

[0305] 7. Gathering Feedback:

[0306] After eating, users provide feedback via a dedicated app, including satisfaction, taste evaluation, changes in emotional state, and physical reactions.

[0307] Example: Users enter feedback into the app, such as "It tasted good," "I was satisfied," or "It reduced stress."

[0308] 8. Optimize the model:

[0309] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions.

[0310] Example: The server feeds user feedback data back into the generative AI model, learning that "Grilled Chicken Salad was very satisfying" and "Drinks with a relaxing effect were effective," and updating the model.

[0311] Prompt Sentence Examples

[0312] "The user's biometric data includes a heart rate of 72 bpm, daily activity of 15,000 steps, and 7.5 hours of sleep. Analysis by the emotion engine reveals that the stress level is high. Please recommend the best buffet menu based on this information."

[0313] In this way, by implementing the system of the present invention, it is possible to provide an optimal meal menu based on the user's health and emotional state, and to create a cycle of further optimization based on feedback.

[0314] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0315] Step 1:

[0316] Data collection:

[0317] The wearable device collects biometric data such as the user's steps, heart rate, and sleep time in real time. The data input is biometric data generated during the user's daily activities. This data is sent to the server at regular intervals. Specifically, the wearable device records that the user walked 15,000 steps in a day, their average heart rate was 72 bpm, and their sleep time was 7.5 hours, and sends this information to the server every 10 minutes. The sent data is used in the next step.

[0318] Step 2:

[0319] Data Retention:

[0320] The server receives the biometric data sent from the wearable device and stores it in a database for each user. The input data is the user's biometric data sent from the wearable device. The output is a database organized for each user. Specifically, the server stores data such as 15,000 steps, 72 bpm, and 7.5 hours in the record corresponding to the user ID. At the same time, it also adds nutritional information for the buffet menu (e.g., nutritional information for "Grilled Chicken Salad": 250 kcal, 25 g protein, 10 g fat) to the database.

[0321] Step 3:

[0322] Health indicator analysis:

[0323] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators. The input data is the user's biometric data. The output is the analyzed health indicators (e.g., daily activity level, resting heart rate, average sleep time over 7 days). Specifically, the server inputs the user's daily data of 15,000 steps, 72 bpm, and 7.5 hours into the generative AI model, and calculates the health indicators based on this data. The generative AI model then evaluates the user's health condition based on this data.

[0324] Step 4:

[0325] Emotional State Analysis:

[0326] The server uses an emotion engine to analyze the user's emotional state from their facial expression data, voice tone, and text. The input data is the user's facial expression data, voice tone, and text data. The output is the analyzed emotional state (e.g., stress level). Specifically, the server analyzes the user's facial expression data to determine whether the user has furrowed brows or a low, restless voice tone, and evaluates whether the user is feeling stressed. The emotion engine uses this information to determine the user's emotional state.

[0327] Step 5:

[0328] Generate the menu:

[0329] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user. The input data is health indicators and emotional state. The output is the optimal buffet menu. Specifically, the generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and if the emotion engine recognizes stress, it also adds relaxing herbal tea to the menu.

[0330] Step 6:

[0331] Menu Notifications:

[0332] The server notifies the user terminal of the generated buffet menu. The input data is the generated menu. The output is a notification to the user terminal. Specifically, the server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea", and the user confirms this. The process of the user selecting the menu is also included here.

[0333] Step 7:

[0334] Collecting feedback:

[0335] After eating, the user provides feedback such as satisfaction, taste evaluation, changes in emotional state, and physical reactions through a dedicated app. The input data is the user's feedback. The output is the feedback data stored on the server. Specifically, the user enters feedback such as "The taste was good," "I was satisfied," or "My stress was reduced" into the app and sends it to the server.

[0336] Step 8:

[0337] Model optimization:

[0338] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions. The input data is user feedback. The output is an optimized generative AI model and emotion engine. Specifically, the server feeds the user's feedback data back to the generative AI model, learning that "the Grilled Chicken Salad was very satisfying" and "drinks with a relaxing effect were effective," and updating the model to make future suggestions even more accurate.

[0339] (Application example 2)

[0340] 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."

[0341] In modern factories, managing employee health and optimizing work efficiency are important issues. The lack of a way to monitor employees' health and emotional state in real time and adjust their breaks and work accordingly can lead to health risks and reduced work efficiency. A system is needed to prevent employee stress and fatigue and optimize the work environment.

[0342] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for storing nutritional information in a database, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, and means for monitoring the health and emotional states of factory workers and generating suggestions to adjust breaks and work content. This makes it possible to manage employee health and optimize work efficiency.

[0343] A "wearable device" is a device used to collect a user's biometric data in real time.

[0344] "Biometric data" refers to data that indicates the user's health condition and physical performance, and specifically includes heart rate, number of steps taken, sleep time, etc.

[0345] The "server" is a central processing unit that receives and stores data sent from the wearable device and analyzes it.

[0346] "Nutrition information" refers to information about the calories and nutrients contained in a particular food or menu item.

[0347] A "database" is a system that can efficiently store and search large amounts of data.

[0348] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal suggestions.

[0349] "Notification" refers to the act of sending server-generated information or suggestions to a user's device to inform them.

[0350] "Feedback" refers to information collected from users, such as their impressions, evaluations, and physical reactions.

[0351] "Emotional state" is data used to evaluate the user's psychological state, and is obtained by analyzing facial expressions and voice.

[0352] "Break timing" refers to the time points within the factory where employees can take breaks at appropriate times.

[0353] "Work content" refers to the specific work tasks performed by an employee.

[0354] "Factory worker" refers to an employee who works in a factory.

[0355] "Work efficiency" is an indicator that shows how efficiently an employee can complete work within a certain amount of time.

[0356] A specific system configuration and processing procedure for an embodiment of the present invention will be described below.

[0357] The system of the present invention is composed of a wearable device, a server, a factory robot, a generative AI model, and an emotion engine. Each element and its processing content will be explained in detail below.

[0358] Data collection using wearable devices

[0359] While worn by the user, the wearable device collects real-time biometric data, including the number of steps taken, heart rate, and sleep time, and transmits this data to a server at regular intervals.

[0360] Data storage and analysis by server

[0361] The server receives the biometric data sent from the wearable device and stores it in a database for each user. It also stores nutritional information for meal menus in a database.

[0362] Using generative AI models

[0363] The server analyzes the stored biometric and nutritional data using a generative AI model, which takes into account the user's health indicators (e.g., daily activity level, heart rate, sleep duration, etc.) to generate optimal meal plans and also suggests adjustments to breaks and work schedules based on the factory worker's health and emotional state.

[0364] Using the Emotion Engine

[0365] The server evaluates the user's emotional state using an emotion engine, which recognizes and evaluates the user's emotional state in real time using facial expression analysis, voice analysis, and text analysis.

[0366] Proposal generation and notification

[0367] The server combines the analysis results of the generative AI model and the emotion engine to generate customized suggestions for each user. For example, for a user who is evaluated as having high stress, it may suggest a relaxing break or a change in work. These suggestions are then communicated to the user via the factory robot.

[0368] Feedback collection and optimization

[0369] After the user performs the suggested break or task, they provide feedback on the results. This feedback includes satisfaction, changes in emotional state, and work efficiency. The server collects this feedback and stores it in a database. The generative AI model is then optimized based on this feedback, improving the accuracy of future suggestions.

[0370] Specific examples

[0371] For example, suppose a factory worker walks 12,000 steps a day, has an average heart rate of 70 bpm, and sleeps for seven hours. This data is collected by a wearable device and sent to a server. The server then inputs this data into a generative AI model, analyzes it, and generates suggestions such as "take a 10-minute break" or "switch to less stressful work." These suggestions are notified to the user via a factory robot. The user then implements the suggestions and provides feedback, including their impressions and evaluation. The server then collects the feedback and optimizes the generative AI model.

[0372] Prompt Sentence Examples

[0373] "Analyze employee data, assess their health and emotions, and generate optimal break timing and work content suggestions. As a concrete example, what suggestions would be made if an employee took 12,000 steps, had a heart rate of 70 bpm, and got 7 hours of sleep?"

[0374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0375] Step 1:

[0376] A wearable device collects the user's biometric data (number of steps, heart rate, sleep time) in real time. The device transmits this data to a server at regular intervals. The input data is the user's biometric information, and the output is the biometric data transmitted to the server.

[0377] Step 2:

[0378] The server stores the biometric data received from the wearable device in a database for each user. The input is the biometric data sent from the wearable device, and the output is the biometric data stored in the database.

[0379] Step 3:

[0380] The server uses a generative AI model to analyze the databased nutritional information and stored biometric data. The generative AI model calculates the user's health indicators and generates optimal meal menus and rest suggestions. The input is the biometric data and nutritional information stored in the database, and the output is the generated suggestions.

[0381] Step 4:

[0382] The server evaluates the user's emotional state using an emotion engine. The emotion engine performs facial expression analysis, voice analysis, and text analysis, thereby evaluating the user's stress level and fatigue. The input is the user's facial expression, voice, and text data, and the output is the evaluated emotional state.

[0383] Step 5:

[0384] The server integrates the evaluation results of the generative AI model and the emotion engine to generate customized suggestions for break timing and work content for each user. The inputs are the output of the generative AI model and the evaluation results of the emotion engine, and the output is optimized suggestions.

[0385] Step 6:

[0386] The server notifies the user of the generated suggestions through the factory robot, which then prompts the user to take a break at an appropriate time. The input is the suggestion sent from the server, and the output is the notification of the suggestion to the user.

[0387] Step 7:

[0388] The user takes a break or performs a task based on the suggestions and provides feedback on the results. The feedback may include satisfaction, changes in emotional state, and work efficiency. The input is the user's execution result, and the output is the provided feedback.

[0389] Step 8:

[0390] The server collects feedback from users and stores it in a database. The collected feedback data is used to optimize the generative AI model. The input is the feedback from users, and the output is the optimization result reflected in the generative AI model.

[0391] 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.

[0392] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0393] 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.

[0394] [Second embodiment]

[0395] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0406] 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."

[0407] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[0408] Program Overview

[0409] The system of the present invention consists of a wearable device, a server, and a user device. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and notifies the user's device of the results. It also collects feedback from users and optimizes the generative AI model.

[0410] Program processing

[0411] Data collection using wearable devices

[0412] The wearable device collects the following biometric data and transmits it to the server at regular intervals.

[0413] User steps

[0414] Heart rate

[0415] sleep time

[0416] Data storage and analysis by server

[0417] The server receives the biometric data sent from the wearable device and stores it in a database, and then compiles and stores the nutritional information of the buffet menu in a database.

[0418] Using generative AI models

[0419] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the model selects a nutritionally balanced buffet menu that is optimal for each user. For example, it suggests high-protein, low-calorie menus for active users.

[0420] Menu Notifications

[0421] The server notifies the user terminal of the generated optimal buffet menu, and the user can check and select the proposed menu on their own terminal.

[0422] Feedback collection and optimization

[0423] Users provide feedback on the proposed menu, including information such as satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback. This process further optimizes future menu suggestions.

[0424] Specific examples

[0425] Examples of data collection

[0426] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server.

[0427] Examples of data storage and analysis

[0428] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[0429] Menu notification example

[0430] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0431] Examples of feedback gathering and optimization

[0432] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server collects this feedback and tunes the generative AI model.

[0433] These processes allow users to have an efficient and healthy diet.

[0434] The processing flow will be explained below.

[0435] Step 1:

[0436] While the user is wearing the device, it collects the following biometric data in real time: number of steps taken, heart rate, and sleep time, and stores the data in a buffer at regular intervals.

[0437] Step 2:

[0438] The device transmits the data stored in the buffer to the server at regular intervals. For example, all data is uploaded to the server at once at midnight every day.

[0439] Step 3:

[0440] The server receives the data sent from the device and stores it in a database for each user. The database stores biometric data in association with each user ID.

[0441] Step 4:

[0442] The server creates a database of nutritional information for the registered buffet menu items. Specifically, it inputs and stores detailed nutritional information for each menu item, such as calories, protein, fat, carbohydrates, vitamins, and minerals.

[0443] Step 5:

[0444] The server analyzes the collected biometric data and stored nutritional information using a generative AI model that incorporates the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over seven days) to select the optimal buffet menu.

[0445] Step 6:

[0446] Based on the analysis results, the server generates a buffet menu customized for each user, suggesting high-protein, low-calorie dishes for active users, for example.

[0447] Step 7:

[0448] The server notifies the user of the generated optimal buffet menu, and the user can check the proposed menu on their own device.

[0449] Step 8:

[0450] The user selects the suggested menu and eats the meal. After eating, the user enters feedback through the app, including information such as satisfaction level, taste rating, and physical reaction.

[0451] Step 9:

[0452] The server collects feedback from users and stores it in a database, whereby the collected feedback data is maintained as a feedback database.

[0453] Step 10:

[0454] The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be more personalized and better adapted to each individual's health status and preferences.

[0455] Example 1

[0456] 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."

[0457] In modern society, it is important to provide appropriate meal menus based on individual health conditions and lifestyle habits. However, existing systems mainly make suggestions based on general health indicators, and are limited in generating optimal meal menus based on individual lifestyles and biometric data. Furthermore, it is difficult to properly collect feedback from users and reflect it in future suggestions, and many systems currently cannot fully meet users' needs.

[0458] 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.

[0459] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, means for periodically transmitting biometric data acquired from the wearable device to the server, means for extracting and analyzing the biometric data and nutritional information stored in the database, and means for generating a nutritionally balanced meal menu based on the user's activity level. This allows for the provision of an optimal meal menu based on each user's biometric data and enables continuous menu optimization based on feedback.

[0460] A "wearable device" is an electronic device that has the function of collecting a user's biometric data and transmitting it to an external system.

[0461] "Biometric data" refers to information about the user's body, specifically data including the number of steps taken, heart rate, and sleep time.

[0462] A "server" is a centralized computer system that receives, stores, and analyzes data sent from outside.

[0463] A "database" is a system for efficiently storing, retrieving, and editing structured data.

[0464] "Nutrition information" refers to information about the ingredients, calories, and nutrient content of a particular meal menu.

[0465] A "generative AI model" is a model that uses machine learning algorithms to analyze data and generate optimal meal menus for individual users.

[0466] "Feedback" refers to information such as impressions, satisfaction, and physical changes provided by users after using the system.

[0467] A "user terminal" is an electronic device that can be directly operated by a user, and includes smartphones, tablets, etc.

[0468] "Analysis" is the process of processing collected data and extracting meaningful information and patterns.

[0469] "Notification" is the act of transmitting information from a server to a user terminal.

[0470] "Optimization" is the process of improving the performance of a generative AI model based on collected feedback.

[0471] MODE FOR CARRYING OUT THE INVENTION

[0472] The following describes in detail the mode for carrying out the present invention. The system of the present invention is mainly composed of a wearable device, a server, and a user terminal. Each device plays a specific role and provides an optimal meal menu for each user based on a generative AI model. The system also includes collecting feedback from users and optimizing the generative AI model.

[0473] Collecting biometric data using wearable devices

[0474] Wearable devices are equipped with numerous sensors that collect the user's biometric data (e.g., number of steps, heart rate, and sleep time) in real time. This data is automatically sent to a server at regular intervals. Specifically, wearable devices include a step sensor, a heart rate sensor, and a sleep monitoring sensor.

