System

Abstract

To provide a system.SOLUTION: The system includes: means of collecting multiple opinions and generating a meal proposal that reflects the collected opinions; means of transmitting to users the generated meal proposal; means of recognizing the feelings of users about the transmitted meal proposal; and means of generating a meal proposal that everyone agrees based on the recognized feelings.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] When making food choices in a group, it is difficult to ensure that everyone's opinions are heard, which can result in some people's opinions being ignored, and it is difficult to take into account individual dietary preferences and restrictions. [Means for solving the problem]

[0005] By providing a means to make meal suggestions that reflect the opinions of multiple people and a means to make suggestions that take everyone's opinions into consideration, it enables meal choices that everyone can agree on. Each individual's dietary preferences and restrictions are collected, and based on this, meal suggestions that everyone can agree on are generated. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

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

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

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

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0021] 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.

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

[0023] 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.

[0024] 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.

[0025] 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.

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

[0027] "Example 1"

[0028] One embodiment of the present invention is a system that collects individual dietary preferences and restrictions through a user interface, where the user inputs and the system collects their preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[0029] "Example 2"

[0030] There is a system that generates meal suggestions that everyone can agree on based on the collected information.

[0031] The system suggests the most agreeable meal options, taking into account everyone's preferences and restrictions. For example, if everyone likes fish and no one is allergic to it, it might suggest a fish restaurant.

[0032] "Example 3"

[0033] There is a system that presents suggested meal options to users and leaves the final choice to the user. Specifically, the system presents the suggested options on a user interface, and the user makes the final choice from among them. This allows for a fair selection process that reflects everyone's opinions.

[0034] The processing flow of each embodiment will be described below.

[0035] "Example 1"

[0036] Step 1: The user accesses the system's user interface.

[0037] Step 2: The user enters their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[0038] Step 3: The system collects the information entered by the user and stores it in a database.

[0039] "Example 2"

[0040] Step 1: The system retrieves everyone's dietary preferences and restrictions from a database.

[0041] Step 2: Based on the information obtained, the system generates meal options that are predicted to be most likely to gain consensus.

[0042] Step 3: Present the generated meal options to the user.

[0043] "Example 3"

[0044] Step 1: The user reviews the meal options presented by the system.

[0045] Step 2: The user makes their final meal selection.

[0046] Step 3: The system receives the user's selection and stores the results.

[0047] Example 1

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

[0049] Conventional meal plan proposal systems have difficulty in properly reflecting each individual's dietary preferences and restrictions, making it difficult to provide a meal plan that satisfies the user. In addition, when generating a meal plan that takes into account the opinions of multiple people, it is difficult to make proposals that everyone can agree on.

[0050] 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.

[0051] In this invention, the server includes a means for collecting each individual's dietary preferences and restrictions, a means for storing the collected information in a database, a means for sending a prompt to the generative AI model based on the stored information, a means for the generative AI model to generate a meal plan suitable for the user, and a means for displaying the generated meal plan to the user. This makes it possible to provide a meal plan that appropriately reflects each individual's dietary preferences and restrictions. Furthermore, when generating a meal plan that takes into account the opinions of multiple people, it is possible to make proposals that are acceptable to all.

[0052] "Means for collecting individual dietary preferences and restrictions" means a means for providing an interface for users to input their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[0053] The "means for storing collected information in a database" refers to a means for storing information about dietary preferences and restrictions entered by a user in a database.

[0054] "Means for sending prompt sentences to the generative AI model based on stored information" refers to means for generating and sending appropriate prompt sentences to the generative AI model based on user information stored in the database.

[0055] "Means by which the generative AI model generates a meal plan appropriate for the user" refers to means by which the generative AI model analyzes the prompt sentence and generates an appropriate meal plan based on the user's dietary preferences and restrictions.

[0056] "Means for displaying the generated meal plan to the user" refers to means for displaying the meal plan generated by the generative AI model on the user's interface.

[0057] This invention is a system for collecting individual dietary preferences and restrictions and generating an appropriate meal plan based on the collected information. The system includes a user interface for a user to input the dietary preferences and restrictions, a server for storing the collected information in a database, a server for sending prompts to a generative AI model based on the stored information, a means for the generative AI model to generate a meal plan appropriate for the user, and a means for displaying the generated meal plan to the user.

[0058] Hardware and software used

[0059] Server: Uses the Django framework to host the web application.

[0060] Database: PostgreSQL is used to store user information.

[0061] Generative AI model: Use an appropriate generative AI model to generate the meal plan for the user.

[0062] Specific operation of the system

[0063] Users access the system through a web browser and enter their dietary preferences and restrictions into the user interface. Specifically, users enter allergy information, likes and dislikes, health restrictions, etc. For example, suppose a user enters the following information:

[0064] Allergy Information: Nuts

[0065] Likes and dislikes: I hate tomatoes

[0066] Health Restrictions: Low Carbohydrate

[0067] This information is entered as follows:

[0068] Allergy Information: Nuts

[0069] Likes and dislikes: I hate tomatoes

[0070] Health Restrictions: Low Carb

[0071] The device sends the information entered by the user to a server, which stores the received information in a database that is later used to generate the user's meal plan.

[0072] The server then sends prompts to the generative AI model based on the stored information, including the user's dietary preferences and restrictions. For example, the following prompts might be generated:

[0073] Generate an appropriate meal plan based on the user's dietary preferences and restrictions. Here is the user's information:

[0074] Allergy Information: Nuts

[0075] Likes and dislikes: I hate tomatoes

[0076] Health Restrictions: Low Carbohydrate

[0077] The generative AI model generates a meal plan suitable for the user based on the received prompt. The generated meal plan is returned to the server, which displays the generated meal plan in the user interface. The user can view the meal plan through their browser.

[0078] In this way, it is possible to provide meal plans that appropriately reflect each individual's dietary preferences and restrictions.In addition, when generating meal plans that take into account the opinions of multiple people, it is possible to make proposals that everyone can agree on.

[0079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0080] Step 1:

[0081] The user inputs their dietary preferences and restrictions.

[0082] Users access the system through a web browser and enter their dietary preferences and restrictions into the user interface, including allergy information, likes and dislikes, and health restrictions.

[0083] Input: User's dietary preferences and restrictions (e.g., nut allergy, dislike of tomatoes, low carb)

[0084] Output: The entered information is displayed in the form.

[0085] Specific Action: A user enters "nuts" in the "Allergy Information" field, "dislikes tomatoes" in the "Likes and Dislikes" field, and "low carb" in the "Health Restrictions" field.

[0086] Step 2:

[0087] The terminal transmits the input information to the server.

[0088] When the user completes the input and clicks the send button, the terminal sends the input information to the server as an HTTP POST request.

[0089] Input: User-entered dietary preferences and restrictions

[0090] Output: HTTP POST request sent to the server

[0091] Specific operation: The device sends a POST request to the " / submit_preferences" endpoint and includes the information entered by the user in the request body.

[0092] Step 3:

[0093] The server stores the received information in a database.

[0094] The server processes the incoming requests and stores the user's dietary preferences and restrictions in a database, which uses PostgreSQL.

[0095] Input: The user's dietary preferences and restrictions received by the server.

[0096] Output: User information stored in the database

[0097] What happens: The server extracts the user's information from the request body and runs an SQL query to connect to a PostgreSQL database and save the information.

[0098] Step 4:

[0099] The server sends a prompt to the generative AI model based on the stored information.

[0100] The server uses the stored information to generate prompts to send to the generative AI model, including the user's dietary preferences and restrictions.

[0101] Input: User information stored in the database

[0102] Output: The prompt sent to the generative AI model

[0103] Specific operation: The server retrieves user information from the database, generates a prompt sentence based on the retrieved information, and sends the generated prompt sentence to the generative AI model.

[0104] Step 5:

[0105] A generative AI model generates a meal plan tailored to the user.

[0106] The generative AI model generates a meal plan suitable for the user based on the received prompt, and the generated meal plan is returned to the server.

[0107] Input: The prompt sent to the generative AI model

[0108] Output: The generated meal plan

[0109] Specific operation: The generative AI model analyzes the prompt, generates a meal plan based on the user's preferences and restrictions, and returns the generated meal plan to the server.

[0110] Step 6:

[0111] The server displays the generated meal plan to the user.

[0112] The server receives the meal plan returned by the generative AI model and displays it in a user interface, where the user can view the meal plan through their browser.

[0113] Input: Meal plan returned from a generative AI model

[0114] Output: Meal plan displayed in the user interface

[0115] Specific operation: The server receives the meal plan returned by the generative AI model, converts the meal plan into HTML format, sends the converted HTML to the user's browser, and the user views the meal plan in the browser.

[0116] (Application example 1)

[0117] Next, a description will be given of Application Example 1 of Embodiment 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."

[0118] Conventional food delivery systems have difficulty proposing menus that fully consider the dietary preferences and restrictions of individual users, and it has been particularly difficult to make proposals that reflect the opinions of multiple people or that everyone can agree on. Furthermore, users have to input their own dietary preferences and restrictions, which is time-consuming, and there has been a lack of a way to efficiently collect and manage this information.

[0119] 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.

[0120] In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple users, means for making suggestions that take into account the opinions of all users, means for providing services for groups, means for collecting each individual's dietary preferences and restrictions, means for proposing an optimal menu based on the collected information, and means for ordering from the suggested menu. This makes it possible to efficiently collect users' dietary preferences and restrictions and to propose optimal menus for each user and the entire group.

