System

Abstract

A system is provided.SOLUTION: A means in which a user inputs a family structure, a physical condition, weather, and a last meal content by using a terminal, a means in which a server receives and stores data transmitted from the terminal, and a means in which a generated AI model analyzes the stored data; A system comprising: means for learning a user's preference and weak ingredients; means for generating an optimal menu based on the day's climate, physical condition, cooking time, and the like in response to the user's request; means for transmitting and displaying the generated menu; means for inputting the user's satisfaction and feedback on the created menu; and means for storing and analyzing the feedback and updating a generated AI model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's busy society, planning daily menus is a significant burden, especially for housewives and those who cook at home. Furthermore, for families with children, planning nutritionally balanced meals according to the age of each child is becoming an even greater challenge. Furthermore, there is a growing demand for systems that contribute to maintaining health by suggesting menus that take into account the user's physical condition and weather. Conventional methods require a great deal of time and effort to accommodate individual conditions and preferences, so these problems need to be solved. [Means for solving the problem]

[0005] The present invention provides a system in which a user inputs information about their family composition, physical condition, weather, and recent meal contents using a device. The data is then received and stored by a server, and a generative AI model analyzes this information. The generative AI model learns the user's preferences and dislikes and generates optimal menus based on the user's requests, taking into account factors such as weather, physical condition, and cooking time. Furthermore, the generated menus are sent to the user's device and displayed, allowing the user to easily receive suggestions. The system collects feedback on the menus created by the user, and sends, stores, and analyzes them on the server to improve the accuracy of the generative AI model. Furthermore, the system supports parents raising children by suggesting baby food ingredients and cooking methods appropriate for the baby's age. This allows users to quickly decide on daily menus, reducing the burden of housework and childcare and maintaining a healthy diet.

[0006] A "terminal" is an electronic device through which a user can input information and view suggested menu items.

[0007] "Family structure" refers to information such as the age and role of each member of the household.

[0008] "Health" refers to information about the health status of the user and their family members.

[0009] "Climate" refers to the external environmental conditions, such as the weather and temperature of the day.

[0010] "Details of most recent meal" refers to the details of the meal the user recently ate.

[0011] "Server" refers to a computer system that receives and stores data sent by users.

[0012] A "generative AI model" refers to an artificial intelligence algorithm that analyzes incoming data and learns the user's preferences and dislikes.

[0013] "Menu" refers to the meal plan for the day, including the menu and the contents of the dishes.

[0014] "Feedback" refers to the evaluation and impressions that users give to the proposed menu.

[0015] "Baby food" refers to food given according to a child's stage of development, with particular consideration given to ingredients and cooking methods appropriate for the child's age. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[0038] Obtaining user input information

[0039] The user uses the terminal to input information about their family, physical condition, weather, and what they ate most recently. For example, today's family is "father, mother, 5-year-old child, 1-year-old child," their physical condition is "mother has a bit of a cold," their weather is "rainy and cold," and their most recent meal is "curry rice last night."

[0040] The server receives and stores the data

[0041] The terminal transmits the input data to the server, which receives the data and stores it in a database.

[0042] AI model analyzes data

[0043] The generative AI model on the server analyzes the stored data and learns the user's preferences and dislikes of certain foods. For example, it might learn that a child dislikes green peppers and a mother likes cheese.

[0044] Generate menu suggestions

[0045] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), and other conditions. For example, it suggests "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0046] Presenting the proposal

[0047] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0048] Gathering feedback

[0049] The user creates a proposed menu and enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database. The AI ​​model on the server analyzes the stored feedback and updates the model to help with future suggestions.

[0050] This system allows users to easily decide on daily menus, reducing the burden of housework and childcare. It also supports the health of the entire family by providing nutritionally balanced meals. For families with children in particular, it suggests baby food according to the child's age, reducing the burden of childcare. This allows users to enjoy a richer diet.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The user starts the application using a terminal and logs in. The user enters information about the family composition, physical condition, weather, and recent meal, and then enters information about each member (e.g., father, mother, 5-year-old child, 1-year-old child) on the "Enter family composition" screen.

[0054] Step 2:

[0055] On the "Enter your physical condition and weather" screen, the user enters, for example, that "my mother is feeling a bit sick" as a physical condition and that "it's rainy and cold" as a weather condition. Also, on the "Enter your most recent meal" screen, the user enters the meal they recently had (for example, "I had curry and rice last night").

[0056] Step 3:

[0057] The terminal sends the entered data to the server, which receives the data and stores it in a database.

[0058] Step 4:

[0059] A generative AI model on the server reads the stored data and preprocesses it into a format that is easy to analyze.

[0060] Step 5:

[0061] The generative AI model learns the user's preferences and dislikes, for example, that a child dislikes green peppers and a mother likes cheese.

[0062] Step 6:

[0063] The user requests "Today's Menu Suggestion" through the app. The server receives the request and generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), and other conditions.

[0064] Step 7:

[0065] The generative AI model generates menus based on conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0066] Step 8:

[0067] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0068] Step 9:

[0069] The user actually creates the suggested menu and provides it to their family. The user then inputs feedback such as satisfaction and areas for improvement into the device.

[0070] Step 10:

[0071] The terminal sends feedback from the user to the server, which receives the data and stores it in a database.

[0072] Step 11:

[0073] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion.

[0074] In this way, the system provides optimal menus based on the information entered by the user, taking into account the weather, physical condition, and past dietary habits, and improves the accuracy of its suggestions through feedback.

[0075] Example 1

[0076] 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."

[0077] There is a need to reduce the time and effort required to plan daily menus and provide appropriate meals that suit the physical condition and preferences of family members. However, with busy lives and child-rearing responsibilities, it is difficult to plan balanced meals, and inappropriate meals can disrupt nutritional balance. In addition, providing meals appropriate to the age of infants and toddlers is particularly important, but achieving this requires specialized knowledge.

[0078] 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.

[0079] In this invention, the server includes a means for a user to input information about members, their health status, weather information, and recent meal contents using a mobile device; a means for the server to receive and store the data transmitted from the mobile device; and a means for the generative AI model to analyze the stored data and learn the user's preferences and food dislikes. This allows users to easily decide daily menus and efficiently provide nutritionally balanced meals for the entire family. Furthermore, the generative AI model takes into account ingredients and cooking methods appropriate for the age of the family when proposing meals for infants, thereby reducing the burden on families raising children.

[0080] A "mobile terminal" is an electronic device that allows a user to input information about family composition, physical condition, weather information, and recent meal details, and includes devices such as smartphones and tablets.

[0081] "Member information" refers to data such as each family member's age, gender, food preferences, and disliked foods.

[0082] "Health status" refers to each family member's current physical condition, medical history, allergy information, etc.

[0083] "Weather information" is data relating to the weather conditions in the area where the user currently resides, including temperature, humidity, rainfall, and the like.

[0084] "Recent meal contents" refers to cooking records and meal menu data created by the user in the past.

[0085] A "server" is a computer system that receives, stores, and processes data sent by users.

[0086] A "database" is a system that systematically manages data such as member information, health status, weather information, and recent meal contents stored on a server.

[0087] "Generative AI model" refers to artificial intelligence technology that analyzes stored data and generates appropriate menus that are presented through a user interface.

[0088] "Analysis" refers to the process by which a generative AI model processes input data, finds patterns and trends, and learns from them.

[0089] "Preferences" refers to data about each family member's favorite ingredients and cooking methods.

[0090] "Difficult ingredients" refers to ingredients that each member of the family dislikes, is allergic to, or would like to avoid.

[0091] A "menu" refers to the combination of dishes suggested by the generative AI model for the user to serve as their meal of the day.

[0092] "Satisfaction level" refers to the evaluation after the user actually creates the suggested menu.

[0093] "Opinions" refers to feedback such as improvements or requests that users have regarding the proposed menu.

[0094] "Machine learning algorithms" refer to the mathematical methods and models that generative AI models use to analyze data and learn patterns.

[0095] "Nutritional balance" refers to a combination of meals that are carefully designed to ensure the appropriate intake of various nutrients, with the family's health in mind.

[0096] "Infant meal suggestions" refers to meal suggestions that take into consideration appropriate ingredients and cooking methods according to the infant's age.

[0097] MODE FOR CARRYING OUT THE INVENTION

[0098] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[0099] System configuration

[0100] User terminal

[0101] The user terminal provides an interface for users to input information about members, their health status, weather information, and recent meal details. Specific examples include mobile devices such as smartphones and tablets. These devices allow users to input data through dedicated applications.

[0102] server

[0103] The server is a computer system that receives and stores data sent from user devices. The server uses a database to systematically store and manage the received data. Furthermore, it uses a generative AI model running on the server to analyze the data and generate menus.

[0104] Generative AI Models

[0105] The generative AI model analyzes the received and stored data and learns the user's preferences and dislikes. This generative AI model is implemented using machine learning algorithms (e.g., GPT-4). Based on the stored data, it creates an appropriate menu according to the user's request.

[0106] Process Overview

[0107] 1. Obtaining user input information: The user opens the app on their mobile device and enters information about their family members, their health condition, weather information, and what they recently ate. For example, they enter "father, mother, 5-year-old child, 1-year-old child" as the family composition, "mother has a bit of a cold" as the health condition, "rainy and cold" as the weather, and "curry rice last night" as the most recent meal.

[0108] 2. The server receives and saves the data: The device sends the entered data to the server, which receives it and saves it in a database.

[0109] 3. The AI ​​model analyzes the data: The generative AI model on the server analyzes the data stored in the database and learns the user's preferences and dislikes. For example, it learns that a child dislikes green peppers and a mother likes cheese.

[0110] 4. Menu suggestion generation: When a user requests "Today's menu suggestion" in the app, the server receives the request, and the AI ​​model generates the optimal menu based on the weather, health condition, recent meals, etc. For example, "digestible chicken ginger soup" and "minced meat and vegetable salad" are suggested.

[0111] 5. Proposal presentation: The server sends the generated menu to the user terminal, which displays it to the user. The user can then create a proposed menu.

[0112] 6. Feedback collection: After the user creates the proposed menu, they input their satisfaction and suggestions for improvement into their mobile device. The device sends this to the server, which stores it in a database. The generative AI model analyzes the feedback and updates the model to help with future suggestions.

[0113] Specific examples

[0114] For example, if the family structure (father, mother, 5-year-old child, 1-year-old child), health condition (mother is feeling a bit under the weather) and weather information (rainy and cold) are entered, along with information such as (curry rice last night), the system will suggest (easy-to-digest) chicken ginger soup and (minced meat and vegetable salad).

[0115] Prompt Sentence Examples

[0116] "Today's family consists of a father, a mother, a five-year-old child, and a one-year-old child, and the mother is feeling a bit under the weather. It's rainy and cold today. Last night, they had curry rice. Based on these conditions, please suggest the best menu for them."

[0117] The system allows users to easily plan their daily meals and provide nutritionally balanced meals for the whole family.The generative AI model also takes age-appropriate ingredients and cooking methods into account when suggesting meals for infants, reducing the burden on families with children.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1:

[0120] The user opens the app on their device and enters their family composition, physical condition, weather, and recent meal details. For example, the input form includes the family composition of "father, mother, 5-year-old child, 1-year-old child," the physical condition of "mother is feeling a bit sick," the weather of "rainy and cold," and "I had curry rice last night."

[0121] Input data: Family composition, physical condition, weather, recent meal contents

[0122] Output data: User input data ready to send

[0123] Step 2:

[0124] The terminal sends the entered data to the server, which receives it as an HTTP request.

[0125] Input data: User-entered data

[0126] Data processing: Convert input data into HTTP requests

[0127] Output data: HTTP request sent

[0128] Step 3:

[0129] The server stores the received data in a database, for example by inserting data into the database using an SQL query.

[0130] Input data: Received data from the HTTP request

[0131] Data manipulation: Inserting data using SQL queries

[0132] Output data: Saved to database

[0133] Step 4:

[0134] The generative AI model on the server analyzes the data stored in the database. It then runs machine learning algorithms to learn the user's preferences and dislikes. For example, it analyzes the data and extracts the user's preference patterns.

[0135] Input data: User-entered data stored in a database

[0136] Data processing: Data analysis using machine learning algorithms

[0137] Output data: Generation of user preference data

[0138] Step 5:

[0139] The user requests "Today's menu suggestions" through the app. The device sends this request to the server.

[0140] Input data: User's menu suggestion request

[0141] Data processing: Generating request data

[0142] Output data: Request sent to server

[0143] Step 6:

[0144] The server receives the request and inputs the prompt into the generative AI model, which generates the optimal menu taking into account the weather, physical condition, and recent meal content of the day.

[0145] Input data: user requests, stored user data

[0146] Data processing: Prompt generation and input to the AI ​​model

[0147] Output data: Generation of optimal menu

[0148] Step 7:

[0149] The server sends the generated menu to the user's device, which receives it and displays the menu on the app screen.

[0150] Input data: Generated menu data

[0151] Data processing: data format conversion and transmission

[0152] Output data: Menu displayed on terminal

[0153] Step 8:

[0154] After the user creates the proposed menu, they input their feedback, such as their level of satisfaction and areas for improvement, into the terminal. The user's evaluation and opinions are entered into an input form.

[0155] Input data: User feedback data

[0156] Output data: Feedback data ready to send

[0157] Step 9:

[0158] The terminal transmits feedback data to the server, and the server stores the received feedback in a database.

[0159] Input data: User feedback data

[0160] Data processing: Sending via HTTP request, inserting data via SQL query

[0161] Output data: Feedback data saved in database

[0162] Step 10:

[0163] The server's generative AI model analyzes the stored feedback data and updates the model, which then reflects the feedback in the next menu suggestion.

[0164] Input data: Saved feedback data

[0165] Data processing: Data analysis and model updating using machine learning algorithms

[0166] Output data: Updated generative AI model

[0167] Through the above processing steps, the user can easily decide on daily menus and provide appropriate, nutritionally balanced meals for the whole family.

[0168] (Application example 1)

[0169] 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."

[0170] In today's busy households, planning a daily menu is a time-consuming and labor-intensive task. In particular, families with children need to provide meals that are suitable for the entire family while taking nutritional balance into consideration. Furthermore, as the use of food delivery services increases, there is a demand for customized meals that address individual health conditions and preferences. However, current services are insufficient in adapting to individual health conditions and preferences, making it difficult to propose an optimal menu for the user and order meals based on that menu. The purpose of this invention is to solve these problems and provide a system that proposes an optimal menu for the user and allows the user to smoothly order food delivery.

[0171] 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.

[0172] In this invention, the server includes: means for a user to input information about family composition, physical condition, weather, and recent meal content using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the menu created by the user into the terminal and transmit it to the server; means for storing and analyzing the feedback and updating the generative AI model; and means for ordering meals from external restaurants based on the generated menu. This allows users to easily determine an optimal menu that corresponds to their individual health condition and preferences, and further enables them to smoothly order meals based on the proposed menu.

[0173] "A means for users to input information about their family composition, physical condition, weather, and recent meal details using a device" refers to an interface that allows users to input information about their own and their family's health status, weather conditions, and recent meal details using electronic devices such as smartphones and tablets.

[0174] "Means for the server to receive and store data sent from the terminal" refers to a system configuration in which information sent from a user terminal is received via a network and the data is stored in a storage device such as a database.

[0175] "Means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients" refers to the process of using a machine learning algorithm based on the stored data to identify the user's preferences and ingredients they want to avoid, learning from them and applying them to future recipes.

[0176] "A means of generating optimal menus based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services" refers to an algorithm that enables AI to design the best menu in response to a user's request, taking into account the weather and physical condition of the day, the specified cooking time, and the menus offered by external services.

[0177] "Means for sending and displaying the generated menu to the user's device" refers to the technology for sending the menu information generated by AI to the user's electronic device and displaying that information on the screen.

[0178] "Means for users to input their satisfaction and feedback regarding the menu they have created into a terminal and send it to a server" refers to a system that allows users to input their thoughts and suggestions about the completed dish and send that information to a server via a network.

[0179] "Means for storing and analyzing said feedback and updating the generative AI model" refers to a series of processes for storing feedback data from users in a storage device and analyzing that data to improve the AI ​​model.

[0180] "Means for ordering meals from external restaurants based on the generated menu" refers to the interface and process for ordering meals from affiliated restaurants and delivery services based on the menu suggested by AI.

[0181] This invention provides a system that generates an optimal menu based on various information such as the user's family composition, physical condition, weather, and recent meal content, and then orders meals from external restaurants based on the menu. Specific embodiments are described below.

[0182] System Configuration

[0183] User terminal

[0184] The user terminal is an electronic device such as a smartphone or tablet, and the user uses this terminal to input information such as their own and their family's health status, weather conditions, and recent meal information.

[0185] server

[0186] The server receives and stores data sent from the user's device. The generative AI model then analyzes the stored data and learns the user's preferences and dislikes. In response to the user's request, the server generates an optimal menu based on the day's weather, physical condition, cooking time, and options from external meal delivery services.

[0187] Generative AI Models

[0188] The generative AI model analyzes the stored data, identifies the user's preferences and ingredients to avoid, and learns from them, which is then reflected in future menu generation.

[0189] System Features

[0190] Entering user information

[0191] The user can enter the following information via the terminal:

[0192] Family composition (e.g., father, mother, 5-year-old child, 1-year-old child)

[0193] Physical condition (e.g., mother has a cold)

[0194] Climate (e.g. rainy and cold)

[0195] What you ate most recently (e.g. curry rice last night)

[0196] Receiving and storing data

[0197] The server receives the information sent by the user from the device and stores it in a database, which includes information such as family composition, physical condition, weather, and recent meal contents.

[0198] Data analysis and menu suggestions

[0199] The generative AI model analyzes the received data and learns the user's preferences and dislikes. For example, it may learn that a child dislikes green peppers and a mother likes cheese. Then, when a user makes a request, the server generates the optimal menu based on the day's conditions.

[0200] Menu display and ordering function

[0201] The generated menu is sent to the user's device and displayed there. The user can then review the proposed menu and order meals from affiliated external restaurants if necessary.

[0202] Gathering feedback and updating the model

[0203] Users can input their feedback on the proposed menu, such as their level of satisfaction and areas for improvement, into their device and send it to the server. The server then stores this feedback and updates the generative AI model, making future menu suggestions more accurate.