[0475] Data storage and analysis by server

[0476] The server receives the biometric data sent from the wearable device and stores it in a database. Examples of database management systems include MySQL and PostgreSQL. The stored data is analyzed using a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used for the generative AI model.

[0477] Menu generation using generative AI models

[0478] The server uses a generative AI model based on the stored biometric and nutritional data to generate a nutritionally balanced meal plan that is optimal for each user. For example, it suggests high-protein, low-calorie meals for active users.

[0479] Menu Notifications

[0480] The server then sends the generated optimal meal menu to the user's device (such as a smartphone or tablet). The notification is sent in the form of a push notification, and the user can check and select the suggested menu through the application.

[0481] Feedback collection and optimization

[0482] After eating, users provide feedback through the application, including information such as satisfaction with the meal, their thoughts, and changes in their body. The server analyzes this feedback and adjusts the parameters of the generative AI model, thereby optimizing future recommendations to be more personalized.

[0483] Specific examples

[0484] 1. Specific examples of data collection

[0485] The wearable device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server at midnight.

[0486] 2. Examples of Data Storage and Analysis

[0487] The server stores the received data in a database and analyzes the user data using a generative AI model. For example, the database contains the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.), and the generative AI model performs analysis based on this information.

[0488] 3. Example of menu notification

[0489] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details. The user checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0490] 4. Examples of Feedback Collection

[0491] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server uses this feedback to adjust the generative AI model and reflect it in the next menu suggestion.

[0492] Prompt Sentence Examples

[0493] Below are some example prompts that the system might use to make specific meal suggestions:

[0494] If a user walks 15,000 steps in a day, use that data to suggest a high-protein, low-calorie buffet menu.

[0495] As a result, the present invention provides a system that efficiently manages the user's health and provides optimal meal menus, thereby supporting the user in maintaining and improving their health.

[0496] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0497] Step 1:

[0498] Data collection using wearable devices

[0499] Wearable devices collect biometric data from users. Specifically, a pedometer sensor measures the user's steps, a heart rate sensor measures the heart rate, and a sleep monitoring sensor measures the amount of sleep. The inputs are the user's movements and heart rate, and the wearable device records these data in real time. The output is the collected biometric data.

[0500] Step 2:

[0501] Sending data

[0502] The wearable device transmits the collected biometric data to a server at regular intervals. For example, a user's daily data is transmitted in batches at midnight every day. The input is the collected biometric data, which is transmitted to the server via network communication. The output is the biometric data received by the server.

[0503] Step 3:

[0504] Data storage by server

[0505] The server stores the received biometric data in a database. Specifically, it uses a database management system (e.g., MySQL or PostgreSQL). The received biometric data is input and recorded in the database. The output is the biometric data stored in the database.

[0506] Step 4:

[0507] Nutrition information database

[0508] The server stores the nutritional information of the buffet menu in a database. The input is the nutritional information of each menu item, which is registered in the database. The output is the nutritional information stored in the database.

[0509] Step 5:

[0510] Data analysis

[0511] The server retrieves the stored biometric and nutritional data and analyzes it using a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used here. The biometric and nutritional data are input, and these are combined and fed into the AI ​​model. The model performs the necessary calculations, and the output is the optimal meal plan for each user.

[0512] Step 6:

[0513] Menu generation

[0514] Based on the data analyzed by the generative AI model, a nutritionally balanced buffet menu optimal for each user is generated. For example, a high-protein, low-calorie menu is suggested for a user who exercises a lot. The input is the analysis results of the generative AI model, and specific menu suggestions are based on this. The output is the generated menu candidates.

[0515] Step 7:

[0516] Menu Notifications

[0517] The server notifies the user device of the generated optimal buffet menu. The input is the generated menu, and the server sends a push notification to the user device. The output is the menu information displayed on the user's smartphone or tablet.

[0518] Step 8:

[0519] Gathering feedback

[0520] The user provides feedback on the proposed menu. Specifically, after eating, the user submits feedback such as "The taste was good," "I was satisfied," and "The portion was large" through a form within the application. The input is the user's impressions and physical reactions, which are sent as feedback data. The output is the feedback data received by the server.

[0521] Step 9:

[0522] Model Optimization

[0523] The server analyzes the collected feedback data and optimizes the generative AI model. This allows menu suggestions to be further optimized individually from the next time onwards. The feedback data is used as input, and the parameters of the AI ​​model are adjusted based on this. The output is an optimized generative AI model.

[0524] Through these steps, the system can provide users with individually optimized buffet menus and support continuous health management.

[0525] (Application example 1)

[0526] 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."

[0527] Conventional food delivery services do not suggest meal menus based on the user's health status or exercise level, making it difficult for each user to select meals that take into account the optimal nutritional balance. Furthermore, they lack the functionality to quickly collect user feedback and reflect it in the next menu suggestion. This creates the issue of insufficient support for users to lead healthy lives while still being satisfied.

[0528] 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.

[0529] In this invention, the server includes a means for transmitting biometric data collected from the wearable device to the server, a means for creating and storing nutritional information in a database, a means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, a means for notifying the user of the generated meal menu to support delivery orders, and a means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to propose an optimal meal menu based on the user's health condition and exercise volume. Furthermore, by quickly incorporating feedback, a system can be provided that increases user satisfaction and supports continuous health management.

[0530] A "wearable device" is a device worn on the user's body that collects biometric data such as the number of steps taken, heart rate, and sleep time.

[0531] "Biometric data" refers to data obtained from the user's body, and primarily includes information such as the number of steps taken, heart rate, and sleep duration.

[0532] "Server" refers to a computer system for receiving, storing, and analyzing biometric data and nutritional information.

[0533] "Nutrition information" refers to data about the nutrients and calories contained in food or meal menus.

[0534] A "database" is an electronic information system that enables specific information to be systematically stored, managed, and searched.

[0535] "Generative AI model" refers to an artificial intelligence (AI) algorithm that analyzes biometric data and nutritional information to generate optimal meal plans for each individual user.

[0536] A "user terminal" is a device used by a user, such as a smartphone or personal computer, that notifies the user of the generated meal menu and places delivery orders.

[0537] "Notification" is the act of sending information or menu suggestions from the server to the user terminal.

[0538] "Delivery order" refers to the act of a user ordering a meal through a food delivery service based on a suggested meal menu.

[0539] "Feedback" refers to opinions and evaluations that users send to the server, such as their satisfaction with the meal menu, their impressions, and changes in their physical condition.

[0540] "Model optimization" refers to the process of improving the accuracy and performance of a generative AI model based on collected feedback.

[0541] MODE FOR CARRYING OUT THE INVENTION

[0542] Specific program processing and its explanation will be described below for an embodiment of the present invention. The system of the present invention is composed of a wearable terminal, a server, and a user terminal.

[0543] Data collection using wearable devices

[0544] Wearable devices collect biometric data from users. The main biometric data are the number of steps taken, heart rate, and sleep time. This data is sent to a server at regular intervals. Specific hardware used for this purpose includes smartwatches and fitness trackers.

[0545] Data storage and analysis by server

[0546] The server receives the biometric data sent from the wearable device and stores it in a database. It then compiles and stores the nutritional information in a database. To analyze the collected biometric data and nutritional information, the server uses a generative AI model. This model is a type of artificial intelligence (AI), and specific software such as TensorFlow and PyTorch are used.

[0547] Using generative AI models

[0548] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the generative AI model generates a nutritionally balanced meal menu that is optimal for each user. For example, it might suggest a high-protein, low-calorie menu for a user who exercises a lot. Below is an example of a prompt sentence.

[0549] Prompt Sentence Examples

[0550] User biometric data:

[0551] Steps: 12,000

[0552] Heart rate: 75 bpm

[0553] Sleep time: 6.5 hours

[0554] Use this information to create a nutritionally balanced menu.

[0555] Menu notifications and delivery orders

[0556] The server then notifies the user of the optimal meal menu that has been generated. The user can then check the proposed menu on their own device and place a delivery order. The user device can be a smartphone or personal computer.

[0557] Feedback collection and optimization

[0558] Users provide feedback on the proposed menu, including information such as their satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be further optimized and personalized.

[0559] For example, if a user walks 12,000 steps in a day, has an average heart rate of 75 bpm, and sleeps 6.5 hours, the generative AI model will use this information to suggest high-protein, low-calorie meals. For example, it might suggest "grilled chicken salad and a low-fat smoothie." The user can then review the suggestions on their smartphone and place a delivery order. After the meal, they can provide feedback, which will be reflected in future recommendations.

[0560] Through the above process, users are suggested optimal meal menus based on their health condition and exercise level, enabling them to live an efficient and healthy life.

[0561] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0562] Step 1: Collecting biometric data using wearable devices

[0563] Wearable devices collect biometric data from users. Specifically, the device periodically measures data such as the number of steps taken, heart rate, and sleep time, and temporarily stores the data. The input is data related to the user's physical activity (number of steps taken, heart rate, and sleep time), and the output is a set of these data.

[0564] Step 2: Sending biometric data to the server

[0565] The device sends the collected biometric data to a server. Specifically, the device periodically uploads the data to the server via the Internet. At this time, the data is encrypted and transmitted securely. The input is the biometric data stored on the device, and the output is the data stored on the server.

[0566] Step 3: Data storage and analysis

[0567] The server stores the received biometric data in a database. It then creates a database of nutritional information and stores it in the same way. The input is biometric data and nutritional information, and the output is a database in which these data are stored. Specifically, a database management system such as "MySQL" or "PostgreSQL" is used.

[0568] Step 4: Generate the menu using a generative AI model

[0569] The server runs a generative AI model using biometric data and nutritional information stored in the database. This model generates an optimal meal plan based on the user's health status and activity level. The input is biometric data and nutritional information, and the output is a suggested meal plan. Specific operations include feeding data to the AI ​​model (e.g., using TensorFlow or PyTorch) and analyzing it.

[0570] Step 5: Creating and parsing prompt statements

[0571] The server creates a prompt based on the analysis results of the generative AI model and inputs it into the model. Specific examples of prompts are as follows:

[0572] Prompt Sentence Examples

[0573] User biometric data:

[0574] Steps: 12,000

[0575] Heart rate: 75 bpm

[0576] Sleep time: 6.5 hours

[0577] Use this information to create a nutritionally balanced menu.

[0578] The input is a prompt and the output is a generated meal menu, which the generative AI model analyzes and suggests the best meal options.

[0579] Step 6: Notification to user device and delivery order

[0580] The server notifies the user of the generated meal menu. The user receives the notification, checks the menu from the provided options, and places a delivery order. The input is the notification of the meal menu, and the output is the delivery order placed by the user. Specific operations include notification and order processing via a smartphone app or web app.

[0581] Step 7: Gather feedback

[0582] After eating, users provide feedback. Specifically, they use their device to send their satisfaction, impressions, physical reactions, etc. to the server. The input is the feedback provided by the user, and the output is the feedback data collected by the server.

[0583] Step 8: Optimizing the generative AI model

[0584] The server analyzes the collected feedback data and performs optimization to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model. Specific operations include adjusting the model parameters based on the feedback data to improve the accuracy of subsequent menu generation.

[0585] Through the above processing steps, the user is presented with an optimal meal menu based on their health condition and amount of exercise, enabling them to lead an efficient and healthy diet.

[0586] 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.

[0587] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[0588] Program Overview

[0589] The system of the present invention consists of a wearable device, a server, a user device, and an emotion engine. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and the emotion engine, and notifies the user's device of the results. In addition, by collecting feedback from users and optimizing the generative AI model, the system customizes the suggestions with even greater precision.

[0590] Program processing

[0591] Data collection using wearable devices

[0592] While the wearable device is worn by the user, it collects the following biometric data in real time and transmits it to a server at regular intervals.

[0593] User steps

[0594] Heart rate

[0595] sleep time

[0596] Data storage and analysis by server

[0597] The server receives the data sent from the wearable device and stores it in a database for each user. It then stores the nutritional information of the buffet menu in a database.

[0598] Using generative AI models

[0599] The server uses a generative AI model that analyzes the user's health indicators based on the stored biometric and nutritional data, and selects the optimal buffet menu based on the user's health indicators (e.g., daily activity, resting heart rate, average sleep time over seven days).

[0600] Using the Emotion Engine

[0601] The server uses an emotion engine that evaluates the user's emotional state through various emotion recognition technologies. The emotion engine analyzes the user's facial expressions, voice, and text, and recognizes and evaluates the user's emotional state in real time based on the results.

[0602] Menu generation and notification

[0603] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[0604] The user can view the proposed menu on their device and make their meal selection.

[0605] Feedback collection and optimization

[0606] After eating, users enter feedback through the app, including information such as satisfaction level, taste rating, changes in emotional state, and physical reactions.

[0607] The server collects user feedback and stores it in a database. Based on this feedback data, the generative AI model is optimized, and menu suggestions for future orders are further optimized individually.

[0608] Specific examples

[0609] Examples of data collection

[0610] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept for 7.5 hours, and sends this data to a server.

[0611] Examples of data storage and analysis

[0612] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[0613] Specific examples of using the Emotion Engine

[0614] The server uses an emotion engine to assess whether the user is feeling stressed based on collected facial expression data and voice tone. If the user is judged to be under high stress, the server suggests a menu containing foods that have a relaxing effect.

[0615] Menu notification example

[0616] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0617] Examples of feedback gathering and optimization

[0618] After eating, users provide feedback through the app, such as "It tasted good," "I was satisfied," "My stress was reduced," etc. The server collects this feedback and tunes the generative AI model and emotion engine.

[0619] These processes enable users to eat efficiently and healthily, and also provide meal suggestions tailored to individual emotional states.

[0620] The processing flow will be explained below.

[0621] Step 1:

[0622] While the user is wearing the device, it collects real-time biometric data (number of steps, heart rate, and sleep time). Specifically, it measures data using an acceleration sensor and heart rate sensor and stores the data in a buffer at regular intervals.

[0623] Step 2:

[0624] The device sends the stored biometric data to the server at a set time each day, using Wi-Fi or Bluetooth to securely transfer the data.

[0625] Step 3:

[0626] The server receives the biometric data sent from the device and stores it in a database for each user. Specifically, it centrally manages each user's data using an SQL or NoSQL database.

[0627] Step 4:

[0628] The server stores the nutritional information of the buffet menu in a database. Detailed nutritional information such as calories, protein, fat, carbohydrates, vitamins, and minerals is recorded and saved for each menu item.

[0629] Step 5:

[0630] The server uses a generative AI model to analyze the stored biometric data and nutritional information. Specifically, it uses machine learning algorithms to select the optimal meal plan for each individual user. This process takes into account the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over a seven-day period).

[0631] Step 6:

[0632] The server uses an emotion engine to recognize and evaluate the user's emotional state. The emotion engine analyzes the user's facial expressions, voice, and text, and determines the user's emotional state in real time based on the results.

[0633] Step 7:

[0634] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[0635] Step 8:

[0636] The server then notifies the user of the optimal buffet menu, allowing them to view the proposed menu on their smartphone or computer.

[0637] Step 9:

[0638] The user selects the menu item for which they received a notification and provides feedback through the app after eating, including taste evaluation, satisfaction, and changes in emotional state (e.g., whether stress was reduced).