[0121] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that makes meal suggestions that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[0122] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively evaluates the collected information about each individual's dietary preferences and restrictions, and generates meal suggestions that everyone can agree on.

[0123] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[0124] "Means for collecting individual dietary preferences and restrictions" refers to a function that allows users to input their own dietary preferences and restrictions (such as allergy information, likes and dislikes, health restrictions, etc.) and the system collects them.

[0125] "Means for suggesting the most suitable menu based on collected information" refers to a function for selecting and suggesting the most suitable menu based on the user's collected dietary preferences and restrictions.

[0126] The "means of ordering from the proposed menu" is a function that allows the user to select from the proposed menu and actually place an order.

[0127] As an embodiment of the present invention, the following system is constructed.

[0128] System Configuration

[0129] The system consists of a server, user terminals, and a network. The server plays a central role in collecting users' dietary preferences and restrictions and proposing optimal menus. The user terminals are devices such as smartphones and tablets that provide an interface for users to input their dietary preferences and restrictions.

[0130] Hardware and software used

[0131] Hardware: Servers, smartphones, tablets

[0132] Software: Python 3.x, JSON library, database management system (e.g., MySQL®)

[0133] Data processing and calculation

[0134] 1. Collecting your dietary preferences and restrictions:

[0135] Through the user terminal, the user inputs their dietary preferences and restrictions (allergy information, likes and dislikes, health restrictions, etc.), which are sent to the server in JSON format and stored in a database.

[0136] 2. Optimal menu suggestions:

[0137] The server selects the optimal menu based on the user's dietary preferences and restrictions. Specifically, it filters out menus that do not include the user's allergies or disliked foods, and prioritizes menus that include the user's favorite foods.

[0138] 3. Menu Viewing and Ordering:

[0139] The suggested menu is displayed on the user's terminal, and the user can select from it and place an order. The order information is then sent back to the server for processing.

[0140] Specific examples

[0141] For example, if a user inputs "tomato" as their allergy information, "chicken" as their favorite food, and "fish" as their least favorite food, the server will suggest the most suitable menu based on this information. Specifically, it may suggest a menu item such as "chicken curry."

[0142] Prompt Sentence Examples

[0143] An example of a prompt to be input to the generative AI model is as follows:

[0144] Build an application that collects a user's dietary preferences and restrictions and suggests the best menu items. Users enter allergies, likes, dislikes, and health restrictions, and filter the menu items based on this. For example, if a user enters "I'm allergic to tomatoes," "I like chicken," and "I don't like fish," suggest "Chicken Curry."

[0145] In this way, users' dietary preferences and restrictions can be efficiently collected and optimal menus can be suggested for individual users and for the group as a whole.

[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0147] Step 1:

[0148] The user uses the device to input their dietary preferences and restrictions. Specifically, they input allergy information, favorite foods, disliked foods, health restrictions, etc. The input data is sent to the server in JSON format. Examples of input data include "allergy information: tomato," "favorite food: chicken," and "disliked food: fish."

[0149] Step 2:

[0150] The server receives the JSON format data sent from the device and stores it in a database. Specifically, it stores allergy information, likes and dislikes, and health restrictions along with the user ID in the database. The input data is in JSON format, and the output is saved in the database.

[0151] Step 3:

[0152] The server selects the optimal menu based on the user's dietary preferences and restrictions stored in the database. Specifically, it filters out menus that do not include allergy information or disliked foods, and prioritizes menus that include favorite foods. The input is the user's preferences and restrictions obtained from the database, and the output is a filtered menu list.

[0153] Step 4:

[0154] The server sends the filtered menu list to the user terminal. Specifically, it sends the selected menu to the terminal in JSON format. The input is the filtered menu list, and the output is the transmission to the terminal.

[0155] Step 5:

[0156] The user selects the desired menu from the menu list displayed on the terminal and places an order. Specifically, by confirming the selected menu and pressing the order button, the order information is sent to the server. The input is the menu selected by the user, and the output is the order information sent to the server.

[0157] Step 6:

[0158] The server processes the received order information and confirms the order. Specifically, it stores the order information in a database and arranges cooking and delivery as necessary. The input is the order information sent by the user, and the output is the confirmation of the order and related arrangements.

[0159] Through the above steps, the optimal menu is proposed and ordered, taking into consideration the user's dietary preferences and restrictions.

[0160] Example 2

[0161] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0162] Conventional meal recommendation systems have difficulty effectively reflecting the opinions and preferences of multiple people, making it difficult to make recommendations that everyone can agree on. Furthermore, there is a problem with insufficient data collection and analysis to take into account individual dietary preferences and restrictions, resulting in low accuracy of recommendations.

[0163] 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.

[0164] In this invention, the server includes a means for inputting user information, a means for collecting and storing the input user information, a means for analyzing the collected user information, a means for generating meal suggestions based on the analysis results, and a means for providing the generated suggestions to the user, thereby effectively reflecting the opinions and preferences of multiple people and making meal suggestions that everyone can agree on.

[0165] A "means for inputting user information" is a device or software that provides an interface for a user to input their dietary preferences and restrictions.

[0166] The "means for collecting and storing input user information" refers to a device or software for transmitting the information input by the user to a server and storing it in a database.

[0167] "Means for analyzing collected user information" refers to a device or software that performs data analysis based on collected user information and generates results that take into account the user's preferences and limitations.

[0168] The "means for generating meal suggestions based on the analysis results" refers to a device or software for generating optimal meal suggestions for a user based on the results of the data analysis.

[0169] The "means for providing generated suggestions to a user" is a device or software that transmits the generated meal suggestions to a user's terminal and allows the user to review the suggestions.

[0170] A "generative AI model" is an artificial intelligence model used to analyze data and generate optimal suggestions, taking into account user preferences and limitations.

[0171] A "prompt" is an instruction given to a generative AI model, containing instructions for achieving a specific result.

[0172] MODE FOR CARRYING OUT THE INVENTION

[0173] The present invention relates to a system that takes into account the dietary preferences and restrictions of users and generates meal proposals that everyone can agree on. A specific embodiment of this system will be described below.

[0174] 1. System Configuration

[0175] The system consists of the following major components:

[0176] A way to enter user information

[0177] A means of collecting and storing input user information

[0178] A means of analyzing collected user information

[0179] A means of generating meal suggestions based on the analysis results

[0180] A means for providing generated suggestions to the user

[0181] 2. Hardware and Software Used

[0182] Server: A central processing unit for collecting, storing, analyzing data, and generating recommendations. It uses MySQL as its database.

[0183] Device: The device (smartphone, PC, etc.) where the user enters information and receives suggestions.

[0184] Generative AI model: An artificial intelligence model (e.g., GPT-4®) used to analyze data and generate optimal recommendations, taking into account user preferences and limitations.

[0185] 3. System Operation

[0186] Enter your user information:

[0187] Users use the terminal to input their dietary preferences and restrictions. For example, User A inputs, "I like fish dishes, I have no allergies."

[0188] Data collection and storage:

[0189] The terminal sends the information entered by the user to the server. The server saves the received data in a database (MySQL). For example, User A's information "I like fish dishes, I have no allergies" is saved in the database.

[0190] Data analysis:

[0191] The server retrieves all user information stored in the database and inputs it into a generative AI model (GPT-4). The generative AI model analyzes the data, taking into account the user's preferences and limitations. For example, it verifies that everyone likes fish dishes and that no one is allergic to fish.

[0192] Proposal generation:

[0193] The server generates meal recommendations that are most likely to gain consensus based on the analysis results obtained from the generative AI model, such as suggesting restaurants serving fish.

[0194] Providing suggestions:

[0195] The server sends the generated suggestions to the user's device. The user can check and select the suggestions through the device. For example, user A checks and selects "fish restaurants" on the device.

[0196] 4. Examples of concrete examples and prompts

[0197] Examples:

[0198] User A: I like fish dishes and I don't have any allergies

[0199] User B: I like fish dishes and I don't have any allergies

[0200] User C: I like fish dishes and I have no allergies

[0201] In this case, the server suggests a fish restaurant.

[0202] Example prompt sentence:

[0203] Generate meal suggestions that everyone can agree on, taking into account the user's dietary preferences and restrictions. Use the following information to make suggestions:

[0204] User A: I like fish dishes and I don't have any allergies

[0205] User B: I like fish dishes and I don't have any allergies

[0206] User C: I like fish dishes and I have no allergies

[0207] In this way, meal suggestions that everyone can agree on are generated and provided to the user.

[0208] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0209] Step 1:

[0210] Entering user information

[0211] Users use the terminal to input their dietary preferences and restrictions. For example, User A inputs, "I like fish dishes, I have no allergies."

[0212] Input: User's dietary preferences and restrictions (e.g., "I like fish dishes, no allergies")

[0213] Output: The entered user information is saved on the device.

[0214] Step 2:

[0215] Data collection and storage

[0216] The terminal transmits the information entered by the user to the server.

[0217] The server stores the received data in a database (MySQL). For example, user A's information "likes fish dishes, no allergies" is stored in the database.

[0218] Input: Information entered by the user (e.g., "I like fish dishes, I have no allergies")

[0219] Output: User information stored in the database

[0220] Step 3:

[0221] Analyzing the data

[0222] The server retrieves all user information stored in a database.

[0223] The server uses a generative AI model (GPT-4) to analyze the data, taking into account user preferences and restrictions, for example, ensuring that everyone likes fish dishes and that no one is allergic to fish.

