System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information on a user's body shape, amount of exercise, health condition, allergies, and dietary preferences; means for creating an individual profile based on the collected user information; means for suggesting a dietary plan according to the user's activity level for the day; means for the user to provide feedback on the suggested dietary plan; and means for learning the user's feedback and improving upcoming suggestions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional meal planning is a manual process requiring expert input, which requires time and effort to address specific user needs. Furthermore, fixed routines and generic meal plans make it difficult to adapt to the diverse needs and health conditions of individual users. There is a need to address this issue and provide efficient and accurate meal plans. Furthermore, the lack of a mechanism for incorporating user feedback and continuously improving meal plans makes it difficult to provide personalized meal plans. [Means for solving the problem]

[0005] The present invention provides a system that collects information on a user's body type, activity level, health condition, allergies, and dietary preferences and creates an individual profile based on the collected information. The system also includes a means for suggesting an optimal meal plan that takes into account the user's activity level for that day based on the user information. The system also includes a means for the user to provide feedback on the suggested meal plan, and a means for learning from the feedback and improving future suggestions. The system further maintains a database of suggested meal plans and uses the database to generate meal plans, thereby providing personalized meal plans tailored to each individual user. The feedback information is saved in a dataset, and the dataset is used to retrain an AI model, enabling more accurate meal plan suggestions.

[0006] "User's body type" refers to the user's height, weight, body fat percentage and other physical indicators.

[0007] "Amount of exercise" refers to the frequency, intensity, and duration of physical activity or exercise that a user engages in on a daily basis.

[0008] "Health Status" refers to a user's existing health problems, medical history, and general health status.

[0009] "Allergy" refers to a situation in which a user has an allergic reaction to a particular food or substance.

[0010] "Dietary preferences" refers to the user's preferred ingredients, eating style, types of cuisine, etc.

[0011] "Individual profile" refers to a user-specific data set that is generated by integrating information about the user's body type, activity level, health status, allergies, and dietary preferences.

[0012] "Activity level" refers to the amount of exercise or physical activity a user has performed that day.

[0013] "Optimal Meal Plan" refers to a nutritionally balanced meal plan suggested based on a user's profile and activity level.

[0014] "Suggested Meal Plan" refers to the specific meal plan generated for the user by the system.

[0015] "Feedback" refers to the ratings and opinions provided by a user regarding a proposed meal plan.

[0016] "Database" refers to the system that records and stores information such as suggested meal plans and user feedback.

[0017] "AI model" refers to the artificial intelligence algorithm that generates and refines meal plans based on user data and feedback.

[0018] "Retraining" refers to the learning process of using new collected data (e.g., feedback) to improve the accuracy and performance of an AI model. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[0041] 1. Collection of User Information

[0042] Terminal

[0043] A user accesses the system using a terminal and inputs information about their body type (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as basic data for creating an individual profile of the user.

[0044] 2. Create a user profile

[0045] server

[0046] The server receives the user information sent from the terminal, stores it in a database, and then automatically generates an individual profile for each user based on this information.

[0047] 3. Meal plan suggestions

[0048] server

[0049] Based on the user's profile, the server generates an optimal meal plan taking into account the user's daily activity level. Specifically, the user's input information is converted into tensor format and fed into an artificial intelligence (AI) model. The AI ​​model processes the information and predicts the optimal meal plan.

[0050] The generated meal plan is based on the user's activity level, health status, allergies, food preferences, etc. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested. Also, if a user prefers Japanese food, a menu centered on Japanese cuisine will be provided.

[0051] 4. Providing suggestions and gathering feedback

[0052] Terminal

[0053] The meal plan generated by the server is sent to the user's device, where the user can review it. The user tries out the proposed meal plan and then inputs their impressions and ratings as feedback.

[0054] 5. Feedback learning and model refinement

[0055] server

[0056] The collected feedback is stored in a database, and the server uses this feedback data to retrain the AI ​​model and improve its next suggestions to better suit the user's preferences.

[0057] Specific examples

[0058] Example user:

[0059] Age: 30

[0060] Weight: 70kg

[0061] Height: 175cm

[0062] Activity level: High

[0063] Health condition: Diabetes

[0064] Allergies: Dairy

[0065] Food preference: Japanese food

[0066] 1. Collection of User Information

[0067] The user inputs the above information from the terminal and transmits it to the server.

[0068] 2. Create a user profile

[0069] The server uses this information to generate individual profiles and stores them in a database.

[0070] 3. Meal plan suggestions

[0071] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[0072] 4. Providing suggestions and gathering feedback

[0073] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[0074] 5. Feedback learning and model refinement

[0075] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[0076] The processing flow will be explained below.

[0077] Step 1: Enter your user information

[0078] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The terminals then send this information to the server.

[0079] Step 2: Save user information

[0080] The server stores the user information received from the terminal in a database, and through this storage process, an individual profile of each user is recorded in the database.

[0081] Step 3: Creating a User Profile

[0082] The server uses the information in the database to generate an individual profile for each user, which is then stored in the database again. The user profile includes information about body type, activity level, health status, allergies, and food preferences that users have entered.

[0083] Step 4: Generate a meal plan

[0084] The server generates an optimal meal plan using an AI model based on the user's profile. Specifically, the server converts the user's information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model then uses the stored data to create the optimal menu for the user.

[0085] Step 5: Submit your meal plan

[0086] The server sends the generated meal plan to the user's terminal, where the user can view the proposed meal plan.

[0087] Step 6: Provide feedback

[0088] The user actually tries out the proposed meal plan and inputs feedback on the results. The terminal sends the user's feedback information to the server.

[0089] Step 7: Save your feedback

[0090] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[0091] Step 8: Retraining the AI ​​model

[0092] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[0093] Step 9: Provide an improved meal plan

[0094] Using the retrained AI model, the server again generates and serves the optimal meal plan to the user, which in turn provides an improved meal plan that incorporates user feedback.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In modern society, it is important to provide meal plans tailored to an individual's health status and lifestyle. However, conventional systems have had difficulty in properly collecting a wide range of user information (e.g., body shape, health status, food preferences, etc.) and providing meal plans tailored to individual needs. Furthermore, there were insufficient means to effectively utilize user feedback and improve future proposals. This resulted in a decline in user satisfaction.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes means for sending collected user information to the server in JSON format, means for saving user information in a database and generating a profile for each user, and means for converting the user profile into tensor format and inputting it into an AI model to generate an optimal meal plan. This enables the generation of a customized meal plan based on detailed user information, and by continuously incorporating user feedback, it is possible to improve the accuracy and satisfaction of subsequent suggestions.

[0100] "User information" is detailed information about the user, such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[0101] A "terminal" is a device used by a user (e.g., a smartphone or PC) and is hardware used to access the system and input and receive information.

[0102] A "server" is a computer system that receives, stores, processes, and analyzes collected user information.

[0103] A "database" is a data structure for storing and managing collected user information and feedback information.

[0104] A "profile" is a collection of individual information about each user that is generated based on collected user information.

[0105] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and perform specific tasks.

[0106] "Tensor format" is user information converted into a multidimensional array format, and is used when inputting it into an AI model.

[0107] A "meal plan" is a meal suggestion tailored to a user, generated based on the user's profile.

[0108] "Feedback" refers to the impressions and ratings provided by users after trying the suggested meal plan.

[0109] "Retraining" is the process of updating an existing AI model with new feedback data collected to improve its accuracy.

[0110] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data in text format and is used for data exchange.

[0111] The "HTTPS protocol" is an abbreviation for HyperText Transfer Protocol Secure, a protocol for encrypting internet communications to send and receive data safely.

[0112] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[0113] 1. Collection of User Information

[0114] Terminal

[0115] Users access the system using a terminal and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as the basis for creating an individual profile of the user. The information is packaged in JSON format and sent using the HTTPS protocol.

[0116] 2. Create a user profile

[0117] server

[0118] The server receives and parses user information in JSON format sent from the device. The collected information is stored in a database, and a profile for each user is generated based on this information. The database software used is a standard SQL database (e.g., MySQL or PostgreSQL).

[0119] 3. Meal plan suggestions

[0120] server

[0121] The server generates an optimal meal plan based on each user's profile. The user profile information is converted into tensor format and input into an AI model using a deep learning library such as TensorFlow. The AI ​​model analyzes the user information and predicts the optimal meal plan for each user. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested, and if a user prefers Japanese food, a menu centered on Japanese cuisine will be generated.

[0122] 4. Providing suggestions and gathering feedback

[0123] Terminal

[0124] The generated meal plan is sent to the user's device, where the user can review it. The user can try out the proposed meal plan and then enter their impressions and ratings as feedback. The feedback is again packaged in JSON format and sent to the server using the HTTPS protocol.

[0125] 5. Feedback learning and model refinement

[0126] server

[0127] The server stores the collected feedback in a database and retrains the AI ​​model. The retraining process is carried out using the new feedback data collected, allowing the system's suggestions to better meet the user's needs in the future.

[0128] Specific examples

[0129] Example user:

[0130] Age: 30

[0131] Weight: 70kg

[0132] Height: 175cm

[0133] Activity level: High

[0134] Health condition: Diabetes

[0135] Allergies: Dairy

[0136] Food preference: Japanese food

[0137] 1. Collection of User Information

[0138] The user inputs the above information from the terminal and sends it to the server.

[0139] 2. Create a user profile

[0140] The server uses this information to generate individual profiles and stores them in a database.

[0141] 3. Meal plan suggestions

[0142] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[0143] 4. Providing suggestions and gathering feedback

[0144] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[0145] 5. Feedback learning and model refinement

[0146] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[0147] Example prompt sentence:

[0148] "Please suggest the best meal plan for a user who is 30 years old, weighs 70kg, is 175cm tall, has a high activity level, has diabetes, is allergic to dairy products, and likes Japanese food."

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1:

[0151] Entering user information

[0152] Users access the system using a terminal and input information such as their body type, amount of exercise, health condition, allergies, and dietary preferences.

[0153] Input: User's body type information (e.g., height 175 cm, weight 70 kg), amount of exercise (e.g., daily jogging), health condition (e.g., diabetes, dairy allergy), food preferences (e.g., Japanese food)

[0154] Output: User information packaged in JSON format

[0155] Specific operation: Information entered on the device interface is converted to JSON format using front-end technologies such as JavaScript.

[0156] Step 2:

[0157] Sending user information

[0158] The terminal transmits the packaged user information to the server via the HTTPS protocol.

[0159] Input: User information in JSON format

[0160] Output: User information is sent to the server

[0161] Specific operation: The device uses an SSL certificate to ensure security when sending information.

[0162] Step 3:

[0163] Creating a User Profile

[0164] The server parses the received JSON formatted user information, stores it in a database, and then generates a profile for each user.

[0165] Input: User information in JSON format

[0166] Output: User profile stored in the database

[0167] Specific operation: The server uses Python or Node.js to parse the JSON information and save it to the database using SQL commands.

[0168] Step 4:

[0169] Generate a meal plan

[0170] The server generates an optimal meal plan based on the user profile, converting the user information into tensor format and inputting it into an AI model running TensorFlow.

[0171] Input: Database user profile

[0172] Output: Meal plan

[0173] How it works: User profile information is converted into tensor format and fed into an AI model using deep learning libraries such as TensorFlow to predict optimal meal plans.

[0174] Step 5:

[0175] Meal plan provided

[0176] The server sends the generated meal plan to the user's terminal.

[0177] Input: Generated meal plan

[0178] Output: Meal plan displayed on user's device

[0179] Specific operation: The server sends the meal plan using the HTTPS protocol, and the device visualizes the received data and displays it to the user.

[0180] Step 6:

[0181] Enter your feedback

[0182] The user checks the proposed meal plan, tries it out, and then enters their impressions and evaluations as feedback into the device.

[0183] Input: Feedback information (e.g., taste, satiety, health effects, etc.)

[0184] Output: Feedback information in JSON format

[0185] Specific behavior: Information entered through the feedback form is packaged in JSON format.

[0186] Step 7:

[0187] Send Feedback

[0188] The terminal sends the feedback information to the server using the HTTPS protocol.

[0189] Input: Feedback information in JSON format

[0190] Output: Feedback information sent to the server

[0191] Specific behavior: Send information securely using an SSL certificate

[0192] Step 8:

[0193] Improve the model based on feedback

[0194] The server stores the received feedback information in a database and retrains the AI ​​model using new feedback data.

[0195] Input: Feedback information

[0196] Output: An improved AI model

[0197] Specific operation: Retrieves feedback data from the database and executes the process of retraining the AI ​​model using TensorFlow.

[0198] (Application example 1)

[0199] 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."

[0200] In modern society, there is a demand for systems that propose optimal meal plans based on an individual's health status and preferences and enable delivery orders. However, conventional systems are unable to fully utilize user information and feedback, making it difficult to provide highly accurate meal plans to individual users. Furthermore, the process for reflecting feedback and improving the next proposal is insufficient. The present invention aims to solve these problems and provide a system that enables the provision of personalized, healthy meal plans and the rapid delivery order of such plans.

[0201] 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.

[0202] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and dietary preferences, means for creating an individual profile based on the collected user information, and means for proposing an optimal meal plan based on the user's activity level for that day and enabling immediate delivery ordering. This allows users to easily obtain a meal plan tailored to their health condition and preferences and quickly order delivery of the plan.

[0203] The system also maintains a database of suggested meal plans, generates meal plans using this database, and uses them for delivery orders, enabling efficient suggestions. Furthermore, feedback information is stored in a dataset, which can be used to retrain the generative AI model, and prompts can be used to refine the next meal plan suggestions, enabling suggestions that are more tailored to each user's preferences.

[0204] "Information regarding the user's body type, amount of exercise, health condition, allergies, and food preferences" refers to data regarding weight, height, exercise habits, medical history, allergies, and food preferences entered by the user.

[0205] An "individual profile" is a collection of information customized for each user that is generated based on collected user information.

[0206] The "activity level for that day" is data relating to the amount of exercise and work intensity of the user for that day.

[0207] The "optimal meal plan" is a meal menu suggestion that is suitable for the user's health condition and food preferences, generated by AI based on the user's profile.

[0208] A "delivery order" is a request for a service to actually cook and deliver the proposed meal plan.

[0209] "Feedback" refers to a user providing feedback or rating on the meal they received.

[0210] A "dataset" is a collection of large amounts of data, including feedback information.

[0211] A "generative AI model" is an artificial intelligence system that is trained to use large amounts of data to generate optimal meal plans.

[0212] A "prompt" is a textual instruction or data entry statement that is input into an AI model.

[0213] This invention relates to a system that proposes personalized meal plans and allows users to instantly order delivery. The system collects information about the user's body type, activity level, health status, allergies, and food preferences, generates a profile based on that information, and proposes an optimal meal plan. Furthermore, the system collects feedback about the proposed meal plans and reflects that feedback in the AI ​​model to improve it.

[0214] 1. System Program

[0215] This system is primarily composed of a smartphone, a server, and a generative AI model. Users enter their information using their smartphone, and the data is sent to the server. The server creates an individual profile based on the received information, and the generative AI model generates an optimal meal plan. The generated meal plan is sent to the user's smartphone, allowing them to order delivery.

[0216] 2. Data processing and calculation

[0217] The smartphone application converts the user's input data into an appropriate format to facilitate sending it to the server. The server receives this data and stores it in a database. It also converts the data into tensor format for input to the generative AI model. The generative AI model is built using TensorFlow and processes the user's profile data to generate an optimal meal plan. Furthermore, feedback data from the user is stored on the server and used to retrain the AI ​​model and improve the accuracy of the next meal plan.

[0218] 3. Specific Examples

[0219] For example, consider a 30-year-old user who is 175 cm tall, weighs 70 kg, has a high activity level, and suffers from diabetes and a dairy allergy. If the user prefers Japanese food, the user first enters this information into a smartphone application. The server generates a profile based on the user information, and the generated AI model proposes a low-carb, dairy-free Japanese meal plan. This proposal is immediately sent to the smartphone, allowing the user to place a delivery order.

[0220] Additionally, after trying a meal, users can provide feedback, such as their impressions and ratings, which the server will collect and use to improve its suggestions for the next time.

[0221] 4. Examples of prompts

[0222] User Profile

[0223] Age: 30

[0224] Weight: 70kg

[0225] Height: 175cm

[0226] Activity level: High

[0227] Health Condition: Diabetes

[0228] Allergies: Dairy

[0229] Food preference: Japanese food

[0230] Based on the user profile above, please suggest the best low-carb, dairy-free Japanese meal menu.

[0231] In this way, the system not only proposes optimal meal plans tailored to the user's health condition and preferences, but also allows for quick delivery orders, allowing users to easily obtain healthy meals.

[0232] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0233] Step 1:

[0234] Users use their smartphones to input information about their body type, amount of exercise, health condition, allergies, food preferences, etc. Input data includes age, weight, height, exercise habits, medical history, allergies, favorite dishes, etc. The input data is temporarily stored on the device and then sent to the server.

[0235] Input data: User's body type, amount of exercise, health condition, allergies, food preferences

[0236] Output data: User profile information sent to the server

[0237] Step 2:

[0238] The server receives the user information sent from the device and stores it in a database. At this time, it organizes various data (body type, amount of exercise, health condition, allergies, food preferences) and creates a user profile for centralized management.

[0239] Input data: User profile information

[0240] Output data: User profile stored in a database

[0241] Step 3:

[0242] The server converts the collected user profile information into tensor format and inputs it into a generative AI model. The AI ​​model is built using TensorFlow and generates an optimal meal plan based on the user's profile data. The generated meal plan is returned to the server via an API.

[0243] Input data: User profile information in tensor format

[0244] Output: Generated meal plan

[0245] Step 4:

[0246] The server sends the generated meal plan to the user's smartphone terminal.

[0247] Input data: Generated meal plan

[0248] Output data: Meal plan displayed on a smartphone

[0249] Step 5:

[0250] The user checks the proposed meal plans on their smartphone, selects the one they like, and places a delivery order. The order information is sent to a server and linked to the restaurant or delivery service.

[0251] Input data: User order information

[0252] Output data: Order request to delivery service

[0253] Step 6:

[0254] After receiving the meal, the user inputs their impressions and evaluation of the meal as feedback into their smartphone, and this feedback data is sent to the server.

[0255] Input data: User feedback on meals

[0256] Output data: Feedback data sent to the server

[0257] Step 7:

[0258] The server stores the collected feedback information in a dataset and uses it to retrain the generative AI model, resulting in more accurate meal plan suggestions for the next time.

[0259] Input data: Feedback data

[0260] Output data: Improved generative AI model

[0261] This is the flow of processing in the program for the system that realizes the application example. At each processing step, specific data processing and calculations are performed, and the system evolves step by step.

[0262] 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.

[0263] The present invention is a system that combines an emotion engine that recognizes the user's emotions to collect information such as a user's body type, amount of exercise, health condition, allergies, and food preferences, create an individual profile based on that information, and propose an optimal meal plan. Specific embodiments of this system are described below.

[0264] 1. Collection of User Information

[0265] Terminal

[0266] A user accesses the system using a terminal and inputs their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[0267] 2. Emotional Recognition

[0268] Terminal

[0269] The device is equipped with an emotion engine that recognizes the user's emotional state from their voice and facial expressions. For example, it analyzes the tone of their voice and facial movements when they interact with the system through voice input or a camera to determine the user's emotions.