[0639] Step 10:

[0640] The server collects user feedback and stores it in a database. It then optimizes the generative AI model based on the collected feedback data, and further optimizes menu suggestions for future meals. During this process, the model is updated taking into account changes in the user's preferences and health status.

[0641] Example 2

[0642] 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."

[0643] In today's busy lifestyles, many people find it difficult to devote sufficient time to their own health and nutrition management. It is particularly challenging to provide customized meal recommendations based on individual biometric information and emotional state. It is also unrealistic to efficiently collect feedback on the extent to which the recommended meals contribute to the user's actual satisfaction and emotional state and reflect this feedback in future recommendations. Therefore, there is a need for a system that provides meal menus optimized for the user's health and emotional state.

[0644] 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.

[0645] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for using an emotion engine to analyze the user's emotional state, means for integrating the analysis results of the generative AI model and the emotion engine to generate an optimal meal menu, means for notifying the user's device of the generated meal menu, and means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to provide an optimal meal menu for each user based on the user's biometric data and emotion data, and to improve the accuracy of suggestions for future meals based on the feedback.

[0646] A "wearable terminal" is a device that can be worn by a user and has the function of collecting biometric data in real time and transmitting it to a server.

[0647] "Biometric data" refers to data for measuring the user's health condition, and examples include the number of steps taken, heart rate, and sleep time.

[0648] A "server" is a computer system for storing and analyzing collected biometric data.

[0649] "Nutritional information" refers to data about the nutrients contained in a meal menu, including, for example, calories, protein, and fat.

[0650] A "generative AI model" is an artificial intelligence model that analyzes a user's biometric data and nutritional information to generate the optimal meal menu for each individual user.

[0651] An "emotion engine" is a technology for analyzing a user's emotional state, and performs facial expression analysis, voice analysis, and text analysis.

[0652] A "database" is a system that systematically stores collected data and nutritional information so that it can be searched and retrieved as needed.

[0653] "Feedback" refers to the user evaluating the actual meal menu provided and providing information such as satisfaction and changes in emotional state.

[0654] "Optimization" refers to the process of improving the performance of the generative AI model based on feedback, thereby increasing the accuracy of meal menu suggestions from the next time onwards.

[0655] A "user terminal" is a device that can be operated by a user and that can check the meal menu notified by the server.

[0656] System configuration

[0657] The system of the present invention is composed of a wearable device, a server, a user device, and an emotion engine. These components work together to provide an optimal meal menu based on the user's health and emotional state.

[0658] Program processing flow

[0659] 1. Data Collection:

[0660] The wearable device collects biometric data such as the number of steps taken, heart rate, and sleep time of the user in real time, and periodically transmits this data to a server.

[0661] Example: A wearable device collects information such as the user's 15,000 steps in a day, their average heart rate is 72 bpm, and their sleep time is 7.5 hours, and sends this information to a server every 10 minutes.

[0662] 2. Data Retention:

[0663] The server stores the biometric data sent from the wearable device in a database for each user, and also registers the nutritional information of the buffet menu in the database.

[0664] Example: The server stores the biometric data described above in the record corresponding to the user ID and adds the nutritional information for "Grilled Chicken Salad" (250 kcal, 25 g protein, 10 g fat) to the database.

[0665] 3. Analysis of health indicators:

[0666] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators (daily activity, resting heart rate, and average sleep time over seven days).

[0667] Example: The server inputs data of the user's daily 15,000 steps, 72 bpm, and 7.5 hours into the generated AI model, and calculates health indicators based on this.

[0668] 4. Emotional state analysis:

[0669] The server uses an emotion engine to analyze the user's emotional state from facial expression data, voice tone, and text, and in particular evaluates whether the user is feeling stressed.

[0670] Example: The server determines from the user's facial expression data that the stress level is high because the user's brow is furrowed and the tone of the voice is low and unsettled.

[0671] 5. Generate the menu:

[0672] The server integrates the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user.

[0673] Example: If a generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and the emotion engine recognizes stress, it will also add relaxing herbal tea to the menu.

[0674] 6. Menu Notifications:

[0675] The server notifies the user terminal of the generated buffet menu, and the user can check the proposed menu on his or her own terminal.

[0676] Example: The server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea," and the user confirms this and makes a selection.

[0677] 7. Gathering Feedback:

[0678] After eating, users provide feedback via a dedicated app, including satisfaction, taste evaluation, changes in emotional state, and physical reactions.

[0679] Example: Users enter feedback into the app, such as "It tasted good," "I was satisfied," or "It reduced stress."

[0680] 8. Optimize the model:

[0681] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions.

[0682] Example: The server feeds user feedback data back into the generative AI model, learning that "Grilled Chicken Salad was very satisfying" and "Drinks with a relaxing effect were effective," and updating the model.

[0683] Prompt Sentence Examples

[0684] "The user's biometric data includes a heart rate of 72 bpm, daily activity of 15,000 steps, and 7.5 hours of sleep. Analysis by the emotion engine reveals that the stress level is high. Please recommend the best buffet menu based on this information."

[0685] In this way, by implementing the system of the present invention, it is possible to provide an optimal meal menu based on the user's health and emotional state, and to create a cycle of further optimization based on feedback.

[0686] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0687] Step 1:

[0688] Data collection:

[0689] The wearable device collects biometric data such as the user's steps, heart rate, and sleep time in real time. The data input is biometric data generated during the user's daily activities. This data is sent to the server at regular intervals. Specifically, the wearable device records that the user walked 15,000 steps in a day, their average heart rate was 72 bpm, and their sleep time was 7.5 hours, and sends this information to the server every 10 minutes. The sent data is used in the next step.

[0690] Step 2:

[0691] Data Retention:

[0692] The server receives the biometric data sent from the wearable device and stores it in a database for each user. The input data is the user's biometric data sent from the wearable device. The output is a database organized for each user. Specifically, the server stores data such as 15,000 steps, 72 bpm, and 7.5 hours in the record corresponding to the user ID. At the same time, it also adds nutritional information for the buffet menu (e.g., nutritional information for "Grilled Chicken Salad": 250 kcal, 25 g protein, 10 g fat) to the database.

[0693] Step 3:

[0694] Health indicator analysis:

[0695] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators. The input data is the user's biometric data. The output is the analyzed health indicators (e.g., daily activity level, resting heart rate, average sleep time over 7 days). Specifically, the server inputs the user's daily data of 15,000 steps, 72 bpm, and 7.5 hours into the generative AI model, and calculates the health indicators based on this data. The generative AI model then evaluates the user's health condition based on this data.

[0696] Step 4:

[0697] Emotional State Analysis:

[0698] The server uses an emotion engine to analyze the user's emotional state from their facial expression data, voice tone, and text. The input data is the user's facial expression data, voice tone, and text data. The output is the analyzed emotional state (e.g., stress level). Specifically, the server analyzes the user's facial expression data to determine whether the user has furrowed brows or a low, restless voice tone, and evaluates whether the user is feeling stressed. The emotion engine uses this information to determine the user's emotional state.

[0699] Step 5:

[0700] Generate the menu:

[0701] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user. The input data is health indicators and emotional state. The output is the optimal buffet menu. Specifically, the generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and if the emotion engine recognizes stress, it also adds relaxing herbal tea to the menu.

[0702] Step 6:

[0703] Menu Notifications:

[0704] The server notifies the user terminal of the generated buffet menu. The input data is the generated menu. The output is a notification to the user terminal. Specifically, the server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea", and the user confirms this. The process of the user selecting the menu is also included here.

[0705] Step 7:

[0706] Collecting feedback:

[0707] After eating, the user provides feedback such as satisfaction, taste evaluation, changes in emotional state, and physical reactions through a dedicated app. The input data is the user's feedback. The output is the feedback data stored on the server. Specifically, the user enters feedback such as "The taste was good," "I was satisfied," or "My stress was reduced" into the app and sends it to the server.

[0708] Step 8:

[0709] Model optimization:

[0710] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions. The input data is user feedback. The output is an optimized generative AI model and emotion engine. Specifically, the server feeds the user's feedback data back to the generative AI model, learning that "the Grilled Chicken Salad was very satisfying" and "drinks with a relaxing effect were effective," and updating the model to make future suggestions even more accurate.

[0711] (Application example 2)

[0712] 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."

[0713] In modern factories, managing employee health and optimizing work efficiency are important issues. The lack of a way to monitor employees' health and emotional state in real time and adjust their breaks and work accordingly can lead to health risks and reduced work efficiency. A system is needed to prevent employee stress and fatigue and optimize the work environment.

[0714] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for storing nutritional information in a database, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, and means for monitoring the health and emotional states of factory workers and generating suggestions to adjust breaks and work content. This makes it possible to manage employee health and optimize work efficiency.

[0715] A "wearable device" is a device used to collect a user's biometric data in real time.

[0716] "Biometric data" refers to data that indicates the user's health condition and physical performance, and specifically includes heart rate, number of steps taken, sleep time, etc.

[0717] The "server" is a central processing unit that receives and stores data sent from the wearable device and analyzes it.

[0718] "Nutrition information" refers to information about the calories and nutrients contained in a particular food or menu item.

[0719] A "database" is a system that can efficiently store and search large amounts of data.

[0720] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal suggestions.

[0721] "Notification" refers to the act of sending server-generated information or suggestions to a user's device to inform them.

[0722] "Feedback" refers to information collected from users, such as their impressions, evaluations, and physical reactions.

[0723] "Emotional state" is data used to evaluate the user's psychological state, and is obtained by analyzing facial expressions and voice.

[0724] "Break timing" refers to the time points within the factory where employees can take breaks at appropriate times.

[0725] "Work content" refers to the specific work tasks performed by an employee.

[0726] "Factory worker" refers to an employee who works in a factory.

[0727] "Work efficiency" is an indicator that shows how efficiently an employee can complete work within a certain amount of time.

[0728] A specific system configuration and processing procedure for an embodiment of the present invention will be described below.

[0729] The system of the present invention is composed of a wearable device, a server, a factory robot, a generative AI model, and an emotion engine. Each element and its processing content will be explained in detail below.

[0730] Data collection using wearable devices

[0731] While worn by the user, the wearable device collects real-time biometric data, including the number of steps taken, heart rate, and sleep time, and transmits this data to a server at regular intervals.

[0732] Data storage and analysis by server

[0733] The server receives the biometric data sent from the wearable device and stores it in a database for each user. It also stores nutritional information for meal menus in a database.

[0734] Using generative AI models

[0735] The server analyzes the stored biometric and nutritional data using a generative AI model, which takes into account the user's health indicators (e.g., daily activity level, heart rate, sleep duration, etc.) to generate optimal meal plans and also suggests adjustments to breaks and work schedules based on the factory worker's health and emotional state.

[0736] Using the Emotion Engine

[0737] The server evaluates the user's emotional state using an emotion engine, which recognizes and evaluates the user's emotional state in real time using facial expression analysis, voice analysis, and text analysis.

[0738] Proposal generation and notification

[0739] The server combines the analysis results of the generative AI model and the emotion engine to generate customized suggestions for each user. For example, for a user who is evaluated as having high stress, it may suggest a relaxing break or a change in work. These suggestions are then communicated to the user via the factory robot.

[0740] Feedback collection and optimization

[0741] After the user performs the suggested break or task, they provide feedback on the results. This feedback includes satisfaction, changes in emotional state, and work efficiency. The server collects this feedback and stores it in a database. The generative AI model is then optimized based on this feedback, improving the accuracy of future suggestions.

[0742] Specific examples

[0743] For example, suppose a factory worker walks 12,000 steps a day, has an average heart rate of 70 bpm, and sleeps for seven hours. This data is collected by a wearable device and sent to a server. The server then inputs this data into a generative AI model, analyzes it, and generates suggestions such as "take a 10-minute break" or "switch to less stressful work." These suggestions are notified to the user via a factory robot. The user then implements the suggestions and provides feedback, including their impressions and evaluation. The server then collects the feedback and optimizes the generative AI model.

[0744] Prompt Sentence Examples

[0745] "Analyze employee data, assess their health and emotions, and generate optimal break timing and work content suggestions. As a concrete example, what suggestions would be made if an employee took 12,000 steps, had a heart rate of 70 bpm, and got 7 hours of sleep?"

[0746] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0747] Step 1:

[0748] A wearable device collects the user's biometric data (number of steps, heart rate, sleep time) in real time. The device transmits this data to a server at regular intervals. The input data is the user's biometric information, and the output is the biometric data transmitted to the server.

[0749] Step 2:

[0750] The server stores the biometric data received from the wearable device in a database for each user. The input is the biometric data sent from the wearable device, and the output is the biometric data stored in the database.

[0751] Step 3:

[0752] The server uses a generative AI model to analyze the databased nutritional information and stored biometric data. The generative AI model calculates the user's health indicators and generates optimal meal menus and rest suggestions. The input is the biometric data and nutritional information stored in the database, and the output is the generated suggestions.

[0753] Step 4:

[0754] The server evaluates the user's emotional state using an emotion engine. The emotion engine performs facial expression analysis, voice analysis, and text analysis, thereby evaluating the user's stress level and fatigue. The input is the user's facial expression, voice, and text data, and the output is the evaluated emotional state.

[0755] Step 5:

[0756] The server integrates the evaluation results of the generative AI model and the emotion engine to generate customized suggestions for break timing and work content for each user. The inputs are the output of the generative AI model and the evaluation results of the emotion engine, and the output is optimized suggestions.

[0757] Step 6:

[0758] The server notifies the user of the generated suggestions through the factory robot, which then prompts the user to take a break at an appropriate time. The input is the suggestion sent from the server, and the output is the notification of the suggestion to the user.

[0759] Step 7:

[0760] The user takes a break or performs a task based on the suggestions and provides feedback on the results. The feedback may include satisfaction, changes in emotional state, and work efficiency. The input is the user's execution result, and the output is the provided feedback.

[0761] Step 8:

[0762] The server collects feedback from users and stores it in a database. The collected feedback data is used to optimize the generative AI model. The input is the feedback from users, and the output is the optimization result reflected in the generative AI model.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] [Third embodiment]

[0767] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0768] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0769] 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).

[0770] 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.

[0771] 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.

[0772] 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).

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[0780] Program Overview

[0781] The system of the present invention consists of a wearable device, a server, and a user device. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and notifies the user's device of the results. It also collects feedback from users and optimizes the generative AI model.

[0782] Program processing

[0783] Data collection using wearable devices

[0784] The wearable device collects the following biometric data and transmits it to the server at regular intervals.

[0785] User steps

[0786] Heart rate

[0787] sleep time

[0788] Data storage and analysis by server

[0789] The server receives the biometric data sent from the wearable device and stores it in a database, and then compiles and stores the nutritional information of the buffet menu in a database.

[0790] Using generative AI models

[0791] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the model selects a nutritionally balanced buffet menu that is optimal for each user. For example, it suggests high-protein, low-calorie menus for active users.

[0792] Menu Notifications

[0793] The server notifies the user terminal of the generated optimal buffet menu, and the user can check and select the proposed menu on their own terminal.

[0794] Feedback collection and optimization

[0795] Users provide feedback on the proposed menu, including information such as satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback. This process further optimizes future menu suggestions.

[0796] Specific examples

[0797] Examples of data collection

[0798] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server.