[0224] Input: All user information stored in the database

[0225] Output: Analysis results from the generative AI model (e.g., "Everyone likes fish dishes, and no one is allergic to fish")

[0226] Step 4:

[0227] Proposal Generation

[0228] The server generates meal recommendations that are most likely to gain consensus based on the analysis results obtained from the generative AI model, such as suggesting restaurants serving fish.

[0229] Input: Analysis results from generative AI model

[0230] Output: Dining suggestions (e.g. "fish restaurants")

[0231] Step 5:

[0232] Providing suggestions

[0233] The server transmits the generated proposal to the user's terminal.

[0234] The user can check the suggestions through the terminal and select one. For example, user A checks and selects "fish restaurants" on the terminal.

[0235] Input: Dining suggestions (e.g., "fish restaurants")

[0236] Output: Proposal displayed on the user's device

[0237] In this way, meal suggestions that everyone can agree on are generated and provided to the user.

[0238] (Application example 2)

[0239] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0240] With conventional food delivery services, it was difficult to suggest meals that took into account the preferences and dietary restrictions of multiple people, making it difficult to find options that would satisfy everyone. Furthermore, manual adjustments were required, making it difficult to make efficient suggestions. This made meal selections for groups cumbersome, resulting in lower satisfaction.

[0241] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0242] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for generating meal suggestions using a generative AI model, and a means for generating prompt sentences and making suggestions, thereby enabling efficient and satisfying meal suggestions that take into account the preferences and dietary restrictions of multiple people.

[0243] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that suggests meal options that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[0244] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively analyzes the collected information about each individual's dietary preferences and restrictions, and generates meal suggestions that everyone can agree on.

[0245] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[0246] "Means for generating meal suggestions using a generative AI model" means a function that uses an artificial intelligence model to automatically generate meal suggestions that take into account a user's preferences and restrictions.

[0247] "Means for generating prompt sentences and making suggestions" is a function that generates sentences to give appropriate instructions to the generative AI model based on the information input by the user, and makes meal suggestions based on the results.

[0248] To implement this invention, a server, a user terminal, and a generative AI model are used. Specific embodiments are described below.

[0249] System Configuration

[0250] The server includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing services for groups, means for generating meal suggestions using a generative AI model, and means for generating prompt sentences and making suggestions.

[0251] The user terminal is a mobile device such as a smartphone or tablet that provides an interface for the user to input their dietary preferences and restrictions.

[0252] Program processing

[0253] The server receives each individual's dietary preferences and restrictions from the user's device and stores them in a database. The server then uses a generative AI model to generate meal suggestions that everyone can agree on. The server also generates prompts and provides appropriate instructions to the generative AI model.

[0254] The hardware used is a computer system with a high-performance processor and large memory capacity as the server, and common smartphones and tablets as the user devices. The software used is the OpenAI (registered trademark) API for the generative AI model, and the program is implemented in Python.

[0255] Specific examples

[0256] For example, suppose user A likes fish and vegetables, dislikes meat, and has a nut allergy. User B likes meat and fish, dislikes vegetables, and has no allergies. User C likes vegetables and fruit, dislikes fish, and is allergic to dairy products. Based on this information, the server generates a prompt like the following:

[0257] Example prompt sentence:

[0258] Generate meal suggestions that everyone can agree on, taking into account user preferences and restrictions. User info: [{"name": "User A", "likes": ["fish", "vegetables"], "dislikes": ["meat"], "allergies": ["nuts"]}, {"name": "User B", "likes": ["meat", "fish"], "dislikes": ["vegetables"], "allergies": []}, {"name": "User C", "likes": ["vegetables", "fruit"], "dislikes": ["fish"], "allergies": ["dairy"]}]

[0259] This prompt is then fed into a generative AI model to generate satisfying meal suggestions, which are then sent to the user's device and displayed to the user.

[0260] In this way, it becomes possible to propose efficient and satisfying meals that take into account the preferences and dietary restrictions of multiple people.

[0261] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0262] Step 1:

[0263] The user uses the terminal to input their dietary preferences and restrictions.

[0264] Input: User preferences (e.g., fish, vegetables), disliked ingredients (e.g., meat), allergy information (e.g., nut allergy)

[0265] Output: The entered information is sent from the terminal to the server.

[0266] Specific actions: The user enters their dietary preferences and restrictions through the smartphone app interface and presses the submit button.

[0267] Step 2:

[0268] The server receives each individual's dietary preferences and restriction information sent from the device and stores it in a database.

[0269] Input: User preferences and restrictions sent from the device

[0270] Output: User information stored in the database

[0271] Specific operation: The server analyzes the received data and stores each user's information in a database.

[0272] Step 3:

[0273] The server retrieves each individual's dietary preferences and restrictions from a database and generates a prompt.

[0274] Input: User information stored in the database

[0275] Output: Generated prompt statement

[0276] Specific operation: The server uses a Python program to generate a prompt based on the user information. For example, it generates the following prompt:

[0277] Generate meal suggestions that everyone can agree on, taking into account user preferences and restrictions. User info: [{"name": "User A", "likes": ["fish", "vegetables"], "dislikes": ["meat"], "allergies": ["nuts"]}, {"name": "User B", "likes": ["meat", "fish"], "dislikes": ["vegetables"], "allergies": []}, {"name": "User C", "likes": ["vegetables", "fruit"], "dislikes": ["fish"], "allergies": ["dairy"]}]

[0278] Step 4:

[0279] The server inputs prompts into the generative AI model to generate meal suggestions.

[0280] Input: Generated prompt statement

[0281] Output: Meal suggestions from a generative AI model

[0282] How it works: The server uses the OpenAI API to send the generated prompt to the AI ​​model and receive meal suggestions.

[0283] Step 5:

[0284] The server transmits the generated meal suggestions to the user terminal.

[0285] Input: Meal suggestions from a generative AI model

[0286] Output: Meal suggestions displayed on the user's device

[0287] Specific operation: The server sends the received meal suggestions to the user's device, allowing the user to review the suggestions through the app.

[0288] Step 6:

[0289] The user uses the terminal to review the suggested meals and place an order.

[0290] Input: Meal suggestions sent by the server

[0291] Output: User's order information

[0292] Specific actions: The user reviews the suggested meals through the app and presses the order button to confirm the order.

[0293] In this way, it is possible to propose and order meals that are efficient and satisfying, taking into account the preferences and dietary restrictions of multiple people.

[0294] Example 3

[0295] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0296] Conventional meal recommendation systems have difficulty providing meal options that fully consider individual users' preferences and allergy information, making it difficult to provide meal options that satisfy everyone. Furthermore, they lack a mechanism for effectively reflecting users' selection results, resulting in problems with reduced recommendation accuracy and satisfaction. This has led to an increasing need for a fair and personalized meal recommendation system to increase user satisfaction.

[0297] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0298] In this invention, the server includes means for receiving requests from users, means for collecting the user's past dietary history and allergy information, means for generating prompt sentences to be input to the generative AI model based on the collected data, means for generating meal options using the generative AI model, means for sending the generated meal options to a user interface, means for displaying the meal options on the user interface, means for sending the user's selection results to the server, and means for saving the user's selection results in a database. This enables personalized meal suggestions that take into account the individual preferences and restrictions of each user, thereby realizing fair selections that everyone can agree on.

[0299] The "means for receiving a request from a user" is a function that allows a user to send a request for meal suggestions to the system and for the server to receive the request.

[0300] "Means for collecting the user's past dietary history and allergy information" is a function for retrieving and collecting information about the meals and allergies selected by the user in the past from a database.

[0301] The "means for generating prompt sentences to be input into the generative AI model" is a function that creates instructions (prompt sentences) for the generative AI model to generate appropriate meal options based on collected data.

[0302] "Means for generating meal options using a generative AI model" refers to a function for inputting a prompt sentence into a generative AI model and generating multiple meal options as a result.

[0303] "Means for transmitting the generated meal options to a user interface" means a function for transmitting the meal options generated by the generative AI model to a user interface so that the user can review them.

[0304] The "means for displaying meal options on the user interface" is a function for visually displaying the meal options generated on the user interface so that the user can confirm them.

[0305] The "means for transmitting the results of the user's selection to the server" is a function for transmitting the results of the meal the user has selected on the user interface to the server.

[0306] "Means for saving the user's selection results in a database" is a function for saving the results of the user's meal selection in a database and reflecting them in future suggestions.

[0307] The present invention is a system that provides a user with personalized meal suggestions and leaves the final selection up to the user. Specific embodiments of this system will be described below.

[0308] Hardware and Software Configuration

[0309] server

[0310] The server receives user requests and has a database for collecting the user's past dietary history and allergy information. The server generates meal options using a generative AI model and sends the generated options to the user interface. Specifically, the server uses the following software and hardware:

[0311] Database Management System (DBMS): Stores and manages users' past dietary history and allergy information.

[0312] Generative AI model: A machine learning model that generates meal options based on user data.

[0313] Web Server: A server that sends data to the user interface.

[0314] Terminal

[0315] The terminal is a device used by the user that receives the meal options sent from the server and displays them on a user interface. The terminal uses software such as:

[0316] Web browser or mobile application: Provides the user interface and allows users to view and select their meal options.

[0317] User

[0318] The user accesses the system through a terminal and makes a final selection from the proposed meal options. The user's selection is sent to the server through the terminal and stored in a database.