[0270] 3. Create a user profile

[0271] server

[0272] The server stores the user information and emotional state sent from the terminal in a database and generates an individual profile for each user based on that information. The generated profile is recorded in the database.

[0273] 4. Generate a meal plan

[0274] server

[0275] The server generates an optimal meal plan based on the user's profile, activity level for that day, and emotional state. The server converts the user's information into tensor format and inputs it into an AI model. The AI ​​model predicts the optimal meal plan based on a combination of the user's body type, exercise level, health status, allergies, food preferences, and emotional state.

[0276] 5. Meal plan offerings

[0277] Terminal

[0278] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan may include ingredients and dishes that match the user's mood.

[0279] 6. Providing Feedback

[0280] User

[0281] After trying the proposed meal plan, the user inputs their impressions and evaluations as feedback, and the device sends this feedback information to the server.

[0282] 7. Saving Feedback

[0283] server

[0284] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[0285] 8. Retraining AI models

[0286] server

[0287] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[0288] Specific examples

[0289] Example user:

[0290] Age: 30

[0291] Weight: 70kg

[0292] Height: 175cm

[0293] Activity level: High

[0294] Health condition: Diabetes

[0295] Allergies: Dairy

[0296] Food preference: Japanese food

[0297] Emotional state: Feeling stressed

[0298] 1. Collection of User Information

[0299] The user inputs the above information from the terminal and transmits it to the server.

[0300] 2. Emotional Recognition

[0301] The device analyzes the user's voice and facial expression and determines that the user is feeling stressed.

[0302] 3. Create a user profile

[0303] The server generates an individual profile based on this information and stores it in a database.

[0304] 4. Generate a meal plan

[0305] Based on this profile, the server generates a menu that is low in carbohydrates, dairy-free, mainly Japanese food, and includes ingredients that reduce stress, and sends it to the user's device.

[0306] 5. Meal plan offerings

[0307] The user reviews the proposed meal plan on the device.

[0308] 6. Providing Feedback

[0309] Users enter feedback about the meal plan they tried, such as "I felt relaxed," and send it to the server via their device.

[0310] 7. Saving Feedback

[0311] The server stores the collected feedback in a database and adds it to the training dataset.

[0312] 8. Retraining AI models

[0313] The server uses the feedback data to retrain the AI ​​model and incorporates the feedback into its next suggestions.

[0314] The processing flow will be explained below.

[0315] Step 1: Enter your user information

[0316] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[0317] Step 2: Recognizing user emotions

[0318] The device uses an emotion engine to analyze the user's voice and facial expressions to recognize their emotional state. For example, when a user interacts with the system via voice input or a camera, the device analyzes their voice tone and facial movements to determine whether they are feeling stressed.

[0319] Step 3: Creating a User Profile

[0320] The server generates an individual profile based on the user information and emotional state received from the device, and the generated profile is stored in a database.

[0321] Step 4: Generate a meal plan

[0322] The server uses an AI model to generate an optimal meal plan, taking into account the user's profile, activity level, and emotional state. Specifically, the server converts user information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model generates the optimal menu based on a combination of data such as body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[0323] Step 5: Submit your meal plan

[0324] The server sends the generated meal plan to the user's device, where the user can view the proposed meal plan.

[0325] Step 6: Provide feedback

[0326] The user tries out the proposed meal plan and inputs feedback on the results, which is then sent to the server by the device.

[0327] Step 7: Save your feedback

[0328] The server stores the feedback information received from the devices in a database, and also adds this feedback information to a dataset for later retraining the model.

[0329] Step 8: Retraining the AI ​​model

[0330] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[0331] Step 9: Provide an improved meal plan

[0332] Using the retrained AI model, the server again generates and provides the optimal meal plan to the user. The improved meal plan reflects the user's feedback. For example, if the user is feeling stressed, a menu containing foods that will reduce stress will be provided.

[0333] Example 2

[0334] 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."

[0335] Conventional meal plan suggestion systems provide meal plans based on basic information such as the user's body type and health condition, but do not take into account the user's emotional state. As a result, they are unable to provide meal plans that are adapted to the user's mood and emotions, which can lead to a decrease in user satisfaction. Furthermore, improvements to the model based on feedback are not made quickly, which can delay improvements in suggestion accuracy.

[0336] 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.

[0337] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, means for proposing a meal plan based on the user's activity level and emotional state for that day, means for recognizing the user's emotional state using an emotion recognition engine installed in the terminal, means for learning from the user's feedback and improving the next proposal, means for saving the feedback information, and means for retraining the AI ​​model using the saved feedback information. This makes it possible to provide an optimal meal plan that takes the user's emotional state into consideration and to quickly improve the model.

[0338] "User information" refers to personal information such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[0339] A "profile" is a data set specific to an individual user that is generated based on collected user information.

[0340] "Activity level" is information indicating the amount of exercise the user does on a daily basis and the intensity of the activity on each day.

[0341] "Emotional state" is information that indicates the user's emotional or mood state, and is recognized from voice and facial expressions.

[0342] A "meal plan" is a menu of meals suggested based on user information, activity level, and emotional state for the day.

[0343] "Feedback" refers to the impressions and evaluations provided by users after trying the proposed meal plan.

[0344] An "emotion recognition engine" is software installed on a device that analyzes the user's emotional state from their voice and facial expressions.

[0345] A "database" is an information management system for storing various data used by the system, such as user information, profiles, and feedback information.

[0346] The "AI model" is a machine learning model that predicts the optimal meal plan based on collected user information and feedback information.

[0347] The "tensor format" is a format that represents data as a multidimensional array and is used as an input format for AI models.

[0348] The present invention relates to a system that collects information on a user's body type, amount of exercise, health condition, allergies, food preferences, emotional state, etc., creates an individual profile based on the collected information, and proposes an optimal meal plan. This system uses a combination of an emotion recognition engine and a generative AI model to optimize the meal plan based on the user's information and emotional state.

[0349] Collection of User Information

[0350] Terminal

[0351] Users access the system using a device such as a smartphone or PC and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is sent from the device to the server.

[0352] Emotion recognition

[0353] Terminal

[0354] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, when a user interacts with the system through voice input or a camera, the system analyzes their voice tone and facial movements to determine whether the user is feeling stressed. This determination result is sent from the device to the server.

[0355] Creating a User Profile

[0356] server

[0357] The server receives the user information and emotional state sent from the terminal and stores it in a database, and based on this, generates an individual user profile and records it in the database.

[0358] Generate a meal plan

[0359] server

[0360] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. The server converts the user information into tensor format and inputs it into a generative AI model. The AI ​​model combines data such as body shape, exercise volume, health status, allergies, food preferences, and emotional state to predict the optimal meal plan. This meal plan is sent to the device in JSON format.

[0361] Meal plan provided

[0362] Terminal

[0363] The optimal meal plan sent from the server is displayed on the user's device, where the user can view it, and the suggested menu includes ingredients and dishes that suit the mood based on the user's emotional state.

[0364] Providing Feedback

[0365] User

[0366] After trying the meal plan provided, the user inputs their impressions and ratings, and this feedback is sent from the device to the server.

[0367] Save your feedback

[0368] server

[0369] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model, so that it can be reflected in the next proposal.

[0370] Retraining an AI model

[0371] server

[0372] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[0373] Specific examples

[0374] Here is a concrete example: Assume a 30-year-old male, weighing 70 kg and 175 cm tall, has a high activity level, suffers from diabetes, and is allergic to dairy products. This user prefers Japanese food and is currently feeling stressed.

[0375] Collecting user information: The user enters information from the terminal and sends it to the server.

[0376] Emotion recognition: The device analyzes the user's voice and facial expressions to determine whether they are feeling stressed.

[0377] Creating a user profile: The server stores the information in a database and creates a profile.

[0378] Meal plan generation: The server generates a menu of mainly Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[0379] Meal plan provided: The user reviews the proposed meal plan on the device.

[0380] Providing feedback: The user tries the meal and provides feedback that it was "relaxing."

[0381] Save Feedback: The server saves the feedback in a database and adds it to the training dataset.

[0382] Retraining the AI ​​model: The server uses the feedback data to retrain the AI ​​model and reflect it in the next proposal.

[0383] Example prompts for generative AI models

[0384] "I'm a 30-year-old man, 180cm tall, weigh 75kg, and run three times a week. I have high blood pressure and no particular allergies. My favorite food is Chinese food, and I've been feeling pretty stressed at work lately. I'd like you to suggest a meal plan that fits these conditions."

[0385] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0386] Step 1:

[0387] Collection of User Information

[0388] Terminal

[0389] Users access the system using a smartphone or PC and enter their body information (e.g., height and weight), exercise volume, health status, allergies, dietary preferences, etc. into the provided interface. The entered information is sent from the device to the server in JSON format.

[0390] Input: User-entered information about your body type, activity level, health status, allergies, and dietary preferences.

[0391] Data processing: Convert the input information into JSON format.

[0392] Output: User information in JSON format is sent from the device to the server.

[0393] What happens: A user opens the app, fills out a form, and presses the "Submit" button.

[0394] Step 2:

[0395] Emotion recognition

[0396] Terminal

[0397] The device's built-in camera and microphone are used to collect the user's voice and facial expressions. The emotion recognition engine analyzes this data and determines the user's emotional state. The results are sent to the server in JSON format.

[0398] Input: User's voice data, facial expression data.

[0399] Data processing: The emotion recognition engine analyzes voice and facial expressions to determine the emotional state.

[0400] Output: The determined emotional state is sent to the server in JSON format.

[0401] Specific operation: The user interacts with the system through voice and captures facial expressions with the camera.

[0402] Step 3:

[0403] Creating a User Profile

[0404] server

[0405] The server stores the user information and emotional state sent from the device in a database, and generates an individual profile for each user based on this information.

[0406] Input: User information and emotional state sent from the device.

[0407] Data processing: User information and emotional state are stored in a database and a profile is generated.

[0408] Output: The generated user profile is recorded in a database.

[0409] Specific operation: The server stores the received data in a database and generates a new profile item.

[0410] Step 4:

[0411] Generate a meal plan

[0412] server

[0413] The server generates an optimal meal plan based on the generated user profile, the activity level and emotional state of the day. The user information is converted into tensor format and input into a generative AI model. The AI ​​model predicts the optimal meal plan based on body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[0414] Input: Stored user profile, activity level, emotional state.

[0415] Data processing: User information is converted into tensor format and input into the generative AI model.

[0416] Output: The generated meal plan is sent to the terminal in JSON format.

[0417] Specific operation: The server inputs profile information into the AI ​​model and outputs a meal plan as the analysis result.

[0418] Step 5:

[0419] Meal plan provided

[0420] Terminal

[0421] The optimal meal plan sent from the server is displayed on the user's device, where the user can check the proposed plan and use it to make daily meal choices.

[0422] Input: Meal plan sent from server.

[0423] Data processing: Display meal plan information on the device.

[0424] Output: User can review the suggested meal plan.

[0425] Specific operation: Display the meal plan sent from the server on the app screen.

[0426] Step 6:

[0427] Providing Feedback

[0428] User

[0429] After trying out the meal plan provided, the user inputs their impressions and ratings, and the input feedback is sent from the device to the server.

[0430] Input: User comments and ratings.

[0431] Data processing: Convert the feedback information into JSON format.

[0432] Output: Feedback information is sent from the device to the server.

[0433] Specific operation: The user enters feedback on the terminal and sends it to the server by clicking the send button.

[0434] Step 7:

[0435] Save your feedback

[0436] server

[0437] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model.

[0438] Input: Feedback information sent from the device.

[0439] Data processing: The feedback information is stored in a database and added to the training dataset.

[0440] Output: The feedback information is stored in a database.

[0441] Specific operation: The server stores the received data in a database and adds it to the training dataset.

[0442] Step 8:

[0443] Retraining an AI model

[0444] server

[0445] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[0446] Input: Saved feedback information.

[0447] Data processing: Retraining the AI ​​model based on feedback information.

[0448] Output: The updated AI model.

[0449] Specific operation: The server inputs the feedback data into the AI ​​model and performs retraining.

[0450] (Application example 2)

[0451] 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."

[0452] In today's busy lifestyles, it is extremely difficult to easily provide optimal meal plans tailored to individual users' health and emotional states. Conventional systems have difficulty proposing personalized meal plans due to insufficient user information input and recognition of emotional states. Furthermore, while there is a demand for meal plans that take into account the user's emotional state, there are limitations in this regard as well. To address this issue, it is necessary to combine emotion recognition with the creation of a profile based on information such as the user's body type, activity level, health status, allergies, and food preferences to propose more accurate meal plans.

[0453] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0454] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, an emotion recognition engine for recognizing the user's emotional state from voice input and facial expressions, means for proposing a meal plan according to the user's activity level and emotional state for that day, means for the user to provide feedback on the proposed meal plan, and means for learning from the user's feedback and improving the next proposal, thereby enabling the provision of a personalized meal plan that takes into account the user's health condition and emotions.

[0455] "User's body type information" is information that indicates the user's physical characteristics such as height and weight.

[0456] "Amount of exercise" is information that indicates the user's daily exercise habits and activity level.

[0457] "Health condition" is information indicating the user's medical history and current health condition.

[0458] "Allergy" is information that indicates that the user has an allergic reaction to a particular food or ingredient.

[0459] "Dietary preferences" is information about the ingredients and cooking styles that the user prefers.

[0460] An "emotion recognition engine" is software or hardware for recognizing a user's emotional state from their voice and facial expressions.

[0461] A "generative AI model" is an artificial intelligence model trained to make optimal suggestions based on user information.

[0462] A "dataset" is a collection of data, such as feedback information, collected for use in retraining an AI model.

[0463] A "meal plan" is a meal suggestion based on a user's profile and their activity level and emotional state for the day.

[0464] "Feedback" refers to the user's evaluation and impressions of the meal plan provided.

[0465] The present invention is a system that creates an individual profile based on a user's body type information, amount of exercise, health condition, allergies, food preferences, and emotional state, and proposes an optimal meal plan. Specific embodiments for implementing the present invention are described below.

[0466] 1. Collection of User Information

[0467] The device collects information entered by the user about their body type (e.g., height and weight), physical activity (e.g., daily exercise habits), health status (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is converted into JSON format and sent to the server.

[0468] 2. Emotional Recognition

[0469] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, it can determine the user's emotions (e.g., whether they are feeling stressed) by analyzing facial expressions through the camera and voice through the microphone. This processing is performed using Python and TensorFlow.

[0470] 3. Create a user profile

[0471] The server stores the user information and emotional state sent from the device in a database and generates an individual profile for each user based on that information. The generated profile is then recorded in the database.

[0472] 4. Generate a meal plan

[0473] The server generates an optimal meal plan based on the user's profile, activity level, and emotional state for that day. The server converts the collected user information into tensor format and inputs it into a generative AI model. This generative AI model predicts the optimal meal plan based on a combination of the user's body type, exercise level, health status, allergies, food preferences, and emotional state.

[0474] 5. Meal plan offerings

[0475] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan includes ingredients and dishes that suit the user's mood.

[0476] 6. Providing Feedback

[0477] After trying the proposed meal plan, the user inputs their impressions and evaluation as feedback, which is then sent from the device to the server.

[0478] 7. Saving Feedback

[0479] The server stores the feedback information received from the terminal in a database, and also adds this feedback information to the training dataset.

[0480] 8. Retraining AI models

[0481] The server uses the stored feedback information to retrain the generative AI model, which makes the next suggestions more accurate and adapted to the user's preferences.

[0482] Specific examples

[0483] Assume the user is 30 years old, weighs 70 kg, is 175 cm tall, has a high activity level, is diabetic and allergic to dairy products, and prefers Japanese food. If the emotion recognition engine determines that the user is feeling stressed, the following steps are performed:

[0484] 1. User Information Collection:

[0485] "Enter your body type, activity level, health status, allergies, and dietary preferences."

[0486] 2. Emotion Recognition:

[0487] "Please speak into the microphone. We will recognize your facial expressions, so please look at the camera."

[0488] 3. Create a user profile:

[0489] The server generates and saves a profile based on this information.

[0490] 4. Generate meal plan:

[0491] "We offer a menu of low-carb, dairy-free Japanese cuisine."

[0492] 5. Meal Plan Offering:

[0493] Users can view the proposed meal plan on their device.

[0494] 6. Providing Feedback:

[0495] Please enter your thoughts after your meal.

[0496] 7. Saving Feedback:

[0497] The server stores the feedback information

[0498] 8. Retraining AI models:

[0499] "We will retrain it based on the feedback information to improve our next proposal."

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

[0501] Step 1:

[0502] Collection of User Information

[0503] The device accepts input from the user about their body type (height and weight), amount of exercise (daily exercise habits), health condition (medical history and allergies), and food preferences (favorite ingredients and cooking styles). The user enters this information on the provided interface, and the device converts it into JSON format and sends it to the server.

[0504] Input: Information about your body type, activity level, health status, allergies, and dietary preferences that you enter into your device

[0505] Output: User information converted to JSON format and sent to the server

[0506] Step 2:

[0507] Emotion recognition

[0508] The device uses an emotion recognition engine to recognize the user's emotional state from their voice and facial expressions. It captures facial expressions using a camera and records audio using a microphone. The emotion recognition engine analyzes facial features and voice tone to determine the user's emotion (e.g., whether they are feeling stressed). The results are converted into JSON format and sent to the server.

[0509] Input: User facial expression images and voice data

[0510] Output: Emotional state information converted to JSON format and sent to the server

[0511] Step 3:

[0512] Creating a User Profile

[0513] The server receives the user information and emotional state sent from the device and stores them in a database. Based on this information, an individual profile of the user is generated. The profile is stored as a tensor-type data structure that comprehensively assesses the user's health and emotional state.

[0514] Input: User information and emotional state information in JSON format

[0515] Output: User profile stored in the database

[0516] Step 4:

[0517] Generate a meal plan

[0518] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. This is done using a generative AI model. The AI ​​model takes user data in tensor format as input and predicts the optimal meal plan based on that data. The generated meal plan is converted to JSON format and sent to the device.

[0519] Input: User profile in tensor format, along with activity level and emotional state for that day

[0520] Output: JSON formatted meal plan sent to the device

[0521] Step 5:

[0522] Meal plan provided

[0523] The device displays the meal plan received from the server, and the user reviews the plan and decides whether to select it. During this process, the plan includes ingredients and dishes that correspond to the user's emotional state.

[0524] Input: JSON format meal plan received from the server

[0525] Output: Meal plan displayed on device

[0526] Step 6:

[0527] Providing Feedback

[0528] After trying the proposed meal plan, the user enters their impressions and evaluations as feedback into the device, which then converts this feedback information into JSON format and sends it to the server.

[0529] Input: User feedback information

[0530] Output: Feedback information converted to JSON format and sent to the server

[0531] Step 7:

[0532] Save your feedback

[0533] The server stores the feedback information received from the devices in a database, which is also used as a data set to help propose improvements for the next time.

[0534] Input: Feedback information in JSON format

[0535] Output: Feedback information stored in a database

[0536] Step 8:

[0537] Retraining an AI model

[0538] The server uses the stored feedback information to retrain the generative AI model, which then gains the ability to generate more accurate and user-specific meal plans for the next time.

[0539] Input: Feedback information stored in the database

[0540] Output: An improved generative AI model

[0541] 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.

[0542] 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.

[0543] 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.

[0544] [Second embodiment]

[0545] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] 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.

[0556] 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."