[0204] For example:

[0205] "The family consists of a father, a mother, a 5-year-old child, and a 1-year-old child. The mother is feeling a bit under the weather, and it's cold and rainy today. Last night we had curry rice. Could you suggest a menu for today?"

[0206] "Yesterday's soup was a little salty. Mom's cold is a little better. What would be best today?"

[0207] By providing the AI ​​model with the above prompts, the model can generate a menu that specifically corresponds to the user's situation, allowing the user to easily determine the optimal menu that corresponds to their individual health condition and preferences, and then smoothly order meals based on the suggested menu.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1: Enter your user information

[0210] The user uses the device to input information about their family, physical condition, weather, and recent meals. The input information specifically includes the following items:

[0211] Family composition (e.g., "Father, mother, 5-year-old child, 1-year-old child")

[0212] Physical condition (e.g., "My mother has a slight cold")

[0213] Climate (e.g., "rainy and cold")

[0214] What you ate most recently (e.g., "I had curry rice last night")

[0215] Input data is collected at the terminal and sent to the server.

[0216] Step 2: Receiving and storing data

[0217] The server receives the data sent from the user terminal. The above information is sent as input, and the server stores it in a database. Specifically,

[0218] Input: Family composition, physical condition, weather, and recent meal details

[0219] Output: Saved database entries

[0220] The data is organized by category and stored for future retrieval and analysis.

[0221] Step 3: Data analysis and user learning

[0222] The generative AI model analyzes the stored data. In this step, data processing and calculations are performed to identify the user's preferences and dislikes.

[0223] Input: Saved database information

[0224] Output: A list of the user's preferences and ingredients to avoid

[0225] Through analysis, the AI ​​model learns user preferences (e.g., "children don't like green peppers" or "mothers like cheese").

[0226] Step 4: Create a menu

[0227] When a user requests "Today's Menu Suggestion," the server receives the request, and the generative AI model generates the optimal menu by taking into account the day's weather, physical condition, cooking time, and options from external services.

[0228] Input: Weather, physical condition, cooking time, menu of external service

[0229] Output: Optimal menu

[0230] During this process, a wide range of data, including weather and physical condition, is analyzed again to determine the most appropriate menu.

[0231] Step 5: View Proposals and Order Function

[0232] The generated menu is sent from the server to the user's terminal and displayed on the terminal. The user can then order meals from external restaurants based on the proposed menu.

[0233] Input: Generated menu data

[0234] Output: Menu displayed on screen, and order confirmation screen

[0235] Specifically, users can check the menu and easily place their order within the app.

[0236] Step 6: Gather feedback

[0237] The user inputs their satisfaction with the meal provided and any areas for improvement into the terminal and sends the input to the server.

[0238] Input: Satisfaction and Feedback

[0239] Output: Saved feedback data

[0240] The user's input is again saved in the database.

[0241] Step 7: Analyze feedback and update the model

[0242] The server analyzes the stored feedback data and updates the generative AI model, a step that involves training to incorporate new insights into the model.

[0243] Input: Feedback data

[0244] Output: Updated generative AI model

[0245] Based on the feedback, the model retrains to make its next suggestions even more accurate.

[0246] 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.

[0247] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[0248] Obtaining user input information

[0249] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[0250] The server receives and stores the data

[0251] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[0252] AI model analyzes data

[0253] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[0254] Generate menu suggestions

[0255] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., tiredness), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[0256] Presenting the proposal

[0257] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0258] Gathering feedback

[0259] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[0260] Analyzing feedback and updating the model

[0261] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[0262] In this way, the system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary habits, and improves the accuracy of suggestions through feedback. By incorporating emotional factors in particular, the system can suggest menus that suit the user's mood that day, achieving more personalized menu decisions.

[0263] The processing flow will be explained below.

[0264] Step 1:

[0265] The user starts the application using a terminal and logs in. The user inputs family composition, physical condition, weather, most recent meal, and emotions. For example, the user inputs "father, mother, 5-year-old child, 1-year-old child" as family composition, "mother has a bit of a cold" as physical condition, "rainy and cold" as weather, "curry rice last night" as most recent meal, and "tired" as emotion.

[0266] Step 2:

[0267] The device sends the input data to the server, which receives the data and stores it in a database. At the same time, the emotion engine analyzes the emotion information from the user's input data and sends the analysis results to the server.

[0268] Step 3:

[0269] The generative AI model on the server reads the stored data and preprocesses it to make it easier to analyze, including filling in missing values ​​and normalizing the data.

[0270] Step 4:

[0271] The generative AI model learns from the user's family structure, physical condition, weather, recent meal content, emotional information, etc. to understand the user's preferences and dislikes of ingredients. For example, it can understand that a child dislikes green peppers and a mother likes cheese, or that the user is tired and wants a meal that is easy to prepare.

[0272] Step 5:

[0273] The user requests "Today's menu suggestion" in the application. The server receives the request and generates the optimal menu taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), emotions (tired), and other conditions.

[0274] Step 6:

[0275] The generative AI model generates optimal menus based on the conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0276] Step 7:

[0277] The server sends the generated menu information to the user terminal, which displays the menu to the user.

[0278] Step 8:

[0279] The user actually creates the suggested menu and provides it to their family. After completing the menu, the user enters feedback such as satisfaction and areas for improvement into the device.

[0280] Step 9:

[0281] The terminal transmits feedback data from the user to the server, which receives the data and stores it in a database.

[0282] Step 10:

[0283] The generative AI model on the server analyzes the stored feedback data and updates the model to help with the next menu suggestion. At the same time, the emotion engine also learns the emotional information obtained from the feedback and reflects it in the next emotion analysis.

[0284] This system can provide optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood on that day, achieving more personalized menu decisions.

[0285] Example 2

[0286] 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."

[0287] In today's busy lifestyles, planning a daily menu can be a burden for many people. Furthermore, determining the optimal menu based on the family's physical condition, preferences, and even their emotions on that day is a difficult task. Adjusting the menu is particularly complicated when family members have diverse preferences and physical conditions. Therefore, there is a strong demand for a system that allows users to easily determine the optimal menu. Furthermore, a mechanism is needed that uses feedback to improve the accuracy of suggestions.

[0288] 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.

[0289] In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for an emotion engine to analyze emotional information from the input data and transmit it to the server; means for a generative AI model to analyze the stored data and emotional information and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, emotions, cooking time, etc. in response to a user's request; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the provided menu into the terminal and transmit it to the server; and means for storing and analyzing the feedback and updating the generative AI model and the emotion engine. This not only allows the user to easily receive optimal menu suggestions based on the physical condition, preferences, and emotions of their family members, but also enables the system to continuously improve its accuracy based on the provided feedback.

[0290] A "user terminal" is an electronic device used by a user to input information.

[0291] A "server" is a computer system that receives and stores data sent from user devices and also runs the generative AI model and emotion engine.

[0292] A "generative AI model" is an artificial intelligence model that analyzes stored data and emotional information, learns the user's preferences and disliked ingredients, and generates optimal menus.

[0293] The "emotion engine" is a software component that analyzes emotional information from user input data and sends the results to the server.

[0294] "Family composition" is information indicating the members of the user's family and their relationships.

[0295] "Physical condition" is information indicating the health condition of the user and their family members.

[0296] "Climate" is information indicating the weather and temperature of the day.

[0297] "Details of most recent meal" is information indicating the details of meals recently eaten by the user and their family.

[0298] "Emotions" is information that indicates the current feelings and moods of the user and their family members.

[0299] "Feedback" is information that indicates the user's opinions and evaluations, such as their satisfaction with the menu provided and areas for improvement.

[0300] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[0301] Obtaining user input information

[0302] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[0303] The server receives and stores the data

[0304] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[0305] AI model analyzes data

[0306] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[0307] Generate menu suggestions

[0308] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[0309] Presenting the proposal

[0310] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0311] Gathering feedback

[0312] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[0313] Analyzing feedback and updating the model

[0314] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[0315] Examples of concrete examples and prompts

[0316] As a specific example, consider the case of suggesting easy-to-make meals for a day when the user is tired.

[0317] Specific examples

[0318] User input: Family composition: "Father, mother, 5-year-old child, 1-year-old child", health condition: "Mother is feeling a bit under the weather", weather: "Rainy and cold", most recent meal: "Curry rice last night", emotion: "Tired".

[0319] Server's suggested menu: Chicken ginger soup, minced meat and vegetable salad.

[0320] Prompt Sentence Examples

[0321] Please suggest the best menu for a family consisting of a father, mother, a 5-year-old child, and a 1-year-old child, where the mother is feeling a bit under the weather, it's rainy and cold, they had curry rice last night, and they are emotionally exhausted.

[0322] This system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood that day, achieving more personalized menu decisions.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1: User enters information from device

[0325] The user starts the terminal application and inputs information about the family (e.g., "father, mother, five-year-old child, one-year-old child"), physical condition (e.g., "mother has a slight cold"), weather (e.g., "rainy and cold"), what they had most recently eaten (e.g., "I had curry rice last night"), and emotions (e.g., "I'm tired"). This information is saved as input data on the terminal.

[0326] Step 2: Send data from the device to the server

[0327] The device transmits the input data to the server in real time. The transmitted data includes family composition, physical condition, weather, recent meal contents, and emotions. The server receives the transmitted data.

[0328] Step 3: The server receives and stores the data

[0329] The server stores the received data in a database, which ensures that all user input is stored permanently.

[0330] Step 4: Emotion analysis using the emotion engine

[0331] The emotion engine analyzes emotional information from the user's input data stored on the server. For example, if the user inputs "I'm tired," it analyzes negative emotions. The results of this analysis are also stored in the database.

[0332] Step 5: Data preprocessing for generative AI models

[0333] The generative AI model on the server reads the user's saved data and emotional information, and performs preprocessing such as handling missing values ​​and normalizing the data, thereby preparing the data in a format that is easy to analyze.

[0334] Step 6: The generative AI model analyzes and learns from the data

[0335] Based on the preprocessed data, the generative AI model learns the user's preferences and dislikes. For example, it understands that a child dislikes green peppers and a mother likes cheese, and that a meal plan that is easy to prepare is desired. This learning result is stored in the model.

[0336] Step 7: User submits request

[0337] The user requests "Today's menu suggestions" from the terminal. This request is sent to the server.

[0338] Step 8: The server receives the request

[0339] The server receives the user's request and retrieves the data stored for that day. The input data includes weather (e.g., "It's cold"), physical condition (e.g., "My mother has a slight cold"), recent meal (e.g., "Curry and rice"), and emotion (e.g., "I'm tired").

[0340] Step 9: Menu generation using generative AI models

[0341] The generative AI model generates optimal menus based on the stored data and analysis results. For example, it selects "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy to make and suitable for children. The generated menu information is output.

[0342] Step 10: Server Sends Proposal

[0343] The server sends the generated menu information to the user terminal. The output menu information arrives at the user terminal.

[0344] Step 11: Your device will display suggestions

[0345] The user device displays the menu information sent from the server, and the user can view the suggested menu on the app screen.

[0346] Step 12: User provides feedback

[0347] The user creates a suggested menu and provides it to their family. After that, they input their feedback, such as their actual satisfaction level and areas for improvement, into the device. The input feedback data is saved on the device.

[0348] Step 13: Device sends feedback

[0349] The device sends the saved feedback data to the server, which then receives information about the user's satisfaction and areas for improvement.

[0350] Step 14: Server saves feedback

[0351] The server stores the received feedback data in a database. All feedback information is stored permanently.

[0352] Step 15: Generative AI model analyzes feedback

[0353] The generative AI model analyzes the saved feedback data. Specifically, it extracts user satisfaction and areas for improvement, and analyzes them to help with the next menu proposal. The analysis results are reflected within the model.

[0354] Step 16: The emotion engine updates its learning

[0355] The emotion engine also learns from the feedback data and updates itself to improve its accuracy. The updated emotion information is used for the next analysis.

[0356] The above is the specific processing flow of the program for this system.

[0357] (Application example 2)

[0358] 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."

[0359] Conventional menu suggestion systems only considered the user's family structure, physical condition, weather, and recent meal content, which meant they were unable to make suggestions that reflected the user's emotions and mood.In addition, there was a lack of data to provide the optimal menu based on the user's physical condition and weather on that day, making it difficult to further improve user satisfaction.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model and an emotion engine to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, cooking time, and emotions in response to a user request; means for transmitting the generated menu to the user's terminal and displaying it; means for inputting user satisfaction and feedback regarding the menu created by the user into the terminal and transmitting it to the server; and means for storing and analyzing the feedback and updating the generative AI model. This enables more personalized menu suggestions to be made in response to the user's emotions and daily changes.

[0361] A "user terminal" is an electronic device through which a user inputs information and receives suggestions.

[0362] "Family composition" is information about family members entered by the user, including the ages and relationships of each member.

[0363] "Physical condition" is information about the health status of the user and family members.

[0364] "Climate" is information about environmental conditions such as the weather and temperature of the day.

[0365] "Most recent meal details" is information about meals recently consumed by the user.

[0366] "Emotion" is information about the current mood or emotional state of the user or family members.

[0367] A "server" is a computer system that receives, stores, and analyzes data from users.

[0368] A "generative AI model" is an artificial intelligence system that analyzes user input data and generates optimal menus.

[0369] An "emotion engine" is a system for analyzing a user's emotional information.

[0370] "Analysis" is the process of processing user-entered data and extracting meaningful information.

[0371] "Preferences" is information about foods and cooking methods preferred by the user and family members.

[0372] "Disliked ingredients" is information about foods that the user or family members want to avoid.

[0373] "Menu suggestion" refers to presenting optimal meal plans based on user input data.

[0374] "Feedback" is information about the user's satisfaction with the proposed menu and areas for improvement.

[0375] "Storage" refers to recording data in a database within a server.

[0376] "Learning" is the process by which the generative AI model recognizes the user's preferences and dislikes and reflects them in future suggestions.

[0377] "Update" refers to improving generative AI models and emotion engines based on feedback.

[0378] The present invention is a system that suggests optimal menus based on information entered by a user using a terminal, such as family composition, physical condition, weather, recent meal contents, and emotions. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[0379] Obtaining user input information

[0380] First, the user uses a device to input information about their family, their physical condition, the weather, what they ate most recently, and their emotions. For example, they might input "father, mother, five-year-old child, one-year-old child" as their family composition, "mother has a bit of a cold" as their physical condition, "rainy and cold" as their weather, "curry rice last night" as their most recent meal, and "tired" as their emotion. This information is typically input through a smartphone application.

[0381] The server receives and stores the data

[0382] The data sent by the device is received and stored by the server. The emotion engine analyzes the user's emotional information based on this data and sends it to the server. The server stores this data in a database.

[0383] Data analysis of AI models and emotion engines

[0384] The data stored on the server is analyzed by a generative AI model. The data is preprocessed and converted into a format that is easy to analyze. The emotional information generated by the emotion engine is also analyzed, and the model learns the user's preferences and dislikes of ingredients. For example, the model can understand that a child dislikes green peppers, a mother likes cheese, and the user is tired and wants a meal that is easy to prepare.

[0385] Generate menu suggestions

[0386] When a user requests "Today's Menu Suggestion" through the app, the server receives the request. The generative AI model generates the optimal menu by taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it suggests "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[0387] Presenting the proposal

[0388] The generated menu is sent to the user's device, which displays it to the user. The user can then review the suggested menu within the app and order food delivery.

[0389] Gathering feedback

[0390] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. This feedback data is sent to the server and stored in a database.

[0391] Analyzing feedback and updating the model

[0392] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[0393] Specific examples

[0394] For example, when suggesting "easy and nutritious recipes that the whole family will enjoy" for dinner, if the mother has a cold and the children don't like vegetables, the app will suggest "chicken ginger soup" and "minced meat and vegetable salad." Instructions on how to proceed with these and how to order food delivery are also provided within the app.

[0395] Prompt Sentence Examples

[0396] For example, the following prompt sentence is input to the generative AI model:

[0397] "Family composition: Father, Mother, 5-year-old child, 1-year-old child. Mother is feeling a bit under the weather. They had curry rice last night. The user is tired, and it was rainy and cold this morning. Please suggest the best dinner menu for today, taking these factors into consideration."

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] The user uses the device to input information about their family, physical condition, weather, recent meal, and emotions. During this information collection process, the device provides an input interface for the user to input the necessary data. The input data is stored in the device's temporary memory.

[0401] Step 2:

[0402] The terminal sends the data entered by the user to the server. The terminal encodes the data into JSON format using the transmission protocol and sends it to the server using an HTTP POST request. The server receives the data using the reception protocol and stores it in the storage system.

[0403] Step 3:

[0404] The server reads the stored data for analysis. In this process, the emotion engine uses natural language processing techniques to classify the user's emotion data into specific emotion categories. The analysis results are stored in a database on the server.

[0405] Step 4:

[0406] The generative AI model learns the user's preferences and dislikes based on data stored on the server. Machine learning algorithms are used to preprocess the data, extract features, and train the model. The learning results are also stored in a database on the server.

[0407] Step 5:

[0408] When a user requests a menu suggestion, the server receives the request. The server generates a prompt that includes weather information, physical condition, recent meal content, and emotional information, and inputs it into the generative AI model. Based on the generated prompt, the AI ​​model suggests the optimal menu.

[0409] Step 6:

[0410] The server sends the generated menu to the user's device. The menu suggestions are displayed on the device, and the user can confirm the suggested menu. The user can also check the suggested menu within the application and order food delivery directly.

[0411] Step 7:

[0412] The user actually creates the suggested menu and serves it to their family. After the meal, the user enters their satisfaction with the menu and any improvements they may have made as feedback via their device. This feedback data is sent from the device to the server.

[0413] Step 8:

[0414] The server analyzes the feedback data and updates the generative AI model and emotion engine. Specifically, it adjusts the model weights based on the feedback to improve the accuracy of the next suggestion. The feedback analysis results are also stored in a database on the server.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] [Second embodiment]

[0419] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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."

[0431] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[0432] Obtaining user input information

[0433] The user uses the terminal to input information about their family, physical condition, weather, and what they ate most recently. For example, today's family is "father, mother, 5-year-old child, 1-year-old child," their physical condition is "mother has a bit of a cold," their weather is "rainy and cold," and their most recent meal is "curry rice last night."

[0434] The server receives and stores the data

[0435] The terminal transmits the input data to the server, which receives the data and stores it in a database.