[0319] Data processing and calculation

[0320] When the server receives a request from a user, it first collects the user's past dietary history and allergy information from a database. Then, based on the collected data, it generates a prompt sentence to be input into the generative AI model. For example, it generates a prompt sentence like the following:

[0321] Example prompt sentence:

[0322] "Generate suggestions for tonight's dinner, taking into account the user's past eating history and allergy information."

[0323] Based on this prompt, the generative AI model generates meal options such as "curry rice," "chicken salad," and "pasta." The generated options are sent from the server to the user interface.

[0324] The device receives the meal options sent from the server and displays them on the user interface. The user makes a final selection from the displayed options and sends the result to the server via the device. The server stores the user's selection in a database and reflects it in future suggestions.

[0325] Specific examples

[0326] For example, if a user requests "today's dinner suggestions," the server might do the following:

[0327] 1. Request received: The server receives a request for "today's dinner suggestions."

[0328] 2. Data collection: The server collects the user's past dietary history and allergy information from the database.

[0329] 3. Prompt generation: The server generates a prompt saying, "Please generate suggestions for today's dinner, taking into account the user's past eating history and allergy information."

[0330] 4. Option generation: The server inputs the prompt sentence into the generative AI model, generating options such as "curry rice," "chicken salad," and "pasta."

[0331] 5. Sending choices: The server sends the generated choices to the user interface.

[0332] 6. Display options: The terminal displays the received options on the user interface.

[0333] 7. User selection: The user selects "curry rice."

[0334] 8. Sending selection results: The device sends the user's selection results to the server.

[0335] 9. Data storage: The server stores the user's selection in a database for future recommendations.

[0336] In this way, the system provides personalized meal suggestions to the user and leaves the final selection up to the user, thereby achieving fair and satisfying meal selection. The flow of the specification process in Example 3 will be described with reference to FIG. 15.

[0337] Step 1:

[0338] Receiving a user request

[0339] Subject: Server

[0340] The server receives a request from a user. For example, a request for "tonight's dinner suggestions" is input. The server analyzes this request and extracts the information needed for the next processing step. The input is the user's request, and the output is the analyzed request information.

[0341] Step 2:

[0342] Data collection

[0343] Subject: Server

[0344] The server collects the user's past dietary history and allergy information from a database. The input is the parsed request information, and the output is the collected user's dietary history and allergy information. Specifically, it executes a database query to obtain the required data.

[0345] Step 3:

[0346] Generate prompt statement

[0347] Subject: Server

[0348] The server generates a prompt sentence to be input into the generative AI model based on the collected data. The input is the collected user's dietary history and allergy information, and the output is the generated prompt sentence. Specifically, it creates a prompt sentence in the format "Please generate suggestions for tonight's dinner, taking into account the user's past dietary history and allergy information."

[0349] Step 4:

[0350] Meal Choice Generation

[0351] Subject: Server

[0352] The server inputs a prompt sentence into the generative AI model to generate meal options. The input is the generated prompt sentence, and the output is the generated meal options. Specifically, the generative AI model generates options such as "curry rice," "chicken salad," and "pasta."

[0353] Step 5:

[0354] Submit your choices

[0355] Subject: Server

[0356] The server sends the generated meal options to the user interface. The input is the generated meal options, and the output is the data sent to the user interface. Specifically, the data is sent using an HTTP request.

[0357] Step 6:

[0358] Displaying options

[0359] Subject: Terminal

[0360] The device receives the meal options sent from the server and displays them on a user interface. The input is the data sent from the server, and the output is the meal options displayed on the user interface. Specifically, the options are displayed in a web browser or a mobile application.

[0361] Step 7:

[0362] User Selection

[0363] Subject: User

[0364] The user checks the proposed meal options through the device's user interface and makes a final selection. The input is the meal options displayed on the user interface, and the output is the user's selection. Specifically, the user selects "curry rice."

[0365] Step 8:

[0366] Sending the selection results

[0367] Subject: Terminal

[0368] The terminal sends the results of the user's selection to the server. The input is the user's selection, and the output is the data sent to the server. Specifically, the data is sent using an HTTP request.

[0369] Step 9:

[0370] Saving and updating data

[0371] Subject: Server

[0372] The server receives the user's final selection and stores it in a database. The input is the data sent to the server, and the output is the selection stored in the database. Specifically, it adds a new record to the database and reflects it in future suggestions.

[0373] (Application example 3)

[0374] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0375] With conventional food delivery systems, when multiple people order a meal together, it is difficult to fairly reflect everyone's opinions. It is also difficult to propose a meal that satisfies everyone while taking into account each individual's dietary preferences and restrictions. This makes meal selection for groups complicated, resulting in a decrease in satisfaction.

[0376] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0377] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for presenting suggested meal options on a user interface so that the user can make a final selection from among them, and a means for determining the option that receives the most votes as the final selection. This makes it possible to make meal suggestions that fairly reflect the opinions of all people and take into account each individual's preferences and restrictions, making it possible to smoothly select meals for a group.

[0378] "Means for providing meal suggestions that reflect the opinions of multiple users" refers to a function that generates appropriate meal options based on dietary preferences and restrictions collected from multiple users.

[0379] "A means of making suggestions that take everyone's opinions into consideration" is a function that makes meal suggestions that everyone can agree on based on the opinions and restrictions collected from each user.

[0380] A "means for providing services for groups" is a function that provides services that are intended for use by multiple users together.

[0381] "A means for presenting suggested meal options on a user interface and allowing the user to make a final selection" refers to a function that displays meal options generated by the system to the user and provides an interface for the user to make a selection from among them.

[0382] The "means of determining the option with the most votes as the final selection" is a function that aggregates the results of users' votes and determines the option with the most votes as the final selection.

[0383] To implement the present invention, a system including a server, a user terminal, and a user interface is required. Specific embodiments are described below.

[0384] System Configuration

[0385] 1. Server:

[0386] The server includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing service for groups, means for presenting suggested meal options on a user interface and allowing the user to make a final selection from among them, and means for determining the option that receives the most votes as the final selection.

[0387] 2. User Device:

[0388] The user terminal is a device such as a smartphone or tablet, and is used by the user to check meal options and cast a vote through an interface provided by the server.

[0389] 3. User Interface:

[0390] The user interface provides a screen for the user to review and vote on the suggested meal options. The interface is designed to be easy for the user to operate.

[0391] Program processing

[0392] The server performs the following process.

[0393] 1. Menu suggestions:

[0394] The server randomly selects three menus from predefined menu options and presents them to the user's device using the Python random.sample module.

[0395] 2. Vote Collection:

[0396] The server collects votes from each user. The user makes a selection from a menu of suggestions and sends that selection to the server. If an invalid selection is made, the user is prompted to select again.

[0397] 3. Final Selection:

[0398] The server tallies the collected votes and determines the menu with the most votes as the final choice, using the Python collections.Counter module.

[0399] Specific examples

[0400] For example, when user 1, user 2, and user 3 order a meal together, the server suggests "pizza," "sushi," and "curry." Each user votes for their preference, and the menu with the most votes is selected as the final menu item.

[0401] Example prompt sentence:

[0402] "User 1, please choose from the following menu: ['Pizza', 'Sushi', 'Curry']:"

[0403] "User 2, please choose from the following menu: ['Pizza', 'Sushi', 'Curry']:"

[0404] "User 3, please choose from the following menu: ['Pizza', 'Sushi', 'Curry']:"

[0405] In this way, it is possible to fairly reflect everyone's opinions and propose meals that take into account each individual's preferences and restrictions, making it easier for groups to choose meals.

[0406] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0407] Step 1:

[0408] The server randomly selects three menus from a predefined menu of options.

[0409] Input: A list of predefined menu options.

[0410] Data processing: Using Python's random.sample module, three menus are randomly selected from the list.

[0411] Output: The three selected menus.

[0412] What happens: The server reads the list of menu options and randomly selects three from it.

[0413] Step 2:

[0414] The server transmits the selected three menus to the user terminal and presents them to the user.

[0415] Input: 3 selected menus.

[0416] Data processing: Converts the selected menu into a format for display on the user interface.

[0417] Output: The menu choices displayed on the user's terminal.

[0418] Specific operation: The server converts the selected menu into a format suitable for the user interface and sends it to the user terminal, which receives it and displays it on the screen.

[0419] Step 3:

[0420] The user selects one from the presented menu and sends it to the server.

[0421] Input: The menu selected by the user.

[0422] Data processing: Converting the user's selection into a data format for sending to the server.

[0423] Output: The user's selection data that is sent to the server.

[0424] Specific operation: The user selects one item from a menu presented through the user interface and sends that selection to the server.

[0425] Step 4:

[0426] The server collects selection data from each user and prompts them to make a selection again if an invalid selection is made.

[0427] Input: Selection data submitted by each user.

[0428] Data processing: Check the validity of the selected data, and if an invalid selection is made, prompt the user to select again.

[0429] Output: A list of valid selections.

[0430] Specific operation: The server receives the selection data sent by each user and checks its validity. If any selection is invalid, it sends a message to the user prompting them to select again.

[0431] Step 5:

[0432] The server tallys the collected selection data and determines the menu with the most votes as the final selection.

[0433] Input: A list of valid selection data.

[0434] Data processing: Use the Python collections.Counter module to count the number of votes for each menu item.

[0435] Output: The menu with the most votes.

[0436] Specific operation: The server aggregates the collected selection data and counts the number of votes for each menu item. The menu item with the most votes is determined as the final selection and notified to the user.