[0557] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[0558] 1. Collection of User Information

[0559] Terminal

[0560] A user accesses the system using a terminal and inputs information about their body type (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as basic data for creating an individual profile of the user.

[0561] 2. Create a user profile

[0562] server

[0563] The server receives the user information sent from the terminal, stores it in a database, and then automatically generates an individual profile for each user based on this information.

[0564] 3. Meal plan suggestions

[0565] server

[0566] Based on the user's profile, the server generates an optimal meal plan taking into account the user's daily activity level. Specifically, the user's input information is converted into tensor format and fed into an artificial intelligence (AI) model. The AI ​​model processes the information and predicts the optimal meal plan.

[0567] The generated meal plan is based on the user's activity level, health status, allergies, food preferences, etc. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested. Also, if a user prefers Japanese food, a menu centered on Japanese cuisine will be provided.

[0568] 4. Providing suggestions and gathering feedback

[0569] Terminal

[0570] The meal plan generated by the server is sent to the user's device, where the user can review it. The user tries out the proposed meal plan and then inputs their impressions and ratings as feedback.

[0571] 5. Feedback learning and model refinement

[0572] server

[0573] The collected feedback is stored in a database, and the server uses this feedback data to retrain the AI ​​model and improve its next suggestions to better suit the user's preferences.

[0574] Specific examples

[0575] Example user:

[0576] Age: 30

[0577] Weight: 70kg

[0578] Height: 175cm

[0579] Activity level: High

[0580] Health condition: Diabetes

[0581] Allergies: Dairy

[0582] Food preference: Japanese food

[0583] 1. Collection of User Information

[0584] The user inputs the above information from the terminal and transmits it to the server.

[0585] 2. Create a user profile

[0586] The server uses this information to generate individual profiles and stores them in a database.

[0587] 3. Meal plan suggestions

[0588] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[0589] 4. Providing suggestions and gathering feedback

[0590] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[0591] 5. Feedback learning and model refinement

[0592] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[0593] The processing flow will be explained below.

[0594] Step 1: Enter your user information

[0595] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The terminals then send this information to the server.

[0596] Step 2: Save user information

[0597] The server stores the user information received from the terminal in a database, and through this storage process, an individual profile of each user is recorded in the database.

[0598] Step 3: Creating a User Profile

[0599] The server uses the information in the database to generate an individual profile for each user, which is then stored in the database again. The user profile includes information about body type, activity level, health status, allergies, and food preferences that users have entered.

[0600] Step 4: Generate a meal plan

[0601] The server generates an optimal meal plan using an AI model based on the user's profile. Specifically, the server converts the user's information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model then uses the stored data to create the optimal menu for the user.

[0602] Step 5: Submit your meal plan

[0603] The server sends the generated meal plan to the user's terminal, where the user can view the proposed meal plan.

[0604] Step 6: Provide feedback

[0605] The user actually tries out the proposed meal plan and inputs feedback on the results. The terminal sends the user's feedback information to the server.

[0606] Step 7: Save your feedback

[0607] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[0608] Step 8: Retraining the AI ​​model

[0609] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[0610] Step 9: Provide an improved meal plan

[0611] Using the retrained AI model, the server again generates and serves the optimal meal plan to the user, which in turn provides an improved meal plan that incorporates user feedback.

[0612] Example 1

[0613] 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."

[0614] In modern society, it is important to provide meal plans tailored to an individual's health status and lifestyle. However, conventional systems have had difficulty in properly collecting a wide range of user information (e.g., body shape, health status, food preferences, etc.) and providing meal plans tailored to individual needs. Furthermore, there were insufficient means to effectively utilize user feedback and improve future proposals. This resulted in a decline in user satisfaction.

[0615] 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.

[0616] In this invention, the server includes means for sending collected user information to the server in JSON format, means for saving user information in a database and generating a profile for each user, and means for converting the user profile into tensor format and inputting it into an AI model to generate an optimal meal plan. This enables the generation of a customized meal plan based on detailed user information, and by continuously incorporating user feedback, it is possible to improve the accuracy and satisfaction of subsequent suggestions.

[0617] "User information" is detailed information about the user, such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[0618] A "terminal" is a device used by a user (e.g., a smartphone or PC) and is hardware used to access the system and input and receive information.

[0619] A "server" is a computer system that receives, stores, processes, and analyzes collected user information.

[0620] A "database" is a data structure for storing and managing collected user information and feedback information.

[0621] A "profile" is a collection of individual information about each user that is generated based on collected user information.

[0622] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and perform specific tasks.

[0623] "Tensor format" is user information converted into a multidimensional array format, and is used when inputting it into an AI model.

[0624] A "meal plan" is a meal suggestion tailored to a user, generated based on the user's profile.

[0625] "Feedback" refers to the impressions and ratings provided by users after trying the suggested meal plan.

[0626] "Retraining" is the process of updating an existing AI model with new feedback data collected to improve its accuracy.

[0627] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data in text format and is used for data exchange.

[0628] The "HTTPS protocol" is an abbreviation for HyperText Transfer Protocol Secure, a protocol for encrypting internet communications to send and receive data safely.

[0629] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[0630] 1. Collection of User Information

[0631] Terminal

[0632] Users access the system using a terminal and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as the basis for creating an individual profile of the user. The information is packaged in JSON format and sent using the HTTPS protocol.

[0633] 2. Create a user profile

[0634] server

[0635] The server receives and parses user information in JSON format sent from the device. The collected information is stored in a database, and a profile for each user is generated based on this information. The database software used is a standard SQL database (e.g., MySQL or PostgreSQL).

[0636] 3. Meal plan suggestions

[0637] server

[0638] The server generates an optimal meal plan based on each user's profile. The user profile information is converted into tensor format and input into an AI model using a deep learning library such as TensorFlow. The AI ​​model analyzes the user information and predicts the optimal meal plan for each user. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested, and if a user prefers Japanese food, a menu centered on Japanese cuisine will be generated.

[0639] 4. Providing suggestions and gathering feedback

[0640] Terminal

[0641] The generated meal plan is sent to the user's device, where the user can review it. The user can try out the proposed meal plan and then enter their impressions and ratings as feedback. The feedback is again packaged in JSON format and sent to the server using the HTTPS protocol.

[0642] 5. Feedback learning and model refinement

[0643] server

[0644] The server stores the collected feedback in a database and retrains the AI ​​model. The retraining process is carried out using the new feedback data collected, allowing the system's suggestions to better meet the user's needs in the future.

[0645] Specific examples

[0646] Example user:

[0647] Age: 30

[0648] Weight: 70kg

[0649] Height: 175cm

[0650] Activity level: High

[0651] Health condition: Diabetes

[0652] Allergies: Dairy

[0653] Food preference: Japanese food

[0654] 1. Collection of User Information

[0655] The user inputs the above information from the terminal and sends it to the server.

[0656] 2. Create a user profile

[0657] The server uses this information to generate individual profiles and stores them in a database.

[0658] 3. Meal plan suggestions

[0659] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[0660] 4. Providing suggestions and gathering feedback

[0661] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[0662] 5. Feedback learning and model refinement

[0663] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[0664] Example prompt sentence:

[0665] "Please suggest the best meal plan for a user who is 30 years old, weighs 70kg, is 175cm tall, has a high activity level, has diabetes, is allergic to dairy products, and likes Japanese food."

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

[0667] Step 1:

[0668] Entering user information

[0669] Users access the system using a terminal and input information such as their body type, amount of exercise, health condition, allergies, and dietary preferences.

[0670] Input: User's body type information (e.g., height 175 cm, weight 70 kg), amount of exercise (e.g., daily jogging), health condition (e.g., diabetes, dairy allergy), food preferences (e.g., Japanese food)

[0671] Output: User information packaged in JSON format

[0672] Specific operation: Information entered on the device interface is converted to JSON format using front-end technologies such as JavaScript.

[0673] Step 2:

[0674] Sending user information

[0675] The terminal transmits the packaged user information to the server via the HTTPS protocol.

[0676] Input: User information in JSON format

[0677] Output: User information is sent to the server

[0678] Specific operation: The device uses an SSL certificate to ensure security when sending information.

[0679] Step 3:

[0680] Creating a User Profile

[0681] The server parses the received JSON formatted user information, stores it in a database, and then generates a profile for each user.

[0682] Input: User information in JSON format

[0683] Output: User profile stored in the database

[0684] Specific operation: The server uses Python or Node.js to parse the JSON information and save it to the database using SQL commands.

[0685] Step 4:

[0686] Generate a meal plan

[0687] The server generates an optimal meal plan based on the user profile, converting the user information into tensor format and inputting it into an AI model running TensorFlow.

[0688] Input: Database user profile

[0689] Output: Meal plan

[0690] How it works: User profile information is converted into tensor format and fed into an AI model using deep learning libraries such as TensorFlow to predict optimal meal plans.

[0691] Step 5:

[0692] Meal plan provided

[0693] The server sends the generated meal plan to the user's terminal.

[0694] Input: Generated meal plan

[0695] Output: Meal plan displayed on user's device

[0696] Specific operation: The server sends the meal plan using the HTTPS protocol, and the device visualizes the received data and displays it to the user.

[0697] Step 6:

[0698] Enter your feedback

[0699] The user checks the proposed meal plan, tries it out, and then enters their impressions and evaluations as feedback into the device.

[0700] Input: Feedback information (e.g., taste, satiety, health effects, etc.)

[0701] Output: Feedback information in JSON format

[0702] Specific behavior: Information entered through the feedback form is packaged in JSON format.

[0703] Step 7:

[0704] Send Feedback

[0705] The terminal sends the feedback information to the server using the HTTPS protocol.

[0706] Input: Feedback information in JSON format

[0707] Output: Feedback information sent to the server

[0708] Specific behavior: Send information securely using an SSL certificate

[0709] Step 8:

[0710] Improve the model based on feedback

[0711] The server stores the received feedback information in a database and retrains the AI ​​model using new feedback data.

[0712] Input: Feedback information

[0713] Output: An improved AI model

[0714] Specific operation: Retrieves feedback data from the database and executes the process of retraining the AI ​​model using TensorFlow.

[0715] (Application example 1)

[0716] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0717] In modern society, there is a demand for systems that propose optimal meal plans based on an individual's health status and preferences and enable delivery orders. However, conventional systems are unable to fully utilize user information and feedback, making it difficult to provide highly accurate meal plans to individual users. Furthermore, the process for reflecting feedback and improving the next proposal is insufficient. The present invention aims to solve these problems and provide a system that enables the provision of personalized, healthy meal plans and the rapid delivery order of such plans.

[0718] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0719] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and dietary preferences, means for creating an individual profile based on the collected user information, and means for proposing an optimal meal plan based on the user's activity level for that day and enabling immediate delivery ordering. This allows users to easily obtain a meal plan tailored to their health condition and preferences and quickly order delivery of the plan.

[0720] The system also maintains a database of suggested meal plans, generates meal plans using this database, and uses them for delivery orders, enabling efficient suggestions. Furthermore, feedback information is stored in a dataset, which can be used to retrain the generative AI model, and prompts can be used to refine the next meal plan suggestions, enabling suggestions that are more tailored to each user's preferences.

[0721] "Information regarding the user's body type, amount of exercise, health condition, allergies, and food preferences" refers to data regarding weight, height, exercise habits, medical history, allergies, and food preferences entered by the user.

[0722] An "individual profile" is a collection of information customized for each user that is generated based on collected user information.

[0723] The "activity level for that day" is data relating to the amount of exercise and work intensity of the user for that day.

[0724] The "optimal meal plan" is a meal menu suggestion that is suitable for the user's health condition and food preferences, generated by AI based on the user's profile.

[0725] A "delivery order" is a request for a service to actually cook and deliver the proposed meal plan.

[0726] "Feedback" refers to a user providing feedback or rating on the meal they received.

[0727] A "dataset" is a collection of large amounts of data, including feedback information.

[0728] A "generative AI model" is an artificial intelligence system that is trained to use large amounts of data to generate optimal meal plans.

[0729] A "prompt" is a textual instruction or data entry statement that is input into an AI model.

[0730] This invention relates to a system that proposes personalized meal plans and allows users to instantly order delivery. The system collects information about the user's body type, activity level, health status, allergies, and food preferences, generates a profile based on that information, and proposes an optimal meal plan. Furthermore, the system collects feedback about the proposed meal plans and reflects that feedback in the AI ​​model to improve it.

[0731] 1. System Program

[0732] This system is primarily composed of a smartphone, a server, and a generative AI model. Users enter their information using their smartphone, and the data is sent to the server. The server creates an individual profile based on the received information, and the generative AI model generates an optimal meal plan. The generated meal plan is sent to the user's smartphone, allowing them to order delivery.

[0733] 2. Data processing and calculation

[0734] The smartphone application converts the user's input data into an appropriate format to facilitate sending it to the server. The server receives this data and stores it in a database. It also converts the data into tensor format for input to the generative AI model. The generative AI model is built using TensorFlow and processes the user's profile data to generate an optimal meal plan. Furthermore, feedback data from the user is stored on the server and used to retrain the AI ​​model and improve the accuracy of the next meal plan.

[0735] 3. Specific Examples

[0736] For example, consider a 30-year-old user who is 175 cm tall, weighs 70 kg, has a high activity level, and suffers from diabetes and a dairy allergy. If the user prefers Japanese food, the user first enters this information into a smartphone application. The server generates a profile based on the user information, and the generated AI model proposes a low-carb, dairy-free Japanese meal plan. This proposal is immediately sent to the smartphone, allowing the user to place a delivery order.

[0737] Additionally, after trying a meal, users can provide feedback, such as their impressions and ratings, which the server will collect and use to improve its suggestions for the next time.

[0738] 4. Examples of prompts

[0739] User Profile

[0740] Age: 30

[0741] Weight: 70kg

[0742] Height: 175cm

[0743] Activity level: High

[0744] Health Condition: Diabetes

[0745] Allergies: Dairy

[0746] Food preference: Japanese food

[0747] Based on the user profile above, please suggest the best low-carb, dairy-free Japanese meal menu.

[0748] In this way, the system not only proposes optimal meal plans tailored to the user's health condition and preferences, but also allows for quick delivery orders, allowing users to easily obtain healthy meals.

[0749] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0750] Step 1:

[0751] Users use their smartphones to input information about their body type, amount of exercise, health condition, allergies, food preferences, etc. Input data includes age, weight, height, exercise habits, medical history, allergies, favorite dishes, etc. The input data is temporarily stored on the device and then sent to the server.

[0752] Input data: User's body type, amount of exercise, health condition, allergies, food preferences

[0753] Output data: User profile information sent to the server

[0754] Step 2:

[0755] The server receives the user information sent from the device and stores it in a database. At this time, it organizes various data (body type, amount of exercise, health condition, allergies, food preferences) and creates a user profile for centralized management.

[0756] Input data: User profile information

[0757] Output data: User profile stored in a database

[0758] Step 3:

[0759] The server converts the collected user profile information into tensor format and inputs it into a generative AI model. The AI ​​model is built using TensorFlow and generates an optimal meal plan based on the user's profile data. The generated meal plan is returned to the server via an API.

[0760] Input data: User profile information in tensor format

[0761] Output: Generated meal plan

[0762] Step 4:

[0763] The server sends the generated meal plan to the user's smartphone terminal.

[0764] Input data: Generated meal plan

[0765] Output data: Meal plan displayed on a smartphone

[0766] Step 5:

[0767] The user checks the proposed meal plans on their smartphone, selects the one they like, and places a delivery order. The order information is sent to a server and linked to the restaurant or delivery service.

[0768] Input data: User order information

[0769] Output data: Order request to delivery service

[0770] Step 6:

[0771] After receiving the meal, the user inputs their impressions and evaluation of the meal as feedback into their smartphone, and this feedback data is sent to the server.

[0772] Input data: User feedback on meals

[0773] Output data: Feedback data sent to the server

[0774] Step 7:

[0775] The server stores the collected feedback information in a dataset and uses it to retrain the generative AI model, resulting in more accurate meal plan suggestions for the next time.

[0776] Input data: Feedback data

[0777] Output data: Improved generative AI model

[0778] This is the flow of processing in the program for the system that realizes the application example. At each processing step, specific data processing and calculations are performed, and the system evolves step by step.

[0779] 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.

[0780] The present invention is a system that combines an emotion engine that recognizes the user's emotions to collect information such as a user's body type, amount of exercise, health condition, allergies, and food preferences, create an individual profile based on that information, and propose an optimal meal plan. Specific embodiments of this system are described below.

[0781] 1. Collection of User Information

[0782] Terminal

[0783] A user accesses the system using a terminal and inputs their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[0784] 2. Emotional Recognition

[0785] Terminal

[0786] The device is equipped with an emotion engine that recognizes the user's emotional state from their voice and facial expressions. For example, it analyzes the tone of their voice and facial movements when they interact with the system through voice input or a camera to determine the user's emotions.

[0787] 3. Create a user profile

[0788] server

[0789] The server stores the user information and emotional state sent from the terminal in a database and generates an individual profile for each user based on that information. The generated profile is recorded in the database.

[0790] 4. Generate a meal plan

[0791] server

[0792] The server generates an optimal meal plan based on the user's profile, activity level for that day, and emotional state. The server converts the user's information into tensor format and inputs it into an AI model. The AI ​​model predicts the optimal meal plan based on a combination of the user's body type, exercise level, health status, allergies, food preferences, and emotional state.

[0793] 5. Meal plan offerings

[0794] Terminal

[0795] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan may include ingredients and dishes that match the user's mood.

[0796] 6. Providing Feedback

[0797] User

[0798] After trying the proposed meal plan, the user inputs their impressions and evaluations as feedback, and the device sends this feedback information to the server.

[0799] 7. Saving Feedback

[0800] server

[0801] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[0802] 8. Retraining AI models

[0803] server

[0804] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[0805] Specific examples

[0806] Example user:

[0807] Age: 30

[0808] Weight: 70kg

[0809] Height: 175cm

[0810] Activity level: High

[0811] Health condition: Diabetes

[0812] Allergies: Dairy

[0813] Food preference: Japanese food

[0814] Emotional state: Feeling stressed

[0815] 1. Collection of User Information

[0816] The user inputs the above information from the terminal and transmits it to the server.

[0817] 2. Emotional Recognition

[0818] The device analyzes the user's voice and facial expression and determines that the user is feeling stressed.

[0819] 3. Create a user profile

[0820] The server generates an individual profile based on this information and stores it in a database.

[0821] 4. Generate a meal plan

[0822] Based on this profile, the server generates a menu that is low in carbohydrates, dairy-free, mainly Japanese food, and includes ingredients that reduce stress, and sends it to the user's device.

[0823] 5. Meal plan offerings

[0824] The user reviews the proposed meal plan on the device.

[0825] 6. Providing Feedback

[0826] Users enter feedback about the meal plan they tried, such as "I felt relaxed," and send it to the server via their device.

[0827] 7. Saving Feedback

[0828] The server stores the collected feedback in a database and adds it to the training dataset.

[0829] 8. Retraining AI models

[0830] The server uses the feedback data to retrain the AI ​​model and incorporates the feedback into its next suggestions.

[0831] The processing flow will be explained below.

[0832] Step 1: Enter your user information

[0833] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[0834] Step 2: Recognizing user emotions

[0835] The device uses an emotion engine to analyze the user's voice and facial expressions to recognize their emotional state. For example, when a user interacts with the system via voice input or a camera, the device analyzes their voice tone and facial movements to determine whether they are feeling stressed.