[0436] AI model analyzes data

[0437] The generative AI model on the server analyzes the stored data and learns the user's preferences and dislikes of certain foods. For example, it might learn that a child dislikes green peppers and a mother likes cheese.

[0438] Generate menu suggestions

[0439] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), and other conditions. For example, it suggests "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0440] Presenting the proposal

[0441] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0442] Gathering feedback

[0443] The user creates a proposed menu and enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database. The AI ​​model on the server analyzes the stored feedback and updates the model to help with future suggestions.

[0444] This system allows users to easily decide on daily menus, reducing the burden of housework and childcare. It also supports the health of the entire family by providing nutritionally balanced meals. For families with children in particular, it suggests baby food according to the child's age, reducing the burden of childcare. This allows users to enjoy a richer diet.

[0445] The processing flow will be explained below.

[0446] Step 1:

[0447] The user starts the application using a terminal and logs in. The user enters information about the family composition, physical condition, weather, and recent meal, and then enters information about each member (e.g., father, mother, 5-year-old child, 1-year-old child) on the "Enter family composition" screen.

[0448] Step 2:

[0449] On the "Enter your physical condition and weather" screen, the user enters, for example, that "my mother is feeling a bit sick" as a physical condition and that "it's rainy and cold" as a weather condition. Also, on the "Enter your most recent meal" screen, the user enters the meal they recently had (for example, "I had curry and rice last night").

[0450] Step 3:

[0451] The terminal sends the entered data to the server, which receives the data and stores it in a database.

[0452] Step 4:

[0453] A generative AI model on the server reads the stored data and preprocesses it into a format that is easy to analyze.

[0454] Step 5:

[0455] The generative AI model learns the user's preferences and dislikes, for example, that a child dislikes green peppers and a mother likes cheese.

[0456] Step 6:

[0457] The user requests "Today's Menu Suggestion" through the app. The server receives the request and generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), and other conditions.

[0458] Step 7:

[0459] The generative AI model generates menus based on conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0460] Step 8:

[0461] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0462] Step 9:

[0463] The user actually creates the suggested menu and provides it to their family. The user then inputs feedback such as satisfaction and areas for improvement into the device.

[0464] Step 10:

[0465] The terminal sends feedback from the user to the server, which receives the data and stores it in a database.

[0466] Step 11:

[0467] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion.

[0468] In this way, the system provides optimal menus based on the information entered by the user, taking into account the weather, physical condition, and past dietary habits, and improves the accuracy of its suggestions through feedback.

[0469] Example 1

[0470] 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."

[0471] There is a need to reduce the time and effort required to plan daily menus and provide appropriate meals that suit the physical condition and preferences of family members. However, with busy lives and child-rearing responsibilities, it is difficult to plan balanced meals, and inappropriate meals can disrupt nutritional balance. In addition, providing meals appropriate to the age of infants and toddlers is particularly important, but achieving this requires specialized knowledge.

[0472] 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.

[0473] In this invention, the server includes a means for a user to input information about members, their health status, weather information, and recent meal contents using a mobile device; a means for the server to receive and store the data transmitted from the mobile device; and a means for the generative AI model to analyze the stored data and learn the user's preferences and food dislikes. This allows users to easily decide daily menus and efficiently provide nutritionally balanced meals for the entire family. Furthermore, the generative AI model takes into account ingredients and cooking methods appropriate for the age of the family when proposing meals for infants, thereby reducing the burden on families raising children.

[0474] A "mobile terminal" is an electronic device that allows a user to input information about family composition, physical condition, weather information, and recent meal details, and includes devices such as smartphones and tablets.

[0475] "Member information" refers to data such as each family member's age, gender, food preferences, and disliked foods.

[0476] "Health status" refers to each family member's current physical condition, medical history, allergy information, etc.

[0477] "Weather information" is data relating to the weather conditions in the area where the user currently resides, including temperature, humidity, rainfall, and the like.

[0478] "Recent meal contents" refers to cooking records and meal menu data created by the user in the past.

[0479] A "server" is a computer system that receives, stores, and processes data sent by users.

[0480] A "database" is a system that systematically manages data such as member information, health status, weather information, and recent meal contents stored on a server.

[0481] "Generative AI model" refers to artificial intelligence technology that analyzes stored data and generates appropriate menus that are presented through a user interface.

[0482] "Analysis" refers to the process by which a generative AI model processes input data, finds patterns and trends, and learns from them.

[0483] "Preferences" refers to data about each family member's favorite ingredients and cooking methods.

[0484] "Difficult ingredients" refers to ingredients that each member of the family dislikes, is allergic to, or would like to avoid.

[0485] A "menu" refers to the combination of dishes suggested by the generative AI model for the user to serve as their meal of the day.

[0486] "Satisfaction level" refers to the evaluation after the user actually creates the suggested menu.

[0487] "Opinions" refers to feedback such as improvements or requests that users have regarding the proposed menu.

[0488] "Machine learning algorithms" refer to the mathematical methods and models that generative AI models use to analyze data and learn patterns.

[0489] "Nutritional balance" refers to a combination of meals that are carefully designed to ensure the appropriate intake of various nutrients, with the family's health in mind.

[0490] "Infant meal suggestions" refers to meal suggestions that take into consideration appropriate ingredients and cooking methods according to the infant's age.

[0491] MODE FOR CARRYING OUT THE INVENTION

[0492] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[0493] System configuration

[0494] User terminal

[0495] The user terminal provides an interface for users to input information about members, their health status, weather information, and recent meal details. Specific examples include mobile devices such as smartphones and tablets. These devices allow users to input data through dedicated applications.

[0496] server

[0497] The server is a computer system that receives and stores data sent from user devices. The server uses a database to systematically store and manage the received data. Furthermore, it uses a generative AI model running on the server to analyze the data and generate menus.

[0498] Generative AI Models

[0499] The generative AI model analyzes the received and stored data and learns the user's preferences and dislikes. This generative AI model is implemented using machine learning algorithms (e.g., GPT-4). Based on the stored data, it creates an appropriate menu according to the user's request.

[0500] Process Overview

[0501] 1. Obtaining user input information: The user opens the app on their mobile device and enters information about their family members, their health condition, weather information, and what they recently ate. For example, they enter "father, mother, 5-year-old child, 1-year-old child" as the family composition, "mother has a bit of a cold" as the health condition, "rainy and cold" as the weather, and "curry rice last night" as the most recent meal.

[0502] 2. The server receives and saves the data: The device sends the entered data to the server, which receives it and saves it in a database.

[0503] 3. The AI ​​model analyzes the data: The generative AI model on the server analyzes the data stored in the database and learns the user's preferences and dislikes. For example, it learns that a child dislikes green peppers and a mother likes cheese.

[0504] 4. Menu suggestion generation: When a user requests "Today's menu suggestion" in the app, the server receives the request, and the AI ​​model generates the optimal menu based on the weather, health condition, recent meals, etc. For example, "digestible chicken ginger soup" and "minced meat and vegetable salad" are suggested.

[0505] 5. Proposal presentation: The server sends the generated menu to the user terminal, which displays it to the user. The user can then create a proposed menu.

[0506] 6. Feedback collection: After the user creates the proposed menu, they input their satisfaction and suggestions for improvement into their mobile device. The device sends this to the server, which stores it in a database. The generative AI model analyzes the feedback and updates the model to help with future suggestions.

[0507] Specific examples

[0508] For example, if the family structure (father, mother, 5-year-old child, 1-year-old child), health condition (mother is feeling a bit under the weather) and weather information (rainy and cold) are entered, along with information such as (curry rice last night), the system will suggest (easy-to-digest) chicken ginger soup and (minced meat and vegetable salad).

[0509] Prompt Sentence Examples

[0510] "Today's family consists of a father, a mother, a five-year-old child, and a one-year-old child, and the mother is feeling a bit under the weather. It's rainy and cold today. Last night, they had curry rice. Based on these conditions, please suggest the best menu for them."

[0511] The system allows users to easily plan their daily meals and provide nutritionally balanced meals for the whole family.The generative AI model also takes age-appropriate ingredients and cooking methods into account when suggesting meals for infants, reducing the burden on families with children.

[0512] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0513] Step 1:

[0514] The user opens the app on their device and enters their family composition, physical condition, weather, and recent meal details. For example, the input form includes the family composition of "father, mother, 5-year-old child, 1-year-old child," the physical condition of "mother is feeling a bit sick," the weather of "rainy and cold," and "I had curry rice last night."

[0515] Input data: Family composition, physical condition, weather, recent meal contents

[0516] Output data: User input data ready to send

[0517] Step 2:

[0518] The terminal sends the entered data to the server, which receives it as an HTTP request.

[0519] Input data: User-entered data

[0520] Data processing: Convert input data into HTTP requests

[0521] Output data: HTTP request sent

[0522] Step 3:

[0523] The server stores the received data in a database, for example by inserting data into the database using an SQL query.

[0524] Input data: Received data from the HTTP request

[0525] Data manipulation: Inserting data using SQL queries

[0526] Output data: Saved to database

[0527] Step 4:

[0528] The generative AI model on the server analyzes the data stored in the database. It then runs machine learning algorithms to learn the user's preferences and dislikes. For example, it analyzes the data and extracts the user's preference patterns.

[0529] Input data: User-entered data stored in a database

[0530] Data processing: Data analysis using machine learning algorithms

[0531] Output data: Generation of user preference data

[0532] Step 5:

[0533] The user requests "Today's menu suggestions" through the app. The device sends this request to the server.

[0534] Input data: User's menu suggestion request

[0535] Data processing: Generating request data

[0536] Output data: Request sent to server

[0537] Step 6:

[0538] The server receives the request and inputs the prompt into the generative AI model, which generates the optimal menu taking into account the weather, physical condition, and recent meal content of the day.

[0539] Input data: user requests, stored user data

[0540] Data processing: Prompt generation and input to the AI ​​model

[0541] Output data: Generation of optimal menu

[0542] Step 7:

[0543] The server sends the generated menu to the user's device, which receives it and displays the menu on the app screen.

[0544] Input data: Generated menu data

[0545] Data processing: data format conversion and transmission

[0546] Output data: Menu displayed on terminal

[0547] Step 8:

[0548] After the user creates the proposed menu, they input their feedback, such as their level of satisfaction and areas for improvement, into the terminal. The user's evaluation and opinions are entered into an input form.

[0549] Input data: User feedback data

[0550] Output data: Feedback data ready to send

[0551] Step 9:

[0552] The terminal transmits feedback data to the server, and the server stores the received feedback in a database.

[0553] Input data: User feedback data

[0554] Data processing: Sending via HTTP request, inserting data via SQL query

[0555] Output data: Feedback data saved in database

[0556] Step 10:

[0557] The server's generative AI model analyzes the stored feedback data and updates the model, which then reflects the feedback in the next menu suggestion.

[0558] Input data: Saved feedback data

[0559] Data processing: Data analysis and model updating using machine learning algorithms

[0560] Output data: Updated generative AI model

[0561] Through the above processing steps, the user can easily decide on daily menus and provide appropriate, nutritionally balanced meals for the whole family.

[0562] (Application example 1)

[0563] 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."

[0564] In today's busy households, planning a daily menu is a time-consuming and labor-intensive task. In particular, families with children need to provide meals that are suitable for the entire family while taking nutritional balance into consideration. Furthermore, as the use of food delivery services increases, there is a demand for customized meals that address individual health conditions and preferences. However, current services are insufficient in adapting to individual health conditions and preferences, making it difficult to propose an optimal menu for the user and order meals based on that menu. The purpose of this invention is to solve these problems and provide a system that proposes an optimal menu for the user and allows the user to smoothly order food delivery.

[0565] 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.

[0566] In this invention, the server includes: means for a user to input information about family composition, physical condition, weather, and recent meal content using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the menu created by the user into the terminal and transmit it to the server; means for storing and analyzing the feedback and updating the generative AI model; and means for ordering meals from external restaurants based on the generated menu. This allows users to easily determine an optimal menu that corresponds to their individual health condition and preferences, and further enables them to smoothly order meals based on the proposed menu.

[0567] "A means for users to input information about their family composition, physical condition, weather, and recent meal details using a device" refers to an interface that allows users to input information about their own and their family's health status, weather conditions, and recent meal details using electronic devices such as smartphones and tablets.

[0568] "Means for the server to receive and store data sent from the terminal" refers to a system configuration in which information sent from a user terminal is received via a network and the data is stored in a storage device such as a database.

[0569] "Means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients" refers to the process of using a machine learning algorithm based on the stored data to identify the user's preferences and ingredients they want to avoid, learning from them and applying them to future recipes.

[0570] "A means of generating optimal menus based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services" refers to an algorithm that enables AI to design the best menu in response to a user's request, taking into account the weather and physical condition of the day, the specified cooking time, and the menus offered by external services.

[0571] "Means for sending and displaying the generated menu to the user's device" refers to the technology for sending the menu information generated by AI to the user's electronic device and displaying that information on the screen.

[0572] "Means for users to input their satisfaction and feedback regarding the menu they have created into a terminal and send it to a server" refers to a system that allows users to input their thoughts and suggestions about the completed dish and send that information to a server via a network.

[0573] "Means for storing and analyzing said feedback and updating the generative AI model" refers to a series of processes for storing feedback data from users in a storage device and analyzing that data to improve the AI ​​model.

[0574] "Means for ordering meals from external restaurants based on the generated menu" refers to the interface and process for ordering meals from affiliated restaurants and delivery services based on the menu suggested by AI.

[0575] This invention provides a system that generates an optimal menu based on various information such as the user's family composition, physical condition, weather, and recent meal content, and then orders meals from external restaurants based on the menu. Specific embodiments are described below.

[0576] System Configuration

[0577] User terminal

[0578] The user terminal is an electronic device such as a smartphone or tablet, and the user uses this terminal to input information such as their own and their family's health status, weather conditions, and recent meal information.

[0579] server

[0580] The server receives and stores data sent from the user's device. The generative AI model then analyzes the stored data and learns the user's preferences and dislikes. In response to the user's request, the server generates an optimal menu based on the day's weather, physical condition, cooking time, and options from external meal delivery services.

[0581] Generative AI Models

[0582] The generative AI model analyzes the stored data, identifies the user's preferences and ingredients to avoid, and learns from them, which is then reflected in future menu generation.

[0583] System Features

[0584] Entering user information

[0585] The user can enter the following information via the terminal:

[0586] Family composition (e.g., father, mother, 5-year-old child, 1-year-old child)

[0587] Physical condition (e.g., mother has a cold)

[0588] Climate (e.g. rainy and cold)

[0589] What you ate most recently (e.g. curry rice last night)

[0590] Receiving and storing data

[0591] The server receives the information sent by the user from the device and stores it in a database, which includes information such as family composition, physical condition, weather, and recent meal contents.

[0592] Data analysis and menu suggestions

[0593] The generative AI model analyzes the received data and learns the user's preferences and dislikes. For example, it may learn that a child dislikes green peppers and a mother likes cheese. Then, when a user makes a request, the server generates the optimal menu based on the day's conditions.

[0594] Menu display and ordering function

[0595] The generated menu is sent to the user's device and displayed there. The user can then review the proposed menu and order meals from affiliated external restaurants if necessary.

[0596] Gathering feedback and updating the model

[0597] Users can input their feedback on the proposed menu, such as their level of satisfaction and areas for improvement, into their device and send it to the server. The server then stores this feedback and updates the generative AI model, making future menu suggestions more accurate.

[0598] For example:

[0599] "The family consists of a father, a mother, a 5-year-old child, and a 1-year-old child. The mother is feeling a bit under the weather, and it's cold and rainy today. Last night we had curry rice. Could you suggest a menu for today?"

[0600] "Yesterday's soup was a little salty. Mom's cold is a little better. What would be best today?"

[0601] By providing the AI ​​model with the above prompts, the model can generate a menu that specifically corresponds to the user's situation, allowing the user to easily determine the optimal menu that corresponds to their individual health condition and preferences, and then smoothly order meals based on the suggested menu.

[0602] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0603] Step 1: Enter your user information

[0604] The user uses the device to input information about their family, physical condition, weather, and recent meals. The input information specifically includes the following items:

[0605] Family composition (e.g., "Father, mother, 5-year-old child, 1-year-old child")

[0606] Physical condition (e.g., "My mother has a slight cold")

[0607] Climate (e.g., "rainy and cold")

[0608] What you ate most recently (e.g., "I had curry rice last night")

[0609] Input data is collected at the terminal and sent to the server.

[0610] Step 2: Receiving and storing data

[0611] The server receives the data sent from the user terminal. The above information is sent as input, and the server stores it in a database. Specifically,

[0612] Input: Family composition, physical condition, weather, and recent meal details

[0613] Output: Saved database entries

[0614] The data is organized by category and stored for future retrieval and analysis.

[0615] Step 3: Data analysis and user learning

[0616] The generative AI model analyzes the stored data. In this step, data processing and calculations are performed to identify the user's preferences and dislikes.

[0617] Input: Saved database information

[0618] Output: A list of the user's preferences and ingredients to avoid

[0619] Through analysis, the AI ​​model learns user preferences (e.g., "children don't like green peppers" or "mothers like cheese").

[0620] Step 4: Create a menu

[0621] When a user requests "Today's Menu Suggestion," the server receives the request, and the generative AI model generates the optimal menu by taking into account the day's weather, physical condition, cooking time, and options from external services.

[0622] Input: Weather, physical condition, cooking time, menu of external service

[0623] Output: Optimal menu

[0624] During this process, a wide range of data, including weather and physical condition, is analyzed again to determine the most appropriate menu.

[0625] Step 5: View Proposals and Order Function

[0626] The generated menu is sent from the server to the user's terminal and displayed on the terminal. The user can then order meals from external restaurants based on the proposed menu.

[0627] Input: Generated menu data

[0628] Output: Menu displayed on screen, and order confirmation screen

[0629] Specifically, users can check the menu and easily place their order within the app.

[0630] Step 6: Gather feedback

[0631] The user inputs their satisfaction with the meal provided and any areas for improvement into the terminal and sends the input to the server.

[0632] Input: Satisfaction and Feedback

[0633] Output: Saved feedback data

[0634] The user's input is again saved in the database.

[0635] Step 7: Analyze feedback and update the model

[0636] The server analyzes the stored feedback data and updates the generative AI model, a step that involves training to incorporate new insights into the model.

[0637] Input: Feedback data

[0638] Output: Updated generative AI model

[0639] Based on the feedback, the model retrains to make its next suggestions even more accurate.