[0437] 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.

[0438] "Example 1"

[0439] In one embodiment of the present invention, a system is provided that includes an emotion engine that recognizes a user's emotions. The system recognizes emotions from the user's facial expressions, tone of voice, text input, etc., and reflects this information in meal recommendations. For example, if a user expresses a happy emotion, the system suggests meals that are predicted to be enjoyed by the user. Alternatively, if a user expresses a sad emotion, the system suggests meals that are predicted to comfort the user.

[0440] "Example 2"

[0441] In another embodiment, a system is provided in which the means for making suggestions that take into account everyone's opinions is based on an emotion engine that recognizes users' emotions and generates meal suggestions that everyone can agree on. This system recognizes the emotions of each user and makes meal suggestions based on those emotions. For example, if everyone is expressing joy, the system suggests meals that are predicted to be liked by everyone. Also, if some users are expressing sadness, the system suggests meals that comfort the user and that other users can agree on.

[0442] "Example 3"

[0443] In yet another embodiment, a system is provided in which the means for providing group-oriented services is based on an emotion engine that recognizes the emotions of users. This system recognizes the emotions of each user and provides services based on the emotions. For example, if a user expresses joy, the system provides the user with a service that is predicted to amplify the joy. Also, if a user expresses sadness, the system provides the user with a service that is predicted to amplify the joy.

[0444] If so, provide the user with a service that is predicted to reduce sadness.

[0445] The processing flow of each embodiment will be described below.

[0446] "Example 1"

[0447] Step 1: Recognize emotions from the user's facial expressions, tone of voice, text input, etc.

[0448] Step 2: Analyze the recognized emotions and determine the user's current emotional state.

[0449] Step 3: Based on the determined emotional state, suggest meals that the user is likely to like.

[0450] Step 1: Recognize each user's emotions.

[0451] Step 2: Analyze the recognized emotions and determine each user's current emotional state.

[0452] Step 3: Generate meal suggestions that everyone can agree on based on the determined emotional state.

[0453] "Example 3"

[0454] Step 1: Recognize each user's emotions.

[0455] Step 2: Analyze the recognized emotions and determine each user's current emotional state.

[0456] Step 3: Providing services to the user based on the determined emotional state.

[0457] Example 1

[0458] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0459] Conventional meal recommendation systems have difficulty taking into account the dietary preferences and restrictions of individual users, and are unable to make suggestions that reflect the user's emotions. Therefore, in order to increase user satisfaction, meal recommendations that take into account individual preferences, restrictions, and emotions are required. It is also difficult to make meal recommendations that reflect the opinions of multiple people or that take into account the opinions of everyone. A system that can solve these issues is needed.

[0460] 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.

[0461] In this invention, the server includes means for collecting each individual's dietary preferences and restrictions, means for recognizing the user's emotions, means for generating meal suggestions based on the collected dietary preferences, restrictions, and emotion information, means for presenting the generated meal suggestions to the user, means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, and means for providing services for groups. This makes it possible to make meal suggestions that take into account the preferences, restrictions, and emotions of each individual user, and also makes suggestions that reflect the opinions of multiple people or that take into account the opinions of all people.

[0462] A "means for collecting individual dietary preferences and restrictions" is a system that includes an interface and database for users to input and collect their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[0463] The "means for recognizing user emotions" refers to a system that includes machine learning models and algorithms for analyzing and recognizing emotions from a user's facial expressions, tone of voice, text input, etc.

[0464] "Means for generating meal suggestions based on collected dietary preferences, restrictions, and emotional information" means a system that includes a generative AI model or algorithm for generating appropriate meal suggestions based on data collected from a user.

[0465] "Means for presenting generated meal suggestions to a user" refers to a system for displaying the generated meal suggestions to a user through a user interface.

[0466] The "means for making meal suggestions that reflect the opinions of multiple people" is a system that generates meal suggestions that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[0467] The "means for making suggestions that take everyone's opinions into consideration" is a system that generates meal suggestions that everyone can agree on based on the collected information about each individual's dietary preferences and restrictions.

[0468] A "group service offering" is a system for providing meal suggestions or other services that can be used by multiple users together.

[0469] The present invention relates to a meal recommendation system that takes into account a user's dietary preferences, dietary restrictions, and emotions. Specific embodiments of this system will be described below.

[0470] System configuration

[0471] This system consists of three main components: a server, a terminal, and a user.

[0472] server

[0473] The server has the following functions:

[0474] 1. Data collection: Collect each individual's dietary preferences and restrictions through a user interface. Use a relational database such as MySQL or PostgreSQL.

[0475] 2. Emotion Recognition: Use machine learning frameworks such as TENSORFLOW® and PyTorch to recognize emotions from the user's facial expressions, tone of voice, text input, etc.

[0476] 3. Meal suggestion generation: Based on the collected data, meal suggestions are generated using a generative AI model (e.g., OpenAI's GPT-3®).

[0477] 4. Providing suggestions: The generated meal suggestions are sent to the terminal to be presented to the user.

[0478] Terminal

[0479] A terminal is a device such as a smartphone or computer that has the following functions:

[0480] 1. Data Entry: Provide an interface for users to enter their dietary preferences and restrictions.

[0481] 2. Emotional data collection: Using a camera and microphone to capture the user's facial expressions and tone of voice, as well as text input.

[0482] 3. Display suggestions: Display meal suggestions sent from the server to the user.

[0483] User

[0484] Users use the system to input their dietary preferences, restrictions, and emotions, and then review suggested meals.

[0485] Specific examples

[0486] Here is a concrete example of how the system works:

[0487] 1. Data entry: The user opens the smartphone application and enters information such as "I have a nut allergy," "I like spicy food," and "I would like to eat a low-calorie diet."

[0488] 2. Emotion data collection: When a user smiles at the camera, the device captures their facial expression and sends it to the server. Also, when a user types "I'm tired today," that data is also sent to the server.

[0489] 3. Emotion Recognition: The server passes the received data to the emotion engine to recognize the user's emotions. For example, it recognizes the emotion "joy" from a smiling face and the emotion "fatigue" from text input.

[0490] 4. Meal suggestion generation: The server generates meal suggestions using a generative AI model based on the collected data. An example of a prompt sentence is, "The user has a nut allergy, likes spicy food, and wants a low-calorie diet. Furthermore, their current emotion is joy. What kind of meal would you suggest?"

[0491] 5. Suggestion presentation: The generated meal suggestion (e.g., "How about your favorite sushi?") is sent to the terminal and displayed to the user.

[0492] In this way, the system can provide meal suggestions tailored to the user's individual needs and emotions.

[0493] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0494] Step 1:

[0495] Users open an application on their smartphone or computer and enter their dietary preferences and restrictions, such as "I have a nut allergy," "I like spicy food," or "I prefer a low-calorie diet."

[0496] Input: Information about the user's dietary preferences and restrictions

[0497] Output: The entered information is saved on the device and sent to the server.

[0498] Step 2:

[0499] The device collects emotion data such as the user's facial expressions, tone of voice, and text input. For example, it uses a camera to capture the user's smile and a microphone to record the tone of voice. If the user inputs text such as "I'm tired today," that data is also collected.

[0500] Input: User facial expressions, tone of voice, and text input

[0501] Output: The collected emotion data is sent to the server.

[0502] Step 3:

[0503] The server receives the dietary preferences, restrictions, and emotional data sent from the device and stores it in a database using a relational database such as MySQL or PostgreSQL.

[0504] Input: Food preferences, restrictions, and emotional data sent from the device

[0505] Output: User information stored in the database

[0506] Step 4:

[0507] The server passes the stored emotion data to the emotion engine, which then recognizes the user's emotion. The emotion engine uses machine learning frameworks such as TensorFlow and PyTorch to analyze emotions from the user's facial expressions, tone of voice, and text input. For example, it can recognize the emotion "joy" from a smiling face and the emotion "fatigue" from text input.

[0508] Input: Stored emotion data

[0509] Output: Recognized user emotion information

[0510] Step 5:

[0511] The server generates meal suggestions using a generative AI model based on the collected dietary preferences and restrictions and the recognized emotion information. For example, the following prompt sentence is input to the generative AI model: "The user has a nut allergy, likes spicy food, and wishes to eat a low-calorie diet. Furthermore, their current emotion is joy. What meal would you suggest?"

[0512] Input: Food preferences and restrictions, perceived emotional information

[0513] Output: Generated meal suggestions

[0514] Step 6:

[0515] The server transmits the generated meal suggestions to the terminal.

[0516] Input: Generated meal suggestions

[0517] Output: Meal suggestions sent to the device

[0518] Step 7:

[0519] The device displays the meal suggestions sent from the server to the user. For example, it displays "How about your favorite sushi?" on the smartphone screen.

[0520] Input: Meal suggestions sent from the server

[0521] Output: Meal suggestions displayed to the user

[0522] In this way, the system can provide meal suggestions tailored to the user's individual needs and emotions.

[0523] (Application example 1)

[0524] Next, a description will be given of Application Example 1 of Embodiment 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."

[0525] Conventional meal recommendation systems can take into account a user's dietary preferences and restrictions, but they cannot make recommendations that reflect the user's emotions. As a result, they are unable to make optimal meal recommendations based on the user's emotional state, making it difficult to increase user satisfaction. In addition, when making meal recommendations that reflect the opinions of multiple people, it is difficult to generate recommendations that take into account everyone's opinions, making it impossible to increase the satisfaction of the entire group.