[0799] Examples of data storage and analysis

[0800] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[0801] Menu notification example

[0802] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0803] Examples of feedback gathering and optimization

[0804] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server collects this feedback and tunes the generative AI model.

[0805] These processes allow users to have an efficient and healthy diet.

[0806] The processing flow will be explained below.

[0807] Step 1:

[0808] While the user is wearing the device, it collects the following biometric data in real time: number of steps taken, heart rate, and sleep time, and stores the data in a buffer at regular intervals.

[0809] Step 2:

[0810] The device transmits the data stored in the buffer to the server at regular intervals. For example, all data is uploaded to the server at once at midnight every day.

[0811] Step 3:

[0812] The server receives the data sent from the device and stores it in a database for each user. The database stores biometric data in association with each user ID.

[0813] Step 4:

[0814] The server creates a database of nutritional information for the registered buffet menu items. Specifically, it inputs and stores detailed nutritional information for each menu item, such as calories, protein, fat, carbohydrates, vitamins, and minerals.

[0815] Step 5:

[0816] The server analyzes the collected biometric data and stored nutritional information using a generative AI model that incorporates the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over seven days) to select the optimal buffet menu.

[0817] Step 6:

[0818] Based on the analysis results, the server generates a buffet menu customized for each user, suggesting high-protein, low-calorie dishes for active users, for example.

[0819] Step 7:

[0820] The server notifies the user of the generated optimal buffet menu, and the user can check the proposed menu on their own device.

[0821] Step 8:

[0822] The user selects the suggested menu and eats the meal. After eating, the user enters feedback through the app, including information such as satisfaction level, taste rating, and physical reaction.

[0823] Step 9:

[0824] The server collects feedback from users and stores it in a database, whereby the collected feedback data is maintained as a feedback database.

[0825] Step 10:

[0826] The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be more personalized and better adapted to each individual's health status and preferences.

[0827] Example 1

[0828] 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."

[0829] In modern society, it is important to provide appropriate meal menus based on individual health conditions and lifestyle habits. However, existing systems mainly make suggestions based on general health indicators, and are limited in generating optimal meal menus based on individual lifestyles and biometric data. Furthermore, it is difficult to properly collect feedback from users and reflect it in future suggestions, and many systems currently cannot fully meet users' needs.

[0830] 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.

[0831] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, means for periodically transmitting biometric data acquired from the wearable device to the server, means for extracting and analyzing the biometric data and nutritional information stored in the database, and means for generating a nutritionally balanced meal menu based on the user's activity level. This allows for the provision of an optimal meal menu based on each user's biometric data and enables continuous menu optimization based on feedback.

[0832] A "wearable device" is an electronic device that has the function of collecting a user's biometric data and transmitting it to an external system.

[0833] "Biometric data" refers to information about the user's body, specifically data including the number of steps taken, heart rate, and sleep time.

[0834] A "server" is a centralized computer system that receives, stores, and analyzes data sent from outside.

[0835] A "database" is a system for efficiently storing, retrieving, and editing structured data.

[0836] "Nutrition information" refers to information about the ingredients, calories, and nutrient content of a particular meal menu.

[0837] A "generative AI model" is a model that uses machine learning algorithms to analyze data and generate optimal meal menus for individual users.

[0838] "Feedback" refers to information such as impressions, satisfaction, and physical changes provided by users after using the system.

[0839] A "user terminal" is an electronic device that can be directly operated by a user, and includes smartphones, tablets, etc.

[0840] "Analysis" is the process of processing collected data and extracting meaningful information and patterns.

[0841] "Notification" is the act of transmitting information from a server to a user terminal.

[0842] "Optimization" is the process of improving the performance of a generative AI model based on collected feedback.

[0843] MODE FOR CARRYING OUT THE INVENTION

[0844] The following describes in detail the mode for carrying out the present invention. The system of the present invention is mainly composed of a wearable device, a server, and a user terminal. Each device plays a specific role and provides an optimal meal menu for each user based on a generative AI model. The system also includes collecting feedback from users and optimizing the generative AI model.

[0845] Collecting biometric data using wearable devices

[0846] Wearable devices are equipped with numerous sensors that collect the user's biometric data (e.g., number of steps, heart rate, and sleep time) in real time. This data is automatically sent to a server at regular intervals. Specifically, wearable devices include a step sensor, a heart rate sensor, and a sleep monitoring sensor.

[0847] Data storage and analysis by server

[0848] The server receives the biometric data sent from the wearable device and stores it in a database. Examples of database management systems include MySQL and PostgreSQL. The stored data is analyzed using a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used for the generative AI model.

[0849] Menu generation using generative AI models

[0850] The server uses a generative AI model based on the stored biometric and nutritional data to generate a nutritionally balanced meal plan that is optimal for each user. For example, it suggests high-protein, low-calorie meals for active users.

[0851] Menu Notifications

[0852] The server then sends the generated optimal meal menu to the user's device (such as a smartphone or tablet). The notification is sent in the form of a push notification, and the user can check and select the suggested menu through the application.

[0853] Feedback collection and optimization

[0854] After eating, users provide feedback through the application, including information such as satisfaction with the meal, their thoughts, and changes in their body. The server analyzes this feedback and adjusts the parameters of the generative AI model, thereby optimizing future recommendations to be more personalized.

[0855] Specific examples

[0856] 1. Specific examples of data collection

[0857] The wearable device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server at midnight.

[0858] 2. Examples of Data Storage and Analysis

[0859] The server stores the received data in a database and analyzes the user data using a generative AI model. For example, the database contains the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.), and the generative AI model performs analysis based on this information.

[0860] 3. Example of menu notification

[0861] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details. The user checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0862] 4. Examples of Feedback Collection

[0863] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server uses this feedback to adjust the generative AI model and reflect it in the next menu suggestion.

[0864] Prompt Sentence Examples

[0865] Below are some example prompts that the system might use to make specific meal suggestions:

[0866] If a user walks 15,000 steps in a day, use that data to suggest a high-protein, low-calorie buffet menu.

[0867] As a result, the present invention provides a system that efficiently manages the user's health and provides optimal meal menus, thereby supporting the user in maintaining and improving their health.

[0868] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0869] Step 1:

[0870] Data collection using wearable devices

[0871] Wearable devices collect biometric data from users. Specifically, a pedometer sensor measures the user's steps, a heart rate sensor measures the heart rate, and a sleep monitoring sensor measures the amount of sleep. The inputs are the user's movements and heart rate, and the wearable device records these data in real time. The output is the collected biometric data.

[0872] Step 2:

[0873] Sending data

[0874] The wearable device transmits the collected biometric data to a server at regular intervals. For example, a user's daily data is transmitted in batches at midnight every day. The input is the collected biometric data, which is transmitted to the server via network communication. The output is the biometric data received by the server.

[0875] Step 3:

[0876] Data storage by server

[0877] The server stores the received biometric data in a database. Specifically, it uses a database management system (e.g., MySQL or PostgreSQL). The received biometric data is input and recorded in the database. The output is the biometric data stored in the database.

[0878] Step 4:

[0879] Nutrition information database

[0880] The server stores the nutritional information of the buffet menu in a database. The input is the nutritional information of each menu item, which is registered in the database. The output is the nutritional information stored in the database.

[0881] Step 5:

[0882] Data analysis

[0883] The server retrieves the stored biometric and nutritional data and analyzes it using a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used here. The biometric and nutritional data are input, and these are combined and fed into the AI ​​model. The model performs the necessary calculations, and the output is the optimal meal plan for each user.

[0884] Step 6:

[0885] Menu generation

[0886] Based on the data analyzed by the generative AI model, a nutritionally balanced buffet menu optimal for each user is generated. For example, a high-protein, low-calorie menu is suggested for a user who exercises a lot. The input is the analysis results of the generative AI model, and specific menu suggestions are based on this. The output is the generated menu candidates.

[0887] Step 7:

[0888] Menu Notifications

[0889] The server notifies the user device of the generated optimal buffet menu. The input is the generated menu, and the server sends a push notification to the user device. The output is the menu information displayed on the user's smartphone or tablet.

[0890] Step 8:

[0891] Gathering feedback

[0892] The user provides feedback on the proposed menu. Specifically, after eating, the user submits feedback such as "The taste was good," "I was satisfied," and "The portion was large" through a form within the application. The input is the user's impressions and physical reactions, which are sent as feedback data. The output is the feedback data received by the server.

[0893] Step 9:

[0894] Model Optimization

[0895] The server analyzes the collected feedback data and optimizes the generative AI model. This allows menu suggestions to be further optimized individually from the next time onwards. The feedback data is used as input, and the parameters of the AI ​​model are adjusted based on this. The output is an optimized generative AI model.

[0896] Through these steps, the system can provide users with individually optimized buffet menus and support continuous health management.

[0897] (Application example 1)

[0898] 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."

[0899] Conventional food delivery services do not suggest meal menus based on the user's health status or exercise level, making it difficult for each user to select meals that take into account the optimal nutritional balance. Furthermore, they lack the functionality to quickly collect user feedback and reflect it in the next menu suggestion. This creates the issue of insufficient support for users to lead healthy lives while still being satisfied.

[0900] 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.

[0901] In this invention, the server includes a means for transmitting biometric data collected from the wearable device to the server, a means for creating and storing nutritional information in a database, a means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, a means for notifying the user of the generated meal menu to support delivery orders, and a means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to propose an optimal meal menu based on the user's health condition and exercise volume. Furthermore, by quickly incorporating feedback, a system can be provided that increases user satisfaction and supports continuous health management.

[0902] A "wearable device" is a device worn on the user's body that collects biometric data such as the number of steps taken, heart rate, and sleep time.

[0903] "Biometric data" refers to data obtained from the user's body, and primarily includes information such as the number of steps taken, heart rate, and sleep duration.

[0904] "Server" refers to a computer system for receiving, storing, and analyzing biometric data and nutritional information.

[0905] "Nutrition information" refers to data about the nutrients and calories contained in food or meal menus.

[0906] A "database" is an electronic information system that enables specific information to be systematically stored, managed, and searched.

[0907] "Generative AI model" refers to an artificial intelligence (AI) algorithm that analyzes biometric data and nutritional information to generate optimal meal plans for each individual user.

[0908] A "user terminal" is a device used by a user, such as a smartphone or personal computer, that notifies the user of the generated meal menu and places delivery orders.

[0909] "Notification" is the act of sending information or menu suggestions from the server to the user terminal.

[0910] "Delivery order" refers to the act of a user ordering a meal through a food delivery service based on a suggested meal menu.

[0911] "Feedback" refers to opinions and evaluations that users send to the server, such as their satisfaction with the meal menu, their impressions, and changes in their physical condition.

[0912] "Model optimization" refers to the process of improving the accuracy and performance of a generative AI model based on collected feedback.

[0913] MODE FOR CARRYING OUT THE INVENTION

[0914] Specific program processing and its explanation will be described below for an embodiment of the present invention. The system of the present invention is composed of a wearable terminal, a server, and a user terminal.

[0915] Data collection using wearable devices

[0916] Wearable devices collect biometric data from users. The main biometric data are the number of steps taken, heart rate, and sleep time. This data is sent to a server at regular intervals. Specific hardware used for this purpose includes smartwatches and fitness trackers.

[0917] Data storage and analysis by server

[0918] The server receives the biometric data sent from the wearable device and stores it in a database. It then compiles and stores the nutritional information in a database. To analyze the collected biometric data and nutritional information, the server uses a generative AI model. This model is a type of artificial intelligence (AI), and specific software such as TensorFlow and PyTorch are used.

[0919] Using generative AI models

[0920] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the generative AI model generates a nutritionally balanced meal menu that is optimal for each user. For example, it might suggest a high-protein, low-calorie menu for a user who exercises a lot. Below is an example of a prompt sentence.

[0921] Prompt Sentence Examples

[0922] User biometric data:

[0923] Steps: 12,000

[0924] Heart rate: 75 bpm

[0925] Sleep time: 6.5 hours

[0926] Use this information to create a nutritionally balanced menu.

[0927] Menu notifications and delivery orders

[0928] The server then notifies the user of the optimal meal menu that has been generated. The user can then check the proposed menu on their own device and place a delivery order. The user device can be a smartphone or personal computer.

[0929] Feedback collection and optimization

[0930] Users provide feedback on the proposed menu, including information such as their satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be further optimized and personalized.

[0931] For example, if a user walks 12,000 steps in a day, has an average heart rate of 75 bpm, and sleeps 6.5 hours, the generative AI model will use this information to suggest high-protein, low-calorie meals. For example, it might suggest "grilled chicken salad and a low-fat smoothie." The user can then review the suggestions on their smartphone and place a delivery order. After the meal, they can provide feedback, which will be reflected in future recommendations.

[0932] Through the above process, users are suggested optimal meal menus based on their health condition and exercise level, enabling them to live an efficient and healthy life.

[0933] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0934] Step 1: Collecting biometric data using wearable devices

[0935] Wearable devices collect biometric data from users. Specifically, the device periodically measures data such as the number of steps taken, heart rate, and sleep time, and temporarily stores the data. The input is data related to the user's physical activity (number of steps taken, heart rate, and sleep time), and the output is a set of these data.

[0936] Step 2: Sending biometric data to the server

[0937] The device sends the collected biometric data to a server. Specifically, the device periodically uploads the data to the server via the Internet. At this time, the data is encrypted and transmitted securely. The input is the biometric data stored on the device, and the output is the data stored on the server.

[0938] Step 3: Data storage and analysis

[0939] The server stores the received biometric data in a database. It then creates a database of nutritional information and stores it in the same way. The input is biometric data and nutritional information, and the output is a database in which these data are stored. Specifically, a database management system such as "MySQL" or "PostgreSQL" is used.

[0940] Step 4: Generate the menu using a generative AI model

[0941] The server runs a generative AI model using biometric data and nutritional information stored in the database. This model generates an optimal meal plan based on the user's health status and activity level. The input is biometric data and nutritional information, and the output is a suggested meal plan. Specific operations include feeding data to the AI ​​model (e.g., using TensorFlow or PyTorch) and analyzing it.

[0942] Step 5: Creating and parsing prompt statements

[0943] The server creates a prompt based on the analysis results of the generative AI model and inputs it into the model. Specific examples of prompts are as follows:

[0944] Prompt Sentence Examples

[0945] User biometric data:

[0946] Steps: 12,000

[0947] Heart rate: 75 bpm

[0948] Sleep time: 6.5 hours

[0949] Use this information to create a nutritionally balanced menu.

[0950] The input is a prompt and the output is a generated meal menu, which the generative AI model analyzes and suggests the best meal options.

[0951] Step 6: Notification to user device and delivery order

[0952] The server notifies the user of the generated meal menu. The user receives the notification, checks the menu from the provided options, and places a delivery order. The input is the notification of the meal menu, and the output is the delivery order placed by the user. Specific operations include notification and order processing via a smartphone app or web app.

[0953] Step 7: Gather feedback

[0954] After eating, users provide feedback. Specifically, they use their device to send their satisfaction, impressions, physical reactions, etc. to the server. The input is the feedback provided by the user, and the output is the feedback data collected by the server.

[0955] Step 8: Optimizing the generative AI model

[0956] The server analyzes the collected feedback data and performs optimization to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model. Specific operations include adjusting the model parameters based on the feedback data to improve the accuracy of subsequent menu generation.