[0836] Step 3: Creating a User Profile

[0837] The server generates an individual profile based on the user information and emotional state received from the device, and the generated profile is stored in a database.

[0838] Step 4: Generate a meal plan

[0839] The server uses an AI model to generate an optimal meal plan, taking into account the user's profile, activity level, and emotional state. Specifically, the server converts user information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model generates the optimal menu based on a combination of data such as body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[0840] Step 5: Submit your meal plan

[0841] The server sends the generated meal plan to the user's device, where the user can view the proposed meal plan.

[0842] Step 6: Provide feedback

[0843] The user tries out the proposed meal plan and inputs feedback on the results, which is then sent to the server by the device.

[0844] Step 7: Save your feedback

[0845] The server stores the feedback information received from the devices in a database, and also adds this feedback information to a dataset for later retraining the model.

[0846] Step 8: Retraining the AI ​​model

[0847] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[0848] Step 9: Provide an improved meal plan

[0849] Using the retrained AI model, the server again generates and provides the optimal meal plan to the user. The improved meal plan reflects the user's feedback. For example, if the user is feeling stressed, a menu containing foods that will reduce stress will be provided.

[0850] Example 2

[0851] 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."

[0852] Conventional meal plan suggestion systems provide meal plans based on basic information such as the user's body type and health condition, but do not take into account the user's emotional state. As a result, they are unable to provide meal plans that are adapted to the user's mood and emotions, which can lead to a decrease in user satisfaction. Furthermore, improvements to the model based on feedback are not made quickly, which can delay improvements in suggestion accuracy.

[0853] 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.

[0854] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, means for proposing a meal plan based on the user's activity level and emotional state for that day, means for recognizing the user's emotional state using an emotion recognition engine installed in the terminal, means for learning from the user's feedback and improving the next proposal, means for saving the feedback information, and means for retraining the AI ​​model using the saved feedback information. This makes it possible to provide an optimal meal plan that takes the user's emotional state into consideration and to quickly improve the model.

[0855] "User information" refers to personal information such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[0856] A "profile" is a data set specific to an individual user that is generated based on collected user information.

[0857] "Activity level" is information indicating the amount of exercise the user does on a daily basis and the intensity of the activity on each day.

[0858] "Emotional state" is information that indicates the user's emotional or mood state, and is recognized from voice and facial expressions.

[0859] A "meal plan" is a menu of meals suggested based on user information, activity level, and emotional state for the day.

[0860] "Feedback" refers to the impressions and evaluations provided by users after trying the proposed meal plan.

[0861] An "emotion recognition engine" is software installed on a device that analyzes the user's emotional state from their voice and facial expressions.

[0862] A "database" is an information management system for storing various data used by the system, such as user information, profiles, and feedback information.

[0863] The "AI model" is a machine learning model that predicts the optimal meal plan based on collected user information and feedback information.

[0864] The "tensor format" is a format that represents data as a multidimensional array and is used as an input format for AI models.

[0865] The present invention relates to a system that collects information on a user's body type, amount of exercise, health condition, allergies, food preferences, emotional state, etc., creates an individual profile based on the collected information, and proposes an optimal meal plan. This system uses a combination of an emotion recognition engine and a generative AI model to optimize the meal plan based on the user's information and emotional state.

[0866] Collection of User Information

[0867] Terminal

[0868] Users access the system using a device such as a smartphone or PC and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is sent from the device to the server.

[0869] Emotion recognition

[0870] Terminal

[0871] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, when a user interacts with the system through voice input or a camera, the system analyzes their voice tone and facial movements to determine whether the user is feeling stressed. This determination result is sent from the device to the server.

[0872] Creating a User Profile

[0873] server

[0874] The server receives the user information and emotional state sent from the terminal and stores it in a database, and based on this, generates an individual user profile and records it in the database.

[0875] Generate a meal plan

[0876] server

[0877] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. The server converts the user information into tensor format and inputs it into a generative AI model. The AI ​​model combines data such as body shape, exercise volume, health status, allergies, food preferences, and emotional state to predict the optimal meal plan. This meal plan is sent to the device in JSON format.

[0878] Meal plan provided

[0879] Terminal

[0880] The optimal meal plan sent from the server is displayed on the user's device, where the user can view it, and the suggested menu includes ingredients and dishes that suit the mood based on the user's emotional state.

[0881] Providing Feedback

[0882] User

[0883] After trying the meal plan provided, the user inputs their impressions and ratings, and this feedback is sent from the device to the server.

[0884] Save your feedback

[0885] server

[0886] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model, so that it can be reflected in the next proposal.

[0887] Retraining an AI model

[0888] server

[0889] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[0890] Specific examples

[0891] Here is a concrete example: Assume a 30-year-old male, weighing 70 kg and 175 cm tall, has a high activity level, suffers from diabetes, and is allergic to dairy products. This user prefers Japanese food and is currently feeling stressed.

[0892] Collecting user information: The user enters information from the terminal and sends it to the server.

[0893] Emotion recognition: The device analyzes the user's voice and facial expressions to determine whether they are feeling stressed.

[0894] Creating a user profile: The server stores the information in a database and creates a profile.

[0895] Meal plan generation: The server generates a menu of mainly Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[0896] Meal plan provided: The user reviews the proposed meal plan on the device.

[0897] Providing feedback: The user tries the meal and provides feedback that it was "relaxing."

[0898] Save Feedback: The server saves the feedback in a database and adds it to the training dataset.

[0899] Retraining the AI ​​model: The server uses the feedback data to retrain the AI ​​model and reflect it in the next proposal.

[0900] Example prompts for generative AI models

[0901] "I'm a 30-year-old man, 180cm tall, weigh 75kg, and run three times a week. I have high blood pressure and no particular allergies. My favorite food is Chinese food, and I've been feeling pretty stressed at work lately. I'd like you to suggest a meal plan that fits these conditions."

[0902] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0903] Step 1:

[0904] Collection of User Information

[0905] Terminal

[0906] Users access the system using a smartphone or PC and enter their body information (e.g., height and weight), exercise volume, health status, allergies, dietary preferences, etc. into the provided interface. The entered information is sent from the device to the server in JSON format.

[0907] Input: User-entered information about your body type, activity level, health status, allergies, and dietary preferences.

[0908] Data processing: Convert the input information into JSON format.

[0909] Output: User information in JSON format is sent from the device to the server.

[0910] What happens: A user opens the app, fills out a form, and presses the "Submit" button.

[0911] Step 2:

[0912] Emotion recognition

[0913] Terminal

[0914] The device's built-in camera and microphone are used to collect the user's voice and facial expressions. The emotion recognition engine analyzes this data and determines the user's emotional state. The results are sent to the server in JSON format.

[0915] Input: User's voice data, facial expression data.

[0916] Data processing: The emotion recognition engine analyzes voice and facial expressions to determine the emotional state.

[0917] Output: The determined emotional state is sent to the server in JSON format.

[0918] Specific operation: The user interacts with the system through voice and captures facial expressions with the camera.

[0919] Step 3:

[0920] Creating a User Profile

[0921] server

[0922] The server stores the user information and emotional state sent from the device in a database, and generates an individual profile for each user based on this information.

[0923] Input: User information and emotional state sent from the device.

[0924] Data processing: User information and emotional state are stored in a database and a profile is generated.

[0925] Output: The generated user profile is recorded in a database.

[0926] Specific operation: The server stores the received data in a database and generates a new profile item.

[0927] Step 4:

[0928] Generate a meal plan

[0929] server

[0930] The server generates an optimal meal plan based on the generated user profile, the activity level and emotional state of the day. The user information is converted into tensor format and input into a generative AI model. The AI ​​model predicts the optimal meal plan based on body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[0931] Input: Stored user profile, activity level, emotional state.

[0932] Data processing: User information is converted into tensor format and input into the generative AI model.

[0933] Output: The generated meal plan is sent to the terminal in JSON format.

[0934] Specific operation: The server inputs profile information into the AI ​​model and outputs a meal plan as the analysis result.

[0935] Step 5:

[0936] Meal plan provided

[0937] Terminal

[0938] The optimal meal plan sent from the server is displayed on the user's device, where the user can check the proposed plan and use it to make daily meal choices.

[0939] Input: Meal plan sent from server.

[0940] Data processing: Display meal plan information on the device.

[0941] Output: User can review the suggested meal plan.

[0942] Specific operation: Display the meal plan sent from the server on the app screen.

[0943] Step 6:

[0944] Providing Feedback

[0945] User

[0946] After trying out the meal plan provided, the user inputs their impressions and ratings, and the input feedback is sent from the device to the server.

[0947] Input: User comments and ratings.

[0948] Data processing: Convert the feedback information into JSON format.

[0949] Output: Feedback information is sent from the device to the server.

[0950] Specific operation: The user enters feedback on the terminal and sends it to the server by clicking the send button.

[0951] Step 7:

[0952] Save your feedback

[0953] server

[0954] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model.

[0955] Input: Feedback information sent from the device.

[0956] Data processing: The feedback information is stored in a database and added to the training dataset.

[0957] Output: The feedback information is stored in a database.

[0958] Specific operation: The server stores the received data in a database and adds it to the training dataset.

[0959] Step 8:

[0960] Retraining an AI model

[0961] server

[0962] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[0963] Input: Saved feedback information.

[0964] Data processing: Retraining the AI ​​model based on feedback information.

[0965] Output: The updated AI model.

[0966] Specific operation: The server inputs the feedback data into the AI ​​model and performs retraining.

[0967] (Application example 2)

[0968] 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."

[0969] In today's busy lifestyles, it is extremely difficult to easily provide optimal meal plans tailored to individual users' health and emotional states. Conventional systems have difficulty proposing personalized meal plans due to insufficient user information input and recognition of emotional states. Furthermore, while there is a demand for meal plans that take into account the user's emotional state, there are limitations in this regard as well. To address this issue, it is necessary to combine emotion recognition with the creation of a profile based on information such as the user's body type, activity level, health status, allergies, and food preferences to propose more accurate meal plans.

[0970] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0971] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, an emotion recognition engine for recognizing the user's emotional state from voice input and facial expressions, means for proposing a meal plan according to the user's activity level and emotional state for that day, means for the user to provide feedback on the proposed meal plan, and means for learning from the user's feedback and improving the next proposal, thereby enabling the provision of a personalized meal plan that takes into account the user's health condition and emotions.

[0972] "User's body type information" is information that indicates the user's physical characteristics such as height and weight.

[0973] "Amount of exercise" is information that indicates the user's daily exercise habits and activity level.

[0974] "Health condition" is information indicating the user's medical history and current health condition.

[0975] "Allergy" is information that indicates that the user has an allergic reaction to a particular food or ingredient.

[0976] "Dietary preferences" is information about the ingredients and cooking styles that the user prefers.

[0977] An "emotion recognition engine" is software or hardware for recognizing a user's emotional state from their voice and facial expressions.

[0978] A "generative AI model" is an artificial intelligence model trained to make optimal suggestions based on user information.

[0979] A "dataset" is a collection of data, such as feedback information, collected for use in retraining an AI model.

[0980] A "meal plan" is a meal suggestion based on a user's profile and their activity level and emotional state for the day.

[0981] "Feedback" refers to the user's evaluation and impressions of the meal plan provided.

[0982] The present invention is a system that creates an individual profile based on a user's body type information, amount of exercise, health condition, allergies, food preferences, and emotional state, and proposes an optimal meal plan. Specific embodiments for implementing the present invention are described below.

[0983] 1. Collection of User Information

[0984] The device collects information entered by the user about their body type (e.g., height and weight), physical activity (e.g., daily exercise habits), health status (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is converted into JSON format and sent to the server.

[0985] 2. Emotional Recognition

[0986] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, it can determine the user's emotions (e.g., whether they are feeling stressed) by analyzing facial expressions through the camera and voice through the microphone. This processing is done using Python and TensorFlow.

[0987] 3. Create a user profile

[0988] The server stores the user information and emotional state sent from the device in a database and generates an individual profile for each user based on that information. The generated profile is then recorded in the database.

[0989] 4. Generate a meal plan

[0990] The server generates an optimal meal plan based on the user's profile, activity level, and emotional state for that day. The server converts the collected user information into tensor format and inputs it into a generative AI model. This generative AI model predicts the optimal meal plan based on a combination of the user's body type, exercise volume, health status, allergies, food preferences, and emotional state.

[0991] 5. Meal plan offerings

[0992] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan includes ingredients and dishes that suit the user's mood.

[0993] 6. Providing Feedback

[0994] After trying the proposed meal plan, the user inputs their impressions and evaluations as feedback, which is then sent from the device to the server.

[0995] 7. Saving Feedback

[0996] The server stores the feedback information received from the terminal in a database, and also adds this feedback information to the training dataset.

[0997] 8. Retraining AI models

[0998] The server uses the stored feedback information to retrain the generative AI model, which makes the next suggestions more accurate and adapted to the user's preferences.

[0999] Specific examples

[1000] Assume the user is 30 years old, weighs 70 kg, is 175 cm tall, has a high activity level, is diabetic and allergic to dairy products, and prefers Japanese food. If the emotion recognition engine determines that the user is feeling stressed, the following steps are performed:

[1001] 1. User Information Collection:

[1002] "Enter your body type, activity level, health status, allergies, and dietary preferences."

[1003] 2. Emotion Recognition:

[1004] "Please speak into the microphone. We will recognize your facial expressions, so please look at the camera."

[1005] 3. Create a user profile:

[1006] The server generates and saves a profile based on this information.

[1007] 4. Generate meal plan:

[1008] "We offer a menu of low-carb, dairy-free Japanese cuisine."

[1009] 5. Meal Plan Offering:

[1010] Users can view the proposed meal plan on their device.

[1011] 6. Providing Feedback:

[1012] Please enter your thoughts after your meal.

[1013] 7. Saving Feedback:

[1014] The server stores the feedback information

[1015] 8. Retraining AI models:

[1016] "We will retrain it based on the feedback information to improve our next proposal."

[1017] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1018] Step 1:

[1019] Collection of User Information

[1020] The device accepts input from the user about their body type (height and weight), amount of exercise (daily exercise habits), health condition (medical history and allergies), and food preferences (favorite ingredients and cooking styles). The user enters this information on the provided interface, and the device converts it into JSON format and sends it to the server.

[1021] Input: Information about your body type, activity level, health status, allergies, and dietary preferences that you enter into your device

[1022] Output: User information converted to JSON format and sent to the server

[1023] Step 2:

[1024] Emotion recognition

[1025] The device uses an emotion recognition engine to recognize the user's emotional state from their voice and facial expressions. It captures facial expressions using a camera and records audio using a microphone. The emotion recognition engine analyzes facial features and voice tone to determine the user's emotion (e.g., whether they are feeling stressed). The results are converted into JSON format and sent to the server.

[1026] Input: User facial expression images and voice data

[1027] Output: Emotional state information converted to JSON format and sent to the server

[1028] Step 3:

[1029] Creating a User Profile

[1030] The server receives the user information and emotional state sent from the device and stores them in a database. Based on this information, an individual profile of the user is generated. The profile is stored as a tensor-type data structure that comprehensively assesses the user's health and emotional state.

[1031] Input: User information and emotional state information in JSON format

[1032] Output: User profile stored in the database

[1033] Step 4:

[1034] Generate a meal plan

[1035] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. This is done using a generative AI model. The AI ​​model takes user data in tensor format as input and predicts the optimal meal plan based on that data. The generated meal plan is converted to JSON format and sent to the device.

[1036] Input: User profile in tensor format, along with activity level and emotional state for that day

[1037] Output: JSON formatted meal plan sent to the device

[1038] Step 5:

[1039] Meal plan provided

[1040] The device displays the meal plan received from the server, and the user reviews the plan and decides whether to select it. During this process, the plan includes ingredients and dishes that correspond to the user's emotional state.

[1041] Input: JSON format meal plan received from the server

[1042] Output: Meal plan displayed on device

[1043] Step 6:

[1044] Providing Feedback

[1045] After trying the proposed meal plan, the user enters their impressions and evaluations as feedback into the device, which then converts this feedback information into JSON format and sends it to the server.

[1046] Input: User feedback information

[1047] Output: Feedback information converted to JSON format and sent to the server

[1048] Step 7:

[1049] Save your feedback

[1050] The server stores the feedback information received from the devices in a database, which is also used as a data set to help propose improvements for the next time.

[1051] Input: Feedback information in JSON format

[1052] Output: Feedback information stored in a database

[1053] Step 8:

[1054] Retraining an AI model

[1055] The server uses the stored feedback information to retrain the generative AI model, which then gains the ability to generate more accurate and user-specific meal plans for the next time.

[1056] Input: Feedback information stored in the database

[1057] Output: An improved generative AI model

[1058] 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.

[1059] 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.

[1060] 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.

[1061] [Third embodiment]

[1062] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1063] 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.

[1064] 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).

[1065] 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.

[1066] 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.

[1067] 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).

[1068] 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.

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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.

[1073] 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."

[1074] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[1075] 1. Collection of User Information

[1076] Terminal

[1077] A user accesses the system using a terminal and inputs information about their body type (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as basic data for creating an individual profile of the user.

[1078] 2. Create a user profile

[1079] server

[1080] The server receives the user information sent from the terminal, stores it in a database, and then automatically generates an individual profile for each user based on this information.

[1081] 3. Meal plan suggestions

[1082] server

[1083] Based on the user's profile, the server generates an optimal meal plan taking into account the user's daily activity level. Specifically, the user's input information is converted into tensor format and fed into an artificial intelligence (AI) model. The AI ​​model processes the information and predicts the optimal meal plan.

[1084] The generated meal plan is based on the user's activity level, health status, allergies, food preferences, etc. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested. Also, if a user prefers Japanese food, a menu centered on Japanese cuisine will be provided.

[1085] 4. Providing suggestions and gathering feedback

[1086] Terminal

[1087] The meal plan generated by the server is sent to the user's device, where the user can review it. The user tries out the proposed meal plan and then inputs their impressions and ratings as feedback.

[1088] 5. Feedback learning and model refinement

[1089] server

[1090] The collected feedback is stored in a database, and the server uses this feedback data to retrain the AI ​​model and improve its next suggestions to better suit the user's preferences.

[1091] Specific examples

[1092] Example user:

[1093] Age: 30

[1094] Weight: 70kg

[1095] Height: 175cm

[1096] Activity level: High

[1097] Health condition: Diabetes

[1098] Allergies: Dairy

[1099] Food preference: Japanese food

[1100] 1. Collection of User Information

[1101] The user inputs the above information from the terminal and transmits it to the server.

[1102] 2. Create a user profile

[1103] The server uses this information to generate individual profiles and stores them in a database.

[1104] 3. Meal plan suggestions

[1105] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[1106] 4. Providing suggestions and gathering feedback

[1107] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[1108] 5. Feedback learning and model refinement

[1109] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[1110] The processing flow will be explained below.

[1111] Step 1: Enter your user information

[1112] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The terminals then send this information to the server.

[1113] Step 2: Save user information

[1114] The server stores the user information received from the terminal in a database, and through this storage process, an individual profile of each user is recorded in the database.

[1115] Step 3: Creating a User Profile

[1116] The server uses the information in the database to generate an individual profile for each user, which is then stored in the database again. The user profile includes information about body type, activity level, health status, allergies, and food preferences that users have entered.