[0526] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing services for groups, means for collecting each individual's dietary preferences and restrictions, means for recognizing the user's emotions, and means for making meal suggestions based on the recognized emotions. This makes it possible to make optimal meal suggestions based on the user's emotional state, and by making suggestions that take into account the opinions of multiple people, it is possible to increase the satisfaction of the entire group.

[0527] "Means for suggesting meals that reflect the opinions of multiple people" is a function that suggests meals that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[0528] The "means of making suggestions that take everyone's opinions into consideration" is a function that generates meal suggestions that everyone can agree on based on the collected information about each individual's dietary preferences and restrictions.

[0529] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[0530] "Means for collecting individual dietary preferences and restrictions" refers to a function that allows users to input their own dietary preferences, allergy information, health restrictions, etc., and the system collects this information.

[0531] "Means for recognizing user emotions" refers to a function for recognizing emotions from the user's facial expressions, tone of voice, text input, etc.

[0532] The "means for suggesting meals based on recognized emotions" is a function for suggesting optimal meals according to the user's emotional state.

[0533] A system for implementing the present invention includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing service for groups, means for collecting each individual's dietary preferences and restrictions, means for recognizing a user's emotions, and means for making meal suggestions based on the recognized emotions.

[0534] Hardware and Software Configuration

[0535] The server uses the following hardware and software:

[0536] Hardware: Smartphone (camera, microphone)

[0537] Software: OpenCV (image processing library), Keras (deep learning library), SpeechRecognition (speech recognition library), TextBlob (text analysis library)

[0538] Data processing and calculation

[0539] 1. Image processing: The image of the user's face taken with the smartphone camera is read, converted to grayscale, and input into the emotion recognition model. This allows the emotion to be recognized from the user's facial expression.

[0540] 2. Speech processing: Converts speech recorded by a smartphone microphone into text and analyzes the sentiment of the text, thereby recognizing emotions from the user's tone of voice.

[0541] 3. Emotion recognition: Integrates emotional information obtained from images and audio to determine the final emotion.

[0542] 4. Meal Suggestion: Based on the determined emotions, appropriate meals are suggested.

[0543] Specific examples

[0544] If the user smiles into the smartphone camera, the system recognizes this as "happy" and suggests meals like sushi or pizza. If the user has a sad expression, the system recognizes this as "sad" and suggests meals like chocolate or soup.

[0545] Prompt Sentence Examples

[0546] Design a system that recognizes emotions from a user's facial and vocal expressions and suggests appropriate meals based on those emotions. For example, if a user expresses happiness, it suggests meals such as sushi or pizza, and if a user expresses sadness, it suggests meals such as chocolate or soup.

[0547] In this way, it is possible to make optimal meal suggestions based on the user's emotional state, and by making suggestions that take into account the opinions of multiple people, it is possible to increase the satisfaction of the entire group.

[0548] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0549] Step 1:

[0550] The user takes a picture of their face in front of the smartphone camera. The input is the user's face image, and the output is image data. The smartphone camera is used to capture the user's face image and save it as image data.

[0551] Step 2:

[0552] The server receives the facial image and converts it to grayscale using OpenCV. The input is facial image data and the output is grayscale image data. The server converts the received facial image to grayscale using the OpenCV library and processes it into a format suitable for the emotion recognition model.

[0553] Step 3:

[0554] The server uses Keras to input grayscale images into an emotion recognition model to recognize emotions. The input is grayscale image data, and the output is the recognized emotion label. The server uses the Keras library to input grayscale images into an emotion recognition model to predict the user's emotion.

[0555] Step 4:

[0556] The user records audio using the smartphone's microphone. The input is the user's voice and the output is audio data. The smartphone's microphone is used to capture the user's voice and save it as audio data.

[0557] Step 5:

[0558] The server receives the voice data and converts it to text using SpeechRecognition. The input is voice data and the output is text data. The server converts the received voice data to text using the SpeechRecognition library.

[0559] Step 6:

[0560] The server analyzes the sentiment of text data using TextBlob. The input is text data and the output is the recognized sentiment label. The server uses the TextBlob library to analyze the sentiment of the text data and predict the user's sentiment.

[0561] Step 7:

[0562] The server integrates the emotional information obtained from the image and audio and determines the final emotion. The input is the emotion label from the image and the emotion label from the audio, and the output is the final emotion label. The server integrates the emotional information obtained from the image and the audio and determines the most appropriate emotion.

[0563] Step 8:

[0564] The server suggests meals based on the final emotion. The input is the final emotion label, and the output is a suggested meal list. The server references a database for suggesting appropriate meals based on the final emotion label and generates a meal list to suggest to the user.

[0565] Step 9:

[0566] The user checks the suggested meal list on their smartphone and selects a meal. The input is the suggested meal list, and the output is the meal selected by the user. The user checks the suggested meal list on the smartphone screen and selects the meal they want.

[0567] Step 10:

[0568] The server sends the user's selected meal to the delivery service and confirms the order. The input is the user's selected meal and the output is the order information for the delivery service. The server sends the user's selected meal to the delivery service and confirms the order.

[0569] Example 2

[0570] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0571] Conventional meal recommendation systems have difficulty reflecting the opinions of multiple people, making it difficult to make recommendations that everyone can agree on. Furthermore, they are unable to take user emotions into account when making recommendations, making it impossible to make optimal recommendations for specific situations. This creates the problem of being unable to increase satisfaction for the entire group.

[0572] 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.

[0573] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for recognizing the emotions of each individual, and a means for generating meal suggestions based on the emotions, thereby enabling optimal meal suggestions that take into account the opinions and emotions of multiple people.

[0574] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that makes meal suggestions that everyone can agree on based on the dietary preferences and restrictions collected from multiple users.

[0575] "Means for making suggestions that take everyone's opinions into consideration" is a function that generates meal suggestions that everyone can agree on based on the collected dietary preferences and restrictions of each user.

[0576] "Means for providing services to groups" refers to a function for providing meal suggestions and other related services to groups of multiple users.

[0577] "Means for recognizing each individual's emotions" is a function that analyzes the user's facial expressions, voice, etc. to understand their emotional state.

[0578] The "means for generating meal suggestions based on emotions" is a function for generating optimal meal suggestions based on the recognized emotional state of the user.

[0579] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions, voice, etc. to recognize their emotional state.

[0580] A "generative AI model" is an artificial intelligence model that generates suggestions and answers in natural language based on input data.

[0581] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[0582] MODE FOR CARRYING OUT THE INVENTION

[0583] The present invention is a system for proposing a meal plan that satisfies all of the opinions and feelings of multiple people. A specific embodiment of this system will be described below.

[0584] Information gathering

[0585] The server collects user preferences and allergy information. Specifically, it stores the questionnaire results entered by the user via their device and past dietary history in a database. The software used is a database management system (e.g., MySQL).

[0586] Specific behavior:

[0587] The user enters "I like fish dishes" and "I don't have any allergies" into the questionnaire form displayed on the device screen.

[0588] The terminal transmits the input information to the server.

[0589] The server stores the received information in a MySQL database.

[0590] Data analysis

[0591] The server then performs data analysis on the collected information, specifically using Python's Pandas library to identify meal options that everyone is likely to like.

[0592] Specific behavior:

[0593] The server retrieves information such as "I like fish dishes" and "I have no allergies" from the MySQL database.

[0594] The server uses the Pandas library to identify everyone's preferred meal options.

[0595] Proposal generation

[0596] The server then uses the analysis results to generate meal recommendations that everyone can agree on, using a generative AI model (e.g., OpenAI's GPT-3) to create the recommendations.

[0597] Specific behavior:

[0598] Based on the analysis result that "everyone likes fish dishes," the server sends a prompt to GPT-3.

[0599] GPT-3 generates the result "Suggest a restaurant that serves fish."

[0600] The server sends the generated proposal to the terminal.

[0601] Emotion Recognition (Alternative Embodiment)

[0602] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the user's facial expressions and voice through a camera and microphone to understand their emotional state. The hardware used is a camera and microphone, and the software used is an emotion recognition engine (e.g., Microsoft® Azure® Emotion API).

[0603] Specific behavior:

[0604] The user smiles into the device's camera.

[0605] The device sends the video captured by the camera to the server.

[0606] The server uses Microsoft Azure's Emotion API to recognize when the user is expressing the emotion "joy."

[0607] Emotion-based suggestions

[0608] The server then uses the emotion recognition results to make meal recommendations that everyone can agree on. Specifically, it uses a generative AI model to create recommendations based on the emotional state of the person.

[0609] Specific behavior:

[0610] Based on the emotion recognition result that "everyone is showing the emotion of joy," the server sends a prompt message to GPT-3.

[0611] GPT-3 generates the result "Suggesting meals that are predicted to be enjoyed by everyone."

[0612] The server sends the generated proposal to the terminal.

[0613] Examples and prompts

[0614] Examples:

[0615] User A: I like fish dishes and I have no allergies.

[0616] User B: I like fish dishes and I don't have any allergies.

[0617] User C: I like fish dishes and I have no allergies.

[0618] Example prompt sentence:

[0619] Generate meal suggestions that everyone can agree on based on user preferences and allergies. Consider the following information:

[0620] User A: I like fish dishes and I have no allergies.

[0621] User B: I like fish dishes and I don't have any allergies.

[0622] User C: I like fish dishes and I have no allergies.

[0623] By feeding this prompt into a generative AI model, we can get meal suggestions that everyone can agree on.