[0957] Through the above processing steps, the user is presented with an optimal meal menu based on their health condition and amount of exercise, enabling them to lead an efficient and healthy diet.

[0958] 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.

[0959] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[0960] Program Overview

[0961] The system of the present invention consists of a wearable device, a server, a user device, and an emotion engine. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and the emotion engine, and notifies the user's device of the results. In addition, by collecting feedback from users and optimizing the generative AI model, the system customizes the suggestions with even greater precision.

[0962] Program processing

[0963] Data collection using wearable devices

[0964] While the wearable device is worn by the user, it collects the following biometric data in real time and transmits it to a server at regular intervals.

[0965] User steps

[0966] Heart rate

[0967] sleep time

[0968] Data storage and analysis by server

[0969] The server receives the data sent from the wearable device and stores it in a database for each user. It then stores the nutritional information of the buffet menu in a database.

[0970] Using generative AI models

[0971] The server uses a generative AI model that analyzes the user's health indicators based on the stored biometric and nutritional data, and selects the optimal buffet menu based on the user's health indicators (e.g., daily activity, resting heart rate, average sleep time over seven days).

[0972] Using the Emotion Engine

[0973] The server uses an emotion engine that evaluates the user's emotional state through various emotion recognition technologies. The emotion engine analyzes the user's facial expressions, voice, and text, and recognizes and evaluates the user's emotional state in real time based on the results.

[0974] Menu generation and notification

[0975] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[0976] The user can view the proposed menu on their device and make their meal selection.

[0977] Feedback collection and optimization

[0978] After eating, users enter feedback through the app, including information such as satisfaction level, taste rating, changes in emotional state, and physical reactions.

[0979] The server collects user feedback and stores it in a database. Based on this feedback data, the generative AI model is optimized, and menu suggestions for future orders are further optimized individually.

[0980] Specific examples

[0981] Examples of data collection

[0982] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept for 7.5 hours, and sends this data to a server.

[0983] Examples of data storage and analysis

[0984] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[0985] Specific examples of using the Emotion Engine

[0986] The server uses an emotion engine to assess whether the user is feeling stressed based on collected facial expression data and voice tone. If the user is judged to be under high stress, the server suggests a menu containing foods that have a relaxing effect.

[0987] Menu notification example

[0988] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[0989] Examples of feedback gathering and optimization

[0990] After eating, users provide feedback through the app, such as "It tasted good," "I was satisfied," "My stress was reduced," etc. The server collects this feedback and tunes the generative AI model and emotion engine.

[0991] These processes enable users to eat efficiently and healthily, and also provide meal suggestions tailored to individual emotional states.

[0992] The processing flow will be explained below.

[0993] Step 1:

[0994] While the user is wearing the device, it collects real-time biometric data (number of steps, heart rate, and sleep time). Specifically, it measures data using an acceleration sensor and heart rate sensor and stores the data in a buffer at regular intervals.

[0995] Step 2:

[0996] The device sends the stored biometric data to the server at a set time each day, using Wi-Fi or Bluetooth to securely transfer the data.

[0997] Step 3:

[0998] The server receives the biometric data sent from the device and stores it in a database for each user. Specifically, it centrally manages each user's data using an SQL or NoSQL database.

[0999] Step 4:

[1000] The server stores the nutritional information of the buffet menu in a database. Detailed nutritional information such as calories, protein, fat, carbohydrates, vitamins, and minerals is recorded and saved for each menu item.

[1001] Step 5:

[1002] The server uses a generative AI model to analyze the stored biometric data and nutritional information. Specifically, it uses machine learning algorithms to select the optimal meal plan for each individual user. This process takes into account the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over a seven-day period).

[1003] Step 6:

[1004] The server uses an emotion engine to recognize and evaluate the user's emotional state. The emotion engine analyzes the user's facial expressions, voice, and text, and determines the user's emotional state in real time based on the results.

[1005] Step 7:

[1006] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[1007] Step 8:

[1008] The server then notifies the user of the optimal buffet menu, allowing them to view the proposed menu on their smartphone or computer.

[1009] Step 9:

[1010] The user selects the menu item for which they received a notification and provides feedback through the app after eating, including taste evaluation, satisfaction, and changes in emotional state (e.g., whether stress was reduced).

[1011] Step 10:

[1012] The server collects user feedback and stores it in a database. It then optimizes the generative AI model based on the collected feedback data, and further optimizes menu suggestions for future meals. During this process, the model is updated taking into account changes in the user's preferences and health status.

[1013] Example 2

[1014] 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."

[1015] In today's busy lifestyles, many people find it difficult to devote sufficient time to their own health and nutrition management. It is particularly challenging to provide customized meal recommendations based on individual biometric information and emotional state. It is also unrealistic to efficiently collect feedback on the extent to which the recommended meals contribute to the user's actual satisfaction and emotional state and reflect this feedback in future recommendations. Therefore, there is a need for a system that provides meal menus optimized for the user's health and emotional state.

[1016] 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.

[1017] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for using an emotion engine to analyze the user's emotional state, means for integrating the analysis results of the generative AI model and the emotion engine to generate an optimal meal menu, means for notifying the user's device of the generated meal menu, and means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to provide an optimal meal menu for each user based on the user's biometric data and emotion data, and to improve the accuracy of suggestions for future meals based on the feedback.

[1018] A "wearable terminal" is a device that can be worn by a user and has the function of collecting biometric data in real time and transmitting it to a server.

[1019] "Biometric data" refers to data for measuring the user's health condition, and examples include the number of steps taken, heart rate, and sleep time.

[1020] A "server" is a computer system for storing and analyzing collected biometric data.

[1021] "Nutritional information" refers to data about the nutrients contained in a meal menu, including, for example, calories, protein, and fat.

[1022] A "generative AI model" is an artificial intelligence model that analyzes a user's biometric data and nutritional information to generate the optimal meal menu for each individual user.

[1023] An "emotion engine" is a technology for analyzing a user's emotional state, and performs facial expression analysis, voice analysis, and text analysis.

[1024] A "database" is a system that systematically stores collected data and nutritional information so that it can be searched and retrieved as needed.

[1025] "Feedback" refers to the user evaluating the actual meal menu provided and providing information such as satisfaction and changes in emotional state.

[1026] "Optimization" refers to the process of improving the performance of the generative AI model based on feedback, thereby increasing the accuracy of meal menu suggestions from the next time onwards.

[1027] A "user terminal" is a device that can be operated by a user and that can check the meal menu notified by the server.

[1028] System configuration

[1029] The system of the present invention is composed of a wearable device, a server, a user device, and an emotion engine. These components work together to provide an optimal meal menu based on the user's health and emotional state.

[1030] Program processing flow

[1031] 1. Data Collection:

[1032] The wearable device collects biometric data such as the number of steps taken, heart rate, and sleep time of the user in real time, and periodically transmits this data to a server.

[1033] Example: A wearable device collects information such as the user's 15,000 steps in a day, their average heart rate is 72 bpm, and their sleep time is 7.5 hours, and sends this information to a server every 10 minutes.

[1034] 2. Data Retention:

[1035] The server stores the biometric data sent from the wearable device in a database for each user, and also registers the nutritional information of the buffet menu in the database.

[1036] Example: The server stores the biometric data described above in the record corresponding to the user ID and adds the nutritional information for "Grilled Chicken Salad" (250 kcal, 25 g protein, 10 g fat) to the database.

[1037] 3. Analysis of health indicators:

[1038] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators (daily activity, resting heart rate, and average sleep time over seven days).

[1039] Example: The server inputs data of the user's daily 15,000 steps, 72 bpm, and 7.5 hours into the generated AI model, and calculates health indicators based on this.

[1040] 4. Emotional state analysis:

[1041] The server uses an emotion engine to analyze the user's emotional state from facial expression data, voice tone, and text, and in particular evaluates whether the user is feeling stressed.

[1042] Example: The server determines from the user's facial expression data that the stress level is high because the user's brow is furrowed and the tone of the voice is low and unsettled.

[1043] 5. Generate the menu:

[1044] The server integrates the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user.

[1045] Example: If a generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and the emotion engine recognizes stress, it will also add relaxing herbal tea to the menu.

[1046] 6. Menu Notifications:

[1047] The server notifies the user terminal of the generated buffet menu, and the user can check the proposed menu on his or her own terminal.

[1048] Example: The server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea," and the user confirms this and makes a selection.

[1049] 7. Gathering Feedback:

[1050] After eating, users provide feedback via a dedicated app, including satisfaction, taste evaluation, changes in emotional state, and physical reactions.

[1051] Example: Users enter feedback into the app, such as "It tasted good," "I was satisfied," or "It reduced stress."

[1052] 8. Optimize the model:

[1053] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions.

[1054] Example: The server feeds user feedback data back into the generative AI model, learning that "Grilled Chicken Salad was very satisfying" and "Drinks with a relaxing effect were effective," and updating the model.

[1055] Prompt Sentence Examples

[1056] "The user's biometric data includes a heart rate of 72 bpm, daily activity of 15,000 steps, and 7.5 hours of sleep. Analysis by the emotion engine reveals that the stress level is high. Please recommend the best buffet menu based on this information."

[1057] In this way, by implementing the system of the present invention, it is possible to provide an optimal meal menu based on the user's health and emotional state, and to create a cycle of further optimization based on feedback.

[1058] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1059] Step 1:

[1060] Data collection:

[1061] The wearable device collects biometric data such as the user's steps, heart rate, and sleep time in real time. The data input is biometric data generated during the user's daily activities. This data is sent to the server at regular intervals. Specifically, the wearable device records that the user walked 15,000 steps in a day, their average heart rate was 72 bpm, and their sleep time was 7.5 hours, and sends this information to the server every 10 minutes. The sent data is used in the next step.

[1062] Step 2:

[1063] Data Retention:

[1064] The server receives the biometric data sent from the wearable device and stores it in a database for each user. The input data is the user's biometric data sent from the wearable device. The output is a database organized for each user. Specifically, the server stores data such as 15,000 steps, 72 bpm, and 7.5 hours in the record corresponding to the user ID. At the same time, it also adds nutritional information for the buffet menu (e.g., nutritional information for "Grilled Chicken Salad": 250 kcal, 25 g protein, 10 g fat) to the database.

[1065] Step 3:

[1066] Health indicator analysis:

[1067] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators. The input data is the user's biometric data. The output is the analyzed health indicators (e.g., daily activity level, resting heart rate, average sleep time over 7 days). Specifically, the server inputs the user's daily data of 15,000 steps, 72 bpm, and 7.5 hours into the generative AI model, and calculates the health indicators based on this data. The generative AI model then evaluates the user's health condition based on this data.

[1068] Step 4:

[1069] Emotional State Analysis:

[1070] The server uses an emotion engine to analyze the user's emotional state from their facial expression data, voice tone, and text. The input data is the user's facial expression data, voice tone, and text data. The output is the analyzed emotional state (e.g., stress level). Specifically, the server analyzes the user's facial expression data to determine whether the user has furrowed brows or a low, restless voice tone, and evaluates whether the user is feeling stressed. The emotion engine uses this information to determine the user's emotional state.

[1071] Step 5:

[1072] Generate the menu:

[1073] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user. The input data is health indicators and emotional state. The output is the optimal buffet menu. Specifically, the generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and if the emotion engine recognizes stress, it also adds relaxing herbal tea to the menu.

[1074] Step 6:

[1075] Menu Notifications:

[1076] The server notifies the user terminal of the generated buffet menu. The input data is the generated menu. The output is a notification to the user terminal. Specifically, the server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea", and the user confirms this. The process of the user selecting the menu is also included here.

[1077] Step 7:

[1078] Collecting feedback:

[1079] After eating, the user provides feedback such as satisfaction, taste evaluation, changes in emotional state, and physical reactions through a dedicated app. The input data is the user's feedback. The output is the feedback data stored on the server. Specifically, the user enters feedback such as "The taste was good," "I was satisfied," or "My stress was reduced" into the app and sends it to the server.

[1080] Step 8:

[1081] Model optimization:

[1082] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions. The input data is user feedback. The output is an optimized generative AI model and emotion engine. Specifically, the server feeds the user's feedback data back to the generative AI model, learning that "the Grilled Chicken Salad was very satisfying" and "drinks with a relaxing effect were effective," and updating the model to make future suggestions even more accurate.

[1083] (Application example 2)

[1084] 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."

[1085] In modern factories, managing employee health and optimizing work efficiency are important issues. The lack of a way to monitor employees' health and emotional state in real time and adjust their breaks and work accordingly can lead to health risks and reduced work efficiency. A system is needed to prevent employee stress and fatigue and optimize the work environment.

[1086] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for storing nutritional information in a database, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, and means for monitoring the health and emotional states of factory workers and generating suggestions to adjust breaks and work content. This makes it possible to manage employee health and optimize work efficiency.

[1087] A "wearable device" is a device used to collect a user's biometric data in real time.

[1088] "Biometric data" refers to data that indicates the user's health condition and physical performance, and specifically includes heart rate, number of steps taken, sleep time, etc.

[1089] The "server" is a central processing unit that receives and stores data sent from the wearable device and analyzes it.

[1090] "Nutrition information" refers to information about the calories and nutrients contained in a particular food or menu item.

[1091] A "database" is a system that can efficiently store and search large amounts of data.

[1092] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal suggestions.

[1093] "Notification" refers to the act of sending server-generated information or suggestions to a user's device to inform them.

[1094] "Feedback" refers to information collected from users, such as their impressions, evaluations, and physical reactions.

[1095] "Emotional state" is data used to evaluate the user's psychological state, and is obtained by analyzing facial expressions and voice.

[1096] "Break timing" refers to the time points within the factory where employees can take breaks at appropriate times.

[1097] "Work content" refers to the specific work tasks performed by an employee.

[1098] "Factory worker" refers to an employee who works in a factory.

[1099] "Work efficiency" is an indicator that shows how efficiently an employee can complete work within a certain amount of time.

[1100] A specific system configuration and processing procedure for an embodiment of the present invention will be described below.

[1101] The system of the present invention is composed of a wearable device, a server, a factory robot, a generative AI model, and an emotion engine. Each element and its processing content will be explained in detail below.

[1102] Data collection using wearable devices

[1103] While worn by the user, the wearable device collects real-time biometric data, including the number of steps taken, heart rate, and sleep time, and transmits this data to a server at regular intervals.

[1104] Data storage and analysis by server

[1105] The server receives the biometric data sent from the wearable device and stores it in a database for each user. It also stores nutritional information for meal menus in a database.

[1106] Using generative AI models

[1107] The server analyzes the stored biometric and nutritional data using a generative AI model, which takes into account the user's health indicators (e.g., daily activity level, heart rate, sleep duration, etc.) to generate optimal meal plans and also suggests adjustments to breaks and work schedules based on the factory worker's health and emotional state.

[1108] Using the Emotion Engine

[1109] The server evaluates the user's emotional state using an emotion engine, which recognizes and evaluates the user's emotional state in real time using facial expression analysis, voice analysis, and text analysis.

[1110] Proposal generation and notification

[1111] The server combines the analysis results of the generative AI model and the emotion engine to generate customized suggestions for each user. For example, for a user who is evaluated as having high stress, it may suggest a relaxing break or a change in work. These suggestions are then communicated to the user via the factory robot.