[1117] Step 4: Generate a meal plan

[1118] The server generates an optimal meal plan using an AI model based on the user's profile. Specifically, the server converts the user's information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model then uses the stored data to create the optimal menu for the user.

[1119] Step 5: Submit your meal plan

[1120] The server sends the generated meal plan to the user's terminal, where the user can view the proposed meal plan.

[1121] Step 6: Provide feedback

[1122] The user actually tries out the proposed meal plan and inputs feedback on the results. The terminal sends the user's feedback information to the server.

[1123] Step 7: Save your feedback

[1124] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[1125] Step 8: Retraining the AI ​​model

[1126] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[1127] Step 9: Provide an improved meal plan

[1128] Using the retrained AI model, the server again generates and serves the optimal meal plan to the user, which in turn provides an improved meal plan that incorporates user feedback.

[1129] Example 1

[1130] 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."

[1131] In modern society, it is important to provide meal plans tailored to an individual's health status and lifestyle. However, conventional systems have had difficulty in properly collecting a wide range of user information (e.g., body shape, health status, food preferences, etc.) and providing meal plans tailored to individual needs. Furthermore, there were insufficient means to effectively utilize user feedback and improve future proposals. This resulted in a decline in user satisfaction.

[1132] 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.

[1133] In this invention, the server includes means for sending collected user information to the server in JSON format, means for saving user information in a database and generating a profile for each user, and means for converting the user profile into tensor format and inputting it into an AI model to generate an optimal meal plan. This enables the generation of a customized meal plan based on detailed user information, and by continuously incorporating user feedback, it is possible to improve the accuracy and satisfaction of subsequent suggestions.

[1134] "User information" is detailed information about the user, such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[1135] A "terminal" is a device used by a user (e.g., a smartphone or PC) and is hardware used to access the system and input and receive information.

[1136] A "server" is a computer system that receives, stores, processes, and analyzes collected user information.

[1137] A "database" is a data structure for storing and managing collected user information and feedback information.

[1138] A "profile" is a collection of individual information about each user that is generated based on collected user information.

[1139] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and perform specific tasks.

[1140] "Tensor format" is user information converted into a multidimensional array format, and is used when inputting it into an AI model.

[1141] A "meal plan" is a meal suggestion tailored to a user, generated based on the user's profile.

[1142] "Feedback" refers to the impressions and ratings provided by users after trying the suggested meal plan.

[1143] "Retraining" is the process of updating an existing AI model with new feedback data collected to improve its accuracy.

[1144] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data in text format and is used for data exchange.

[1145] The "HTTPS protocol" is an abbreviation for HyperText Transfer Protocol Secure, a protocol for encrypting internet communications to send and receive data safely.

[1146] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[1147] 1. Collection of User Information

[1148] Terminal

[1149] Users access the system using a terminal and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as the basis for creating an individual profile of the user. The information is packaged in JSON format and sent using the HTTPS protocol.

[1150] 2. Create a user profile

[1151] server

[1152] The server receives and parses user information in JSON format sent from the device. The collected information is stored in a database, and a profile for each user is generated based on this information. The database software used is a standard SQL database (e.g., MySQL or PostgreSQL).

[1153] 3. Meal plan suggestions

[1154] server

[1155] The server generates an optimal meal plan based on each user's profile. The user profile information is converted into tensor format and input into an AI model using a deep learning library such as TensorFlow. The AI ​​model analyzes the user information and predicts the optimal meal plan for each user. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested, and if a user prefers Japanese food, a menu centered on Japanese cuisine will be generated.

[1156] 4. Providing suggestions and gathering feedback

[1157] Terminal

[1158] The generated meal plan is sent to the user's device, where the user can review it. The user can try out the proposed meal plan and then enter their impressions and ratings as feedback. The feedback is again packaged in JSON format and sent to the server using the HTTPS protocol.

[1159] 5. Feedback learning and model refinement

[1160] server

[1161] The server stores the collected feedback in a database and retrains the AI ​​model. The retraining process is carried out using the new feedback data collected, allowing the system's suggestions to better meet the user's needs in the future.

[1162] Specific examples

[1163] Example user:

[1164] Age: 30

[1165] Weight: 70kg

[1166] Height: 175cm

[1167] Activity level: High

[1168] Health condition: Diabetes

[1169] Allergies: Dairy

[1170] Food preference: Japanese food

[1171] 1. Collection of User Information

[1172] The user inputs the above information from the terminal and sends it to the server.

[1173] 2. Create a user profile

[1174] The server uses this information to generate individual profiles and stores them in a database.

[1175] 3. Meal plan suggestions

[1176] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[1177] 4. Providing suggestions and gathering feedback

[1178] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[1179] 5. Feedback learning and model refinement

[1180] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[1181] Example prompt sentence:

[1182] "Please suggest the best meal plan for a user who is 30 years old, weighs 70kg, is 175cm tall, has a high activity level, has diabetes, is allergic to dairy products, and likes Japanese food."

[1183] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1184] Step 1:

[1185] Entering user information

[1186] Users access the system using a terminal and input information such as their body type, amount of exercise, health condition, allergies, and dietary preferences.

[1187] Input: User's body type information (e.g., height 175 cm, weight 70 kg), amount of exercise (e.g., daily jogging), health condition (e.g., diabetes, dairy allergy), food preferences (e.g., Japanese food)

[1188] Output: User information packaged in JSON format

[1189] Specific operation: Information entered on the device interface is converted to JSON format using front-end technologies such as JavaScript.

[1190] Step 2:

[1191] Sending user information

[1192] The terminal transmits the packaged user information to the server via the HTTPS protocol.

[1193] Input: User information in JSON format

[1194] Output: User information is sent to the server

[1195] Specific operation: The device uses an SSL certificate to ensure security when sending information.

[1196] Step 3:

[1197] Creating a User Profile

[1198] The server parses the received JSON formatted user information, stores it in a database, and then generates a profile for each user.

[1199] Input: User information in JSON format

[1200] Output: User profile stored in the database

[1201] Specific operation: The server uses Python or Node.js to parse the JSON information and save it to the database using SQL commands.

[1202] Step 4:

[1203] Generate a meal plan

[1204] The server generates an optimal meal plan based on the user profile, converting the user information into tensor format and inputting it into an AI model running TensorFlow.

[1205] Input: Database user profile

[1206] Output: Meal plan

[1207] How it works: User profile information is converted into tensor format and fed into an AI model using deep learning libraries such as TensorFlow to predict optimal meal plans.

[1208] Step 5:

[1209] Meal plan provided

[1210] The server sends the generated meal plan to the user's terminal.

[1211] Input: Generated meal plan

[1212] Output: Meal plan displayed on user's device

[1213] Specific operation: The server sends the meal plan using the HTTPS protocol, and the device visualizes the received data and displays it to the user.

[1214] Step 6:

[1215] Enter your feedback

[1216] The user checks the proposed meal plan, tries it out, and then enters their impressions and evaluations as feedback into the device.

[1217] Input: Feedback information (e.g., taste, satiety, health effects, etc.)

[1218] Output: Feedback information in JSON format

[1219] Specific behavior: Information entered through the feedback form is packaged in JSON format.

[1220] Step 7:

[1221] Send Feedback

[1222] The terminal sends the feedback information to the server using the HTTPS protocol.

[1223] Input: Feedback information in JSON format

[1224] Output: Feedback information sent to the server

[1225] Specific behavior: Send information securely using an SSL certificate

[1226] Step 8:

[1227] Improve the model based on feedback

[1228] The server stores the received feedback information in a database and retrains the AI ​​model using new feedback data.

[1229] Input: Feedback information

[1230] Output: An improved AI model

[1231] Specific operation: Retrieves feedback data from the database and executes the process of retraining the AI ​​model using TensorFlow.

[1232] (Application example 1)

[1233] 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."

[1234] In modern society, there is a demand for systems that propose optimal meal plans based on an individual's health status and preferences and enable delivery orders. However, conventional systems are unable to fully utilize user information and feedback, making it difficult to provide highly accurate meal plans to individual users. Furthermore, the process for reflecting feedback and improving the next proposal is insufficient. The present invention aims to solve these problems and provide a system that enables the provision of personalized, healthy meal plans and the rapid delivery order of such plans.

[1235] 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.

[1236] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and dietary preferences, means for creating an individual profile based on the collected user information, and means for proposing an optimal meal plan based on the user's activity level for that day and enabling immediate delivery ordering. This allows users to easily obtain a meal plan tailored to their health condition and preferences and quickly order delivery of the plan.

[1237] The system also maintains a database of suggested meal plans, generates meal plans using this database, and uses them for delivery orders, enabling efficient suggestions. Furthermore, feedback information is stored in a dataset, which can be used to retrain the generative AI model, and prompts can be used to refine the next meal plan suggestions, enabling suggestions that are more tailored to each user's preferences.

[1238] "Information regarding the user's body type, amount of exercise, health condition, allergies, and food preferences" refers to data regarding weight, height, exercise habits, medical history, allergies, and food preferences entered by the user.

[1239] An "individual profile" is a collection of information customized for each user that is generated based on collected user information.

[1240] The "activity level for that day" is data relating to the amount of exercise and work intensity of the user for that day.

[1241] The "optimal meal plan" is a meal menu suggestion that is suitable for the user's health condition and food preferences, generated by AI based on the user's profile.

[1242] A "delivery order" is a request for a service to actually cook and deliver the proposed meal plan.

[1243] "Feedback" refers to a user providing feedback or rating on the meal they received.

[1244] A "dataset" is a collection of large amounts of data, including feedback information.

[1245] A "generative AI model" is an artificial intelligence system that is trained to use large amounts of data to generate optimal meal plans.

[1246] A "prompt" is a textual instruction or data entry statement that is input into an AI model.

[1247] This invention relates to a system that proposes personalized meal plans and allows users to instantly order delivery. The system collects information about the user's body type, activity level, health status, allergies, and food preferences, generates a profile based on that information, and proposes an optimal meal plan. Furthermore, the system collects feedback about the proposed meal plans and reflects that feedback in the AI ​​model to improve it.

[1248] 1. System Program

[1249] This system is primarily composed of a smartphone, a server, and a generative AI model. Users enter their information using their smartphone, and the data is sent to the server. The server creates an individual profile based on the received information, and the generative AI model generates an optimal meal plan. The generated meal plan is sent to the user's smartphone, allowing them to order delivery.

[1250] 2. Data processing and calculation

[1251] The smartphone application converts the user's input data into an appropriate format to facilitate sending it to the server. The server receives this data and stores it in a database. It also converts the data into tensor format for input to the generative AI model. The generative AI model is built using TensorFlow and processes the user's profile data to generate an optimal meal plan. Furthermore, feedback data from the user is stored on the server and used to retrain the AI ​​model and improve the accuracy of the next meal plan.

[1252] 3. Specific Examples

[1253] For example, consider a 30-year-old user who is 175 cm tall, weighs 70 kg, has a high activity level, and suffers from diabetes and a dairy allergy. If the user prefers Japanese food, the user first enters this information into a smartphone application. The server generates a profile based on the user information, and the generated AI model proposes a low-carb, dairy-free Japanese meal plan. This proposal is immediately sent to the smartphone, allowing the user to place a delivery order.

[1254] Additionally, after trying a meal, users can provide feedback, such as their impressions and ratings, which the server will collect and use to improve its suggestions for the next time.

[1255] 4. Examples of prompts

[1256] User Profile

[1257] Age: 30

[1258] Weight: 70kg

[1259] Height: 175cm

[1260] Activity level: High

[1261] Health Condition: Diabetes

[1262] Allergies: Dairy

[1263] Food preference: Japanese food

[1264] Based on the user profile above, please suggest the best low-carb, dairy-free Japanese meal menu.

[1265] In this way, the system not only proposes optimal meal plans tailored to the user's health condition and preferences, but also allows for quick delivery orders, allowing users to easily obtain healthy meals.

[1266] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1267] Step 1:

[1268] Users use their smartphones to input information about their body type, amount of exercise, health condition, allergies, food preferences, etc. Input data includes age, weight, height, exercise habits, medical history, allergies, favorite dishes, etc. The input data is temporarily stored on the device and then sent to the server.

[1269] Input data: User's body type, amount of exercise, health condition, allergies, food preferences

[1270] Output data: User profile information sent to the server

[1271] Step 2:

[1272] The server receives the user information sent from the device and stores it in a database. At this time, it organizes various data (body type, amount of exercise, health condition, allergies, food preferences) and creates a user profile for centralized management.

[1273] Input data: User profile information

[1274] Output data: User profile stored in a database

[1275] Step 3:

[1276] The server converts the collected user profile information into tensor format and inputs it into a generative AI model. The AI ​​model is built using TensorFlow and generates an optimal meal plan based on the user's profile data. The generated meal plan is returned to the server via an API.

[1277] Input data: User profile information in tensor format

[1278] Output: Generated meal plan

[1279] Step 4:

[1280] The server sends the generated meal plan to the user's smartphone terminal.

[1281] Input data: Generated meal plan

[1282] Output data: Meal plan displayed on a smartphone

[1283] Step 5:

[1284] The user checks the proposed meal plans on their smartphone, selects the one they like, and places a delivery order. The order information is sent to a server and linked to the restaurant or delivery service.

[1285] Input data: User order information

[1286] Output data: Order request to delivery service

[1287] Step 6:

[1288] After receiving the meal, the user inputs their impressions and evaluation of the meal as feedback into their smartphone, and this feedback data is sent to the server.

[1289] Input data: User feedback on meals

[1290] Output data: Feedback data sent to the server

[1291] Step 7:

[1292] The server stores the collected feedback information in a dataset and uses it to retrain the generative AI model, resulting in more accurate meal plan suggestions for the next time.

[1293] Input data: Feedback data

[1294] Output data: Improved generative AI model

[1295] This is the flow of processing in the program for the system that realizes the application example. At each processing step, specific data processing and calculations are performed, and the system evolves step by step.

[1296] 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.

[1297] The present invention is a system that combines an emotion engine that recognizes the user's emotions to collect information such as a user's body type, amount of exercise, health condition, allergies, and food preferences, create an individual profile based on that information, and propose an optimal meal plan. Specific embodiments of this system are described below.

[1298] 1. Collection of User Information

[1299] Terminal

[1300] A user accesses the system using a terminal and inputs their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[1301] 2. Emotional Recognition

[1302] Terminal

[1303] The device is equipped with an emotion engine that recognizes the user's emotional state from their voice and facial expressions. For example, it analyzes the tone of their voice and facial movements when they interact with the system through voice input or a camera to determine the user's emotions.

[1304] 3. Create a user profile

[1305] server

[1306] The server stores the user information and emotional state sent from the terminal in a database and generates an individual profile for each user based on that information. The generated profile is recorded in the database.

[1307] 4. Generate a meal plan

[1308] server

[1309] The server generates an optimal meal plan based on the user's profile, activity level for that day, and emotional state. The server converts the user's information into tensor format and inputs it into an AI model. The AI ​​model predicts the optimal meal plan based on a combination of the user's body type, exercise level, health status, allergies, food preferences, and emotional state.

[1310] 5. Meal plan offerings

[1311] Terminal

[1312] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan may include ingredients and dishes that match the user's mood.

[1313] 6. Providing Feedback

[1314] User

[1315] After trying the proposed meal plan, the user inputs their impressions and evaluations as feedback, and the device sends this feedback information to the server.

[1316] 7. Saving Feedback

[1317] server

[1318] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[1319] 8. Retraining AI models

[1320] server

[1321] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[1322] Specific examples

[1323] Example user:

[1324] Age: 30

[1325] Weight: 70kg

[1326] Height: 175cm

[1327] Activity level: High

[1328] Health condition: Diabetes

[1329] Allergies: Dairy

[1330] Food preference: Japanese food

[1331] Emotional state: Feeling stressed

[1332] 1. Collection of User Information

[1333] The user inputs the above information from the terminal and transmits it to the server.

[1334] 2. Emotional Recognition

[1335] The device analyzes the user's voice and facial expression and determines that the user is feeling stressed.

[1336] 3. Create a user profile

[1337] The server generates an individual profile based on this information and stores it in a database.

[1338] 4. Generate a meal plan

[1339] Based on this profile, the server generates a menu that is low in carbohydrates, dairy-free, mainly Japanese food, and includes ingredients that reduce stress, and sends it to the user's device.

[1340] 5. Meal plan offerings

[1341] The user reviews the proposed meal plan on the device.

[1342] 6. Providing Feedback

[1343] Users enter feedback about the meal plan they tried, such as "I felt relaxed," and send it to the server via their device.

[1344] 7. Saving Feedback

[1345] The server stores the collected feedback in a database and adds it to the training dataset.

[1346] 8. Retraining AI models

[1347] The server uses the feedback data to retrain the AI ​​model and incorporates the feedback into its next suggestions.

[1348] The processing flow will be explained below.

[1349] Step 1: Enter your user information

[1350] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[1351] Step 2: Recognizing user emotions

[1352] The device uses an emotion engine to analyze the user's voice and facial expressions to recognize their emotional state. For example, when a user interacts with the system via voice input or a camera, the device analyzes their voice tone and facial movements to determine whether they are feeling stressed.

[1353] Step 3: Creating a User Profile

[1354] The server generates an individual profile based on the user information and emotional state received from the device, and the generated profile is stored in a database.

[1355] Step 4: Generate a meal plan

[1356] The server uses an AI model to generate an optimal meal plan, taking into account the user's profile, activity level, and emotional state. Specifically, the server converts user information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model generates the optimal menu based on a combination of data such as body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[1357] Step 5: Submit your meal plan

[1358] The server sends the generated meal plan to the user's device, where the user can view the proposed meal plan.

[1359] Step 6: Provide feedback

[1360] The user tries out the proposed meal plan and inputs feedback on the results, which is then sent to the server by the device.

[1361] Step 7: Save your feedback

[1362] The server stores the feedback information received from the devices in a database, and also adds this feedback information to a dataset for later retraining the model.

[1363] Step 8: Retraining the AI ​​model

[1364] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[1365] Step 9: Provide an improved meal plan

[1366] Using the retrained AI model, the server again generates and provides the optimal meal plan to the user. The improved meal plan reflects the user's feedback. For example, if the user is feeling stressed, a menu containing foods that will reduce stress will be provided.

[1367] Example 2

[1368] 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."

[1369] Conventional meal plan suggestion systems provide meal plans based on basic information such as the user's body type and health condition, but do not take into account the user's emotional state. As a result, they are unable to provide meal plans that are adapted to the user's mood and emotions, which can lead to a decrease in user satisfaction. Furthermore, improvements to the model based on feedback are not made quickly, which can delay improvements in suggestion accuracy.

[1370] 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.

[1371] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, means for proposing a meal plan based on the user's activity level and emotional state for that day, means for recognizing the user's emotional state using an emotion recognition engine installed in the terminal, means for learning from the user's feedback and improving the next proposal, means for saving the feedback information, and means for retraining the AI ​​model using the saved feedback information. This makes it possible to provide an optimal meal plan that takes the user's emotional state into consideration and to quickly improve the model.

[1372] "User information" refers to personal information such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[1373] A "profile" is a data set specific to an individual user that is generated based on collected user information.

[1374] "Activity level" is information indicating the amount of exercise the user does on a daily basis and the intensity of the activity on each day.

[1375] "Emotional state" is information that indicates the user's emotional or mood state, and is recognized from voice and facial expressions.