[0624] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0625] Program processing flow

[0626] Step 1: Gather information

[0627] Specific description:

[0628] The server collects information about the user's preferences and allergies, specifically, the results of a questionnaire entered by the user via their device and past meal history, and stores this information in a database.

[0629] Input: Preferences and allergy information you enter into your device.

[0630] Output: User preferences and allergy information stored in a database.

[0631] Specific behavior:

[0632] The user enters "I like fish dishes" and "I don't have any allergies" into the questionnaire form displayed on the terminal screen.

[0633] The terminal transmits the input information to the server.

[0634] The server stores the received information in a MySQL database.

[0635] Step 2: Data analysis

[0636] Specific description:

[0637] The server then performs data analysis on the collected information, specifically using Python's Pandas library to identify meal options that everyone is likely to like.

[0638] Input: User preferences and allergy information retrieved from a database.

[0639] Output: Meal options that everyone is likely to like.

[0640] Specific behavior:

[0641] The server retrieves information such as "I like fish dishes" and "I have no allergies" from the MySQL database.

[0642] The server uses the Pandas library to identify everyone's preferred meal options.

[0643] Step 3: Proposal Generation

[0644] Specific description:

[0645] The server then uses the analysis results to generate meal recommendations that everyone can agree on, using a generative AI model (e.g., OpenAI's GPT-3) to create the recommendations.

[0646] Input: Data analysis results.

[0647] Output: Meal suggestions that everyone can agree on.

[0648] Specific behavior:

[0649] The server sends a prompt to GPT-3 based on the analysis result that "everyone likes fish dishes."

[0650] GPT-3 generates the result "Suggest a restaurant that serves fish."

[0651] The server transmits the generated proposal to the terminal.

[0652] Step 4: Emotion Recognition (Alternative Embodiment)

[0653] Specific description:

[0654] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the user's facial expressions and voice through a camera and microphone to understand their emotional state.

[0655] Input: User facial expressions and voice captured from camera and microphone.

[0656] Output: Perceived emotional state of the user.

[0657] Specific behavior:

[0658] The user smiles into the device's camera.

[0659] The terminal transmits the video captured by the camera to the server.

[0660] The server uses an emotion recognition engine to recognize that the user is expressing the emotion "happiness."

[0661] Step 5: Emotion-based suggestions

[0662] Specific description:

[0663] The server then uses the emotion recognition results to make meal recommendations that everyone can agree on. Specifically, it uses a generative AI model to create recommendations based on the emotional state of the person.

[0664] Input: Emotion recognition results.

[0665] Output: Food suggestions based on emotional state.

[0666] Specific behavior:

[0667] The server sends a prompt message to GPT-3 based on the emotion recognition result that "everyone is showing the emotion of joy."

[0668] GPT-3 generates the result: "Suggest meals that are predicted to be enjoyed by everyone."

[0669] The server transmits the generated proposal to the terminal.

[0670] (Application example 2)

[0671] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0672] Conventional meal recommendation systems have difficulty reflecting the opinions of multiple users, making it difficult to find meal options that everyone can agree on. Furthermore, because suggestions do not take user emotions into account, satisfaction may decrease in certain situations. Furthermore, when generating suggestions, individual preferences and restrictions may not be fully reflected, making it impossible to make optimal suggestions. To solve these issues, a system is needed that recognizes user emotions and uses a generative AI model to make meal recommendations that everyone can agree on.

[0673] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0674] In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple users, means for making suggestions that take into account the opinions of all users, means for providing group services, means for recognizing user emotions, means for making meal suggestions based on the emotions, means for generating meal suggestions using a generative AI model based on collected information, and means for outputting the generated suggestions as prompt sentences. This makes it possible to make meal suggestions that everyone can agree on while taking into account the emotions of users.

[0675] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that suggests meal options that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[0676] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively analyzes each user's collected dietary preferences and restrictions and generates meal suggestions that everyone can agree on.

[0677] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[0678] "Means for recognizing user emotions" refers to a function for recognizing emotions in real time from the user's facial expressions, voice, etc.

[0679] The "means for suggesting meals based on emotions" is a function for suggesting optimal meals by taking into account the recognized emotions of the user.

[0680] "Means for generating meal suggestions using a generative AI model based on collected information" refers to a function that uses a generative AI model to generate optimal meal suggestions based on information such as a user's preferences, restrictions, and emotions.

[0681] "Means for outputting generated suggestions as prompt sentences" refers to a function for outputting meal suggestions generated by a generative AI model in a format that is easy for the user to understand.

[0682] The system for carrying out the present invention proposes meals that are satisfactory to all users based on information collected from multiple users. A specific embodiment of this system will be described below.

[0683] Hardware and software used

[0684] Hardware: Smartphones, smart glasses

[0685] Software: Emotion recognition engine (e.g., Affectiva SDK), database (e.g., Firebase), generative AI model (e.g., GPT-4)

[0686] System configuration

[0687] 1. Collection of User Information

[0688] The camera on a smartphone or smart glasses is used to capture the user's facial expressions in real time.

[0689] An emotion recognition engine is used to extract emotion data from the captured facial expressions.

[0690] Store user dietary preferences and allergy information in your Firebase database.

[0691] 2. Generating Meal Suggestions

[0692] Based on the collected user information and emotional data, prompts are input into a generative AI model (GPT-4).

[0693] A generative AI model generates optimal meal suggestions.

[0694] 3. Order Optimization

[0695] It presents suggested meals to users and provides an easy ordering interface.

[0696] Run algorithms to optimize delivery times and costs.

[0697] Specific examples

[0698] scenario

[0699] Three users are trying to order food together. User A likes pizza, User B is a vegetarian, and User C is allergic to fish. Users A and B show happy emotions, while User C shows sad emotions.

[0700] Prompt Sentence Examples

[0701] User A likes: Pizza

[0702] User B's preference: Vegetarian

[0703] User C's preference: Fish allergy

[0704] User A's emotion: Joy

[0705] User B's emotion: joy

[0706] User C's emotion: Sadness

[0707] Generate meal suggestions that everyone can agree on.

[0708] This prompt can then be fed into a generative AI model, which can generate suggestions such as "vegetarian pizza" or "fish-free pasta dishes," making it possible to create meal recommendations that everyone can agree on.

[0709] Processing flow

[0710] The server recognizes the user's emotions and generates meal suggestions using a generative AI model based on the collected information. The generated suggestions are output as prompts and presented to the user. This makes it possible to provide meal suggestions that everyone can agree on while taking into account the user's emotions.

[0711] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0712] Step 1:

[0713] Users use their smartphones or smart glasses to input their dietary preferences and allergy information, which then collects personalized information about the user and stores it in a Firebase database.

[0714] Step 2:

[0715] The device captures the user's facial expressions in real time using a smartphone or smart glasses camera, and the captured facial data is sent to an emotion recognition engine (e.g., Affectiva SDK).

[0716] Step 3:

[0717] The server uses an emotion recognition engine to extract the user's emotions from the captured facial expression data, and the extracted emotion data is stored in the Firebase database.

[0718] Step 4:

[0719] The server retrieves the user's dietary preferences, allergy information, and emotional data collected from the Firebase database, which is used to generate prompts that are fed into a generative AI model (e.g., GPT-4).

[0720] Step 5:

[0721] The server inputs a prompt sentence into the generative AI model to generate optimal meal suggestions, which are then output as prompt sentences.

[0722] Step 6:

[0723] The terminal presents the generated meal suggestions to the user, who can then review the suggested meal suggestions and place an order.

[0724] Step 7:

[0725] The server receives the user's order information, executes an algorithm to optimize delivery time and cost, and notifies the user of the optimized delivery information.

[0726] Step 8:

[0727] The user checks the optimized delivery information and finalizes the order. The server then sends the order information to the restaurant or delivery service, which then arranges for the meal to be delivered.

[0728] Example 3

[0729] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0730] Conventional systems have problems in that they do not adequately reflect the opinions of multiple people when proposing meals or providing services based on the user's emotions. They also face the challenge of accurately recognizing the emotions of individual users and providing appropriate services based on those emotions. This can lead to a decrease in user satisfaction.

[0731] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0732] In this invention, the server includes means for generating suggestions, means for presenting the generated suggestions, means for accepting a user's selection, means for recognizing the user's emotion, and means for providing a service based on the recognized emotion, thereby enabling meal suggestions that reflect the opinions of multiple people and the provision of a service based on the user's emotion.

[0733] The "means for generating a proposal" is a device or program having a function for generating a proposal to a user.

[0734] The "means for presenting the generated proposal" is a device or program having a function for visually or audibly presenting the generated proposal to the user.

[0735] The "means for accepting a user's selection" is a device or program that has the function of accepting a selection when the user makes a selection from the presented suggestions.

[0736] The "means for recognizing a user's emotions" refers to a device or program that has the function of detecting and recognizing a user's emotions.

[0737] The "means for providing a service based on the recognized emotion" is a device or program having a function for providing an appropriate service based on the recognized emotion of the user.

[0738] A "generative AI model" is a model that uses artificial intelligence to generate suggestions.

[0739] An "emotion engine" is software or hardware that recognizes a user's emotions.

[0740] The present invention provides a system for generating and presenting suggestions to a user, accepting the user's selection, recognizing the user's emotions, and providing services based on those emotions. Specific embodiments of this system are described below.

[0741] Hardware and software used

[0742] Server: A server for data processing and proposal generation. For example, a virtual server of a cloud service is used.