[1112] Feedback collection and optimization

[1113] After the user performs the suggested break or task, they provide feedback on the results. This feedback includes satisfaction, changes in emotional state, and work efficiency. The server collects this feedback and stores it in a database. The generative AI model is then optimized based on this feedback, improving the accuracy of future suggestions.

[1114] Specific examples

[1115] For example, suppose a factory worker walks 12,000 steps a day, has an average heart rate of 70 bpm, and sleeps for seven hours. This data is collected by a wearable device and sent to a server. The server then inputs this data into a generative AI model, analyzes it, and generates suggestions such as "take a 10-minute break" or "switch to less stressful work." These suggestions are notified to the user via a factory robot. The user then implements the suggestions and provides feedback, including their impressions and evaluation. The server then collects the feedback and optimizes the generative AI model.

[1116] Prompt Sentence Examples

[1117] "Analyze employee data, assess their health and emotions, and generate optimal break timing and work content suggestions. As a concrete example, what suggestions would be made if an employee took 12,000 steps, had a heart rate of 70 bpm, and got 7 hours of sleep?"

[1118] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1119] Step 1:

[1120] A wearable device collects the user's biometric data (number of steps, heart rate, sleep time) in real time. The device transmits this data to a server at regular intervals. The input data is the user's biometric information, and the output is the biometric data transmitted to the server.

[1121] Step 2:

[1122] The server stores the biometric data received from the wearable device in a database for each user. The input is the biometric data sent from the wearable device, and the output is the biometric data stored in the database.

[1123] Step 3:

[1124] The server uses a generative AI model to analyze the databased nutritional information and stored biometric data. The generative AI model calculates the user's health indicators and generates optimal meal menus and rest suggestions. The input is the biometric data and nutritional information stored in the database, and the output is the generated suggestions.

[1125] Step 4:

[1126] The server evaluates the user's emotional state using an emotion engine. The emotion engine performs facial expression analysis, voice analysis, and text analysis, thereby evaluating the user's stress level and fatigue. The input is the user's facial expression, voice, and text data, and the output is the evaluated emotional state.

[1127] Step 5:

[1128] The server integrates the evaluation results of the generative AI model and the emotion engine to generate customized suggestions for break timing and work content for each user. The inputs are the output of the generative AI model and the evaluation results of the emotion engine, and the output is optimized suggestions.

[1129] Step 6:

[1130] The server notifies the user of the generated suggestions through the factory robot, which then prompts the user to take a break at an appropriate time. The input is the suggestion sent from the server, and the output is the notification of the suggestion to the user.

[1131] Step 7:

[1132] The user takes a break or performs a task based on the suggestions and provides feedback on the results. The feedback may include satisfaction, changes in emotional state, and work efficiency. The input is the user's execution result, and the output is the provided feedback.

[1133] Step 8:

[1134] The server collects feedback from users and stores it in a database. The collected feedback data is used to optimize the generative AI model. The input is the feedback from users, and the output is the optimization result reflected in the generative AI model.

[1135] 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.

[1136] 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.

[1137] 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.

[1138] [Fourth embodiment]

[1139] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1140] 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.

[1141] 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).

[1142] 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.

[1143] 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.

[1144] 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).

[1145] 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.

[1146] 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.

[1147] 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.

[1148] 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.

[1149] 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.

[1150] 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.

[1151] 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."

[1152] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[1153] Program Overview

[1154] The system of the present invention consists of a wearable device, a server, and a user device. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and notifies the user's device of the results. It also collects feedback from users and optimizes the generative AI model.

[1155] Program processing

[1156] Data collection using wearable devices

[1157] The wearable device collects the following biometric data and transmits it to the server at regular intervals.

[1158] User steps

[1159] Heart rate

[1160] sleep time

[1161] Data storage and analysis by server

[1162] The server receives the biometric data sent from the wearable device and stores it in a database, and then compiles and stores the nutritional information of the buffet menu in a database.

[1163] Using generative AI models

[1164] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the model selects a nutritionally balanced buffet menu that is optimal for each user. For example, it suggests high-protein, low-calorie menus for active users.

[1165] Menu Notifications

[1166] The server notifies the user terminal of the generated optimal buffet menu, and the user can check and select the proposed menu on their own terminal.

[1167] Feedback collection and optimization

[1168] Users provide feedback on the proposed menu, including information such as satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback. This process further optimizes future menu suggestions.

[1169] Specific examples

[1170] Examples of data collection

[1171] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server.

[1172] Examples of data storage and analysis

[1173] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[1174] Menu notification example

[1175] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[1176] Examples of feedback gathering and optimization

[1177] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server collects this feedback and tunes the generative AI model.

[1178] These processes allow users to have an efficient and healthy diet.

[1179] The processing flow will be explained below.

[1180] Step 1:

[1181] While the user is wearing the device, it collects the following biometric data in real time: number of steps taken, heart rate, and sleep time, and stores the data in a buffer at regular intervals.

[1182] Step 2:

[1183] The device transmits the data stored in the buffer to the server at regular intervals. For example, all data is uploaded to the server at once at midnight every day.

[1184] Step 3:

[1185] The server receives the data sent from the device and stores it in a database for each user. The database stores biometric data in association with each user ID.

[1186] Step 4:

[1187] The server creates a database of nutritional information for the registered buffet menu items. Specifically, it inputs and stores detailed nutritional information for each menu item, such as calories, protein, fat, carbohydrates, vitamins, and minerals.

[1188] Step 5:

[1189] The server analyzes the collected biometric data and stored nutritional information using a generative AI model that incorporates the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over seven days) to select the optimal buffet menu.

[1190] Step 6:

[1191] Based on the analysis results, the server generates a buffet menu customized for each user, suggesting high-protein, low-calorie dishes for active users, for example.

[1192] Step 7:

[1193] The server notifies the user of the generated optimal buffet menu, and the user can check the proposed menu on their own device.

[1194] Step 8:

[1195] The user selects the suggested menu and eats the meal. After eating, the user enters feedback through the app, including information such as satisfaction level, taste rating, and physical reaction.

[1196] Step 9:

[1197] The server collects feedback from users and stores it in a database, whereby the collected feedback data is maintained as a feedback database.

[1198] Step 10:

[1199] The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be more personalized and better adapted to each individual's health status and preferences.

[1200] Example 1

[1201] 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."

[1202] In modern society, it is important to provide appropriate meal menus based on individual health conditions and lifestyle habits. However, existing systems mainly make suggestions based on general health indicators, and are limited in generating optimal meal menus based on individual lifestyles and biometric data. Furthermore, it is difficult to properly collect feedback from users and reflect it in future suggestions, and many systems currently cannot fully meet users' needs.

[1203] 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.

[1204] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, means for periodically transmitting biometric data acquired from the wearable device to the server, means for extracting and analyzing the biometric data and nutritional information stored in the database, and means for generating a nutritionally balanced meal menu based on the user's activity level. This allows for the provision of an optimal meal menu based on each user's biometric data and enables continuous menu optimization based on feedback.

[1205] A "wearable device" is an electronic device that has the function of collecting a user's biometric data and transmitting it to an external system.

[1206] "Biometric data" refers to information about the user's body, specifically data including the number of steps taken, heart rate, and sleep time.

[1207] A "server" is a centralized computer system that receives, stores, and analyzes data sent from outside.

[1208] A "database" is a system for efficiently storing, retrieving, and editing structured data.

[1209] "Nutrition information" refers to information about the ingredients, calories, and nutrient content of a particular meal menu.

[1210] A "generative AI model" is a model that uses machine learning algorithms to analyze data and generate optimal meal menus for individual users.

[1211] "Feedback" refers to information such as impressions, satisfaction, and physical changes provided by users after using the system.

[1212] A "user terminal" is an electronic device that can be directly operated by a user, and includes smartphones, tablets, etc.

[1213] "Analysis" is the process of processing collected data and extracting meaningful information and patterns.

[1214] "Notification" is the act of transmitting information from a server to a user terminal.

[1215] "Optimization" is the process of improving the performance of a generative AI model based on collected feedback.

[1216] MODE FOR CARRYING OUT THE INVENTION

[1217] The following describes in detail the mode for carrying out the present invention. The system of the present invention is mainly composed of a wearable device, a server, and a user terminal. Each device plays a specific role and provides an optimal meal menu for each user based on a generative AI model. The system also includes collecting feedback from users and optimizing the generative AI model.

[1218] Collecting biometric data using wearable devices

[1219] Wearable devices are equipped with numerous sensors that collect the user's biometric data (e.g., number of steps, heart rate, and sleep time) in real time. This data is automatically sent to a server at regular intervals. Specifically, wearable devices include a step sensor, a heart rate sensor, and a sleep monitoring sensor.

[1220] Data storage and analysis by server

[1221] The server receives the biometric data sent from the wearable device and stores it in a database. Examples of database management systems include MySQL and PostgreSQL. The stored data is analyzed using a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used for the generative AI model.

[1222] Menu generation using generative AI models

[1223] The server uses a generative AI model based on the stored biometric and nutritional data to generate a nutritionally balanced meal plan that is optimal for each user. For example, it suggests high-protein, low-calorie meals for active users.

[1224] Menu Notifications

[1225] The server then sends the generated optimal meal menu to the user's device (such as a smartphone or tablet). The notification is sent in the form of a push notification, and the user can check and select the suggested menu through the application.

[1226] Feedback collection and optimization

[1227] After eating, users provide feedback through the application, including information such as satisfaction with the meal, their thoughts, and changes in their body. The server analyzes this feedback and adjusts the parameters of the generative AI model, thereby optimizing future recommendations to be more personalized.

[1228] Specific examples

[1229] 1. Specific examples of data collection

[1230] The wearable device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept 7.5 hours, and sends this data to a server at midnight.

[1231] 2. Examples of Data Storage and Analysis

[1232] The server stores the received data in a database and analyzes the user data using a generative AI model. For example, the database contains the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.), and the generative AI model performs analysis based on this information.

[1233] 3. Example of menu notification

[1234] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details. The user checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[1235] 4. Examples of Feedback Collection

[1236] After eating, users provide feedback through the app, such as "The taste was good," "I was satisfied," and "The portion was large." The server uses this feedback to adjust the generative AI model and reflect it in the next menu suggestion.

[1237] Prompt Sentence Examples

[1238] Below are some example prompts that the system might use to make specific meal suggestions:

[1239] If a user walks 15,000 steps in a day, use that data to suggest a high-protein, low-calorie buffet menu.

[1240] As a result, the present invention provides a system that efficiently manages the user's health and provides optimal meal menus, thereby supporting the user in maintaining and improving their health.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] Data collection using wearable devices

[1244] Wearable devices collect biometric data from users. Specifically, a pedometer sensor measures the user's steps, a heart rate sensor measures the heart rate, and a sleep monitoring sensor measures the amount of sleep. The inputs are the user's movements and heart rate, and the wearable device records these data in real time. The output is the collected biometric data.

[1245] Step 2:

[1246] Sending data

[1247] The wearable device transmits the collected biometric data to a server at regular intervals. For example, a user's daily data is transmitted in batches at midnight every day. The input is the collected biometric data, which is transmitted to the server via network communication. The output is the biometric data received by the server.

[1248] Step 3:

[1249] Data storage by server

[1250] The server stores the received biometric data in a database. Specifically, it uses a database management system (e.g., MySQL or PostgreSQL). The received biometric data is input and recorded in the database. The output is the biometric data stored in the database.

[1251] Step 4:

[1252] Nutrition information database

[1253] The server stores the nutritional information of the buffet menu in a database. The input is the nutritional information of each menu item, which is registered in the database. The output is the nutritional information stored in the database.

[1254] Step 5:

[1255] Data analysis

[1256] The server retrieves the stored biometric and nutritional data and analyzes it using a generative AI model. Machine learning frameworks such as TensorFlow and PyTorch are used here. The biometric and nutritional data are input, and these are combined and fed into the AI ​​model. The model performs the necessary calculations, and the output is the optimal meal plan for each user.

[1257] Step 6:

[1258] Menu generation

[1259] Based on the data analyzed by the generative AI model, a nutritionally balanced buffet menu optimal for each user is generated. For example, a high-protein, low-calorie menu is suggested for a user who exercises a lot. The input is the analysis results of the generative AI model, and specific menu suggestions are based on this. The output is the generated menu candidates.

[1260] Step 7:

[1261] Menu Notifications

[1262] The server notifies the user device of the generated optimal buffet menu. The input is the generated menu, and the server sends a push notification to the user device. The output is the menu information displayed on the user's smartphone or tablet.

[1263] Step 8:

[1264] Gathering feedback

[1265] The user provides feedback on the proposed menu. Specifically, after eating, the user submits feedback such as "The taste was good," "I was satisfied," and "The portion was large" through a form within the application. The input is the user's impressions and physical reactions, which are sent as feedback data. The output is the feedback data received by the server.

[1266] Step 9:

[1267] Model Optimization

[1268] The server analyzes the collected feedback data and optimizes the generative AI model. This allows menu suggestions to be further optimized individually from the next time onwards. The feedback data is used as input, and the parameters of the AI ​​model are adjusted based on this. The output is an optimized generative AI model.

[1269] Through these steps, the system can provide users with individually optimized buffet menus and support continuous health management.

[1270] (Application example 1)

[1271] 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."

[1272] Conventional food delivery services do not suggest meal menus based on the user's health status or exercise level, making it difficult for each user to select meals that take into account the optimal nutritional balance. Furthermore, they lack the functionality to quickly collect user feedback and reflect it in the next menu suggestion. This creates the issue of insufficient support for users to lead healthy lives while still being satisfied.

[1273] 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.

[1274] In this invention, the server includes a means for transmitting biometric data collected from the wearable device to the server, a means for creating and storing nutritional information in a database, a means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, a means for notifying the user of the generated meal menu to support delivery orders, and a means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to propose an optimal meal menu based on the user's health condition and exercise volume. Furthermore, by quickly incorporating feedback, a system can be provided that increases user satisfaction and supports continuous health management.

[1275] A "wearable device" is a device worn on the user's body that collects biometric data such as the number of steps taken, heart rate, and sleep time.

[1276] "Biometric data" refers to data obtained from the user's body, and primarily includes information such as the number of steps taken, heart rate, and sleep duration.

[1277] "Server" refers to a computer system for receiving, storing, and analyzing biometric data and nutritional information.

[1278] "Nutrition information" refers to data about the nutrients and calories contained in food or meal menus.

[1279] A "database" is an electronic information system that enables specific information to be systematically stored, managed, and searched.

[1280] "Generative AI model" refers to an artificial intelligence (AI) algorithm that analyzes biometric data and nutritional information to generate optimal meal plans for each individual user.

[1281] A "user terminal" is a device used by a user, such as a smartphone or personal computer, that notifies the user of the generated meal menu and places delivery orders.

[1282] "Notification" is the act of sending information or menu suggestions from the server to the user terminal.

[1283] "Delivery order" refers to the act of a user ordering a meal through a food delivery service based on a suggested meal menu.

[1284] "Feedback" refers to opinions and evaluations that users send to the server, such as their satisfaction with the meal menu, their impressions, and changes in their physical condition.

[1285] "Model optimization" refers to the process of improving the accuracy and performance of a generative AI model based on collected feedback.