[0640] 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.

[0641] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[0642] Obtaining user input information

[0643] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[0644] The server receives and stores the data

[0645] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[0646] AI model analyzes data

[0647] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[0648] Generate menu suggestions

[0649] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., tiredness), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[0650] Presenting the proposal

[0651] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0652] Gathering feedback

[0653] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[0654] Analyzing feedback and updating the model

[0655] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[0656] In this way, the system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary habits, and improves the accuracy of suggestions through feedback. By incorporating emotional factors in particular, the system can suggest menus that suit the user's mood that day, achieving more personalized menu decisions.

[0657] The processing flow will be explained below.

[0658] Step 1:

[0659] The user starts the application using a terminal and logs in. The user inputs family composition, physical condition, weather, most recent meal, and emotions. For example, the user inputs "father, mother, 5-year-old child, 1-year-old child" as family composition, "mother has a bit of a cold" as physical condition, "rainy and cold" as weather, "curry rice last night" as most recent meal, and "tired" as emotion.

[0660] Step 2:

[0661] The device sends the input data to the server, which receives the data and stores it in a database. At the same time, the emotion engine analyzes the emotion information from the user's input data and sends the analysis results to the server.

[0662] Step 3:

[0663] The generative AI model on the server reads the stored data and preprocesses it to make it easier to analyze, including filling in missing values ​​and normalizing the data.

[0664] Step 4:

[0665] The generative AI model learns from the user's family structure, physical condition, weather, recent meal content, emotional information, etc. to understand the user's preferences and dislikes of ingredients. For example, it can understand that a child dislikes green peppers and a mother likes cheese, or that the user is tired and wants a meal that is easy to prepare.

[0666] Step 5:

[0667] The user requests "Today's menu suggestion" in the application. The server receives the request and generates the optimal menu taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), emotions (tired), and other conditions.

[0668] Step 6:

[0669] The generative AI model generates optimal menus based on the conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0670] Step 7:

[0671] The server sends the generated menu information to the user terminal, which displays the menu to the user.

[0672] Step 8:

[0673] The user actually creates the suggested menu and provides it to their family. After completing the menu, the user enters feedback such as satisfaction and areas for improvement into the device.

[0674] Step 9:

[0675] The terminal transmits feedback data from the user to the server, which receives the data and stores it in a database.

[0676] Step 10:

[0677] The generative AI model on the server analyzes the stored feedback data and updates the model to help with the next menu suggestion. At the same time, the emotion engine also learns the emotional information obtained from the feedback and reflects it in the next emotion analysis.

[0678] This system can provide optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood on that day, achieving more personalized menu decisions.

[0679] Example 2

[0680] 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."

[0681] In today's busy lifestyles, planning a daily menu can be a burden for many people. Furthermore, determining the optimal menu based on the family's physical condition, preferences, and even their emotions on that day is a difficult task. Adjusting the menu is particularly complicated when family members have diverse preferences and physical conditions. Therefore, there is a strong demand for a system that allows users to easily determine the optimal menu. Furthermore, a mechanism is needed that uses feedback to improve the accuracy of suggestions.

[0682] 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.

[0683] In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for an emotion engine to analyze emotional information from the input data and transmit it to the server; means for a generative AI model to analyze the stored data and emotional information and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, emotions, cooking time, etc. in response to a user's request; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the provided menu into the terminal and transmit it to the server; and means for storing and analyzing the feedback and updating the generative AI model and the emotion engine. This not only allows the user to easily receive optimal menu suggestions based on the physical condition, preferences, and emotions of their family members, but also enables the system to continuously improve its accuracy based on the provided feedback.

[0684] A "user terminal" is an electronic device used by a user to input information.

[0685] A "server" is a computer system that receives and stores data sent from user devices and also runs the generative AI model and emotion engine.

[0686] A "generative AI model" is an artificial intelligence model that analyzes stored data and emotional information, learns the user's preferences and disliked ingredients, and generates optimal menus.

[0687] The "emotion engine" is a software component that analyzes emotional information from user input data and sends the results to the server.

[0688] "Family composition" is information indicating the members of the user's family and their relationships.

[0689] "Physical condition" is information indicating the health condition of the user and their family members.

[0690] "Climate" is information indicating the weather and temperature of the day.

[0691] "Details of most recent meal" is information indicating the details of meals recently eaten by the user and their family.

[0692] "Emotions" is information that indicates the current feelings and moods of the user and their family members.

[0693] "Feedback" is information that indicates the user's opinions and evaluations, such as their satisfaction with the menu provided and areas for improvement.

[0694] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[0695] Obtaining user input information

[0696] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[0697] The server receives and stores the data

[0698] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[0699] AI model analyzes data

[0700] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[0701] Generate menu suggestions

[0702] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[0703] Presenting the proposal

[0704] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0705] Gathering feedback

[0706] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[0707] Analyzing feedback and updating the model

[0708] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[0709] Examples of concrete examples and prompts

[0710] As a specific example, consider the case of suggesting easy-to-make meals for a day when the user is tired.

[0711] Specific examples

[0712] User input: Family composition: "Father, mother, 5-year-old child, 1-year-old child", health condition: "Mother is feeling a bit under the weather", weather: "Rainy and cold", most recent meal: "Curry rice last night", emotion: "Tired".

[0713] Server's suggested menu: Chicken ginger soup, minced meat and vegetable salad.

[0714] Prompt Sentence Examples

[0715] Please suggest the best menu for a family consisting of a father, mother, a 5-year-old child, and a 1-year-old child, where the mother is feeling a bit under the weather, it's rainy and cold, they had curry rice last night, and they are emotionally exhausted.

[0716] This system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood that day, achieving more personalized menu decisions.

[0717] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0718] Step 1: User enters information from device

[0719] The user starts the terminal application and inputs information about the family (e.g., "father, mother, five-year-old child, one-year-old child"), physical condition (e.g., "mother has a slight cold"), weather (e.g., "rainy and cold"), what they had most recently eaten (e.g., "I had curry rice last night"), and emotions (e.g., "I'm tired"). This information is saved as input data on the terminal.

[0720] Step 2: Send data from the device to the server

[0721] The device transmits the input data to the server in real time. The transmitted data includes family composition, physical condition, weather, recent meal contents, and emotions. The server receives the transmitted data.

[0722] Step 3: The server receives and stores the data

[0723] The server stores the received data in a database, which ensures that all user input is stored permanently.

[0724] Step 4: Emotion analysis using the emotion engine

[0725] The emotion engine analyzes emotional information from the user's input data stored on the server. For example, if the user inputs "I'm tired," it analyzes negative emotions. The results of this analysis are also stored in the database.

[0726] Step 5: Data preprocessing for generative AI models

[0727] The generative AI model on the server reads the user's saved data and emotional information, and performs preprocessing such as handling missing values ​​and normalizing the data, thereby preparing the data in a format that is easy to analyze.

[0728] Step 6: The generative AI model analyzes and learns from the data

[0729] Based on the preprocessed data, the generative AI model learns the user's preferences and dislikes. For example, it understands that a child dislikes green peppers and a mother likes cheese, and that a meal plan that is easy to prepare is desired. This learning result is stored in the model.

[0730] Step 7: User submits request

[0731] The user requests "Today's menu suggestions" from the terminal. This request is sent to the server.

[0732] Step 8: The server receives the request

[0733] The server receives the user's request and retrieves the data stored for that day. The input data includes weather (e.g., "It's cold"), physical condition (e.g., "My mother has a slight cold"), recent meal (e.g., "Curry and rice"), and emotion (e.g., "I'm tired").

[0734] Step 9: Menu generation using generative AI models

[0735] The generative AI model generates optimal menus based on the stored data and analysis results. For example, it selects "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy to make and suitable for children. The generated menu information is output.

[0736] Step 10: Server Sends Proposal

[0737] The server sends the generated menu information to the user terminal. The output menu information arrives at the user terminal.

[0738] Step 11: Your device will display suggestions

[0739] The user device displays the menu information sent from the server, and the user can view the suggested menu on the app screen.

[0740] Step 12: User provides feedback

[0741] The user creates a suggested menu and provides it to their family. After that, they input their feedback, such as their actual satisfaction level and areas for improvement, into the device. The input feedback data is saved on the device.

[0742] Step 13: Device sends feedback

[0743] The device sends the saved feedback data to the server, which then receives information about the user's satisfaction and areas for improvement.

[0744] Step 14: Server saves feedback

[0745] The server stores the received feedback data in a database. All feedback information is stored permanently.

[0746] Step 15: Generative AI model analyzes feedback

[0747] The generative AI model analyzes the saved feedback data. Specifically, it extracts user satisfaction and areas for improvement, and analyzes them to help with the next menu proposal. The analysis results are reflected within the model.

[0748] Step 16: The emotion engine updates its learning

[0749] The emotion engine also learns from the feedback data and updates itself to improve its accuracy. The updated emotion information is used for the next analysis.

[0750] The above is the specific processing flow of the program for this system.

[0751] (Application example 2)

[0752] 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."

[0753] Conventional menu suggestion systems only considered the user's family structure, physical condition, weather, and recent meal content, which meant they were unable to make suggestions that reflected the user's emotions and mood.In addition, there was a lack of data to provide the optimal menu based on the user's physical condition and weather on that day, making it difficult to further improve user satisfaction.

[0754] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model and an emotion engine to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, cooking time, and emotions in response to a user request; means for transmitting the generated menu to the user's terminal and displaying it; means for inputting user satisfaction and feedback regarding the menu created by the user into the terminal and transmitting it to the server; and means for storing and analyzing the feedback and updating the generative AI model. This enables more personalized menu suggestions to be made in response to the user's emotions and daily changes.

[0755] A "user terminal" is an electronic device through which a user inputs information and receives suggestions.

[0756] "Family composition" is information about family members entered by the user, including the ages and relationships of each member.

[0757] "Physical condition" is information about the health status of the user and family members.

[0758] "Climate" is information about environmental conditions such as the weather and temperature of the day.

[0759] "Most recent meal details" is information about meals recently consumed by the user.

[0760] "Emotion" is information about the current mood or emotional state of the user or family members.

[0761] A "server" is a computer system that receives, stores, and analyzes data from users.

[0762] A "generative AI model" is an artificial intelligence system that analyzes user input data and generates optimal menus.

[0763] An "emotion engine" is a system for analyzing a user's emotional information.

[0764] "Analysis" is the process of processing user-entered data and extracting meaningful information.

[0765] "Preferences" is information about foods and cooking methods preferred by the user and family members.

[0766] "Disliked ingredients" is information about foods that the user or family members want to avoid.

[0767] "Menu suggestion" refers to presenting optimal meal plans based on user input data.

[0768] "Feedback" is information about the user's satisfaction with the proposed menu and areas for improvement.

[0769] "Storage" refers to recording data in a database within a server.

[0770] "Learning" is the process by which the generative AI model recognizes the user's preferences and dislikes and reflects them in future suggestions.

[0771] "Update" refers to improving generative AI models and emotion engines based on feedback.

[0772] The present invention is a system that suggests optimal menus based on information entered by a user using a terminal, such as family composition, physical condition, weather, recent meal contents, and emotions. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[0773] Obtaining user input information

[0774] First, the user uses a device to input information about their family, their physical condition, the weather, what they ate most recently, and their emotions. For example, they might input "father, mother, five-year-old child, one-year-old child" as their family composition, "mother has a bit of a cold" as their physical condition, "rainy and cold" as their weather, "curry rice last night" as their most recent meal, and "tired" as their emotion. This information is typically input through a smartphone application.

[0775] The server receives and stores the data

[0776] The data sent by the device is received and stored by the server. The emotion engine analyzes the user's emotional information based on this data and sends it to the server. The server stores this data in a database.

[0777] Data analysis of AI models and emotion engines

[0778] The data stored on the server is analyzed by a generative AI model. The data is preprocessed and converted into a format that is easy to analyze. The emotional information generated by the emotion engine is also analyzed, and the model learns the user's preferences and dislikes of ingredients. For example, the model can understand that a child dislikes green peppers, a mother likes cheese, and the user is tired and wants a meal that is easy to prepare.

[0779] Generate menu suggestions

[0780] When a user requests "Today's Menu Suggestion" through the app, the server receives the request. The generative AI model generates the optimal menu by taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it suggests "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[0781] Presenting the proposal

[0782] The generated menu is sent to the user's device, which displays it to the user. The user can then review the suggested menu within the app and order food delivery.

[0783] Gathering feedback

[0784] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. This feedback data is sent to the server and stored in a database.

[0785] Analyzing feedback and updating the model

[0786] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[0787] Specific examples

[0788] For example, when suggesting "easy and nutritious recipes that the whole family will enjoy" for dinner, if the mother has a cold and the children don't like vegetables, the app will suggest "chicken ginger soup" and "minced meat and vegetable salad." Instructions on how to proceed with these and how to order food delivery are also provided within the app.

[0789] Prompt Sentence Examples

[0790] For example, the following prompt sentence is input to the generative AI model:

[0791] "Family composition: Father, Mother, 5-year-old child, 1-year-old child. Mother is feeling a bit under the weather. They had curry rice last night. The user is tired, and it was rainy and cold this morning. Please suggest the best dinner menu for today, taking these factors into consideration."

[0792] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0793] Step 1:

[0794] The user uses the device to input information about their family, physical condition, weather, recent meal, and emotions. During this information collection process, the device provides an input interface for the user to input the necessary data. The input data is stored in the device's temporary memory.

[0795] Step 2:

[0796] The terminal sends the data entered by the user to the server. The terminal encodes the data into JSON format using the transmission protocol and sends it to the server using an HTTP POST request. The server receives the data using the reception protocol and stores it in the storage system.

[0797] Step 3:

[0798] The server reads the stored data for analysis. In this process, the emotion engine uses natural language processing techniques to classify the user's emotion data into specific emotion categories. The analysis results are stored in a database on the server.

[0799] Step 4:

[0800] The generative AI model learns the user's preferences and dislikes based on data stored on the server. Machine learning algorithms are used to preprocess the data, extract features, and train the model. The learning results are also stored in a database on the server.

[0801] Step 5:

[0802] When a user requests a menu suggestion, the server receives the request. The server generates a prompt that includes weather information, physical condition, recent meal content, and emotional information, and inputs it into the generative AI model. Based on the generated prompt, the AI ​​model suggests the optimal menu.

[0803] Step 6:

[0804] The server sends the generated menu to the user's device. The menu suggestions are displayed on the device, and the user can confirm the suggested menu. The user can also check the suggested menu within the application and order food delivery directly.

[0805] Step 7:

[0806] The user actually creates the suggested menu and serves it to their family. After the meal, the user enters their satisfaction with the menu and any improvements they may have made as feedback via their device. This feedback data is sent from the device to the server.

[0807] Step 8:

[0808] The server analyzes the feedback data and updates the generative AI model and emotion engine. Specifically, it adjusts the model weights based on the feedback to improve the accuracy of the next suggestion. The feedback analysis results are also stored in a database on the server.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] [Third embodiment]

[0813] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0814] 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.

[0815] 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).

[0816] 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.

[0817] 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.

[0818] 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).

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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."

[0825] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[0826] Obtaining user input information

[0827] The user uses the terminal to input information about their family, physical condition, weather, and what they ate most recently. For example, today's family is "father, mother, 5-year-old child, 1-year-old child," their physical condition is "mother has a bit of a cold," their weather is "rainy and cold," and their most recent meal is "curry rice last night."

[0828] The server receives and stores the data

[0829] The terminal transmits the input data to the server, which receives the data and stores it in a database.

[0830] AI model analyzes data

[0831] The generative AI model on the server analyzes the stored data and learns the user's preferences and dislikes of certain foods. For example, it might learn that a child dislikes green peppers and a mother likes cheese.

[0832] Generate menu suggestions

[0833] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), and other conditions. For example, it suggests "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0834] Presenting the proposal

[0835] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0836] Gathering feedback

[0837] The user creates a proposed menu and enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database. The AI ​​model on the server analyzes the stored feedback and updates the model to help with future suggestions.

[0838] This system allows users to easily decide on daily menus, reducing the burden of housework and childcare. It also supports the health of the entire family by providing nutritionally balanced meals. For families with children in particular, it suggests baby food according to the child's age, reducing the burden of childcare. This allows users to enjoy a richer diet.

[0839] The processing flow will be explained below.

[0840] Step 1:

[0841] The user starts the application using a terminal and logs in. The user enters information about the family composition, physical condition, weather, and recent meal, and then enters information about each member (e.g., father, mother, 5-year-old child, 1-year-old child) on the "Enter family composition" screen.

[0842] Step 2:

[0843] On the "Enter your physical condition and weather" screen, the user enters, for example, that "my mother is feeling a bit sick" as a physical condition and that "it's rainy and cold" as a weather condition. Also, on the "Enter your most recent meal" screen, the user enters the meal they recently had (for example, "I had curry and rice last night").

[0844] Step 3:

[0845] The terminal sends the entered data to the server, which receives the data and stores it in a database.

[0846] Step 4:

[0847] A generative AI model on the server reads the stored data and preprocesses it into a format that is easy to analyze.

[0848] Step 5:

[0849] The generative AI model learns the user's preferences and dislikes, for example, that a child dislikes green peppers and a mother likes cheese.

[0850] Step 6:

[0851] The user requests "Today's Menu Suggestion" through the app. The server receives the request and generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), and other conditions.

[0852] Step 7:

[0853] The generative AI model generates menus based on conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[0854] Step 8:

[0855] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[0856] Step 9:

[0857] The user actually creates the suggested menu and provides it to their family. The user then inputs feedback such as satisfaction and areas for improvement into the device.

[0858] Step 10:

[0859] The terminal sends feedback from the user to the server, which receives the data and stores it in a database.

[0860] Step 11:

[0861] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion.

[0862] In this way, the system provides optimal menus based on the information entered by the user, taking into account the weather, physical condition, and past dietary habits, and improves the accuracy of its suggestions through feedback.

[0863] Example 1

[0864] 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."

[0865] There is a need to reduce the time and effort required to plan daily menus and provide appropriate meals that suit the physical condition and preferences of family members. However, with busy lives and child-rearing responsibilities, it is difficult to plan balanced meals, and inappropriate meals can disrupt nutritional balance. In addition, providing meals appropriate to the age of infants and toddlers is particularly important, but achieving this requires specialized knowledge.

[0866] 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.