[1376] A "meal plan" is a menu of meals suggested based on user information, activity level, and emotional state for the day.

[1377] "Feedback" refers to the impressions and evaluations provided by users after trying the proposed meal plan.

[1378] An "emotion recognition engine" is software installed on a device that analyzes the user's emotional state from their voice and facial expressions.

[1379] A "database" is an information management system for storing various data used by the system, such as user information, profiles, and feedback information.

[1380] The "AI model" is a machine learning model that predicts the optimal meal plan based on collected user information and feedback information.

[1381] The "tensor format" is a format that represents data as a multidimensional array and is used as an input format for AI models.

[1382] The present invention relates to a system that collects information on a user's body type, amount of exercise, health condition, allergies, food preferences, emotional state, etc., creates an individual profile based on the collected information, and proposes an optimal meal plan. This system uses a combination of an emotion recognition engine and a generative AI model to optimize the meal plan based on the user's information and emotional state.

[1383] Collection of User Information

[1384] Terminal

[1385] Users access the system using a device such as a smartphone or PC and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is sent from the device to the server.

[1386] Emotion recognition

[1387] Terminal

[1388] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, when a user interacts with the system through voice input or a camera, the system analyzes their voice tone and facial movements to determine whether the user is feeling stressed. This determination result is sent from the device to the server.

[1389] Creating a User Profile

[1390] server

[1391] The server receives the user information and emotional state sent from the terminal and stores it in a database, and based on this, generates an individual user profile and records it in the database.

[1392] Generate a meal plan

[1393] server

[1394] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. The server converts the user information into tensor format and inputs it into a generative AI model. The AI ​​model combines data such as body shape, exercise volume, health status, allergies, food preferences, and emotional state to predict the optimal meal plan. This meal plan is sent to the device in JSON format.

[1395] Meal plan provided

[1396] Terminal

[1397] The optimal meal plan sent from the server is displayed on the user's device, where the user can view it, and the suggested menu includes ingredients and dishes that suit the mood based on the user's emotional state.

[1398] Providing Feedback

[1399] User

[1400] After trying the meal plan provided, the user inputs their impressions and ratings, and this feedback is sent from the device to the server.

[1401] Save your feedback

[1402] server

[1403] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model, so that it can be reflected in the next proposal.

[1404] Retraining an AI model

[1405] server

[1406] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[1407] Specific examples

[1408] Here is a concrete example: Assume a 30-year-old male, weighing 70 kg and 175 cm tall, has a high activity level, suffers from diabetes, and is allergic to dairy products. This user prefers Japanese food and is currently feeling stressed.

[1409] Collecting user information: The user enters information from the terminal and sends it to the server.

[1410] Emotion recognition: The device analyzes the user's voice and facial expressions to determine whether they are feeling stressed.

[1411] Creating a user profile: The server stores the information in a database and creates a profile.

[1412] Meal plan generation: The server generates a menu of mainly Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[1413] Meal plan provided: The user reviews the proposed meal plan on the device.

[1414] Providing feedback: The user tries the meal and provides feedback that it was "relaxing."

[1415] Save Feedback: The server saves the feedback in a database and adds it to the training dataset.

[1416] Retraining the AI ​​model: The server uses the feedback data to retrain the AI ​​model and reflect it in the next proposal.

[1417] Example prompts for generative AI models

[1418] "I'm a 30-year-old man, 180cm tall, weigh 75kg, and run three times a week. I have high blood pressure and no particular allergies. My favorite food is Chinese food, and I've been feeling pretty stressed at work lately. I'd like you to suggest a meal plan that fits these conditions."

[1419] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1420] Step 1:

[1421] Collection of User Information

[1422] Terminal

[1423] Users access the system using a smartphone or PC and enter their body information (e.g., height and weight), exercise volume, health status, allergies, dietary preferences, etc. into the provided interface. The entered information is sent from the device to the server in JSON format.

[1424] Input: User-entered information about your body type, activity level, health status, allergies, and dietary preferences.

[1425] Data processing: Convert the input information into JSON format.

[1426] Output: User information in JSON format is sent from the device to the server.

[1427] What happens: A user opens the app, fills out a form, and presses the "Submit" button.

[1428] Step 2:

[1429] Emotion recognition

[1430] Terminal

[1431] The device's built-in camera and microphone are used to collect the user's voice and facial expressions. The emotion recognition engine analyzes this data and determines the user's emotional state. The results are sent to the server in JSON format.

[1432] Input: User's voice data, facial expression data.

[1433] Data processing: The emotion recognition engine analyzes voice and facial expressions to determine the emotional state.

[1434] Output: The determined emotional state is sent to the server in JSON format.

[1435] Specific operation: The user interacts with the system through voice and captures facial expressions with the camera.

[1436] Step 3:

[1437] Creating a User Profile

[1438] server

[1439] The server stores the user information and emotional state sent from the device in a database, and generates an individual profile for each user based on this information.

[1440] Input: User information and emotional state sent from the device.

[1441] Data processing: User information and emotional state are stored in a database and a profile is generated.

[1442] Output: The generated user profile is recorded in a database.

[1443] Specific operation: The server stores the received data in a database and generates a new profile item.

[1444] Step 4:

[1445] Generate a meal plan

[1446] server

[1447] The server generates an optimal meal plan based on the generated user profile, the activity level and emotional state of the day. The user information is converted into tensor format and input into a generative AI model. The AI ​​model predicts the optimal meal plan based on body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[1448] Input: Stored user profile, activity level, emotional state.

[1449] Data processing: User information is converted into tensor format and input into the generative AI model.

[1450] Output: The generated meal plan is sent to the terminal in JSON format.

[1451] Specific operation: The server inputs profile information into the AI ​​model and outputs a meal plan as the analysis result.

[1452] Step 5:

[1453] Meal plan provided

[1454] Terminal

[1455] The optimal meal plan sent from the server is displayed on the user's device, where the user can check the proposed plan and use it to make daily meal choices.

[1456] Input: Meal plan sent from server.

[1457] Data processing: Display meal plan information on the device.

[1458] Output: User can review the suggested meal plan.

[1459] Specific operation: Display the meal plan sent from the server on the app screen.

[1460] Step 6:

[1461] Providing Feedback

[1462] User

[1463] After trying out the meal plan provided, the user inputs their impressions and ratings, and the input feedback is sent from the device to the server.

[1464] Input: User comments and ratings.

[1465] Data processing: Convert the feedback information into JSON format.

[1466] Output: Feedback information is sent from the device to the server.

[1467] Specific operation: The user enters feedback on the terminal and sends it to the server by clicking the send button.

[1468] Step 7:

[1469] Save your feedback

[1470] server

[1471] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model.

[1472] Input: Feedback information sent from the device.

[1473] Data processing: The feedback information is stored in a database and added to the training dataset.

[1474] Output: The feedback information is stored in a database.

[1475] Specific operation: The server stores the received data in a database and adds it to the training dataset.

[1476] Step 8:

[1477] Retraining an AI model

[1478] server

[1479] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[1480] Input: Saved feedback information.

[1481] Data processing: Retraining the AI ​​model based on feedback information.

[1482] Output: The updated AI model.

[1483] Specific operation: The server inputs the feedback data into the AI ​​model and performs retraining.

[1484] (Application example 2)

[1485] 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."

[1486] In today's busy lifestyles, it is extremely difficult to easily provide optimal meal plans tailored to individual users' health and emotional states. Conventional systems have difficulty proposing personalized meal plans due to insufficient user information input and recognition of emotional states. Furthermore, while there is a demand for meal plans that take into account the user's emotional state, there are limitations in this regard as well. To address this issue, it is necessary to combine emotion recognition with the creation of a profile based on information such as the user's body type, activity level, health status, allergies, and food preferences to propose more accurate meal plans.

[1487] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1488] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, an emotion recognition engine for recognizing the user's emotional state from voice input and facial expressions, means for proposing a meal plan according to the user's activity level and emotional state for that day, means for the user to provide feedback on the proposed meal plan, and means for learning from the user's feedback and improving the next proposal, thereby enabling the provision of a personalized meal plan that takes into account the user's health condition and emotions.

[1489] "User's body type information" is information that indicates the user's physical characteristics such as height and weight.

[1490] "Amount of exercise" is information that indicates the user's daily exercise habits and activity level.

[1491] "Health condition" is information indicating the user's medical history and current health condition.

[1492] "Allergy" is information that indicates that the user has an allergic reaction to a particular food or ingredient.

[1493] "Dietary preferences" is information about the ingredients and cooking styles that the user prefers.

[1494] An "emotion recognition engine" is software or hardware for recognizing a user's emotional state from their voice and facial expressions.

[1495] A "generative AI model" is an artificial intelligence model trained to make optimal suggestions based on user information.

[1496] A "dataset" is a collection of data, such as feedback information, collected for use in retraining an AI model.

[1497] A "meal plan" is a meal suggestion based on a user's profile and their activity level and emotional state for the day.

[1498] "Feedback" refers to the user's evaluation and impressions of the meal plan provided.

[1499] The present invention is a system that creates an individual profile based on a user's body type information, amount of exercise, health condition, allergies, food preferences, and emotional state, and proposes an optimal meal plan. Specific embodiments for implementing the present invention are described below.

[1500] 1. Collection of User Information

[1501] The device collects information entered by the user about their body type (e.g., height and weight), physical activity (e.g., daily exercise habits), health status (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is converted into JSON format and sent to the server.

[1502] 2. Emotional Recognition

[1503] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, it can determine the user's emotions (e.g., whether they are feeling stressed) by analyzing facial expressions through the camera and voice through the microphone. This processing is performed using Python and TensorFlow.

[1504] 3. Create a user profile

[1505] The server stores the user information and emotional state sent from the device in a database and generates an individual profile for each user based on that information. The generated profile is then recorded in the database.

[1506] 4. Generate a meal plan

[1507] The server generates an optimal meal plan based on the user's profile, activity level, and emotional state for that day. The server converts the collected user information into tensor format and inputs it into a generative AI model. This generative AI model predicts the optimal meal plan based on a combination of the user's body type, exercise level, health status, allergies, food preferences, and emotional state.

[1508] 5. Meal plan offerings

[1509] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan includes ingredients and dishes that suit the user's mood.

[1510] 6. Providing Feedback

[1511] After trying the proposed meal plan, the user inputs their impressions and evaluation as feedback, which is then sent from the device to the server.

[1512] 7. Saving Feedback

[1513] The server stores the feedback information received from the terminal in a database, and also adds this feedback information to the training dataset.

[1514] 8. Retraining AI models

[1515] The server uses the stored feedback information to retrain the generative AI model, which makes the next suggestions more accurate and adapted to the user's preferences.

[1516] Specific examples

[1517] Assume the user is 30 years old, weighs 70 kg, is 175 cm tall, has a high activity level, is diabetic and allergic to dairy products, and prefers Japanese food. If the emotion recognition engine determines that the user is feeling stressed, the following steps are performed:

[1518] 1. User Information Collection:

[1519] "Enter your body type, activity level, health status, allergies, and dietary preferences."

[1520] 2. Emotion Recognition:

[1521] "Please speak into the microphone. We will recognize your facial expressions, so please look at the camera."

[1522] 3. Create a user profile:

[1523] The server generates and saves a profile based on this information.

[1524] 4. Generate meal plan:

[1525] "We offer a menu of low-carb, dairy-free Japanese cuisine."

[1526] 5. Meal Plan Offering:

[1527] Users can view the proposed meal plan on their device.

[1528] 6. Providing Feedback:

[1529] Please enter your thoughts after your meal.

[1530] 7. Saving Feedback:

[1531] The server stores the feedback information

[1532] 8. Retraining AI models:

[1533] "We will retrain it based on the feedback information to improve our next proposal."

[1534] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1535] Step 1:

[1536] Collection of User Information

[1537] The device accepts input from the user about their body type (height and weight), amount of exercise (daily exercise habits), health condition (medical history and allergies), and food preferences (favorite ingredients and cooking styles). The user enters this information on the provided interface, and the device converts it into JSON format and sends it to the server.

[1538] Input: Information about your body type, activity level, health status, allergies, and dietary preferences that you enter into your device

[1539] Output: User information converted to JSON format and sent to the server

[1540] Step 2:

[1541] Emotion recognition

[1542] The device uses an emotion recognition engine to recognize the user's emotional state from their voice and facial expressions. It captures facial expressions using a camera and records audio using a microphone. The emotion recognition engine analyzes facial features and voice tone to determine the user's emotion (e.g., whether they are feeling stressed). The results are converted into JSON format and sent to the server.

[1543] Input: User facial expression images and voice data

[1544] Output: Emotional state information converted to JSON format and sent to the server

[1545] Step 3:

[1546] Creating a User Profile

[1547] The server receives the user information and emotional state sent from the device and stores them in a database. Based on this information, an individual profile of the user is generated. The profile is stored as a tensor-type data structure that comprehensively assesses the user's health and emotional state.

[1548] Input: User information and emotional state information in JSON format

[1549] Output: User profile stored in the database

[1550] Step 4:

[1551] Generate a meal plan

[1552] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. This is done using a generative AI model. The AI ​​model takes user data in tensor format as input and predicts the optimal meal plan based on that data. The generated meal plan is converted to JSON format and sent to the device.

[1553] Input: User profile in tensor format, along with activity level and emotional state for that day

[1554] Output: JSON formatted meal plan sent to the device

[1555] Step 5:

[1556] Meal plan provided

[1557] The device displays the meal plan received from the server, and the user reviews the plan and decides whether to select it. During this process, the plan includes ingredients and dishes that correspond to the user's emotional state.

[1558] Input: JSON format meal plan received from the server

[1559] Output: Meal plan displayed on device

[1560] Step 6:

[1561] Providing Feedback

[1562] After trying the proposed meal plan, the user enters their impressions and evaluations as feedback into the device, which then converts this feedback information into JSON format and sends it to the server.

[1563] Input: User feedback information

[1564] Output: Feedback information converted to JSON format and sent to the server

[1565] Step 7:

[1566] Save your feedback

[1567] The server stores the feedback information received from the devices in a database, which is also used as a data set to help propose improvements for the next time.

[1568] Input: Feedback information in JSON format

[1569] Output: Feedback information stored in a database

[1570] Step 8:

[1571] Retraining an AI model

[1572] The server uses the stored feedback information to retrain the generative AI model, which then gains the ability to generate more accurate and user-specific meal plans for the next time.

[1573] Input: Feedback information stored in the database

[1574] Output: An improved generative AI model

[1575] 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.

[1576] 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.

[1577] 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.

[1578] [Fourth embodiment]

[1579] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1580] 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.

[1581] 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).

[1582] 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.

[1583] 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.

[1584] 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).

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] 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."

[1592] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[1593] 1. Collection of User Information

[1594] Terminal

[1595] A user accesses the system using a terminal and inputs information about their body type (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as basic data for creating an individual profile of the user.

[1596] 2. Create a user profile

[1597] server

[1598] The server receives the user information sent from the terminal, stores it in a database, and then automatically generates an individual profile for each user based on this information.

[1599] 3. Meal plan suggestions

[1600] server

[1601] Based on the user's profile, the server generates an optimal meal plan taking into account the user's daily activity level. Specifically, the user's input information is converted into tensor format and fed into an artificial intelligence (AI) model. The AI ​​model processes the information and predicts the optimal meal plan.

[1602] The generated meal plan is based on the user's activity level, health status, allergies, food preferences, etc. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested. Also, if a user prefers Japanese food, a menu centered on Japanese cuisine will be provided.

[1603] 4. Providing suggestions and gathering feedback

[1604] Terminal

[1605] The meal plan generated by the server is sent to the user's device, where the user can review it. The user tries out the proposed meal plan and then inputs their impressions and ratings as feedback.

[1606] 5. Feedback learning and model refinement

[1607] server

[1608] The collected feedback is stored in a database, and the server uses this feedback data to retrain the AI ​​model and improve its next suggestions to better suit the user's preferences.

[1609] Specific examples

[1610] Example user:

[1611] Age: 30

[1612] Weight: 70kg

[1613] Height: 175cm

[1614] Activity level: High

[1615] Health condition: Diabetes

[1616] Allergies: Dairy

[1617] Food preference: Japanese food

[1618] 1. Collection of User Information

[1619] The user inputs the above information from the terminal and transmits it to the server.

[1620] 2. Create a user profile

[1621] The server uses this information to generate individual profiles and stores them in a database.

[1622] 3. Meal plan suggestions

[1623] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[1624] 4. Providing suggestions and gathering feedback

[1625] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[1626] 5. Feedback learning and model refinement

[1627] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[1628] The processing flow will be explained below.

[1629] Step 1: Enter your user information

[1630] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The terminals then send this information to the server.

[1631] Step 2: Save user information

[1632] The server stores the user information received from the terminal in a database, and through this storage process, an individual profile of each user is recorded in the database.

[1633] Step 3: Creating a User Profile

[1634] The server uses the information in the database to generate an individual profile for each user, which is then stored in the database again. The user profile includes information about body type, activity level, health status, allergies, and food preferences that users have entered.

[1635] Step 4: Generate a meal plan

[1636] The server generates an optimal meal plan using an AI model based on the user's profile. Specifically, the server converts the user's information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model then uses the stored data to create the optimal menu for the user.

[1637] Step 5: Submit your meal plan

[1638] The server sends the generated meal plan to the user's terminal, where the user can view the proposed meal plan.

[1639] Step 6: Provide feedback

[1640] The user actually tries out the proposed meal plan and inputs feedback on the results. The terminal sends the user's feedback information to the server.

[1641] Step 7: Save your feedback

[1642] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[1643] Step 8: Retraining the AI ​​model

[1644] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[1645] Step 9: Provide an improved meal plan

[1646] Using the retrained AI model, the server again generates and serves the optimal meal plan to the user, which in turn provides an improved meal plan that incorporates user feedback.

[1647] Example 1

[1648] 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."

[1649] In modern society, it is important to provide meal plans tailored to an individual's health status and lifestyle. However, conventional systems have had difficulty in properly collecting a wide range of user information (e.g., body shape, health status, food preferences, etc.) and providing meal plans tailored to individual needs. Furthermore, there were insufficient means to effectively utilize user feedback and improve future proposals. This resulted in a decline in user satisfaction.

[1650] 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.

[1651] In this invention, the server includes means for sending collected user information to the server in JSON format, means for saving user information in a database and generating a profile for each user, and means for converting the user profile into tensor format and inputting it into an AI model to generate an optimal meal plan. This enables the generation of a customized meal plan based on detailed user information, and by continuously incorporating user feedback, it is possible to improve the accuracy and satisfaction of subsequent suggestions.

[1652] "User information" is detailed information about the user, such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[1653] A "terminal" is a device used by a user (e.g., a smartphone or PC) and is hardware used to access the system and input and receive information.

[1654] A "server" is a computer system that receives, stores, processes, and analyzes collected user information.

[1655] A "database" is a data structure for storing and managing collected user information and feedback information.

[1656] A "profile" is a collection of individual information about each user that is generated based on collected user information.

[1657] An "AI model" is a mathematical model that uses artificial intelligence technology to analyze data and perform specific tasks.

[1658] "Tensor format" is user information converted into a multidimensional array format, and is used when inputting it into an AI model.

[1659] A "meal plan" is a meal suggestion tailored to a user, generated based on the user's profile.

[1660] "Feedback" refers to the impressions and ratings provided by users after trying the suggested meal plan.