[1286] MODE FOR CARRYING OUT THE INVENTION

[1287] Specific program processing and its explanation will be described below for an embodiment of the present invention. The system of the present invention is composed of a wearable terminal, a server, and a user terminal.

[1288] Data collection using wearable devices

[1289] Wearable devices collect biometric data from users. The main biometric data are the number of steps taken, heart rate, and sleep time. This data is sent to a server at regular intervals. Specific hardware used for this purpose includes smartwatches and fitness trackers.

[1290] Data storage and analysis by server

[1291] The server receives the biometric data sent from the wearable device and stores it in a database. It then compiles and stores the nutritional information in a database. To analyze the collected biometric data and nutritional information, the server uses a generative AI model. This model is a type of artificial intelligence (AI), and specific software such as TensorFlow and PyTorch are used.

[1292] Using generative AI models

[1293] The server uses a generative AI model to analyze the stored biometric and nutritional data. Based on the collected data, the generative AI model generates a nutritionally balanced meal menu that is optimal for each user. For example, it might suggest a high-protein, low-calorie menu for a user who exercises a lot. Below is an example of a prompt sentence.

[1294] Prompt Sentence Examples

[1295] User biometric data:

[1296] Steps: 12,000

[1297] Heart rate: 75 bpm

[1298] Sleep time: 6.5 hours

[1299] Use this information to create a nutritionally balanced menu.

[1300] Menu notifications and delivery orders

[1301] The server then notifies the user of the optimal meal menu that has been generated. The user can then check the proposed menu on their own device and place a delivery order. The user device can be a smartphone or personal computer.

[1302] Feedback collection and optimization

[1303] Users provide feedback on the proposed menu, including information such as their satisfaction with the meal, their impressions, and their physical reactions. The server then optimizes the generative AI model based on the collected feedback, allowing future menu suggestions to be further optimized and personalized.

[1304] For example, if a user walks 12,000 steps in a day, has an average heart rate of 75 bpm, and sleeps 6.5 hours, the generative AI model will use this information to suggest high-protein, low-calorie meals. For example, it might suggest "grilled chicken salad and a low-fat smoothie." The user can then review the suggestions on their smartphone and place a delivery order. After the meal, they can provide feedback, which will be reflected in future recommendations.

[1305] Through the above process, users are suggested optimal meal menus based on their health condition and exercise level, enabling them to live an efficient and healthy life.

[1306] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1307] Step 1: Collecting biometric data using wearable devices

[1308] Wearable devices collect biometric data from users. Specifically, the device periodically measures data such as the number of steps taken, heart rate, and sleep time, and temporarily stores the data. The input is data related to the user's physical activity (number of steps taken, heart rate, and sleep time), and the output is a set of these data.

[1309] Step 2: Sending biometric data to the server

[1310] The device sends the collected biometric data to a server. Specifically, the device periodically uploads the data to the server via the Internet. At this time, the data is encrypted and transmitted securely. The input is the biometric data stored on the device, and the output is the data stored on the server.

[1311] Step 3: Data storage and analysis

[1312] The server stores the received biometric data in a database. It then creates a database of nutritional information and stores it in the same way. The input is biometric data and nutritional information, and the output is a database in which these data are stored. Specifically, a database management system such as "MySQL" or "PostgreSQL" is used.

[1313] Step 4: Generate the menu using a generative AI model

[1314] The server runs a generative AI model using biometric data and nutritional information stored in the database. This model generates an optimal meal plan based on the user's health status and activity level. The input is biometric data and nutritional information, and the output is a suggested meal plan. Specific operations include feeding data to the AI ​​model (e.g., using TensorFlow or PyTorch) and analyzing it.

[1315] Step 5: Creating and parsing prompt statements

[1316] The server creates a prompt based on the analysis results of the generative AI model and inputs it into the model. Specific examples of prompts are as follows:

[1317] Prompt Sentence Examples

[1318] User biometric data:

[1319] Steps: 12,000

[1320] Heart rate: 75 bpm

[1321] Sleep time: 6.5 hours

[1322] Use this information to create a nutritionally balanced menu.

[1323] The input is a prompt and the output is a generated meal menu, which the generative AI model analyzes and suggests the best meal options.

[1324] Step 6: Notification to user device and delivery order

[1325] The server notifies the user of the generated meal menu. The user receives the notification, checks the menu from the provided options, and places a delivery order. The input is the notification of the meal menu, and the output is the delivery order placed by the user. Specific operations include notification and order processing via a smartphone app or web app.

[1326] Step 7: Gather feedback

[1327] After eating, users provide feedback. Specifically, they use their device to send their satisfaction, impressions, physical reactions, etc. to the server. The input is the feedback provided by the user, and the output is the feedback data collected by the server.

[1328] Step 8: Optimizing the generative AI model

[1329] The server analyzes the collected feedback data and performs optimization to improve the accuracy of the generative AI model. The input is the feedback data, and the output is an updated generative AI model. Specific operations include adjusting the model parameters based on the feedback data to improve the accuracy of subsequent menu generation.

[1330] Through the above processing steps, the user is presented with an optimal meal menu based on their health condition and amount of exercise, enabling them to lead an efficient and healthy diet.

[1331] 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.

[1332] Specific program processing and its explanation will be described below as an embodiment of the present invention.

[1333] Program Overview

[1334] The system of the present invention consists of a wearable device, a server, a user device, and an emotion engine. The wearable device collects the user's biometric data and sends it to the server. The server uses the collected data to generate an optimal buffet menu using a generative AI model and the emotion engine, and notifies the user's device of the results. In addition, by collecting feedback from users and optimizing the generative AI model, the system customizes the suggestions with even greater precision.

[1335] Program processing

[1336] Data collection using wearable devices

[1337] While the wearable device is worn by the user, it collects the following biometric data in real time and transmits it to a server at regular intervals.

[1338] User steps

[1339] Heart rate

[1340] sleep time

[1341] Data storage and analysis by server

[1342] The server receives the data sent from the wearable device and stores it in a database for each user. It then stores the nutritional information of the buffet menu in a database.

[1343] Using generative AI models

[1344] The server uses a generative AI model that analyzes the user's health indicators based on the stored biometric and nutritional data, and selects the optimal buffet menu based on the user's health indicators (e.g., daily activity, resting heart rate, average sleep time over seven days).

[1345] Using the Emotion Engine

[1346] The server uses an emotion engine that evaluates the user's emotional state through various emotion recognition technologies. The emotion engine analyzes the user's facial expressions, voice, and text, and recognizes and evaluates the user's emotional state in real time based on the results.

[1347] Menu generation and notification

[1348] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[1349] The user can view the proposed menu on their device and make their meal selection.

[1350] Feedback collection and optimization

[1351] After eating, users enter feedback through the app, including information such as satisfaction level, taste rating, changes in emotional state, and physical reactions.

[1352] The server collects user feedback and stores it in a database. Based on this feedback data, the generative AI model is optimized, and menu suggestions for future orders are further optimized individually.

[1353] Specific examples

[1354] Examples of data collection

[1355] The device measures that the user walked 15,000 steps in a day, had an average heart rate of 72 bpm, and slept for 7.5 hours, and sends this data to a server.

[1356] Examples of data storage and analysis

[1357] The server stores this biometric data in the user's database and registers the nutritional information for "Grilled Chicken Salad" (calories: 250 kcal, protein: 25 g, fat: 10 g, etc.) in the database. A generative AI model analyzes the user's data and selects a menu with an appropriate nutritional balance.

[1358] Specific examples of using the Emotion Engine

[1359] The server uses an emotion engine to assess whether the user is feeling stressed based on collected facial expression data and voice tone. If the user is judged to be under high stress, the server suggests a menu containing foods that have a relaxing effect.

[1360] Menu notification example

[1361] The server proposes three menu options, including "Grilled Chicken Salad," to the user and notifies the user of the details via their smartphone. The user then checks the proposed menu options on their smartphone and selects "Grilled Chicken Salad."

[1362] Examples of feedback gathering and optimization

[1363] After eating, users provide feedback through the app, such as "It tasted good," "I was satisfied," "My stress was reduced," etc. The server collects this feedback and tunes the generative AI model and emotion engine.

[1364] These processes enable users to eat efficiently and healthily, and also provide meal suggestions tailored to individual emotional states.

[1365] The processing flow will be explained below.

[1366] Step 1:

[1367] While the user is wearing the device, it collects real-time biometric data (number of steps, heart rate, and sleep time). Specifically, it measures data using an acceleration sensor and heart rate sensor and stores the data in a buffer at regular intervals.

[1368] Step 2:

[1369] The device sends the stored biometric data to the server at a set time each day, using Wi-Fi or Bluetooth to securely transfer the data.

[1370] Step 3:

[1371] The server receives the biometric data sent from the device and stores it in a database for each user. Specifically, it centrally manages each user's data using an SQL or NoSQL database.

[1372] Step 4:

[1373] The server stores the nutritional information of the buffet menu in a database. Detailed nutritional information such as calories, protein, fat, carbohydrates, vitamins, and minerals is recorded and saved for each menu item.

[1374] Step 5:

[1375] The server uses a generative AI model to analyze the stored biometric data and nutritional information. Specifically, it uses machine learning algorithms to select the optimal meal plan for each individual user. This process takes into account the user's health indicators (e.g., daily activity, resting heart rate, and average sleep duration over a seven-day period).

[1376] Step 6:

[1377] The server uses an emotion engine to recognize and evaluate the user's emotional state. The emotion engine analyzes the user's facial expressions, voice, and text, and determines the user's emotional state in real time based on the results.

[1378] Step 7:

[1379] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user, suggesting a menu including foods with a relaxing effect for a user experiencing high stress, for example.

[1380] Step 8:

[1381] The server then notifies the user of the optimal buffet menu, allowing them to view the proposed menu on their smartphone or computer.

[1382] Step 9:

[1383] The user selects the menu item for which they received a notification and provides feedback through the app after eating, including taste evaluation, satisfaction, and changes in emotional state (e.g., whether stress was reduced).

[1384] Step 10:

[1385] The server collects user feedback and stores it in a database. It then optimizes the generative AI model based on the collected feedback data, and further optimizes menu suggestions for future meals. During this process, the model is updated taking into account changes in the user's preferences and health status.

[1386] Example 2

[1387] 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."

[1388] In today's busy lifestyles, many people find it difficult to devote sufficient time to their own health and nutrition management. It is particularly challenging to provide customized meal recommendations based on individual biometric information and emotional state. It is also unrealistic to efficiently collect feedback on the extent to which the recommended meals contribute to the user's actual satisfaction and emotional state and reflect this feedback in future recommendations. Therefore, there is a need for a system that provides meal menus optimized for the user's health and emotional state.

[1389] 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.

[1390] In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for database-storing and storing nutritional information, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for using an emotion engine to analyze the user's emotional state, means for integrating the analysis results of the generative AI model and the emotion engine to generate an optimal meal menu, means for notifying the user's device of the generated meal menu, and means for collecting feedback from the user and optimizing the generative AI model. This makes it possible to provide an optimal meal menu for each user based on the user's biometric data and emotion data, and to improve the accuracy of suggestions for future meals based on the feedback.

[1391] A "wearable terminal" is a device that can be worn by a user and has the function of collecting biometric data in real time and transmitting it to a server.

[1392] "Biometric data" refers to data for measuring the user's health condition, and examples include the number of steps taken, heart rate, and sleep time.

[1393] A "server" is a computer system for storing and analyzing collected biometric data.

[1394] "Nutritional information" refers to data about the nutrients contained in a meal menu, including, for example, calories, protein, and fat.

[1395] A "generative AI model" is an artificial intelligence model that analyzes a user's biometric data and nutritional information to generate the optimal meal menu for each individual user.

[1396] An "emotion engine" is a technology for analyzing a user's emotional state, and performs facial expression analysis, voice analysis, and text analysis.

[1397] A "database" is a system that systematically stores collected data and nutritional information so that it can be searched and retrieved as needed.

[1398] "Feedback" refers to the user evaluating the actual meal menu provided and providing information such as satisfaction and changes in emotional state.

[1399] "Optimization" refers to the process of improving the performance of the generative AI model based on feedback, thereby increasing the accuracy of meal menu suggestions from the next time onwards.

[1400] A "user terminal" is a device that can be operated by a user and that can check the meal menu notified by the server.

[1401] System configuration

[1402] The system of the present invention is composed of a wearable device, a server, a user device, and an emotion engine. These components work together to provide an optimal meal menu based on the user's health and emotional state.

[1403] Program processing flow

[1404] 1. Data Collection:

[1405] The wearable device collects biometric data such as the number of steps taken, heart rate, and sleep time of the user in real time, and periodically transmits this data to a server.

[1406] Example: A wearable device collects information such as the user's 15,000 steps in a day, their average heart rate is 72 bpm, and their sleep time is 7.5 hours, and sends this information to a server every 10 minutes.

[1407] 2. Data Retention:

[1408] The server stores the biometric data sent from the wearable device in a database for each user, and also registers the nutritional information of the buffet menu in the database.

[1409] Example: The server stores the biometric data described above in the record corresponding to the user ID and adds the nutritional information for "Grilled Chicken Salad" (250 kcal, 25 g protein, 10 g fat) to the database.

[1410] 3. Analysis of health indicators:

[1411] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators (daily activity, resting heart rate, and average sleep time over seven days).

[1412] Example: The server inputs data of the user's daily 15,000 steps, 72 bpm, and 7.5 hours into the generated AI model, and calculates health indicators based on this.

[1413] 4. Emotional state analysis:

[1414] The server uses an emotion engine to analyze the user's emotional state from facial expression data, voice tone, and text, and in particular evaluates whether the user is feeling stressed.

[1415] Example: The server determines from the user's facial expression data that the stress level is high because the user's brow is furrowed and the tone of the voice is low and unsettled.

[1416] 5. Generate the menu:

[1417] The server integrates the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user.

[1418] Example: If a generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and the emotion engine recognizes stress, it will also add relaxing herbal tea to the menu.

[1419] 6. Menu Notifications:

[1420] The server notifies the user terminal of the generated buffet menu, and the user can check the proposed menu on his or her own terminal.

[1421] Example: The server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea," and the user confirms this and makes a selection.

[1422] 7. Gathering Feedback:

[1423] After eating, users provide feedback via a dedicated app, including satisfaction, taste evaluation, changes in emotional state, and physical reactions.

[1424] Example: Users enter feedback into the app, such as "It tasted good," "I was satisfied," or "It reduced stress."

[1425] 8. Optimize the model:

[1426] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions.

[1427] Example: The server feeds user feedback data back into the generative AI model, learning that "Grilled Chicken Salad was very satisfying" and "Drinks with a relaxing effect were effective," and updating the model.

[1428] Prompt Sentence Examples

[1429] "The user's biometric data includes a heart rate of 72 bpm, daily activity of 15,000 steps, and 7.5 hours of sleep. Analysis by the emotion engine reveals that the stress level is high. Please recommend the best buffet menu based on this information."

[1430] In this way, by implementing the system of the present invention, it is possible to provide an optimal meal menu based on the user's health and emotional state, and to create a cycle of further optimization based on feedback.