[0867] In this invention, the server includes a means for a user to input information about members, their health status, weather information, and recent meal contents using a mobile device; a means for the server to receive and store the data transmitted from the mobile device; and a means for the generative AI model to analyze the stored data and learn the user's preferences and food dislikes. This allows users to easily decide daily menus and efficiently provide nutritionally balanced meals for the entire family. Furthermore, the generative AI model takes into account ingredients and cooking methods appropriate for the age of the family when proposing meals for infants, thereby reducing the burden on families raising children.

[0868] A "mobile terminal" is an electronic device that allows a user to input information about family composition, physical condition, weather information, and recent meal details, and includes devices such as smartphones and tablets.

[0869] "Member information" refers to data such as each family member's age, gender, food preferences, and disliked foods.

[0870] "Health status" refers to each family member's current physical condition, medical history, allergy information, etc.

[0871] "Weather information" is data relating to the weather conditions in the area where the user currently resides, including temperature, humidity, rainfall, and the like.

[0872] "Recent meal contents" refers to cooking records and meal menu data created by the user in the past.

[0873] A "server" is a computer system that receives, stores, and processes data sent by users.

[0874] A "database" is a system that systematically manages data such as member information, health status, weather information, and recent meal contents stored on a server.

[0875] "Generative AI model" refers to artificial intelligence technology that analyzes stored data and generates appropriate menus that are presented through a user interface.

[0876] "Analysis" refers to the process by which a generative AI model processes input data, finds patterns and trends, and learns from them.

[0877] "Preferences" refers to data about each family member's favorite ingredients and cooking methods.

[0878] "Difficult ingredients" refers to ingredients that each member of the family dislikes, is allergic to, or would like to avoid.

[0879] A "menu" refers to the combination of dishes suggested by the generative AI model for the user to serve as their meal of the day.

[0880] "Satisfaction level" refers to the evaluation after the user actually creates the suggested menu.

[0881] "Opinions" refers to feedback such as improvements or requests that users have regarding the proposed menu.

[0882] "Machine learning algorithms" refer to the mathematical methods and models that generative AI models use to analyze data and learn patterns.

[0883] "Nutritional balance" refers to a combination of meals that are carefully designed to ensure the appropriate intake of various nutrients, with the family's health in mind.

[0884] "Infant meal suggestions" refers to meal suggestions that take into consideration appropriate ingredients and cooking methods according to the infant's age.

[0885] MODE FOR CARRYING OUT THE INVENTION

[0886] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[0887] System configuration

[0888] User terminal

[0889] The user terminal provides an interface for users to input information about members, their health status, weather information, and recent meal details. Specific examples include mobile devices such as smartphones and tablets. These devices allow users to input data through dedicated applications.

[0890] server

[0891] The server is a computer system that receives and stores data sent from user devices. The server uses a database to systematically store and manage the received data. Furthermore, it uses a generative AI model running on the server to analyze the data and generate menus.

[0892] Generative AI Models

[0893] The generative AI model analyzes the received and stored data and learns the user's preferences and dislikes. This generative AI model is implemented using machine learning algorithms (e.g., GPT-4). Based on the stored data, it creates an appropriate menu according to the user's request.

[0894] Process Overview

[0895] 1. Obtaining user input information: The user opens the app on their mobile device and enters information about their family members, their health condition, weather information, and what they recently ate. For example, they enter "father, mother, 5-year-old child, 1-year-old child" as the family composition, "mother has a bit of a cold" as the health condition, "rainy and cold" as the weather, and "curry rice last night" as the most recent meal.

[0896] 2. The server receives and saves the data: The device sends the entered data to the server, which receives it and saves it in a database.

[0897] 3. The AI ​​model analyzes the data: The generative AI model on the server analyzes the data stored in the database and learns the user's preferences and dislikes. For example, it learns that a child dislikes green peppers and a mother likes cheese.

[0898] 4. Menu suggestion generation: When a user requests "Today's menu suggestion" in the app, the server receives the request, and the AI ​​model generates the optimal menu based on the weather, health condition, recent meals, etc. For example, "digestible chicken ginger soup" and "minced meat and vegetable salad" are suggested.

[0899] 5. Proposal presentation: The server sends the generated menu to the user terminal, which displays it to the user. The user can then create a proposed menu.

[0900] 6. Feedback collection: After the user creates the proposed menu, they input their satisfaction and suggestions for improvement into their mobile device. The device sends this to the server, which stores it in a database. The generative AI model analyzes the feedback and updates the model to help with future suggestions.

[0901] Specific examples

[0902] For example, if the family structure (father, mother, 5-year-old child, 1-year-old child), health condition (mother is feeling a bit under the weather) and weather information (rainy and cold) are entered, along with information such as (curry rice last night), the system will suggest (easy-to-digest) chicken ginger soup and (minced meat and vegetable salad).

[0903] Prompt Sentence Examples

[0904] "Today's family consists of a father, a mother, a five-year-old child, and a one-year-old child, and the mother is feeling a bit under the weather. It's rainy and cold today. Last night, they had curry rice. Based on these conditions, please suggest the best menu for them."

[0905] The system allows users to easily plan their daily meals and provide nutritionally balanced meals for the whole family.The generative AI model also takes age-appropriate ingredients and cooking methods into account when suggesting meals for infants, reducing the burden on families with children.

[0906] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0907] Step 1:

[0908] The user opens the app on their device and enters their family composition, physical condition, weather, and recent meal details. For example, the input form includes the family composition of "father, mother, 5-year-old child, 1-year-old child," the physical condition of "mother is feeling a bit sick," the weather of "rainy and cold," and "I had curry rice last night."

[0909] Input data: Family composition, physical condition, weather, recent meal contents

[0910] Output data: User input data ready to send

[0911] Step 2:

[0912] The terminal sends the entered data to the server, which receives it as an HTTP request.

[0913] Input data: User-entered data

[0914] Data processing: Convert input data into HTTP requests

[0915] Output data: HTTP request sent

[0916] Step 3:

[0917] The server stores the received data in a database, for example by inserting data into the database using an SQL query.

[0918] Input data: Received data from the HTTP request

[0919] Data manipulation: Inserting data using SQL queries

[0920] Output data: Saved to database

[0921] Step 4:

[0922] The generative AI model on the server analyzes the data stored in the database. It then runs machine learning algorithms to learn the user's preferences and dislikes. For example, it analyzes the data and extracts the user's preference patterns.

[0923] Input data: User-entered data stored in a database

[0924] Data processing: Data analysis using machine learning algorithms

[0925] Output data: Generation of user preference data

[0926] Step 5:

[0927] The user requests "Today's menu suggestions" through the app. The device sends this request to the server.

[0928] Input data: User's menu suggestion request

[0929] Data processing: Generating request data

[0930] Output data: Request sent to server

[0931] Step 6:

[0932] The server receives the request and inputs the prompt into the generative AI model, which generates the optimal menu taking into account the weather, physical condition, and recent meal content of the day.

[0933] Input data: user requests, stored user data

[0934] Data processing: Prompt generation and input to the AI ​​model

[0935] Output data: Generation of optimal menu

[0936] Step 7:

[0937] The server sends the generated menu to the user's device, which receives it and displays the menu on the app screen.

[0938] Input data: Generated menu data

[0939] Data processing: data format conversion and transmission

[0940] Output data: Menu displayed on terminal

[0941] Step 8:

[0942] After the user creates the proposed menu, they input their feedback, such as their level of satisfaction and areas for improvement, into the terminal. The user's evaluation and opinions are entered into an input form.

[0943] Input data: User feedback data

[0944] Output data: Feedback data ready to send

[0945] Step 9:

[0946] The terminal transmits feedback data to the server, and the server stores the received feedback in a database.

[0947] Input data: User feedback data

[0948] Data processing: Sending via HTTP request, inserting data via SQL query

[0949] Output data: Feedback data saved in database

[0950] Step 10:

[0951] The server's generative AI model analyzes the stored feedback data and updates the model, which then reflects the feedback in the next menu suggestion.

[0952] Input data: Saved feedback data

[0953] Data processing: Data analysis and model updating using machine learning algorithms

[0954] Output data: Updated generative AI model

[0955] Through the above processing steps, the user can easily decide on daily menus and provide appropriate, nutritionally balanced meals for the whole family.

[0956] (Application example 1)

[0957] 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."

[0958] In today's busy households, planning a daily menu is a time-consuming and labor-intensive task. In particular, families with children need to provide meals that are suitable for the entire family while taking nutritional balance into consideration. Furthermore, as the use of food delivery services increases, there is a demand for customized meals that address individual health conditions and preferences. However, current services are insufficient in adapting to individual health conditions and preferences, making it difficult to propose an optimal menu for the user and order meals based on that menu. The purpose of this invention is to solve these problems and provide a system that proposes an optimal menu for the user and allows the user to smoothly order food delivery.

[0959] 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.

[0960] In this invention, the server includes: means for a user to input information about family composition, physical condition, weather, and recent meal content using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the menu created by the user into the terminal and transmit it to the server; means for storing and analyzing the feedback and updating the generative AI model; and means for ordering meals from external restaurants based on the generated menu. This allows users to easily determine an optimal menu that corresponds to their individual health condition and preferences, and further enables them to smoothly order meals based on the proposed menu.

[0961] "A means for users to input information about their family composition, physical condition, weather, and recent meal details using a device" refers to an interface that allows users to input information about their own and their family's health status, weather conditions, and recent meal details using electronic devices such as smartphones and tablets.

[0962] "Means for the server to receive and store data sent from the terminal" refers to a system configuration in which information sent from a user terminal is received via a network and the data is stored in a storage device such as a database.

[0963] "Means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients" refers to the process of using a machine learning algorithm based on the stored data to identify the user's preferences and ingredients they want to avoid, learning from them and applying them to future recipes.

[0964] "A means of generating optimal menus based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services" refers to an algorithm that enables AI to design the best menu in response to a user's request, taking into account the weather and physical condition of the day, the specified cooking time, and the menus offered by external services.

[0965] "Means for sending and displaying the generated menu to the user's device" refers to the technology for sending the menu information generated by AI to the user's electronic device and displaying that information on the screen.

[0966] "Means for users to input their satisfaction and feedback regarding the menu they have created into a terminal and send it to a server" refers to a system that allows users to input their thoughts and suggestions about the completed dish and send that information to a server via a network.

[0967] "Means for storing and analyzing said feedback and updating the generative AI model" refers to a series of processes for storing feedback data from users in a storage device and analyzing that data to improve the AI ​​model.

[0968] "Means for ordering meals from external restaurants based on the generated menu" refers to the interface and process for ordering meals from affiliated restaurants and delivery services based on the menu suggested by AI.

[0969] This invention provides a system that generates an optimal menu based on various information such as the user's family composition, physical condition, weather, and recent meal content, and then orders meals from external restaurants based on the menu. Specific embodiments are described below.

[0970] System Configuration

[0971] User terminal

[0972] The user terminal is an electronic device such as a smartphone or tablet, and the user uses this terminal to input information such as their own and their family's health status, weather conditions, and recent meal information.

[0973] server

[0974] The server receives and stores data sent from the user's device. The generative AI model then analyzes the stored data and learns the user's preferences and dislikes. In response to the user's request, the server generates an optimal menu based on the day's weather, physical condition, cooking time, and options from external meal delivery services.

[0975] Generative AI Models

[0976] The generative AI model analyzes the stored data, identifies the user's preferences and ingredients to avoid, and learns from them, which is then reflected in future menu generation.

[0977] System Features

[0978] Entering user information

[0979] The user can enter the following information via the terminal:

[0980] Family composition (e.g., father, mother, 5-year-old child, 1-year-old child)

[0981] Physical condition (e.g., mother has a cold)

[0982] Climate (e.g. rainy and cold)

[0983] What you ate most recently (e.g. curry rice last night)

[0984] Receiving and storing data

[0985] The server receives the information sent by the user from the device and stores it in a database, which includes information such as family composition, physical condition, weather, and recent meal contents.

[0986] Data analysis and menu suggestions

[0987] The generative AI model analyzes the received data and learns the user's preferences and dislikes. For example, it may learn that a child dislikes green peppers and a mother likes cheese. Then, when a user makes a request, the server generates the optimal menu based on the day's conditions.

[0988] Menu display and ordering function

[0989] The generated menu is sent to the user's device and displayed there. The user can then review the proposed menu and order meals from affiliated external restaurants if necessary.

[0990] Gathering feedback and updating the model

[0991] Users can input their feedback on the proposed menu, such as their level of satisfaction and areas for improvement, into their device and send it to the server. The server then stores this feedback and updates the generative AI model, making future menu suggestions more accurate.

[0992] For example:

[0993] "The family consists of a father, a mother, a 5-year-old child, and a 1-year-old child. The mother is feeling a bit under the weather, and it's cold and rainy today. Last night we had curry rice. Could you suggest a menu for today?"

[0994] "Yesterday's soup was a little salty. Mom's cold is a little better. What would be best today?"

[0995] By providing the AI ​​model with the above prompts, the model can generate a menu that specifically corresponds to the user's situation, allowing the user to easily determine the optimal menu that corresponds to their individual health condition and preferences, and then smoothly order meals based on the suggested menu.

[0996] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0997] Step 1: Enter your user information

[0998] The user uses the device to input information about their family, physical condition, weather, and recent meals. The input information specifically includes the following items:

[0999] Family composition (e.g., "Father, mother, 5-year-old child, 1-year-old child")

[1000] Physical condition (e.g., "My mother has a slight cold")

[1001] Climate (e.g., "rainy and cold")

[1002] What you ate most recently (e.g., "I had curry rice last night")

[1003] Input data is collected at the terminal and sent to the server.

[1004] Step 2: Receiving and storing data

[1005] The server receives the data sent from the user terminal. The above information is sent as input, and the server stores it in a database. Specifically,

[1006] Input: Family composition, physical condition, weather, and recent meal details

[1007] Output: Saved database entries

[1008] The data is organized by category and stored for future retrieval and analysis.

[1009] Step 3: Data analysis and user learning

[1010] The generative AI model analyzes the stored data. In this step, data processing and calculations are performed to identify the user's preferences and dislikes.

[1011] Input: Saved database information

[1012] Output: A list of the user's preferences and ingredients to avoid

[1013] Through analysis, the AI ​​model learns user preferences (e.g., "children don't like green peppers" or "mothers like cheese").

[1014] Step 4: Create a menu

[1015] When a user requests "Today's Menu Suggestion," the server receives the request, and the generative AI model generates the optimal menu by taking into account the day's weather, physical condition, cooking time, and options from external services.

[1016] Input: Weather, physical condition, cooking time, menu of external service

[1017] Output: Optimal menu

[1018] During this process, a wide range of data, including weather and physical condition, is analyzed again to determine the most appropriate menu.

[1019] Step 5: View Proposals and Order Function

[1020] The generated menu is sent from the server to the user's terminal and displayed on the terminal. The user can then order meals from external restaurants based on the proposed menu.

[1021] Input: Generated menu data

[1022] Output: Menu displayed on screen, and order confirmation screen

[1023] Specifically, users can check the menu and easily place their order within the app.

[1024] Step 6: Gather feedback

[1025] The user inputs their satisfaction with the meal provided and any areas for improvement into the terminal and sends the input to the server.

[1026] Input: Satisfaction and Feedback

[1027] Output: Saved feedback data

[1028] The user's input is again saved in the database.

[1029] Step 7: Analyze feedback and update the model

[1030] The server analyzes the stored feedback data and updates the generative AI model, a step that involves training to incorporate new insights into the model.

[1031] Input: Feedback data

[1032] Output: Updated generative AI model

[1033] Based on the feedback, the model retrains to make its next suggestions even more accurate.

[1034] 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.

[1035] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[1036] Obtaining user input information

[1037] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[1038] The server receives and stores the data

[1039] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[1040] AI model analyzes data

[1041] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[1042] Generate menu suggestions

[1043] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., tiredness), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[1044] Presenting the proposal

[1045] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[1046] Gathering feedback

[1047] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[1048] Analyzing feedback and updating the model

[1049] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[1050] In this way, the system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary habits, and improves the accuracy of suggestions through feedback. By incorporating emotional factors in particular, the system can suggest menus that suit the user's mood that day, achieving more personalized menu decisions.

[1051] The processing flow will be explained below.

[1052] Step 1:

[1053] The user starts the application using a terminal and logs in. The user inputs family composition, physical condition, weather, most recent meal, and emotions. For example, the user inputs "father, mother, 5-year-old child, 1-year-old child" as family composition, "mother has a bit of a cold" as physical condition, "rainy and cold" as weather, "curry rice last night" as most recent meal, and "tired" as emotion.

[1054] Step 2:

[1055] The device sends the input data to the server, which receives the data and stores it in a database. At the same time, the emotion engine analyzes the emotion information from the user's input data and sends the analysis results to the server.

[1056] Step 3:

[1057] The generative AI model on the server reads the stored data and preprocesses it to make it easier to analyze, including filling in missing values ​​and normalizing the data.

[1058] Step 4:

[1059] The generative AI model learns from the user's family structure, physical condition, weather, recent meal content, emotional information, etc. to understand the user's preferences and dislikes of ingredients. For example, it can understand that a child dislikes green peppers and a mother likes cheese, or that the user is tired and wants a meal that is easy to prepare.

[1060] Step 5:

[1061] The user requests "Today's menu suggestion" in the application. The server receives the request and generates the optimal menu taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), emotions (tired), and other conditions.

[1062] Step 6:

[1063] The generative AI model generates optimal menus based on the conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[1064] Step 7:

[1065] The server sends the generated menu information to the user terminal, which displays the menu to the user.

[1066] Step 8:

[1067] The user actually creates the suggested menu and provides it to their family. After completing the menu, the user enters feedback such as satisfaction and areas for improvement into the device.

[1068] Step 9:

[1069] The terminal transmits feedback data from the user to the server, which receives the data and stores it in a database.

[1070] Step 10:

[1071] The generative AI model on the server analyzes the stored feedback data and updates the model to help with the next menu suggestion. At the same time, the emotion engine also learns the emotional information obtained from the feedback and reflects it in the next emotion analysis.

[1072] This system can provide optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood on that day, achieving more personalized menu decisions.

[1073] Example 2

[1074] 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."