[1661] "Retraining" is the process of updating an existing AI model with new feedback data collected to improve its accuracy.

[1662] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format that represents data in text format and is used for data exchange.

[1663] The "HTTPS protocol" is an abbreviation for HyperText Transfer Protocol Secure, a protocol for encrypting internet communications to send and receive data safely.

[1664] The present invention is a system that collects information on a user's body type, amount of exercise, health condition, allergies, dietary preferences, etc., creates an individual profile based on that information, and proposes an optimal meal plan. Specific embodiments of this system are described below.

[1665] 1. Collection of User Information

[1666] Terminal

[1667] Users access the system using a terminal and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking style). This information is sent to the server as the basis for creating an individual profile of the user. The information is packaged in JSON format and sent using the HTTPS protocol.

[1668] 2. Create a user profile

[1669] server

[1670] The server receives and parses user information in JSON format sent from the device. The collected information is stored in a database, and a profile for each user is generated based on this information. The database software used is a standard SQL database (e.g., MySQL or PostgreSQL).

[1671] 3. Meal plan suggestions

[1672] server

[1673] The server generates an optimal meal plan based on each user's profile. The user profile information is converted into tensor format and input into an AI model using a deep learning library such as TensorFlow. The AI ​​model analyzes the user information and predicts the optimal meal plan for each user. For example, if a user has diabetes, a low-carb, nutritionally balanced menu will be suggested, and if a user prefers Japanese food, a menu centered on Japanese cuisine will be generated.

[1674] 4. Providing suggestions and gathering feedback

[1675] Terminal

[1676] The generated meal plan is sent to the user's device, where the user can review it. The user can try out the proposed meal plan and then enter their impressions and ratings as feedback. The feedback is again packaged in JSON format and sent to the server using the HTTPS protocol.

[1677] 5. Feedback learning and model refinement

[1678] server

[1679] The server stores the collected feedback in a database and retrains the AI ​​model. The retraining process is carried out using the new feedback data collected, allowing the system's suggestions to better meet the user's needs in the future.

[1680] Specific examples

[1681] Example user:

[1682] Age: 30

[1683] Weight: 70kg

[1684] Height: 175cm

[1685] Activity level: High

[1686] Health condition: Diabetes

[1687] Allergies: Dairy

[1688] Food preference: Japanese food

[1689] 1. Collection of User Information

[1690] The user inputs the above information from the terminal and sends it to the server.

[1691] 2. Create a user profile

[1692] The server uses this information to generate individual profiles and stores them in a database.

[1693] 3. Meal plan suggestions

[1694] Based on this profile, the server generates a menu centered on Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[1695] 4. Providing suggestions and gathering feedback

[1696] The user reviews the proposed meal plan, tries it out, and then enters feedback via the device.

[1697] 5. Feedback learning and model refinement

[1698] The server adds the collected feedback to the dataset and retrains the AI ​​model, a process that improves future recommendations to better suit the user's preferences and health status.

[1699] Example prompt sentence:

[1700] "Please suggest the best meal plan for a user who is 30 years old, weighs 70kg, is 175cm tall, has a high activity level, has diabetes, is allergic to dairy products, and likes Japanese food."

[1701] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1702] Step 1:

[1703] Entering user information

[1704] Users access the system using a terminal and input information such as their body type, amount of exercise, health condition, allergies, and dietary preferences.

[1705] Input: User's body type information (e.g., height 175 cm, weight 70 kg), amount of exercise (e.g., daily jogging), health condition (e.g., diabetes, dairy allergy), food preferences (e.g., Japanese food)

[1706] Output: User information packaged in JSON format

[1707] Specific operation: Information entered on the device interface is converted to JSON format using front-end technologies such as JavaScript.

[1708] Step 2:

[1709] Sending user information

[1710] The terminal transmits the packaged user information to the server via the HTTPS protocol.

[1711] Input: User information in JSON format

[1712] Output: User information is sent to the server

[1713] Specific operation: The device uses an SSL certificate to ensure security when sending information.

[1714] Step 3:

[1715] Creating a User Profile

[1716] The server parses the received JSON formatted user information, stores it in a database, and then generates a profile for each user.

[1717] Input: User information in JSON format

[1718] Output: User profile stored in the database

[1719] Specific operation: The server uses Python or Node.js to parse the JSON information and save it to the database using SQL commands.

[1720] Step 4:

[1721] Generate a meal plan

[1722] The server generates an optimal meal plan based on the user profile, converting the user information into tensor format and inputting it into an AI model running TensorFlow.

[1723] Input: Database user profile

[1724] Output: Meal plan

[1725] How it works: User profile information is converted into tensor format and fed into an AI model using deep learning libraries such as TensorFlow to predict optimal meal plans.

[1726] Step 5:

[1727] Meal plan provided

[1728] The server sends the generated meal plan to the user's terminal.

[1729] Input: Generated meal plan

[1730] Output: Meal plan displayed on user's device

[1731] Specific operation: The server sends the meal plan using the HTTPS protocol, and the device visualizes the received data and displays it to the user.

[1732] Step 6:

[1733] Enter your feedback

[1734] The user checks the proposed meal plan, tries it out, and then enters their impressions and evaluations as feedback into the device.

[1735] Input: Feedback information (e.g., taste, satiety, health effects, etc.)

[1736] Output: Feedback information in JSON format

[1737] Specific behavior: Information entered through the feedback form is packaged in JSON format.

[1738] Step 7:

[1739] Send Feedback

[1740] The terminal sends the feedback information to the server using the HTTPS protocol.

[1741] Input: Feedback information in JSON format

[1742] Output: Feedback information sent to the server

[1743] Specific behavior: Send information securely using an SSL certificate

[1744] Step 8:

[1745] Improve the model based on feedback

[1746] The server stores the received feedback information in a database and retrains the AI ​​model using new feedback data.

[1747] Input: Feedback information

[1748] Output: An improved AI model

[1749] Specific operation: Retrieves feedback data from the database and executes the process of retraining the AI ​​model using TensorFlow.

[1750] (Application example 1)

[1751] 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."

[1752] In modern society, there is a demand for systems that propose optimal meal plans based on an individual's health status and preferences and enable delivery orders. However, conventional systems are unable to fully utilize user information and feedback, making it difficult to provide highly accurate meal plans to individual users. Furthermore, the process for reflecting feedback and improving the next proposal is insufficient. The present invention aims to solve these problems and provide a system that enables the provision of personalized, healthy meal plans and the rapid delivery order of such plans.

[1753] 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.

[1754] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and dietary preferences, means for creating an individual profile based on the collected user information, and means for proposing an optimal meal plan based on the user's activity level for that day and enabling immediate delivery ordering. This allows users to easily obtain a meal plan tailored to their health condition and preferences and quickly order delivery of the plan.

[1755] The system also maintains a database of suggested meal plans, generates meal plans using this database, and uses them for delivery orders, enabling efficient suggestions. Furthermore, feedback information is stored in a dataset, which can be used to retrain the generative AI model, and prompts can be used to refine the next meal plan suggestions, enabling suggestions that are more tailored to each user's preferences.

[1756] "Information regarding the user's body type, amount of exercise, health condition, allergies, and food preferences" refers to data regarding weight, height, exercise habits, medical history, allergies, and food preferences entered by the user.

[1757] An "individual profile" is a collection of information customized for each user that is generated based on collected user information.

[1758] The "activity level for that day" is data relating to the amount of exercise and work intensity of the user for that day.

[1759] The "optimal meal plan" is a meal menu suggestion that is suitable for the user's health condition and food preferences, generated by AI based on the user's profile.

[1760] A "delivery order" is a request for a service to actually cook and deliver the proposed meal plan.

[1761] "Feedback" refers to a user providing feedback or rating on the meal they received.

[1762] A "dataset" is a collection of large amounts of data, including feedback information.

[1763] A "generative AI model" is an artificial intelligence system that is trained to use large amounts of data to generate optimal meal plans.

[1764] A "prompt" is a textual instruction or data entry statement that is input into an AI model.

[1765] This invention relates to a system that proposes personalized meal plans and allows users to instantly order delivery. The system collects information about the user's body type, activity level, health status, allergies, and food preferences, generates a profile based on that information, and proposes an optimal meal plan. Furthermore, the system collects feedback about the proposed meal plans and reflects that feedback in the AI ​​model to improve it.

[1766] 1. System Program

[1767] This system is primarily composed of a smartphone, a server, and a generative AI model. Users enter their information using their smartphone, and the data is sent to the server. The server creates an individual profile based on the received information, and the generative AI model generates an optimal meal plan. The generated meal plan is sent to the user's smartphone, allowing them to order delivery.

[1768] 2. Data processing and calculation

[1769] The smartphone application converts the user's input data into an appropriate format to facilitate sending it to the server. The server receives this data and stores it in a database. It also converts the data into tensor format for input to the generative AI model. The generative AI model is built using TensorFlow and processes the user's profile data to generate an optimal meal plan. Furthermore, feedback data from the user is stored on the server and used to retrain the AI ​​model and improve the accuracy of the next meal plan.

[1770] 3. Specific Examples

[1771] For example, consider a 30-year-old user who is 175 cm tall, weighs 70 kg, has a high activity level, and suffers from diabetes and a dairy allergy. If the user prefers Japanese food, the user first enters this information into a smartphone application. The server generates a profile based on the user information, and the generated AI model proposes a low-carb, dairy-free Japanese meal plan. This proposal is immediately sent to the smartphone, allowing the user to place a delivery order.

[1772] Additionally, after trying a meal, users can provide feedback, such as their impressions and ratings, which the server will collect and use to improve its suggestions for the next time.

[1773] 4. Examples of prompts

[1774] User Profile

[1775] Age: 30

[1776] Weight: 70kg

[1777] Height: 175cm

[1778] Activity level: High

[1779] Health Condition: Diabetes

[1780] Allergies: Dairy

[1781] Food preference: Japanese food

[1782] Based on the user profile above, please suggest the best low-carb, dairy-free Japanese meal menu.

[1783] In this way, the system not only proposes optimal meal plans tailored to the user's health condition and preferences, but also allows for quick delivery orders, allowing users to easily obtain healthy meals.

[1784] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1785] Step 1:

[1786] Users use their smartphones to input information about their body type, amount of exercise, health condition, allergies, food preferences, etc. Input data includes age, weight, height, exercise habits, medical history, allergies, favorite dishes, etc. The input data is temporarily stored on the device and then sent to the server.

[1787] Input data: User's body type, amount of exercise, health condition, allergies, food preferences

[1788] Output data: User profile information sent to the server

[1789] Step 2:

[1790] The server receives the user information sent from the device and stores it in a database. At this time, it organizes various data (body type, amount of exercise, health condition, allergies, food preferences) and creates a user profile for centralized management.

[1791] Input data: User profile information

[1792] Output data: User profile stored in a database

[1793] Step 3:

[1794] The server converts the collected user profile information into tensor format and inputs it into a generative AI model. The AI ​​model is built using TensorFlow and generates an optimal meal plan based on the user's profile data. The generated meal plan is returned to the server via an API.

[1795] Input data: User profile information in tensor format

[1796] Output: Generated meal plan

[1797] Step 4:

[1798] The server sends the generated meal plan to the user's smartphone terminal.

[1799] Input data: Generated meal plan

[1800] Output data: Meal plan displayed on a smartphone

[1801] Step 5:

[1802] The user checks the proposed meal plans on their smartphone, selects the one they like, and places a delivery order. The order information is sent to a server and linked to the restaurant or delivery service.

[1803] Input data: User order information

[1804] Output data: Order request to delivery service

[1805] Step 6:

[1806] After receiving the meal, the user inputs their impressions and evaluation of the meal as feedback into their smartphone, and this feedback data is sent to the server.

[1807] Input data: User feedback on meals

[1808] Output data: Feedback data sent to the server

[1809] Step 7:

[1810] The server stores the collected feedback information in a dataset and uses it to retrain the generative AI model, resulting in more accurate meal plan suggestions for the next time.

[1811] Input data: Feedback data

[1812] Output data: Improved generative AI model

[1813] This is the flow of processing in the program for the system that realizes the application example. At each processing step, specific data processing and calculations are performed, and the system evolves step by step.

[1814] 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.

[1815] The present invention is a system that combines an emotion engine that recognizes the user's emotions to collect information such as a user's body type, amount of exercise, health condition, allergies, and food preferences, create an individual profile based on that information, and propose an optimal meal plan. Specific embodiments of this system are described below.

[1816] 1. Collection of User Information

[1817] Terminal

[1818] A user accesses the system using a terminal and inputs their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[1819] 2. Emotional Recognition

[1820] Terminal

[1821] The device is equipped with an emotion engine that recognizes the user's emotional state from their voice and facial expressions. For example, it analyzes the tone of their voice and facial movements when they interact with the system through voice input or a camera to determine the user's emotions.

[1822] 3. Create a user profile

[1823] server

[1824] The server stores the user information and emotional state sent from the terminal in a database and generates an individual profile for each user based on that information. The generated profile is recorded in the database.

[1825] 4. Generate a meal plan

[1826] server

[1827] The server generates an optimal meal plan based on the user's profile, activity level for that day, and emotional state. The server converts the user's information into tensor format and inputs it into an AI model. The AI ​​model predicts the optimal meal plan based on a combination of the user's body type, exercise level, health status, allergies, food preferences, and emotional state.

[1828] 5. Meal plan offerings

[1829] Terminal

[1830] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan may include ingredients and dishes that match the user's mood.

[1831] 6. Providing Feedback

[1832] User

[1833] After trying the proposed meal plan, the user inputs their impressions and evaluations as feedback, and the device sends this feedback information to the server.

[1834] 7. Saving Feedback

[1835] server

[1836] The server stores the feedback information received from the device in a database, and also adds this feedback information to the training dataset.

[1837] 8. Retraining AI models

[1838] server

[1839] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[1840] Specific examples

[1841] Example user:

[1842] Age: 30

[1843] Weight: 70kg

[1844] Height: 175cm

[1845] Activity level: High

[1846] Health condition: Diabetes

[1847] Allergies: Dairy

[1848] Food preference: Japanese food

[1849] Emotional state: Feeling stressed

[1850] 1. Collection of User Information

[1851] The user inputs the above information from the terminal and transmits it to the server.

[1852] 2. Emotional Recognition

[1853] The device analyzes the user's voice and facial expression and determines that the user is feeling stressed.

[1854] 3. Create a user profile

[1855] The server generates an individual profile based on this information and stores it in a database.

[1856] 4. Generate a meal plan

[1857] Based on this profile, the server generates a menu that is low in carbohydrates, dairy-free, mainly Japanese food, and includes ingredients that reduce stress, and sends it to the user's device.

[1858] 5. Meal plan offerings

[1859] The user reviews the proposed meal plan on the device.

[1860] 6. Providing Feedback

[1861] Users enter feedback about the meal plan they tried, such as "I felt relaxed," and send it to the server via their device.

[1862] 7. Saving Feedback

[1863] The server stores the collected feedback in a database and adds it to the training dataset.

[1864] 8. Retraining AI models

[1865] The server uses the feedback data to retrain the AI ​​model and incorporates the feedback into its next suggestions.

[1866] The processing flow will be explained below.

[1867] Step 1: Enter your user information

[1868] Users access the system from their terminals and input their body type (height, weight, etc.), amount of exercise (frequency, duration, etc.), health condition (medical history, allergies, etc.), and food preferences (favorite ingredients and cooking styles). The input information is sent from the terminal to the server.

[1869] Step 2: Recognizing user emotions

[1870] The device uses an emotion engine to analyze the user's voice and facial expressions to recognize their emotional state. For example, when a user interacts with the system via voice input or a camera, the device analyzes their voice tone and facial movements to determine whether they are feeling stressed.

[1871] Step 3: Creating a User Profile

[1872] The server generates an individual profile based on the user information and emotional state received from the device, and the generated profile is stored in a database.

[1873] Step 4: Generate a meal plan

[1874] The server uses an AI model to generate an optimal meal plan, taking into account the user's profile, activity level, and emotional state. Specifically, the server converts user information into tensor format and inputs it into the AI ​​model to predict the meal plan. The AI ​​model generates the optimal menu based on a combination of data such as body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[1875] Step 5: Submit your meal plan

[1876] The server sends the generated meal plan to the user's device, where the user can view the proposed meal plan.

[1877] Step 6: Provide feedback

[1878] The user tries out the proposed meal plan and inputs feedback on the results, which is then sent to the server by the device.

[1879] Step 7: Save your feedback

[1880] The server stores the feedback information received from the devices in a database, and also adds this feedback information to a dataset for later retraining the model.

[1881] Step 8: Retraining the AI ​​model

[1882] The server uses the stored feedback information to retrain the AI ​​model, making its next suggestions more accurate and tailored to the user's preferences.

[1883] Step 9: Provide an improved meal plan

[1884] Using the retrained AI model, the server again generates and provides the optimal meal plan to the user. The improved meal plan reflects the user's feedback. For example, if the user is feeling stressed, a menu containing foods that will reduce stress will be provided.

[1885] Example 2

[1886] 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."

[1887] Conventional meal plan suggestion systems provide meal plans based on basic information such as the user's body type and health condition, but do not take into account the user's emotional state. As a result, they are unable to provide meal plans that are adapted to the user's mood and emotions, which can lead to a decrease in user satisfaction. Furthermore, improvements to the model based on feedback are not made quickly, which can delay improvements in suggestion accuracy.

[1888] 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.

[1889] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, means for proposing a meal plan based on the user's activity level and emotional state for that day, means for recognizing the user's emotional state using an emotion recognition engine installed in the terminal, means for learning from the user's feedback and improving the next proposal, means for saving the feedback information, and means for retraining the AI ​​model using the saved feedback information. This makes it possible to provide an optimal meal plan that takes the user's emotional state into consideration and to quickly improve the model.

[1890] "User information" refers to personal information such as the user's body type, amount of exercise, health condition, allergies, and food preferences.

[1891] A "profile" is a data set specific to an individual user that is generated based on collected user information.

[1892] "Activity level" is information indicating the amount of exercise the user does on a daily basis and the intensity of the activity on each day.

[1893] "Emotional state" is information that indicates the user's emotional or mood state, and is recognized from voice and facial expressions.

[1894] A "meal plan" is a menu of meals suggested based on user information, activity level, and emotional state for the day.

[1895] "Feedback" refers to the impressions and evaluations provided by users after trying the proposed meal plan.

[1896] An "emotion recognition engine" is software installed on a device that analyzes the user's emotional state from their voice and facial expressions.

[1897] A "database" is an information management system for storing various data used by the system, such as user information, profiles, and feedback information.

[1898] The "AI model" is a machine learning model that predicts the optimal meal plan based on collected user information and feedback information.

[1899] The "tensor format" is a format that represents data as a multidimensional array and is used as an input format for AI models.

[1900] The present invention relates to a system that collects information on a user's body type, amount of exercise, health condition, allergies, food preferences, emotional state, etc., creates an individual profile based on the collected information, and proposes an optimal meal plan. This system uses a combination of an emotion recognition engine and a generative AI model to optimize the meal plan based on the user's information and emotional state.

[1901] Collection of User Information

[1902] Terminal

[1903] Users access the system using a device such as a smartphone or PC and enter their body type information (e.g., height and weight), amount of exercise (e.g., daily exercise habits), health condition (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is sent from the device to the server.