[1431] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1432] Step 1:

[1433] Data collection:

[1434] The wearable device collects biometric data such as the user's steps, heart rate, and sleep time in real time. The data input is biometric data generated during the user's daily activities. This data is sent to the server at regular intervals. Specifically, the wearable device records that the user walked 15,000 steps in a day, their average heart rate was 72 bpm, and their sleep time was 7.5 hours, and sends this information to the server every 10 minutes. The sent data is used in the next step.

[1435] Step 2:

[1436] Data Retention:

[1437] The server receives the biometric data sent from the wearable device and stores it in a database for each user. The input data is the user's biometric data sent from the wearable device. The output is a database organized for each user. Specifically, the server stores data such as 15,000 steps, 72 bpm, and 7.5 hours in the record corresponding to the user ID. At the same time, it also adds nutritional information for the buffet menu (e.g., nutritional information for "Grilled Chicken Salad": 250 kcal, 25 g protein, 10 g fat) to the database.

[1438] Step 3:

[1439] Health indicator analysis:

[1440] The server uses a generative AI model based on the stored biometric data to analyze the user's health indicators. The input data is the user's biometric data. The output is the analyzed health indicators (e.g., daily activity level, resting heart rate, average sleep time over 7 days). Specifically, the server inputs the user's daily data of 15,000 steps, 72 bpm, and 7.5 hours into the generative AI model, and calculates the health indicators based on this data. The generative AI model then evaluates the user's health condition based on this data.

[1441] Step 4:

[1442] Emotional State Analysis:

[1443] The server uses an emotion engine to analyze the user's emotional state from their facial expression data, voice tone, and text. The input data is the user's facial expression data, voice tone, and text data. The output is the analyzed emotional state (e.g., stress level). Specifically, the server analyzes the user's facial expression data to determine whether the user has furrowed brows or a low, restless voice tone, and evaluates whether the user is feeling stressed. The emotion engine uses this information to determine the user's emotional state.

[1444] Step 5:

[1445] Generate the menu:

[1446] The server combines the analysis results of the generative AI model and the emotion engine to generate a buffet menu customized for each user. The input data is health indicators and emotional state. The output is the optimal buffet menu. Specifically, the generative AI model recommends "Grilled Chicken Salad" based on the user's health indicators, and if the emotion engine recognizes stress, it also adds relaxing herbal tea to the menu.

[1447] Step 6:

[1448] Menu Notifications:

[1449] The server notifies the user terminal of the generated buffet menu. The input data is the generated menu. The output is a notification to the user terminal. Specifically, the server notifies the user terminal of "Recommended menu: 1. Grilled Chicken Salad, 2. Herbal Tea", and the user confirms this. The process of the user selecting the menu is also included here.

[1450] Step 7:

[1451] Collecting feedback:

[1452] After eating, the user provides feedback such as satisfaction, taste evaluation, changes in emotional state, and physical reactions through a dedicated app. The input data is the user's feedback. The output is the feedback data stored on the server. Specifically, the user enters feedback such as "The taste was good," "I was satisfied," or "My stress was reduced" into the app and sends it to the server.

[1453] Step 8:

[1454] Model optimization:

[1455] The server uses the collected feedback to tune the generative AI model and emotion engine, improving the accuracy of future menu suggestions. The input data is user feedback. The output is an optimized generative AI model and emotion engine. Specifically, the server feeds the user's feedback data back to the generative AI model, learning that "the Grilled Chicken Salad was very satisfying" and "drinks with a relaxing effect were effective," and updating the model to make future suggestions even more accurate.

[1456] (Application example 2)

[1457] 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."

[1458] In modern factories, managing employee health and optimizing work efficiency are important issues. The lack of a way to monitor employees' health and emotional state in real time and adjust their breaks and work accordingly can lead to health risks and reduced work efficiency. A system is needed to prevent employee stress and fatigue and optimize the work environment.

[1459] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for transmitting biometric data collected from the wearable device to the server, means for storing nutritional information in a database, means for analyzing the collected biometric data and nutritional information and using a generative AI model to generate an optimal meal menu for each user, means for notifying the user's device of the generated meal menu, means for collecting feedback from the user and optimizing the generative AI model, and means for monitoring the health and emotional states of factory workers and generating suggestions to adjust breaks and work content. This makes it possible to manage employee health and optimize work efficiency.

[1460] A "wearable device" is a device used to collect a user's biometric data in real time.

[1461] "Biometric data" refers to data that indicates the user's health condition and physical performance, and specifically includes heart rate, number of steps taken, sleep time, etc.

[1462] The "server" is a central processing unit that receives and stores data sent from the wearable device and analyzes it.

[1463] "Nutrition information" refers to information about the calories and nutrients contained in a particular food or menu item.

[1464] A "database" is a system that can efficiently store and search large amounts of data.

[1465] A "generative AI model" is an artificial intelligence model that analyzes collected data and generates optimal suggestions.

[1466] "Notification" refers to the act of sending server-generated information or suggestions to a user's device to inform them.

[1467] "Feedback" refers to information collected from users, such as their impressions, evaluations, and physical reactions.

[1468] "Emotional state" is data used to evaluate the user's psychological state, and is obtained by analyzing facial expressions and voice.

[1469] "Break timing" refers to the time points within the factory where employees can take breaks at appropriate times.

[1470] "Work content" refers to the specific work tasks performed by an employee.

[1471] "Factory worker" refers to an employee who works in a factory.

[1472] "Work efficiency" is an indicator that shows how efficiently an employee can complete work within a certain amount of time.

[1473] A specific system configuration and processing procedure for an embodiment of the present invention will be described below.

[1474] The system of the present invention is composed of a wearable device, a server, a factory robot, a generative AI model, and an emotion engine. Each element and its processing content will be explained in detail below.

[1475] Data collection using wearable devices

[1476] While worn by the user, the wearable device collects real-time biometric data, including the number of steps taken, heart rate, and sleep time, and transmits this data to a server at regular intervals.

[1477] Data storage and analysis by server

[1478] The server receives the biometric data sent from the wearable device and stores it in a database for each user. It also stores nutritional information for meal menus in a database.

[1479] Using generative AI models

[1480] The server analyzes the stored biometric and nutritional data using a generative AI model, which takes into account the user's health indicators (e.g., daily activity level, heart rate, sleep duration, etc.) to generate optimal meal plans and also suggests adjustments to breaks and work schedules based on the factory worker's health and emotional state.

[1481] Using the Emotion Engine

[1482] The server evaluates the user's emotional state using an emotion engine, which recognizes and evaluates the user's emotional state in real time using facial expression analysis, voice analysis, and text analysis.

[1483] Proposal generation and notification

[1484] The server combines the analysis results of the generative AI model and the emotion engine to generate customized suggestions for each user. For example, for a user who is evaluated as having high stress, it may suggest a relaxing break or a change in work. These suggestions are then communicated to the user via the factory robot.

[1485] Feedback collection and optimization

[1486] After the user performs the suggested break or task, they provide feedback on the results. This feedback includes satisfaction, changes in emotional state, and work efficiency. The server collects this feedback and stores it in a database. The generative AI model is then optimized based on this feedback, improving the accuracy of future suggestions.

[1487] Specific examples

[1488] For example, suppose a factory worker walks 12,000 steps a day, has an average heart rate of 70 bpm, and sleeps for seven hours. This data is collected by a wearable device and sent to a server. The server then inputs this data into a generative AI model, analyzes it, and generates suggestions such as "take a 10-minute break" or "switch to less stressful work." These suggestions are notified to the user via a factory robot. The user then implements the suggestions and provides feedback, including their impressions and evaluation. The server then collects the feedback and optimizes the generative AI model.

[1489] Prompt Sentence Examples

[1490] "Analyze employee data, assess their health and emotions, and generate optimal break timing and work content suggestions. As a concrete example, what suggestions would be made if an employee took 12,000 steps, had a heart rate of 70 bpm, and got 7 hours of sleep?"

[1491] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1492] Step 1:

[1493] A wearable device collects the user's biometric data (number of steps, heart rate, sleep time) in real time. The device transmits this data to a server at regular intervals. The input data is the user's biometric information, and the output is the biometric data transmitted to the server.

[1494] Step 2:

[1495] The server stores the biometric data received from the wearable device in a database for each user. The input is the biometric data sent from the wearable device, and the output is the biometric data stored in the database.

[1496] Step 3:

[1497] The server uses a generative AI model to analyze the databased nutritional information and stored biometric data. The generative AI model calculates the user's health indicators and generates optimal meal menus and rest suggestions. The input is the biometric data and nutritional information stored in the database, and the output is the generated suggestions.

[1498] Step 4:

[1499] The server evaluates the user's emotional state using an emotion engine. The emotion engine performs facial expression analysis, voice analysis, and text analysis, thereby evaluating the user's stress level and fatigue. The input is the user's facial expression, voice, and text data, and the output is the evaluated emotional state.

[1500] Step 5:

[1501] The server integrates the evaluation results of the generative AI model and the emotion engine to generate customized suggestions for break timing and work content for each user. The inputs are the output of the generative AI model and the evaluation results of the emotion engine, and the output is optimized suggestions.

[1502] Step 6:

[1503] The server notifies the user of the generated suggestions through the factory robot, which then prompts the user to take a break at an appropriate time. The input is the suggestion sent from the server, and the output is the notification of the suggestion to the user.

[1504] Step 7:

[1505] The user takes a break or performs a task based on the suggestions and provides feedback on the results. The feedback may include satisfaction, changes in emotional state, and work efficiency. The input is the user's execution result, and the output is the provided feedback.

[1506] Step 8:

[1507] The server collects feedback from users and stores it in a database. The collected feedback data is used to optimize the generative AI model. The input is the feedback from users, and the output is the optimization result reflected in the generative AI model.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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).

[1515] 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.

[1516] 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."

[1517] 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.

[1518] 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).

[1519] 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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.

[1529] The following is further disclosed regarding the above embodiment.

[1530] (Claim 1)

[1531] means for transmitting biometric data collected from the wearable device to a server;

[1532] A means for creating and storing nutrition information in a database;

[1533] Using a generative AI model that analyzes the collected biometric data and nutritional information to generate optimal meal plans for each individual user;

[1534] a means for notifying a user of the generated meal menu on the user's terminal;

[1535] A means of collecting user feedback and optimizing the generative AI model; and

[1536] A system including:

[1537] (Claim 2)

[1538] The system described in claim 1, characterized in that the feedback collection means acquires data such as user satisfaction, impressions of meals, and physical changes, and reflects this in the generative AI model.

[1539] (Claim 3)

[1540] The system described in claim 1, characterized in that the generative AI model compares and analyzes the user's health indicators with a nutritional database, and customizes the optimal meal menu based on the user's exercise level and health condition.

[1541] "Example 1"

[1542] (Claim 1)

[1543] means for transmitting biometric data collected from the wearable device to a server;

[1544] A means for creating and storing nutrition information in a database;

[1545] Using a generative AI model that analyzes the collected biometric data and nutritional information to generate optimal meal plans for each individual user;

[1546] a means for notifying a user of the generated meal menu on the user's terminal;

[1547] A means of collecting user feedback and optimizing the generative AI model; and

[1548] means for transmitting biometric data acquired from the wearable device to a server at regular intervals;

[1549] means for retrieving and analyzing the biological data and nutritional information stored in the database;

[1550] means for generating a nutritionally balanced meal menu based on the user's activity level;

[1551] A system including:

[1552] (Claim 2)

[1553] The system described in claim 1, characterized in that the feedback collection means acquires data such as user satisfaction, impressions of meals, and physical changes, and reflects this in the generative AI model.

[1554] (Claim 3)

[1555] The system described in claim 1, characterized in that the generative AI model compares and analyzes the user's health indicators with a nutritional database, and customizes the optimal meal menu based on the user's exercise level and health condition.

[1556] "Application Example 1"

[1557] (Claim 1)

[1558] means for transmitting biometric data collected from the wearable device to a server;

[1559] A means for creating and storing nutrition information in a database;

[1560] Using a generative AI model that analyzes the collected biometric data and nutritional information to generate optimal meal plans for each individual user;

[1561] A means for notifying a user of the generated meal menu on their device and supporting delivery orders;

[1562] A means of collecting user feedback and optimizing the generative AI model; and

[1563] A system including:

[1564] (Claim 2)

[1565] The system described in claim 1, characterized in that the feedback collection means acquires data such as user satisfaction, impressions of meals, and physical changes, and reflects this in the generative AI model.

[1566] (Claim 3)

[1567] The system described in claim 1 is characterized in that the generative AI model compares and analyzes the user's health indicators with a nutritional database, customizes the optimal meal menu based on the user's exercise level and health condition, and assists with delivery orders.

[1568] "Example 2: Combining Emotion Engines"

[1569] (Claim 1)

[1570] means for transmitting biometric data collected from the wearable device to a server;

[1571] A means for creating and storing nutrition information in a database;

[1572] Using a generative AI model that analyzes the collected biometric data and nutritional information to generate optimal meal plans for each individual user;

[1573] a means for using an emotion engine to analyze the user's emotional state;

[1574] A means to integrate the analysis results of the generative AI model and the emotion engine to generate the optimal meal menu;

[1575] a means for notifying a user of the generated meal menu on the user's terminal;

[1576] A means of collecting user feedback and optimizing the generative AI model; and

[1577] A system including:

[1578] (Claim 2)

[1579] The system described in claim 1, characterized in that the feedback collection means acquires data such as user satisfaction, impressions of meals, and physical changes, and reflects this in the generative AI model.

[1580] (Claim 3)

[1581] The system described in claim 1, characterized in that the generative AI model compares and analyzes the user's health indicators with a nutritional database, and customizes the optimal meal menu based on the user's exercise level and health condition.

[1582] "Application example 2 when combining emotion engines"

[1583] (Claim 1)

[1584] means for transmitting biometric data collected from the wearable device to a server;

[1585] A means for creating and storing nutrition information in a database;

[1586] Using a generative AI model that analyzes the collected biometric data and nutritional information to generate optimal meal plans for each individual user;

[1587] a means for notifying a user of the generated meal menu on the user's terminal;

[1588] A means of collecting user feedback and optimizing the generative AI model; and

[1589] A means for monitoring the health and emotional state of factory workers and generating suggestions for adjusting breaks and work content;

[1590] A system including:

[1591] (Claim 2)

[1592] The system described in claim 1 is characterized in that the means for collecting feedback acquires data such as user satisfaction, impressions of meals, physical changes, and work efficiency, and reflects this in the generative AI model.

[1593] (Claim 3)

[1594] The system described in claim 1, characterized in that the generative AI model compares and analyzes the user's health indicators, emotional state, and work efficiency data, and customizes optimal break timing and work content based on the amount of exercise and health condition. [Explanation of symbols]

[1595] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for transmitting biometric data collected from the wearable device to a server; A means for creating and storing nutrition information in a database; Using a generative AI model that analyzes the collected biometric data and nutritional information to generate optimal meal plans for each individual user; a means for notifying a user of the generated meal menu on the user's terminal; A means of collecting user feedback and optimizing the generative AI model; and A system including:

2. The system described in claim 1, characterized in that the feedback collection means acquires data such as user satisfaction, impressions of meals, and physical changes, and reflects this in the generative AI model.

3. The system described in claim 1, characterized in that the generative AI model compares and analyzes the user's health indicators with a nutritional database, and customizes an optimal meal menu based on the user's exercise level and health condition.

Images