[1075] In today's busy lifestyles, planning a daily menu can be a burden for many people. Furthermore, determining the optimal menu based on the family's physical condition, preferences, and even their emotions on that day is a difficult task. Adjusting the menu is particularly complicated when family members have diverse preferences and physical conditions. Therefore, there is a strong demand for a system that allows users to easily determine the optimal menu. Furthermore, a mechanism is needed that uses feedback to improve the accuracy of suggestions.

[1076] 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.

[1077] In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for an emotion engine to analyze emotional information from the input data and transmit it to the server; means for a generative AI model to analyze the stored data and emotional information and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, emotions, cooking time, etc. in response to a user's request; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the provided menu into the terminal and transmit it to the server; and means for storing and analyzing the feedback and updating the generative AI model and the emotion engine. This not only allows the user to easily receive optimal menu suggestions based on the physical condition, preferences, and emotions of their family members, but also enables the system to continuously improve its accuracy based on the provided feedback.

[1078] A "user terminal" is an electronic device used by a user to input information.

[1079] A "server" is a computer system that receives and stores data sent from user devices and also runs the generative AI model and emotion engine.

[1080] A "generative AI model" is an artificial intelligence model that analyzes stored data and emotional information, learns the user's preferences and disliked ingredients, and generates optimal menus.

[1081] The "emotion engine" is a software component that analyzes emotional information from user input data and sends the results to the server.

[1082] "Family composition" is information indicating the members of the user's family and their relationships.

[1083] "Physical condition" is information indicating the health condition of the user and their family members.

[1084] "Climate" is information indicating the weather and temperature of the day.

[1085] "Details of most recent meal" is information indicating the details of meals recently eaten by the user and their family.

[1086] "Emotions" is information that indicates the current feelings and moods of the user and their family members.

[1087] "Feedback" is information that indicates the user's opinions and evaluations, such as their satisfaction with the menu provided and areas for improvement.

[1088] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[1089] Obtaining user input information

[1090] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[1091] The server receives and stores the data

[1092] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[1093] AI model analyzes data

[1094] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[1095] Generate menu suggestions

[1096] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[1097] Presenting the proposal

[1098] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[1099] Gathering feedback

[1100] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[1101] Analyzing feedback and updating the model

[1102] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[1103] Examples of concrete examples and prompts

[1104] As a specific example, consider the case of suggesting easy-to-make meals for a day when the user is tired.

[1105] Specific examples

[1106] User input: Family composition: "Father, mother, 5-year-old child, 1-year-old child", health condition: "Mother is feeling a bit under the weather", weather: "Rainy and cold", most recent meal: "Curry rice last night", emotion: "Tired".

[1107] Server's suggested menu: Chicken ginger soup, minced meat and vegetable salad.

[1108] Prompt Sentence Examples

[1109] Please suggest the best menu for a family consisting of a father, mother, a 5-year-old child, and a 1-year-old child, where the mother is feeling a bit under the weather, it's rainy and cold, they had curry rice last night, and they are emotionally exhausted.

[1110] This system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood that day, achieving more personalized menu decisions.

[1111] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1112] Step 1: User enters information from device

[1113] The user starts the terminal application and inputs information about the family (e.g., "father, mother, five-year-old child, one-year-old child"), physical condition (e.g., "mother has a slight cold"), weather (e.g., "rainy and cold"), what they had most recently eaten (e.g., "I had curry rice last night"), and emotions (e.g., "I'm tired"). This information is saved as input data on the terminal.

[1114] Step 2: Send data from the device to the server

[1115] The device transmits the input data to the server in real time. The transmitted data includes family composition, physical condition, weather, recent meal contents, and emotions. The server receives the transmitted data.

[1116] Step 3: The server receives and stores the data

[1117] The server stores the received data in a database, which ensures that all user input is stored permanently.

[1118] Step 4: Emotion analysis using the emotion engine

[1119] The emotion engine analyzes emotional information from the user's input data stored on the server. For example, if the user inputs "I'm tired," it analyzes negative emotions. The results of this analysis are also stored in the database.

[1120] Step 5: Data preprocessing for generative AI models

[1121] The generative AI model on the server reads the user's saved data and emotional information, and performs preprocessing such as handling missing values ​​and normalizing the data, thereby preparing the data in a format that is easy to analyze.

[1122] Step 6: The generative AI model analyzes and learns from the data

[1123] Based on the preprocessed data, the generative AI model learns the user's preferences and dislikes. For example, it understands that a child dislikes green peppers and a mother likes cheese, and that a meal plan that is easy to prepare is desired. This learning result is stored in the model.

[1124] Step 7: User submits request

[1125] The user requests "Today's menu suggestions" from the terminal. This request is sent to the server.

[1126] Step 8: The server receives the request

[1127] The server receives the user's request and retrieves the data stored for that day. The input data includes weather (e.g., "It's cold"), physical condition (e.g., "My mother has a slight cold"), recent meal (e.g., "Curry and rice"), and emotion (e.g., "I'm tired").

[1128] Step 9: Menu generation using generative AI models

[1129] The generative AI model generates optimal menus based on the stored data and analysis results. For example, it selects "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy to make and suitable for children. The generated menu information is output.

[1130] Step 10: Server Sends Proposal

[1131] The server sends the generated menu information to the user terminal. The output menu information arrives at the user terminal.

[1132] Step 11: Your device will display suggestions

[1133] The user device displays the menu information sent from the server, and the user can view the suggested menu on the app screen.

[1134] Step 12: User provides feedback

[1135] The user creates a suggested menu and provides it to their family. After that, they input their feedback, such as their actual satisfaction level and areas for improvement, into the device. The input feedback data is saved on the device.

[1136] Step 13: Device sends feedback

[1137] The device sends the saved feedback data to the server, which then receives information about the user's satisfaction and areas for improvement.

[1138] Step 14: Server saves feedback

[1139] The server stores the received feedback data in a database. All feedback information is stored permanently.

[1140] Step 15: Generative AI model analyzes feedback

[1141] The generative AI model analyzes the saved feedback data. Specifically, it extracts user satisfaction and areas for improvement, and analyzes them to help with the next menu proposal. The analysis results are reflected within the model.

[1142] Step 16: The emotion engine updates its learning

[1143] The emotion engine also learns from the feedback data and updates itself to improve its accuracy. The updated emotion information is used for the next analysis.

[1144] The above is the specific processing flow of the program for this system.

[1145] (Application example 2)

[1146] 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."

[1147] Conventional menu suggestion systems only considered the user's family structure, physical condition, weather, and recent meal content, which meant they were unable to make suggestions that reflected the user's emotions and mood.In addition, there was a lack of data to provide the optimal menu based on the user's physical condition and weather on that day, making it difficult to further improve user satisfaction.

[1148] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model and an emotion engine to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, cooking time, and emotions in response to a user request; means for transmitting the generated menu to the user's terminal and displaying it; means for inputting user satisfaction and feedback regarding the menu created by the user into the terminal and transmitting it to the server; and means for storing and analyzing the feedback and updating the generative AI model. This enables more personalized menu suggestions to be made in response to the user's emotions and daily changes.

[1149] A "user terminal" is an electronic device through which a user inputs information and receives suggestions.

[1150] "Family composition" is information about family members entered by the user, including the ages and relationships of each member.

[1151] "Physical condition" is information about the health status of the user and family members.

[1152] "Climate" is information about environmental conditions such as the weather and temperature of the day.

[1153] "Most recent meal details" is information about meals recently consumed by the user.

[1154] "Emotion" is information about the current mood or emotional state of the user or family members.

[1155] A "server" is a computer system that receives, stores, and analyzes data from users.

[1156] A "generative AI model" is an artificial intelligence system that analyzes user input data and generates optimal menus.

[1157] An "emotion engine" is a system for analyzing a user's emotional information.

[1158] "Analysis" is the process of processing user-entered data and extracting meaningful information.

[1159] "Preferences" is information about foods and cooking methods preferred by the user and family members.

[1160] "Disliked ingredients" is information about foods that the user or family members want to avoid.

[1161] "Menu suggestion" refers to presenting optimal meal plans based on user input data.

[1162] "Feedback" is information about the user's satisfaction with the proposed menu and areas for improvement.

[1163] "Storage" refers to recording data in a database within a server.

[1164] "Learning" is the process by which the generative AI model recognizes the user's preferences and dislikes and reflects them in future suggestions.

[1165] "Update" refers to improving generative AI models and emotion engines based on feedback.

[1166] The present invention is a system that suggests optimal menus based on information entered by a user using a terminal, such as family composition, physical condition, weather, recent meal contents, and emotions. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[1167] Obtaining user input information

[1168] First, the user uses a device to input information about their family, their physical condition, the weather, what they ate most recently, and their emotions. For example, they might input "father, mother, five-year-old child, one-year-old child" as their family composition, "mother has a bit of a cold" as their physical condition, "rainy and cold" as their weather, "curry rice last night" as their most recent meal, and "tired" as their emotion. This information is typically input through a smartphone application.

[1169] The server receives and stores the data

[1170] The data sent by the device is received and stored by the server. The emotion engine analyzes the user's emotional information based on this data and sends it to the server. The server stores this data in a database.

[1171] Data analysis of AI models and emotion engines

[1172] The data stored on the server is analyzed by a generative AI model. The data is preprocessed and converted into a format that is easy to analyze. The emotional information generated by the emotion engine is also analyzed, and the model learns the user's preferences and dislikes of ingredients. For example, the model can understand that a child dislikes green peppers, a mother likes cheese, and the user is tired and wants a meal that is easy to prepare.

[1173] Generate menu suggestions

[1174] When a user requests "Today's Menu Suggestion" through the app, the server receives the request. The generative AI model generates the optimal menu by taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it suggests "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[1175] Presenting the proposal

[1176] The generated menu is sent to the user's device, which displays it to the user. The user can then review the suggested menu within the app and order food delivery.

[1177] Gathering feedback

[1178] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. This feedback data is sent to the server and stored in a database.

[1179] Analyzing feedback and updating the model

[1180] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[1181] Specific examples

[1182] For example, when suggesting "easy and nutritious recipes that the whole family will enjoy" for dinner, if the mother has a cold and the children don't like vegetables, the app will suggest "chicken ginger soup" and "minced meat and vegetable salad." Instructions on how to proceed with these and how to order food delivery are also provided within the app.

[1183] Prompt Sentence Examples

[1184] For example, the following prompt sentence is input to the generative AI model:

[1185] "Family composition: Father, Mother, 5-year-old child, 1-year-old child. Mother is feeling a bit under the weather. They had curry rice last night. The user is tired, and it was rainy and cold this morning. Please suggest the best dinner menu for today, taking these factors into consideration."

[1186] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1187] Step 1:

[1188] The user uses the device to input information about their family, physical condition, weather, recent meal, and emotions. During this information collection process, the device provides an input interface for the user to input the necessary data. The input data is stored in the device's temporary memory.

[1189] Step 2:

[1190] The terminal sends the data entered by the user to the server. The terminal encodes the data into JSON format using the transmission protocol and sends it to the server using an HTTP POST request. The server receives the data using the reception protocol and stores it in the storage system.

[1191] Step 3:

[1192] The server reads the stored data for analysis. In this process, the emotion engine uses natural language processing techniques to classify the user's emotion data into specific emotion categories. The analysis results are stored in a database on the server.

[1193] Step 4:

[1194] The generative AI model learns the user's preferences and dislikes based on data stored on the server. Machine learning algorithms are used to preprocess the data, extract features, and train the model. The learning results are also stored in a database on the server.

[1195] Step 5:

[1196] When a user requests a menu suggestion, the server receives the request. The server generates a prompt that includes weather information, physical condition, recent meal content, and emotional information, and inputs it into the generative AI model. Based on the generated prompt, the AI ​​model suggests the optimal menu.

[1197] Step 6:

[1198] The server sends the generated menu to the user's device. The menu suggestions are displayed on the device, and the user can confirm the suggested menu. The user can also check the suggested menu within the application and order food delivery directly.

[1199] Step 7:

[1200] The user actually creates the suggested menu and serves it to their family. After the meal, the user enters their satisfaction with the menu and any improvements they may have made as feedback via their device. This feedback data is sent from the device to the server.

[1201] Step 8:

[1202] The server analyzes the feedback data and updates the generative AI model and emotion engine. Specifically, it adjusts the model weights based on the feedback to improve the accuracy of the next suggestion. The feedback analysis results are also stored in a database on the server.

[1203] 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.

[1204] 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.

[1205] 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.

[1206] [Fourth embodiment]

[1207] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1208] 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.

[1209] 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).

[1210] 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.

[1211] 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.

[1212] 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).

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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."

[1220] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[1221] Obtaining user input information

[1222] The user uses the terminal to input information about their family, physical condition, weather, and what they ate most recently. For example, today's family is "father, mother, 5-year-old child, 1-year-old child," their physical condition is "mother has a bit of a cold," their weather is "rainy and cold," and their most recent meal is "curry rice last night."

[1223] The server receives and stores the data

[1224] The terminal transmits the input data to the server, which receives the data and stores it in a database.

[1225] AI model analyzes data

[1226] The generative AI model on the server analyzes the stored data and learns the user's preferences and dislikes of certain foods. For example, it might learn that a child dislikes green peppers and a mother likes cheese.

[1227] Generate menu suggestions

[1228] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), and other conditions. For example, it suggests "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[1229] Presenting the proposal

[1230] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[1231] Gathering feedback

[1232] The user creates a proposed menu and enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database. The AI ​​model on the server analyzes the stored feedback and updates the model to help with future suggestions.

[1233] This system allows users to easily decide on daily menus, reducing the burden of housework and childcare. It also supports the health of the entire family by providing nutritionally balanced meals. For families with children in particular, it suggests baby food according to the child's age, reducing the burden of childcare. This allows users to enjoy a richer diet.

[1234] The processing flow will be explained below.

[1235] Step 1:

[1236] The user starts the application using a terminal and logs in. The user enters information about the family composition, physical condition, weather, and recent meal, and then enters information about each member (e.g., father, mother, 5-year-old child, 1-year-old child) on the "Enter family composition" screen.

[1237] Step 2:

[1238] On the "Enter your physical condition and weather" screen, the user enters, for example, that "my mother is feeling a bit sick" as a physical condition and that "it's rainy and cold" as a weather condition. Also, on the "Enter your most recent meal" screen, the user enters the meal they recently had (for example, "I had curry and rice last night").

[1239] Step 3:

[1240] The terminal sends the entered data to the server, which receives the data and stores it in a database.

[1241] Step 4:

[1242] A generative AI model on the server reads the stored data and preprocesses it into a format that is easy to analyze.

[1243] Step 5:

[1244] The generative AI model learns the user's preferences and dislikes, for example, that a child dislikes green peppers and a mother likes cheese.

[1245] Step 6:

[1246] The user requests "Today's Menu Suggestion" through the app. The server receives the request and generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), and other conditions.

[1247] Step 7:

[1248] The generative AI model generates menus based on conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[1249] Step 8:

[1250] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[1251] Step 9:

[1252] The user actually creates the suggested menu and provides it to their family. The user then inputs feedback such as satisfaction and areas for improvement into the device.

[1253] Step 10:

[1254] The terminal sends feedback from the user to the server, which receives the data and stores it in a database.

[1255] Step 11:

[1256] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion.

[1257] In this way, the system provides optimal menus based on the information entered by the user, taking into account the weather, physical condition, and past dietary habits, and improves the accuracy of its suggestions through feedback.

[1258] Example 1

[1259] 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."

[1260] There is a need to reduce the time and effort required to plan daily menus and provide appropriate meals that suit the physical condition and preferences of family members. However, with busy lives and child-rearing responsibilities, it is difficult to plan balanced meals, and inappropriate meals can disrupt nutritional balance. In addition, providing meals appropriate to the age of infants and toddlers is particularly important, but achieving this requires specialized knowledge.

[1261] 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.

[1262] In this invention, the server includes a means for a user to input information about members, their health status, weather information, and recent meal contents using a mobile device; a means for the server to receive and store the data transmitted from the mobile device; and a means for the generative AI model to analyze the stored data and learn the user's preferences and food dislikes. This allows users to easily decide daily menus and efficiently provide nutritionally balanced meals for the entire family. Furthermore, the generative AI model takes into account ingredients and cooking methods appropriate for the age of the family when proposing meals for infants, thereby reducing the burden on families raising children.

[1263] A "mobile terminal" is an electronic device that allows a user to input information about family composition, physical condition, weather information, and recent meal details, and includes devices such as smartphones and tablets.

[1264] "Member information" refers to data such as each family member's age, gender, food preferences, and disliked foods.

[1265] "Health status" refers to each family member's current physical condition, medical history, allergy information, etc.

[1266] "Weather information" is data relating to the weather conditions in the area where the user currently resides, including temperature, humidity, rainfall, and the like.

[1267] "Recent meal contents" refers to cooking records and meal menu data created by the user in the past.

[1268] A "server" is a computer system that receives, stores, and processes data sent by users.

[1269] A "database" is a system that systematically manages data such as member information, health status, weather information, and recent meal contents stored on a server.

[1270] "Generative AI model" refers to artificial intelligence technology that analyzes stored data and generates appropriate menus that are presented through a user interface.

[1271] "Analysis" refers to the process by which a generative AI model processes input data, finds patterns and trends, and learns from them.

[1272] "Preferences" refers to data about each family member's favorite ingredients and cooking methods.

[1273] "Difficult ingredients" refers to ingredients that each member of the family dislikes, is allergic to, or would like to avoid.

[1274] A "menu" refers to the combination of dishes suggested by the generative AI model for the user to serve as their meal of the day.

[1275] "Satisfaction level" refers to the evaluation after the user actually creates the suggested menu.

[1276] "Opinions" refers to feedback such as improvements or requests that users have regarding the proposed menu.

[1277] "Machine learning algorithms" refer to the mathematical methods and models that generative AI models use to analyze data and learn patterns.

[1278] "Nutritional balance" refers to a combination of meals that are carefully designed to ensure the appropriate intake of various nutrients, with the family's health in mind.

[1279] "Infant meal suggestions" refers to meal suggestions that take into consideration appropriate ingredients and cooking methods according to the infant's age.

[1280] MODE FOR CARRYING OUT THE INVENTION

[1281] The present invention provides a system that proposes optimal meals based on the physical condition and preferences of family members, eliminating the need for users to plan their daily menus. The system includes a user terminal, a server, and a generative AI model.