[1904] Emotion recognition

[1905] Terminal

[1906] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, when a user interacts with the system through voice input or a camera, the system analyzes their voice tone and facial movements to determine whether the user is feeling stressed. This determination result is sent from the device to the server.

[1907] Creating a User Profile

[1908] server

[1909] The server receives the user information and emotional state sent from the terminal and stores it in a database, and based on this, generates an individual user profile and records it in the database.

[1910] Generate a meal plan

[1911] server

[1912] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. The server converts the user information into tensor format and inputs it into a generative AI model. The AI ​​model combines data such as body shape, exercise volume, health status, allergies, food preferences, and emotional state to predict the optimal meal plan. This meal plan is sent to the device in JSON format.

[1913] Meal plan provided

[1914] Terminal

[1915] The optimal meal plan sent from the server is displayed on the user's device, where the user can view it, and the suggested menu includes ingredients and dishes that suit the mood based on the user's emotional state.

[1916] Providing Feedback

[1917] User

[1918] After trying the meal plan provided, the user inputs their impressions and ratings, and this feedback is sent from the device to the server.

[1919] Save your feedback

[1920] server

[1921] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model, so that it can be reflected in the next proposal.

[1922] Retraining an AI model

[1923] server

[1924] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[1925] Specific examples

[1926] Here is a concrete example: Assume a 30-year-old male, weighing 70 kg and 175 cm tall, has a high activity level, suffers from diabetes, and is allergic to dairy products. This user prefers Japanese food and is currently feeling stressed.

[1927] Collecting user information: The user enters information from the terminal and sends it to the server.

[1928] Emotion recognition: The device analyzes the user's voice and facial expressions to determine whether they are feeling stressed.

[1929] Creating a user profile: The server stores the information in a database and creates a profile.

[1930] Meal plan generation: The server generates a menu of mainly Japanese cuisine that is low in carbohydrates and does not contain dairy products, and sends it to the user's device.

[1931] Meal plan provided: The user reviews the proposed meal plan on the device.

[1932] Providing feedback: The user tries the meal and provides feedback that it was "relaxing."

[1933] Save Feedback: The server saves the feedback in a database and adds it to the training dataset.

[1934] Retraining the AI ​​model: The server uses the feedback data to retrain the AI ​​model and reflect it in the next proposal.

[1935] Example prompts for generative AI models

[1936] "I'm a 30-year-old man, 180cm tall, weigh 75kg, and run three times a week. I have high blood pressure and no particular allergies. My favorite food is Chinese food, and I've been feeling pretty stressed at work lately. I'd like you to suggest a meal plan that fits these conditions."

[1937] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1938] Step 1:

[1939] Collection of User Information

[1940] Terminal

[1941] Users access the system using a smartphone or PC and enter their body information (e.g., height and weight), exercise volume, health status, allergies, dietary preferences, etc. into the provided interface. The entered information is sent from the device to the server in JSON format.

[1942] Input: User-entered information about your body type, activity level, health status, allergies, and dietary preferences.

[1943] Data processing: Convert the input information into JSON format.

[1944] Output: User information in JSON format is sent from the device to the server.

[1945] What happens: A user opens the app, fills out a form, and presses the "Submit" button.

[1946] Step 2:

[1947] Emotion recognition

[1948] Terminal

[1949] The device's built-in camera and microphone are used to collect the user's voice and facial expressions. The emotion recognition engine analyzes this data and determines the user's emotional state. The results are sent to the server in JSON format.

[1950] Input: User's voice data, facial expression data.

[1951] Data processing: The emotion recognition engine analyzes voice and facial expressions to determine the emotional state.

[1952] Output: The determined emotional state is sent to the server in JSON format.

[1953] Specific operation: The user interacts with the system through voice and captures facial expressions with the camera.

[1954] Step 3:

[1955] Creating a User Profile

[1956] server

[1957] The server stores the user information and emotional state sent from the device in a database, and generates an individual profile for each user based on this information.

[1958] Input: User information and emotional state sent from the device.

[1959] Data processing: User information and emotional state are stored in a database and a profile is generated.

[1960] Output: The generated user profile is recorded in a database.

[1961] Specific operation: The server stores the received data in a database and generates a new profile item.

[1962] Step 4:

[1963] Generate a meal plan

[1964] server

[1965] The server generates an optimal meal plan based on the generated user profile, the activity level and emotional state of the day. The user information is converted into tensor format and input into a generative AI model. The AI ​​model predicts the optimal meal plan based on body type information, exercise volume, health status, allergies, food preferences, and emotional state.

[1966] Input: Stored user profile, activity level, emotional state.

[1967] Data processing: User information is converted into tensor format and input into the generative AI model.

[1968] Output: The generated meal plan is sent to the terminal in JSON format.

[1969] Specific operation: The server inputs profile information into the AI ​​model and outputs a meal plan as the analysis result.

[1970] Step 5:

[1971] Meal plan provided

[1972] Terminal

[1973] The optimal meal plan sent from the server is displayed on the user's device, where the user can check the proposed plan and use it to make daily meal choices.

[1974] Input: Meal plan sent from server.

[1975] Data processing: Display meal plan information on the device.

[1976] Output: User can review the suggested meal plan.

[1977] Specific operation: Display the meal plan sent from the server on the app screen.

[1978] Step 6:

[1979] Providing Feedback

[1980] User

[1981] After trying out the meal plan provided, the user inputs their impressions and ratings, and the input feedback is sent from the device to the server.

[1982] Input: User comments and ratings.

[1983] Data processing: Convert the feedback information into JSON format.

[1984] Output: Feedback information is sent from the device to the server.

[1985] Specific operation: The user enters feedback on the terminal and sends it to the server by clicking the send button.

[1986] Step 7:

[1987] Save your feedback

[1988] server

[1989] The server stores the feedback information received from the device in a database, and also adds this feedback information to a dataset for retraining the AI ​​model.

[1990] Input: Feedback information sent from the device.

[1991] Data processing: The feedback information is stored in a database and added to the training dataset.

[1992] Output: The feedback information is stored in a database.

[1993] Specific operation: The server stores the received data in a database and adds it to the training dataset.

[1994] Step 8:

[1995] Retraining an AI model

[1996] server

[1997] The server uses the stored feedback information to retrain the AI ​​model, which improves the accuracy of the suggestions and allows for more personalized suggestions based on the user's preferences.

[1998] Input: Saved feedback information.

[1999] Data processing: Retraining the AI ​​model based on feedback information.

[2000] Output: The updated AI model.

[2001] Specific operation: The server inputs the feedback data into the AI ​​model and performs retraining.

[2002] (Application example 2)

[2003] 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."

[2004] In today's busy lifestyles, it is extremely difficult to easily provide optimal meal plans tailored to individual users' health and emotional states. Conventional systems have difficulty proposing personalized meal plans due to insufficient user information input and recognition of emotional states. Furthermore, while there is a demand for meal plans that take into account the user's emotional state, there are limitations in this regard as well. To address this issue, it is necessary to combine emotion recognition with the creation of a profile based on information such as the user's body type, activity level, health status, allergies, and food preferences to propose more accurate meal plans.

[2005] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2006] In this invention, the server includes means for collecting information on the user's body type, amount of exercise, health condition, allergies, and food preferences, means for creating an individual profile based on the collected user information, an emotion recognition engine for recognizing the user's emotional state from voice input and facial expressions, means for proposing a meal plan according to the user's activity level and emotional state for that day, means for the user to provide feedback on the proposed meal plan, and means for learning from the user's feedback and improving the next proposal, thereby enabling the provision of a personalized meal plan that takes into account the user's health condition and emotions.

[2007] "User's body type information" is information that indicates the user's physical characteristics such as height and weight.

[2008] "Amount of exercise" is information that indicates the user's daily exercise habits and activity level.

[2009] "Health condition" is information indicating the user's medical history and current health condition.

[2010] "Allergy" is information that indicates that the user has an allergic reaction to a particular food or ingredient.

[2011] "Dietary preferences" is information about the ingredients and cooking styles that the user prefers.

[2012] An "emotion recognition engine" is software or hardware for recognizing a user's emotional state from their voice and facial expressions.

[2013] A "generative AI model" is an artificial intelligence model trained to make optimal suggestions based on user information.

[2014] A "dataset" is a collection of data, such as feedback information, collected for use in retraining an AI model.

[2015] A "meal plan" is a meal suggestion based on a user's profile and their activity level and emotional state for the day.

[2016] "Feedback" refers to the user's evaluation and impressions of the meal plan provided.

[2017] The present invention is a system that creates an individual profile based on a user's body type information, amount of exercise, health condition, allergies, food preferences, and emotional state, and proposes an optimal meal plan. Specific embodiments for implementing the present invention are described below.

[2018] 1. Collection of User Information

[2019] The device collects information entered by the user about their body type (e.g., height and weight), physical activity (e.g., daily exercise habits), health status (e.g., medical history and allergies), and food preferences (e.g., favorite ingredients and cooking styles). This information is converted into JSON format and sent to the server.

[2020] 2. Emotional Recognition

[2021] The device is equipped with an emotion recognition engine that recognizes the user's emotional state from their voice and facial expressions. For example, it can determine the user's emotions (e.g., whether they are feeling stressed) by analyzing facial expressions through the camera and voice through the microphone. This processing is performed using Python and TensorFlow.

[2022] 3. Create a user profile

[2023] The server stores the user information and emotional state sent from the device in a database and generates an individual profile for each user based on that information. The generated profile is then recorded in the database.

[2024] 4. Generate a meal plan

[2025] The server generates an optimal meal plan based on the user's profile, activity level, and emotional state for that day. The server converts the collected user information into tensor format and inputs it into a generative AI model. This generative AI model predicts the optimal meal plan based on a combination of the user's body type, exercise level, health status, allergies, food preferences, and emotional state.

[2026] 5. Meal plan offerings

[2027] The server generates an optimal meal plan, which is then sent to the user's device, where the user can view it. Depending on the user's emotional state, the suggested meal plan includes ingredients and dishes that suit the user's mood.

[2028] 6. Providing Feedback

[2029] After trying the proposed meal plan, the user inputs their impressions and evaluation as feedback, which is then sent from the device to the server.

[2030] 7. Saving Feedback

[2031] The server stores the feedback information received from the terminal in a database, and also adds this feedback information to the training dataset.

[2032] 8. Retraining AI models

[2033] The server uses the stored feedback information to retrain the generative AI model, which makes the next suggestions more accurate and adapted to the user's preferences.

[2034] Specific examples

[2035] Assume the user is 30 years old, weighs 70 kg, is 175 cm tall, has a high activity level, is diabetic and allergic to dairy products, and prefers Japanese food. If the emotion recognition engine determines that the user is feeling stressed, the following steps are performed:

[2036] 1. User Information Collection:

[2037] "Enter your body type, activity level, health status, allergies, and dietary preferences."

[2038] 2. Emotion Recognition:

[2039] "Please speak into the microphone. We will recognize your facial expressions, so please look at the camera."

[2040] 3. Create a user profile:

[2041] The server generates and saves a profile based on this information.

[2042] 4. Generate meal plan:

[2043] "We offer a menu of low-carb, dairy-free Japanese cuisine."

[2044] 5. Meal Plan Offering:

[2045] Users can view the proposed meal plan on their device.

[2046] 6. Providing Feedback:

[2047] Please enter your thoughts after your meal.

[2048] 7. Saving Feedback:

[2049] The server stores the feedback information

[2050] 8. Retraining AI models:

[2051] "We will retrain it based on the feedback information to improve our next proposal."

[2052] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2053] Step 1:

[2054] Collection of User Information

[2055] The device accepts input from the user about their body type (height and weight), amount of exercise (daily exercise habits), health condition (medical history and allergies), and food preferences (favorite ingredients and cooking styles). The user enters this information on the provided interface, and the device converts it into JSON format and sends it to the server.

[2056] Input: Information about your body type, activity level, health status, allergies, and dietary preferences that you enter into your device

[2057] Output: User information converted to JSON format and sent to the server

[2058] Step 2:

[2059] Emotion recognition

[2060] The device uses an emotion recognition engine to recognize the user's emotional state from their voice and facial expressions. It captures facial expressions using a camera and records audio using a microphone. The emotion recognition engine analyzes facial features and voice tone to determine the user's emotion (e.g., whether they are feeling stressed). The results are converted into JSON format and sent to the server.

[2061] Input: User facial expression images and voice data

[2062] Output: Emotional state information converted to JSON format and sent to the server

[2063] Step 3:

[2064] Creating a User Profile

[2065] The server receives the user information and emotional state sent from the device and stores them in a database. Based on this information, an individual profile of the user is generated. The profile is stored as a tensor-type data structure that comprehensively assesses the user's health and emotional state.

[2066] Input: User information and emotional state information in JSON format

[2067] Output: User profile stored in the database

[2068] Step 4:

[2069] Generate a meal plan

[2070] The server generates an optimal meal plan based on the generated user profile and the day's activity level and emotional state. This is done using a generative AI model. The AI ​​model takes user data in tensor format as input and predicts the optimal meal plan based on that data. The generated meal plan is converted to JSON format and sent to the device.

[2071] Input: User profile in tensor format, along with activity level and emotional state for that day

[2072] Output: JSON formatted meal plan sent to the device

[2073] Step 5:

[2074] Meal plan provided

[2075] The device displays the meal plan received from the server, and the user reviews the plan and decides whether to select it. During this process, the plan includes ingredients and dishes that correspond to the user's emotional state.

[2076] Input: JSON format meal plan received from the server

[2077] Output: Meal plan displayed on device

[2078] Step 6:

[2079] Providing Feedback

[2080] After trying the proposed meal plan, the user enters their impressions and evaluations as feedback into the device, which then converts this feedback information into JSON format and sends it to the server.

[2081] Input: User feedback information

[2082] Output: Feedback information converted to JSON format and sent to the server

[2083] Step 7:

[2084] Save your feedback

[2085] The server stores the feedback information received from the devices in a database, which is also used as a data set to help propose improvements for the next time.

[2086] Input: Feedback information in JSON format

[2087] Output: Feedback information stored in a database

[2088] Step 8:

[2089] Retraining an AI model

[2090] The server uses the stored feedback information to retrain the generative AI model, which then gains the ability to generate more accurate and user-specific meal plans for the next time.

[2091] Input: Feedback information stored in the database

[2092] Output: An improved generative AI model

[2093] 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.

[2094] 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.

[2095] 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.

[2096] 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.

[2097] 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.

[2098] 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.

[2099] 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).

[2100] 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.

[2101] 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."

[2102] 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.

[2103] 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).

[2104] 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.

[2105] 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.

[2106] 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.

[2107] 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.

[2108] 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.

[2109] 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.

[2110] 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.

[2111] 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.

[2112] 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.

[2113] 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.

[2114] The following is further disclosed regarding the above embodiment.

[2115] (Claim 1)

[2116] a means of [collecting information about the user's body type, activity level, health status, allergies, and dietary preferences];

[2117] a means for creating individual profiles based on collected user information; and

[2118] a means for suggesting meal plans based on the user's activity level for that day;

[2119] a means for users to provide feedback on the proposed meal plan;

[2120] A way to learn from user feedback and improve our next proposal;

[2121] A system including:

[2122] (Claim 2)

[2123] 10. The system of claim 1, wherein the system maintains a database of suggested meal plans and uses the database to generate the meal plans.

[2124] (Claim 3)

[2125] The system of claim 1, wherein the feedback information is stored in a dataset and the dataset is used to retrain the AI ​​model.

[2126] "Example 1"

[2127] (Claim 1)

[2128] a means of [collecting information about the user's body type, activity level, health status, allergies, and dietary preferences];

[2129] A means to send collected user information to the server in JSON format;

[2130] a means for storing user information in a database and generating a profile for each user;

[2131] A means to convert the user's profile into tensor format and input it into an AI model to generate an optimal meal plan;

[2132] a means for providing the generated meal plan to a user's terminal;

[2133] a means for the user to input feedback on the proposed meal plan;

[2134] A means for sending user feedback to a server and retraining the AI ​​model based on the feedback;

[2135] A system including:

[2136] (Claim 2)

[2137] 10. The system of claim 1, wherein the system maintains a database of suggested meal plans and uses the database to generate the meal plans.

[2138] (Claim 3)

[2139] The system of claim 1, wherein the feedback information is stored in a dataset and the dataset is used to retrain the AI ​​model.

[2140] "Application Example 1"

[2141] (Claim 1)

[2142] a means of [collecting information about the user's body type, activity level, health status, allergies, and dietary preferences];

[2143] a means for creating individual profiles based on collected user information; and

[2144] A means to propose optimal meal plans based on the user's activity level for the day and enable instant delivery orders; and

[2145] a means for users to provide feedback on the proposed meal plan;

[2146] A way to learn from user feedback and improve our next proposal;

[2147] A system including:

[2148] (Claim 2)

[2149] The system of claim 1 [maintaining a database of suggested meal plans and using this database to generate meal plans for use in delivery orders].

[2150] (Claim 3)

[2151] The system of claim 1, wherein the feedback information is stored in a dataset, the dataset is used to retrain the generative AI model, and the prompt sentences are used to refine the next meal plan suggestions.

[2152] "Example 2: Combining Emotion Engines"

[2153] (Claim 1)

[2154] a means of [collecting information about the user's body type, activity level, health status, allergies, and dietary preferences];

[2155] a means for creating individual profiles based on collected user information; and

[2156] a means for suggesting a meal plan based on the user's activity level and emotional state for the day;

[2157] a means for users to provide feedback on the proposed meal plan;

[2158] a means for recognizing the emotional state of a user using an emotion recognition engine installed in the device;

[2159] A way to learn from user feedback and improve our next proposal;

[2160] a means for storing feedback information; and

[2161] a means for retraining the AI ​​model using the stored feedback information; and

[2162] A system including:

[2163] (Claim 2)

[2164] 10. The system of claim 1, wherein the system maintains a database of suggested meal plans and uses the database to generate the meal plans.

[2165] (Claim 3)

[2166] The system of claim 1, wherein the feedback information is stored in a dataset and the dataset is used to retrain the AI ​​model.

[2167] "Application example 2 when combining emotion engines"

[2168] (Claim 1)

[2169] a means of [collecting information about the user's body type, activity level, health status, allergies, and dietary preferences];

[2170] a means for creating individual profiles based on collected user information; and

[2171] [An emotion recognition engine that recognizes the user's emotional state from their voice input and facial expressions] means;

[2172] a means for suggesting a meal plan based on the user's activity level and emotional state for the day;

[2173] a means for users to provide feedback on the proposed meal plan;

[2174] A way to learn from user feedback and improve our next proposal;

[2175] A system including:

[2176] (Claim 2)

[2177] 10. The system of claim 1, wherein the system maintains a database of suggested meal plans and uses the database to generate the meal plans.

[2178] (Claim 3)

[2179] The system of claim 1, wherein the feedback information is stored in a dataset and the dataset is used to retrain the generative AI model. [Explanation of symbols]

[2180] 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. A means for collecting information about the user's body type, activity level, health condition, allergies, and dietary preferences; means for creating individual profiles based on collected user information; a means for suggesting a meal plan based on the user's activity level for that day; a means for the user to provide feedback on the proposed meal plan; A way to learn from user feedback and improve our next proposal; A system including:

2. 10. The system of claim 1, further comprising: maintaining a database of suggested meal plans; and using the database to generate the meal plans.

3. 10. The system of claim 1, wherein the feedback information is stored in a dataset and the dataset is used to retrain the AI ​​model.

Images