[1282] System configuration

[1283] User terminal

[1284] The user terminal provides an interface for users to input information about members, their health status, weather information, and recent meal details. Specific examples include mobile devices such as smartphones and tablets. These devices allow users to input data through dedicated applications.

[1285] server

[1286] The server is a computer system that receives and stores data sent from user devices. The server uses a database to systematically store and manage the received data. Furthermore, it uses a generative AI model running on the server to analyze the data and generate menus.

[1287] Generative AI Models

[1288] The generative AI model analyzes the received and stored data and learns the user's preferences and dislikes. This generative AI model is implemented using machine learning algorithms (e.g., GPT-4). Based on the stored data, it creates an appropriate menu according to the user's request.

[1289] Process Overview

[1290] 1. Obtaining user input information: The user opens the app on their mobile device and enters information about their family members, their health condition, weather information, and what they recently ate. For example, they enter "father, mother, 5-year-old child, 1-year-old child" as the family composition, "mother has a bit of a cold" as the health condition, "rainy and cold" as the weather, and "curry rice last night" as the most recent meal.

[1291] 2. The server receives and saves the data: The device sends the entered data to the server, which receives it and saves it in a database.

[1292] 3. The AI ​​model analyzes the data: The generative AI model on the server analyzes the data stored in the database and learns the user's preferences and dislikes. For example, it learns that a child dislikes green peppers and a mother likes cheese.

[1293] 4. Menu suggestion generation: When a user requests "Today's menu suggestion" in the app, the server receives the request, and the AI ​​model generates the optimal menu based on the weather, health condition, recent meals, etc. For example, "digestible chicken ginger soup" and "minced meat and vegetable salad" are suggested.

[1294] 5. Proposal presentation: The server sends the generated menu to the user terminal, which displays it to the user. The user can then create a proposed menu.

[1295] 6. Feedback collection: After the user creates the proposed menu, they input their satisfaction and suggestions for improvement into their mobile device. The device sends this to the server, which stores it in a database. The generative AI model analyzes the feedback and updates the model to help with future suggestions.

[1296] Specific examples

[1297] For example, if the family structure (father, mother, 5-year-old child, 1-year-old child), health condition (mother is feeling a bit under the weather) and weather information (rainy and cold) are entered, along with information such as (curry rice last night), the system will suggest (easy-to-digest) chicken ginger soup and (minced meat and vegetable salad).

[1298] Prompt Sentence Examples

[1299] "Today's family consists of a father, a mother, a five-year-old child, and a one-year-old child, and the mother is feeling a bit under the weather. It's rainy and cold today. Last night, they had curry rice. Based on these conditions, please suggest the best menu for them."

[1300] The system allows users to easily plan their daily meals and provide nutritionally balanced meals for the whole family.The generative AI model also takes age-appropriate ingredients and cooking methods into account when suggesting meals for infants, reducing the burden on families with children.

[1301] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1302] Step 1:

[1303] The user opens the app on their device and enters their family composition, physical condition, weather, and recent meal details. For example, the input form includes the family composition of "father, mother, 5-year-old child, 1-year-old child," the physical condition of "mother is feeling a bit sick," the weather of "rainy and cold," and "I had curry rice last night."

[1304] Input data: Family composition, physical condition, weather, recent meal contents

[1305] Output data: User input data ready to send

[1306] Step 2:

[1307] The terminal sends the entered data to the server, which receives it as an HTTP request.

[1308] Input data: User-entered data

[1309] Data processing: Convert input data into HTTP requests

[1310] Output data: HTTP request sent

[1311] Step 3:

[1312] The server stores the received data in a database, for example by inserting data into the database using an SQL query.

[1313] Input data: Received data from the HTTP request

[1314] Data manipulation: Inserting data using SQL queries

[1315] Output data: Saved to database

[1316] Step 4:

[1317] The generative AI model on the server analyzes the data stored in the database. It then runs machine learning algorithms to learn the user's preferences and dislikes. For example, it analyzes the data and extracts the user's preference patterns.

[1318] Input data: User-entered data stored in a database

[1319] Data processing: Data analysis using machine learning algorithms

[1320] Output data: Generation of user preference data

[1321] Step 5:

[1322] The user requests "Today's menu suggestions" through the app. The device sends this request to the server.

[1323] Input data: User's menu suggestion request

[1324] Data processing: Generating request data

[1325] Output data: Request sent to server

[1326] Step 6:

[1327] The server receives the request and inputs the prompt into the generative AI model, which generates the optimal menu taking into account the weather, physical condition, and recent meal content of the day.

[1328] Input data: user requests, stored user data

[1329] Data processing: Prompt generation and input to the AI ​​model

[1330] Output data: Generation of optimal menu

[1331] Step 7:

[1332] The server sends the generated menu to the user's device, which receives it and displays the menu on the app screen.

[1333] Input data: Generated menu data

[1334] Data processing: data format conversion and transmission

[1335] Output data: Menu displayed on terminal

[1336] Step 8:

[1337] After the user creates the proposed menu, they input their feedback, such as their level of satisfaction and areas for improvement, into the terminal. The user's evaluation and opinions are entered into an input form.

[1338] Input data: User feedback data

[1339] Output data: Feedback data ready to send

[1340] Step 9:

[1341] The terminal transmits feedback data to the server, and the server stores the received feedback in a database.

[1342] Input data: User feedback data

[1343] Data processing: Sending via HTTP request, inserting data via SQL query

[1344] Output data: Feedback data saved in database

[1345] Step 10:

[1346] The server's generative AI model analyzes the stored feedback data and updates the model, which then reflects the feedback in the next menu suggestion.

[1347] Input data: Saved feedback data

[1348] Data processing: Data analysis and model updating using machine learning algorithms

[1349] Output data: Updated generative AI model

[1350] Through the above processing steps, the user can easily decide on daily menus and provide appropriate, nutritionally balanced meals for the whole family.

[1351] (Application example 1)

[1352] 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."

[1353] In today's busy households, planning a daily menu is a time-consuming and labor-intensive task. In particular, families with children need to provide meals that are suitable for the entire family while taking nutritional balance into consideration. Furthermore, as the use of food delivery services increases, there is a demand for customized meals that address individual health conditions and preferences. However, current services are insufficient in adapting to individual health conditions and preferences, making it difficult to propose an optimal menu for the user and order meals based on that menu. The purpose of this invention is to solve these problems and provide a system that proposes an optimal menu for the user and allows the user to smoothly order food delivery.

[1354] 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.

[1355] In this invention, the server includes: means for a user to input information about family composition, physical condition, weather, and recent meal content using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the menu created by the user into the terminal and transmit it to the server; means for storing and analyzing the feedback and updating the generative AI model; and means for ordering meals from external restaurants based on the generated menu. This allows users to easily determine an optimal menu that corresponds to their individual health condition and preferences, and further enables them to smoothly order meals based on the proposed menu.

[1356] "A means for users to input information about their family composition, physical condition, weather, and recent meal details using a device" refers to an interface that allows users to input information about their own and their family's health status, weather conditions, and recent meal details using electronic devices such as smartphones and tablets.

[1357] "Means for the server to receive and store data sent from the terminal" refers to a system configuration in which information sent from a user terminal is received via a network and the data is stored in a storage device such as a database.

[1358] "Means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients" refers to the process of using a machine learning algorithm based on the stored data to identify the user's preferences and ingredients they want to avoid, learning from them and applying them to future recipes.

[1359] "A means of generating optimal menus based on the user's request, such as the weather and physical condition of the day, cooking time, and options from meal delivery services" refers to an algorithm that enables AI to design the best menu in response to a user's request, taking into account the weather and physical condition of the day, the specified cooking time, and the menus offered by external services.

[1360] "Means for sending and displaying the generated menu to the user's device" refers to the technology for sending the menu information generated by AI to the user's electronic device and displaying that information on the screen.

[1361] "Means for users to input their satisfaction and feedback regarding the menu they have created into a terminal and send it to a server" refers to a system that allows users to input their thoughts and suggestions about the completed dish and send that information to a server via a network.

[1362] "Means for storing and analyzing said feedback and updating the generative AI model" refers to a series of processes for storing feedback data from users in a storage device and analyzing that data to improve the AI ​​model.

[1363] "Means for ordering meals from external restaurants based on the generated menu" refers to the interface and process for ordering meals from affiliated restaurants and delivery services based on the menu suggested by AI.

[1364] This invention provides a system that generates an optimal menu based on various information such as the user's family composition, physical condition, weather, and recent meal content, and then orders meals from external restaurants based on the menu. Specific embodiments are described below.

[1365] System Configuration

[1366] User terminal

[1367] The user terminal is an electronic device such as a smartphone or tablet, and the user uses this terminal to input information such as their own and their family's health status, weather conditions, and recent meal information.

[1368] server

[1369] The server receives and stores data sent from the user's device. The generative AI model then analyzes the stored data and learns the user's preferences and dislikes. In response to the user's request, the server generates an optimal menu based on the day's weather, physical condition, cooking time, and options from external meal delivery services.

[1370] Generative AI Models

[1371] The generative AI model analyzes the stored data, identifies the user's preferences and ingredients to avoid, and learns from them, which is then reflected in future menu generation.

[1372] System Features

[1373] Entering user information

[1374] The user can enter the following information via the terminal:

[1375] Family composition (e.g., father, mother, 5-year-old child, 1-year-old child)

[1376] Physical condition (e.g., mother has a cold)

[1377] Climate (e.g. rainy and cold)

[1378] What you ate most recently (e.g. curry rice last night)

[1379] Receiving and storing data

[1380] The server receives the information sent by the user from the device and stores it in a database, which includes information such as family composition, physical condition, weather, and recent meal contents.

[1381] Data analysis and menu suggestions

[1382] The generative AI model analyzes the received data and learns the user's preferences and dislikes. For example, it may learn that a child dislikes green peppers and a mother likes cheese. Then, when a user makes a request, the server generates the optimal menu based on the day's conditions.

[1383] Menu display and ordering function

[1384] The generated menu is sent to the user's device and displayed there. The user can then review the proposed menu and order meals from affiliated external restaurants if necessary.

[1385] Gathering feedback and updating the model

[1386] Users can input their feedback on the proposed menu, such as their level of satisfaction and areas for improvement, into their device and send it to the server. The server then stores this feedback and updates the generative AI model, making future menu suggestions more accurate.

[1387] For example:

[1388] "The family consists of a father, a mother, a 5-year-old child, and a 1-year-old child. The mother is feeling a bit under the weather, and it's cold and rainy today. Last night we had curry rice. Could you suggest a menu for today?"

[1389] "Yesterday's soup was a little salty. Mom's cold is a little better. What would be best today?"

[1390] By providing the AI ​​model with the above prompts, the model can generate a menu that specifically corresponds to the user's situation, allowing the user to easily determine the optimal menu that corresponds to their individual health condition and preferences, and then smoothly order meals based on the suggested menu.

[1391] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1392] Step 1: Enter your user information

[1393] The user uses the device to input information about their family, physical condition, weather, and recent meals. The input information specifically includes the following items:

[1394] Family composition (e.g., "Father, mother, 5-year-old child, 1-year-old child")

[1395] Physical condition (e.g., "My mother has a slight cold")

[1396] Climate (e.g., "rainy and cold")

[1397] What you ate most recently (e.g., "I had curry rice last night")

[1398] Input data is collected at the terminal and sent to the server.

[1399] Step 2: Receiving and storing data

[1400] The server receives the data sent from the user terminal. The above information is sent as input, and the server stores it in a database. Specifically,

[1401] Input: Family composition, physical condition, weather, and recent meal details

[1402] Output: Saved database entries

[1403] The data is organized by category and stored for future retrieval and analysis.

[1404] Step 3: Data analysis and user learning

[1405] The generative AI model analyzes the stored data. In this step, data processing and calculations are performed to identify the user's preferences and dislikes.

[1406] Input: Saved database information

[1407] Output: A list of the user's preferences and ingredients to avoid

[1408] Through analysis, the AI ​​model learns user preferences (e.g., "children don't like green peppers" or "mothers like cheese").

[1409] Step 4: Create a menu

[1410] When a user requests "Today's Menu Suggestion," the server receives the request, and the generative AI model generates the optimal menu by taking into account the day's weather, physical condition, cooking time, and options from external services.

[1411] Input: Weather, physical condition, cooking time, menu of external service

[1412] Output: Optimal menu

[1413] During this process, a wide range of data, including weather and physical condition, is analyzed again to determine the most appropriate menu.

[1414] Step 5: View Proposals and Order Function

[1415] The generated menu is sent from the server to the user's terminal and displayed on the terminal. The user can then order meals from external restaurants based on the proposed menu.

[1416] Input: Generated menu data

[1417] Output: Menu displayed on screen, and order confirmation screen

[1418] Specifically, users can check the menu and easily place their order within the app.

[1419] Step 6: Gather feedback

[1420] The user inputs their satisfaction with the meal provided and any areas for improvement into the terminal and sends the input to the server.

[1421] Input: Satisfaction and Feedback

[1422] Output: Saved feedback data

[1423] The user's input is again saved in the database.

[1424] Step 7: Analyze feedback and update the model

[1425] The server analyzes the stored feedback data and updates the generative AI model, a step that involves training to incorporate new insights into the model.

[1426] Input: Feedback data

[1427] Output: Updated generative AI model

[1428] Based on the feedback, the model retrains to make its next suggestions even more accurate.

[1429] 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.

[1430] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[1431] Obtaining user input information

[1432] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[1433] The server receives and stores the data

[1434] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[1435] AI model analyzes data

[1436] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[1437] Generate menu suggestions

[1438] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., tiredness), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[1439] Presenting the proposal

[1440] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[1441] Gathering feedback

[1442] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[1443] Analyzing feedback and updating the model

[1444] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[1445] In this way, the system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary habits, and improves the accuracy of suggestions through feedback. By incorporating emotional factors in particular, the system can suggest menus that suit the user's mood that day, achieving more personalized menu decisions.

[1446] The processing flow will be explained below.

[1447] Step 1:

[1448] The user starts the application using a terminal and logs in. The user inputs family composition, physical condition, weather, most recent meal, and emotions. For example, the user inputs "father, mother, 5-year-old child, 1-year-old child" as family composition, "mother has a bit of a cold" as physical condition, "rainy and cold" as weather, "curry rice last night" as most recent meal, and "tired" as emotion.

[1449] Step 2:

[1450] The device sends the input data to the server, which receives the data and stores it in a database. At the same time, the emotion engine analyzes the emotion information from the user's input data and sends the analysis results to the server.

[1451] Step 3:

[1452] The generative AI model on the server reads the stored data and preprocesses it to make it easier to analyze, including filling in missing values ​​and normalizing the data.

[1453] Step 4:

[1454] The generative AI model learns from the user's family structure, physical condition, weather, recent meal content, emotional information, etc. to understand the user's preferences and dislikes of ingredients. For example, it can understand that a child dislikes green peppers and a mother likes cheese, or that the user is tired and wants a meal that is easy to prepare.

[1455] Step 5:

[1456] The user requests "Today's menu suggestion" in the application. The server receives the request and generates the optimal menu taking into account the weather (cold), physical condition (mother has a cold), recent meal (curry rice), emotions (tired), and other conditions.

[1457] Step 6:

[1458] The generative AI model generates optimal menus based on the conditions, suggesting, for example, "chicken ginger soup" that is easy to digest and "minced meat and vegetable salad" that is easy for children to eat.

[1459] Step 7:

[1460] The server sends the generated menu information to the user terminal, which displays the menu to the user.

[1461] Step 8:

[1462] The user actually creates the suggested menu and provides it to their family. After completing the menu, the user enters feedback such as satisfaction and areas for improvement into the device.

[1463] Step 9:

[1464] The terminal transmits feedback data from the user to the server, which receives the data and stores it in a database.

[1465] Step 10:

[1466] The generative AI model on the server analyzes the stored feedback data and updates the model to help with the next menu suggestion. At the same time, the emotion engine also learns the emotional information obtained from the feedback and reflects it in the next emotion analysis.

[1467] This system can provide optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood on that day, achieving more personalized menu decisions.

[1468] Example 2

[1469] 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."

[1470] In today's busy lifestyles, planning a daily menu can be a burden for many people. Furthermore, determining the optimal menu based on the family's physical condition, preferences, and even their emotions on that day is a difficult task. Adjusting the menu is particularly complicated when family members have diverse preferences and physical conditions. Therefore, there is a strong demand for a system that allows users to easily determine the optimal menu. Furthermore, a mechanism is needed that uses feedback to improve the accuracy of suggestions.

[1471] 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.

[1472] In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for an emotion engine to analyze emotional information from the input data and transmit it to the server; means for a generative AI model to analyze the stored data and emotional information and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, emotions, cooking time, etc. in response to a user's request; means for transmitting the generated menu to the user's terminal and displaying it; means for the user to input satisfaction and feedback regarding the provided menu into the terminal and transmit it to the server; and means for storing and analyzing the feedback and updating the generative AI model and the emotion engine. This not only allows the user to easily receive optimal menu suggestions based on the physical condition, preferences, and emotions of their family members, but also enables the system to continuously improve its accuracy based on the provided feedback.

[1473] A "user terminal" is an electronic device used by a user to input information.

[1474] A "server" is a computer system that receives and stores data sent from user devices and also runs the generative AI model and emotion engine.

[1475] A "generative AI model" is an artificial intelligence model that analyzes stored data and emotional information, learns the user's preferences and disliked ingredients, and generates optimal menus.

[1476] The "emotion engine" is a software component that analyzes emotional information from user input data and sends the results to the server.

[1477] "Family composition" is information indicating the members of the user's family and their relationships.

[1478] "Physical condition" is information indicating the health condition of the user and their family members.

[1479] "Climate" is information indicating the weather and temperature of the day.

[1480] "Details of most recent meal" is information indicating the details of meals recently eaten by the user and their family.

[1481] "Emotions" is information that indicates the current feelings and moods of the user and their family members.

[1482] "Feedback" is information that indicates the user's opinions and evaluations, such as their satisfaction with the menu provided and areas for improvement.

[1483] The present invention provides a system that proposes optimal meals based on the physical condition, preferences, and emotions of family members, eliminating the need for users to plan their daily meals. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[1484] Obtaining user input information

[1485] The user uses the terminal to input information about their family, physical condition, weather, recent meal, and emotions. For example, the family is input as "father, mother, 5-year-old child, 1-year-old child," their physical condition is input as "mother has a cold," their weather is input as "rainy and cold," their recent meal is input as "curry rice last night," and their emotion is input as "tired."

[1486] The server receives and stores the data

[1487] The device sends the input data to the server, which receives the data and stores it in a database. The emotion engine analyzes the emotion information from the user's input data and sends it back to the server.

[1488] AI model analyzes data

[1489] The generative AI model on the server reads the saved data and preprocesses it into a format that is easy to analyze. It learns the user's preferences and dislikes, including the emotional information generated by the emotion engine. For example, it can understand that a child dislikes green peppers, while a mother likes cheese, and that the user is tired and wants a meal that is easy to prepare.

[1490] Generate menu suggestions

[1491] When a user requests "Today's Menu Suggestion" through the app, the server receives the request and the generative AI model generates the optimal menu, taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it might suggest "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[1492] Presenting the proposal

[1493] The server transmits the generated menu to a user terminal, and the terminal displays the menu to the user.

[1494] Gathering feedback

[1495] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. The feedback is sent to the server and stored in a database.

[1496] Analyzing feedback and updating the model

[1497] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[1498] Examples of concrete examples and prompts

[1499] As a specific example, consider the case of suggesting easy-to-make meals for a day when the user is tired.

[1500] Specific examples

[1501] User input: Family composition: "Father, mother, 5-year-old child, 1-year-old child", health condition: "Mother is feeling a bit under the weather", weather: "Rainy and cold", most recent meal: "Curry rice last night", emotion: "Tired".

[1502] Server's suggested menu: Chicken ginger soup, minced meat and vegetable salad.

[1503] Prompt Sentence Examples

[1504] Please suggest the best menu for a family consisting of a father, mother, a 5-year-old child, and a 1-year-old child, where the mother is feeling a bit under the weather, it's rainy and cold, they had curry rice last night, and they are emotionally exhausted.

[1505] This system provides optimal menus based on the user's input and emotional information, taking into account the weather, physical condition, emotions, and past dietary history, and can improve the accuracy of suggestions through feedback. In particular, by incorporating emotional factors, it can suggest menus that match the user's mood that day, achieving more personalized menu decisions.

[1506] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1507] Step 1: User enters information from device

[1508] The user starts the terminal application and inputs information about the family (e.g., "father, mother, five-year-old child, one-year-old child"), physical condition (e.g., "mother has a slight cold"), weather (e.g., "rainy and cold"), what they had most recently eaten (e.g., "I had curry rice last night"), and emotions (e.g., "I'm tired"). This information is saved as input data on the terminal.

[1509] Step 2: Send data from the device to the server

[1510] The device transmits the input data to the server in real time. The transmitted data includes family composition, physical condition, weather, recent meal contents, and emotions. The server receives the transmitted data.

[1511] Step 3: The server receives and stores the data

[1512] The server stores the received data in a database, which ensures that all user input is stored permanently.

[1513] Step 4: Emotion analysis using the emotion engine

[1514] The emotion engine analyzes emotional information from the user's input data stored on the server. For example, if the user inputs "I'm tired," it analyzes negative emotions. The results of this analysis are also stored in the database.

[1515] Step 5: Data preprocessing for generative AI models

[1516] The generative AI model on the server reads the user's saved data and emotional information, and performs preprocessing such as handling missing values ​​and normalizing the data, thereby preparing the data in a format that is easy to analyze.

[1517] Step 6: The generative AI model analyzes and learns from the data

[1518] Based on the preprocessed data, the generative AI model learns the user's preferences and dislikes. For example, it understands that a child dislikes green peppers and a mother likes cheese, and that a meal plan that is easy to prepare is desired. This learning result is stored in the model.

[1519] Step 7: User submits request

[1520] The user requests "Today's menu suggestions" from the terminal. This request is sent to the server.

[1521] Step 8: The server receives the request

[1522] The server receives the user's request and retrieves the data stored for that day. The input data includes weather (e.g., "It's cold"), physical condition (e.g., "My mother has a slight cold"), recent meal (e.g., "Curry and rice"), and emotion (e.g., "I'm tired").

[1523] Step 9: Menu generation using generative AI models

[1524] The generative AI model generates optimal menus based on the stored data and analysis results. For example, it selects "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy to make and suitable for children. The generated menu information is output.

[1525] Step 10: Server Sends Proposal

[1526] The server sends the generated menu information to the user terminal. The output menu information arrives at the user terminal.

[1527] Step 11: Your device will display suggestions

[1528] The user device displays the menu information sent from the server, and the user can view the suggested menu on the app screen.

[1529] Step 12: User provides feedback

[1530] The user creates a suggested menu and provides it to their family. After that, they input their feedback, such as their actual satisfaction level and areas for improvement, into the device. The input feedback data is saved on the device.

[1531] Step 13: Device sends feedback

[1532] The device sends the saved feedback data to the server, which then receives information about the user's satisfaction and areas for improvement.

[1533] Step 14: Server saves feedback

[1534] The server stores the received feedback data in a database. All feedback information is stored permanently.

[1535] Step 15: Generative AI model analyzes feedback

[1536] The generative AI model analyzes the saved feedback data. Specifically, it extracts user satisfaction and areas for improvement, and analyzes them to help with the next menu proposal. The analysis results are reflected within the model.

[1537] Step 16: The emotion engine updates its learning

[1538] The emotion engine also learns from the feedback data and updates itself to improve its accuracy. The updated emotion information is used for the next analysis.

[1539] The above is the specific processing flow of the program for this system.

[1540] (Application example 2)

[1541] 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."

[1542] Conventional menu suggestion systems only considered the user's family structure, physical condition, weather, and recent meal content, which meant they were unable to make suggestions that reflected the user's emotions and mood.In addition, there was a lack of data to provide the optimal menu based on the user's physical condition and weather on that day, making it difficult to further improve user satisfaction.

[1543] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input family composition, physical condition, weather, recent meal contents, and emotions using a terminal; means for the server to receive and store the data transmitted from the terminal; means for a generative AI model and an emotion engine to analyze the stored data and learn the user's preferences and disliked ingredients; means for generating an optimal menu based on the day's weather, physical condition, cooking time, and emotions in response to a user request; means for transmitting the generated menu to the user's terminal and displaying it; means for inputting user satisfaction and feedback regarding the menu created by the user into the terminal and transmitting it to the server; and means for storing and analyzing the feedback and updating the generative AI model. This enables more personalized menu suggestions to be made in response to the user's emotions and daily changes.

[1544] A "user terminal" is an electronic device through which a user inputs information and receives suggestions.

[1545] "Family composition" is information about family members entered by the user, including the ages and relationships of each member.

[1546] "Physical condition" is information about the health status of the user and family members.

[1547] "Climate" is information about environmental conditions such as the weather and temperature of the day.

[1548] "Most recent meal details" is information about meals recently consumed by the user.

[1549] "Emotion" is information about the current mood or emotional state of the user or family members.

[1550] A "server" is a computer system that receives, stores, and analyzes data from users.

[1551] A "generative AI model" is an artificial intelligence system that analyzes user input data and generates optimal menus.

[1552] An "emotion engine" is a system for analyzing a user's emotional information.

[1553] "Analysis" is the process of processing user-entered data and extracting meaningful information.

[1554] "Preferences" is information about foods and cooking methods preferred by the user and family members.

[1555] "Disliked ingredients" is information about foods that the user or family members want to avoid.

[1556] "Menu suggestion" refers to presenting optimal meal plans based on user input data.

[1557] "Feedback" is information about the user's satisfaction with the proposed menu and areas for improvement.

[1558] "Storage" refers to recording data in a database within a server.

[1559] "Learning" is the process by which the generative AI model recognizes the user's preferences and dislikes and reflects them in future suggestions.

[1560] "Update" refers to improving generative AI models and emotion engines based on feedback.

[1561] The present invention is a system that suggests optimal menus based on information entered by a user using a terminal, such as family composition, physical condition, weather, recent meal contents, and emotions. The system includes a user terminal, a server, a generative AI model, and an emotion engine.

[1562] Obtaining user input information

[1563] First, the user uses a device to input information about their family, their physical condition, the weather, what they ate most recently, and their emotions. For example, they might input "father, mother, five-year-old child, one-year-old child" as their family composition, "mother has a bit of a cold" as their physical condition, "rainy and cold" as their weather, "curry rice last night" as their most recent meal, and "tired" as their emotion. This information is typically input through a smartphone application.

[1564] The server receives and stores the data

[1565] The data sent by the device is received and stored by the server. The emotion engine analyzes the user's emotional information based on this data and sends it to the server. The server stores this data in a database.

[1566] Data analysis of AI models and emotion engines

[1567] The data stored on the server is analyzed by a generative AI model. The data is preprocessed and converted into a format that is easy to analyze. The emotional information generated by the emotion engine is also analyzed, and the model learns the user's preferences and dislikes of ingredients. For example, the model can understand that a child dislikes green peppers, a mother likes cheese, and the user is tired and wants a meal that is easy to prepare.

[1568] Generate menu suggestions

[1569] When a user requests "Today's Menu Suggestion" through the app, the server receives the request. The generative AI model generates the optimal menu by taking into account the weather (e.g., cold), physical condition (e.g., mother has a cold), recent meal (e.g., curry rice), emotions (e.g., fatigue), and other conditions. For example, it suggests "chicken ginger soup," which is easy to digest, and "minced meat and vegetable salad," which is easy for children to eat.

[1570] Presenting the proposal

[1571] The generated menu is sent to the user's device, which displays it to the user. The user can then review the suggested menu within the app and order food delivery.

[1572] Gathering feedback

[1573] The user actually creates the suggested menu and provides it to their family. The user then enters feedback such as satisfaction and areas for improvement into the device. This feedback data is sent to the server and stored in a database.

[1574] Analyzing feedback and updating the model

[1575] The generative AI model on the server analyzes the feedback data and updates the model to help with the next menu suggestion. The emotion engine also learns the emotional information obtained from the feedback and performs even more accurate emotion analysis.

[1576] Specific examples

[1577] For example, when suggesting "easy and nutritious recipes that the whole family will enjoy" for dinner, if the mother has a cold and the children don't like vegetables, the app will suggest "chicken ginger soup" and "minced meat and vegetable salad." Instructions on how to proceed with these and how to order food delivery are also provided within the app.

[1578] Prompt Sentence Examples

[1579] For example, the following prompt sentence is input to the generative AI model:

[1580] "Family composition: Father, Mother, 5-year-old child, 1-year-old child. Mother is feeling a bit under the weather. They had curry rice last night. The user is tired, and it was rainy and cold this morning. Please suggest the best dinner menu for today, taking these factors into consideration."

[1581] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1582] Step 1:

[1583] The user uses the device to input information about their family, physical condition, weather, recent meal, and emotions. During this information collection process, the device provides an input interface for the user to input the necessary data. The input data is stored in the device's temporary memory.

[1584] Step 2:

[1585] The terminal sends the data entered by the user to the server. The terminal encodes the data into JSON format using the transmission protocol and sends it to the server using an HTTP POST request. The server receives the data using the reception protocol and stores it in the storage system.

[1586] Step 3:

[1587] The server reads the stored data for analysis. In this process, the emotion engine uses natural language processing techniques to classify the user's emotion data into specific emotion categories. The analysis results are stored in a database on the server.

[1588] Step 4:

[1589] The generative AI model learns the user's preferences and dislikes based on data stored on the server. Machine learning algorithms are used to preprocess the data, extract features, and train the model. The learning results are also stored in a database on the server.

[1590] Step 5:

[1591] When a user requests a menu suggestion, the server receives the request. The server generates a prompt that includes weather information, physical condition, recent meal content, and emotional information, and inputs it into the generative AI model. Based on the generated prompt, the AI ​​model suggests the optimal menu.

[1592] Step 6:

[1593] The server sends the generated menu to the user's device. The menu suggestions are displayed on the device, and the user can confirm the suggested menu. The user can also check the suggested menu within the application and order food delivery directly.

[1594] Step 7:

[1595] The user actually creates the suggested menu and serves it to their family. After the meal, the user enters their satisfaction with the menu and any improvements they may have made as feedback via their device. This feedback data is sent from the device to the server.

[1596] Step 8:

[1597] The server analyzes the feedback data and updates the generative AI model and emotion engine. Specifically, it adjusts the model weights based on the feedback to improve the accuracy of the next suggestion. The feedback analysis results are also stored in a database on the server.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] 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.

[1603] 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.

[1604] 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).

[1605] 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.

[1606] 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."

[1607] 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.

[1608] 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).

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] The following is further disclosed regarding the above embodiment.

[1620] (Claim 1)

[1621] A means for a user to input information about family composition, physical condition, weather, and recent meal content using a terminal;

[1622] A server receives and stores data transmitted from the terminal;

[1623] A means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients;

[1624] A means for generating an optimal menu based on the weather, physical condition, cooking time, etc. of the day in response to a user's request;

[1625] A means for transmitting the generated menu to a user terminal and displaying it;

[1626] A means for inputting satisfaction and feedback regarding the menu created by the user into the terminal and transmitting the information to the server;

[1627] means for storing and analyzing said feedback and updating a generative AI model;

[1628] A system including:

[1629] (Claim 2)

[1630] The system according to claim 1, further comprising a user terminal for inputting information about family composition, physical condition, weather, and recent meal contents.

[1631] (Claim 3)

[1632] The system of claim 1, wherein the generative AI model includes means for considering ingredients and cooking methods appropriate to the baby's age when suggesting baby food.

[1633] "Example 1"

[1634] (Claim 1)

[1635] A means for a user to input information about members, their health status, weather information, and recent meal details using a mobile terminal;

[1636] A server receives and stores data transmitted from the mobile terminal;

[1637] A means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients;

[1638] A means for creating an appropriate menu based on the weather, health condition, cooking time, etc. of the day in response to a user's request;

[1639] A means for transmitting the generated menu to a mobile device and displaying it;

[1640] A means for inputting a user's satisfaction level and opinions about the menu created by the user into a mobile terminal and transmitting the information to a server;

[1641] means for storing and analyzing the opinions and updating the generative AI model;

[1642] A system including:

[1643] (Claim 2)

[1644] The system of claim 1, further comprising a mobile device for inputting member information, health status, weather information, and recent meal contents.

[1645] (Claim 3)

[1646] 10. The system of claim 1, wherein the generative AI model includes means for considering age-appropriate ingredients and cooking methods in meal suggestions for infants.

[1647] "Application Example 1"

[1648] (Claim 1)

[1649] A means for a user to input information about family composition, physical condition, weather, and recent meal content using a terminal;

[1650] A server receives and stores data transmitted from the terminal;

[1651] A means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients;

[1652] A means for generating an optimal menu in response to a user's request based on the weather and physical condition of the day, cooking time, options from meal provision services, etc.;

[1653] A means for transmitting the generated menu to a user terminal and displaying it;

[1654] A means for inputting satisfaction and feedback regarding the menu created by the user into the terminal and transmitting the information to the server;

[1655] means for storing and analyzing said feedback and updating a generative AI model;

[1656] A means for ordering meals from external stores based on the generated menu;

[1657] A system including:

[1658] (Claim 2)

[1659] The system according to claim 1, further comprising a user terminal for inputting information about family composition, physical condition, weather, and recent meal contents.

[1660] (Claim 3)

[1661] The system of claim 1, wherein the generative AI model includes means for considering ingredients and cooking methods appropriate to the baby's age when suggesting baby food.

[1662] "Example 2: Combining Emotion Engines"

[1663] (Claim 1)

[1664] A means for a user to input information about family composition, physical condition, weather, recent meal content, and emotions using a terminal;

[1665] A server receives and stores data transmitted from the terminal;

[1666] means for an emotion engine to analyze emotion information from the input data and transmit the information to the server;

[1667] A means for the generative AI model to analyze the stored data and emotional information and learn the user's preferences and disliked ingredients;

[1668] A means for generating an optimal menu based on the weather, physical condition, emotions, cooking time, etc. of the day in response to a user's request;

[1669] A means for transmitting the generated menu to a user terminal and displaying it;

[1670] A means for the user to input into the terminal his / her satisfaction level and feedback regarding the provided menu and transmit the input to the server;

[1671] means for storing and analyzing said feedback to update the generative AI model and emotion engine;

[1672] A system including:

[1673] (Claim 2)

[1674] The system according to claim 1, further comprising a user terminal for inputting information about family composition, physical condition, weather, recent meal contents, and emotions.

[1675] (Claim 3)

[1676] The system of claim 1, wherein the generative AI model includes means for considering ingredients and cooking methods appropriate to the baby's age when suggesting baby food.

[1677] "Application example 2 when combining emotion engines"

[1678] (Claim 1)

[1679] A means for the user to input information about family composition, physical condition, weather, recent meal contents, and emotions using a terminal;

[1680] A server receives and stores data transmitted from the terminal;

[1681] A means for the generative AI model and emotion engine to analyze the stored data and learn the user's preferences and disliked ingredients;

[1682] A means for generating an optimal menu based on the weather, physical condition, cooking time, and emotions of the day in response to a user's request;

[1683] A means for transmitting the generated menu to a user terminal and displaying it;

[1684] A means for inputting satisfaction and feedback regarding the menu created by the user into the terminal and transmitting the information to the server;

[1685] means for storing and analyzing said feedback and updating a generative AI model;

[1686] A system including:

[1687] (Claim 2)

[1688] 10. The system of claim 1, further comprising a user terminal for inputting user information such as user composition, physical condition, weather, recent meal content, and emotions.

[1689] (Claim 3)

[1690] 2. The system of claim 1, wherein the generative AI model and emotion engine include means for considering age-appropriate ingredients and cooking methods when suggesting baby food. [Explanation of symbols]

[1691] 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 a user to input information about family composition, physical condition, weather, and recent meal content using a terminal; A server receives and stores data transmitted from the terminal; A means for the generative AI model to analyze the stored data and learn the user's preferences and disliked ingredients; A means for generating an optimal menu based on the weather, physical condition, cooking time, etc. of the day in response to a user's request; A means for transmitting the generated menu to a user terminal and displaying it; A means for inputting satisfaction and feedback regarding the menu created by the user into the terminal and transmitting the information to the server; means for storing and analyzing said feedback and updating a generative AI model; A system including:

2. The system according to claim 1, further comprising a user terminal for inputting information about family composition, physical condition, weather, and recent meal content.

3. The system of claim 1 , wherein the generative AI model includes means for considering ingredients and cooking methods according to age when suggesting baby food.

Images