[0743] Device: The device on which the user interface is displayed. For example, a smartphone or tablet.

[0744] Emotion engine: Software for recognizing user emotions. For example, using an emotion recognition API.

[0745] Generative AI model: An AI model for generating suggestions. For example, we use a natural language processing model.

[0746] Explanation of program processing

[0747] 1. Proposal generation

[0748] The server uses the generative AI model to generate suggested meal options for the user.

[0749] The server sends a prompt to the generative AI model, for example, "Suggest the following food options for the user: sushi, pizza, salad."

[0750] The generative AI model generates meal options based on the prompt and returns them to the server.

[0751] The server stores the generated suggestions in a database.

[0752] 2. Presenting the proposal

[0753] The server instructs the terminal to display the generated meal options on a user interface.

[0754] The device presents suggestions to the user through a user interface, specifically displaying the options "sushi," "pizza," and "salad" in the form of buttons on the screen.

[0755] 3. User Choice

[0756] The user makes a final choice from the presented options. For example, the user clicks the "Sushi" button.

[0757] The terminal transmits the user's selection to the server, specifically, data including information about the selected "sushi" to the server.

[0758] 4. Emotion recognition

[0759] The server uses an emotion engine to recognize the user's emotion.

[0760] The server sends the user's facial image and voice data to the emotion engine and receives the emotion analysis results. For example, the emotion "joy" is recognized from the user's facial image.

[0761] 5. Provision of Services

[0762] The server uses a generative AI model to suggest appropriate services based on the recognized emotions. Example: "Please suggest services to increase the user's joy."

[0763] The generative AI model generates a service based on the prompt and returns it to the server, suggesting, for example, a "discount coupon for sushi."

[0764] The server transmits the generated service to the terminal.

[0765] The device presents users with services based on their emotions, such as displaying a "sushi discount coupon" on the screen.

[0766] Examples of concrete examples and prompts

[0767] Example 1: Food options

[0768] The server sends the generative AI model a prompt: "Suggest the following food options for the user: sushi, pizza, salad."

[0769] The generative AI model generates the options "sushi," "pizza," and "salad" and returns them to the server.

[0770] The server stores these choices in a database and sends them to the device.

[0771] The device displays the options "Sushi," "Pizza," and "Salad" on the user interface.

[0772] Example 2: Emotion-based service delivery

[0773] The user selects "sushi" and the device sends that information to the server.

[0774] The server sends the user's facial image to the emotion engine, which recognizes the emotion of "joy."

[0775] The server sends a prompt to the generative AI model: "Please suggest a service to increase user joy."

[0776] The generative AI model generates a "sushi discount coupon" and returns it to the server.

[0777] The server sends this service to the terminal, which then displays a "sushi discount coupon" to the user.

[0778] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0779] Step 1:

[0780] Proposal generation

[0781] The server sends a prompt to the generative AI model, using as input a prompt to generate suggested meal options for the user (e.g., "Please suggest the following meal options for the user: sushi, pizza, salad.").

[0782] The generative AI model generates meal options based on the prompt sentence and returns the options "sushi," "pizza," and "salad" to the server as output.

[0783] The server saves the generated suggestions in a database. As a specific operation, it writes the generated options to the database.

[0784] Step 2:

[0785] Presenting the proposal

[0786] The server instructs the terminal to display the generated meal options on a user interface, using the options stored in the database as input.

[0787] The device presents suggestions to the user through a user interface. Specifically, the options "Sushi," "Pizza," and "Salad" are displayed in the form of buttons on the screen. As an output, the user is presented with a visual representation of the options.

[0788] Step 3:

[0789] User Selection

[0790] The user makes the final choice from the presented options, using the button the user selects (e.g., "Sushi") as input.

[0791] The terminal transmits the user's selection to the server. Specifically, it transmits data including information about the selected "sushi" to the server. As an output, the user's selection information is transmitted to the server.

[0792] Step 4:

[0793] emotion recognition

[0794] The server uses an emotion engine to recognize the user's emotions, using the user's facial image and voice data as input.

[0795] The server sends the user's facial image and voice data to the emotion engine and receives the emotion analysis results. Specifically, the server sends data to the emotion engine and receives the analysis results. The output is the user's emotion (e.g., "joy").

[0796] Step 5:

[0797] Service provision

[0798] The server uses a generative AI model to suggest appropriate services based on the recognized emotion, using the recognized emotion (e.g., "joy") and a prompt sentence (e.g., "Please suggest services to increase the user's joy.") as input.

[0799] The generative AI model generates a service based on the prompt sentence and returns "Sushi discount coupon" to the server as output.

[0800] The server transmits the generated service to the terminal, specifically, transmitting the generated service information to the terminal.

[0801] The device presents services based on the user's emotions. Specifically, it displays a "sushi discount coupon" on the screen. The output is a visual representation of the service to the user.

[0802] (Application example 3)

[0803] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0804] Conventional meal recommendation systems have difficulty making fair recommendations that reflect the opinions of multiple people, and do not provide services that take user emotions into consideration. This makes it difficult to increase user satisfaction. Furthermore, when presenting meal options, they are unable to make optimal recommendations based on the user's emotions, resulting in a lack of service that meets the user's needs. This makes it difficult to make recommendations that satisfy everyone, especially when choosing meals for a group.

[0805] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0806] In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple users, means for making suggestions that take into account the opinions of all users, means for providing group services, means for recognizing a user's emotions, means for suggesting meal options based on the recognized emotions, means for presenting the suggested meal options on a user interface and allowing the user to make a final selection, and means for ordering the selected meal through a delivery service. This enables optimal meal suggestions that take into account the user's emotions, making it possible to realize meal selections that satisfy everyone.

[0807] "Means for making meal suggestions that reflect the opinions of multiple people" refers to a function that generates meal options that reflect everyone's opinions based on the dietary preferences and restrictions collected from multiple users.

[0808] "Means for making suggestions that take everyone's opinions into consideration" is a function that generates meal suggestions that everyone can agree on based on the collected information about each individual's dietary preferences and restrictions.

[0809] A "means for providing group services" is a function for providing common services to multiple users.

[0810] "Means for recognizing user emotions" refers to a function that analyzes data such as the user's face and voice and identifies their emotions.

[0811] "Means for suggesting meal options based on recognized emotions" refers to a function that generates meal options appropriate to a user's emotions based on their emotional data.

[0812] "A means for presenting suggested meal options on a user interface and allowing the user to make a final selection" is a function that displays meal options through a user interface and allows the user to make a final selection from among them.

[0813] "Means for ordering selected meals through a delivery service" refers to a function that allows a user to order selected meals using a delivery service.

[0814] A system for implementing the present invention includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing service for groups, means for recognizing a user's emotion, means for suggesting meal options based on the recognized emotion, means for presenting the suggested meal options on a user interface and allowing the user to make a final selection, and means for ordering the selected meal through a delivery service.

[0815] Hardware and software used

[0816] Hardware: Smartphones, smart glasses, cameras

[0817] Software: Emotion recognition engines (e.g., Microsoft Azure's Emotion API), food delivery service APIs (e.g., Uber Eats and DoorDash), user interface (UI) frameworks

[0818] Data processing and calculation

[0819] 1. Emotion recognition:

[0820] The server scans the user's face using the camera on the smartphone or smart glasses, and then uses an emotion recognition engine to recognize the user's emotions. Specifically, it uses Microsoft Azure's Emotion API to obtain emotional data from the user's facial image.

[0821] 2. Meal Suggestions:

[0822] The server generates optimal meal options for the user based on the recognized emotion data, for example, suggesting special desserts or celebratory meals if the user expresses joy.

[0823] 3. User Interface:

[0824] The server displays the suggested meal options on a user interface, which is provided via a smartphone or smart glasses display, from which the user makes a final selection.

[0825] 4. Delivery arrangements:

[0826] The server orders the meal selected by the user through a food delivery service API, for example, Uber Eats or DoorDash, and arranges for the selected meal to be delivered.

[0827] Specific examples

[0828] Example 1:

[0829] When a user takes a photo of their face with their smartphone and the app recognizes the emotion "joy," it suggests "cake" or "celebration dinner." The user selects "cake" from the suggested options on their smartphone screen, and the app automatically completes the order through a food delivery service.

[0830] Example 2:

[0831] When the user is wearing the smart glasses, the glasses' camera scans the user's face and similarly recognizes emotions to suggest meals, and the user reviews the options on the glasses' display and makes the final selection via voice command.

[0832] Prompt Sentence Examples

[0833] "Write a Python program that recognizes a user's emotions and suggests the best meal options based on those emotions. Use Microsoft Azure's Emotion API for emotion recognition and use conditional branching based on the emotion data to suggest meals."

[0834] The above is an embodiment of the present invention.

[0835] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0836] Step 1:

[0837] A user takes a picture of their face using the camera on their smartphone or smart glasses.

[0838] Input: User's face image

[0839] Output: Face image data

[0840] Specific operation: The user activates the camera on their smartphone or smart glasses and takes a picture of their face. The captured image is then stored on the device.

[0841] Step 2:

[0842] The terminal transmits the captured facial image to the server.

[0843] Input: Face image data

[0844] Output: Facial image data sent to the server

[0845] Specific operation: The device uploads the captured facial image data to a server via the Internet. The server stores the received facial image data.

[0846] Step 3:

[0847] The server transmits the facial image data to an emotion recognition engine to recognize the emotion of the user.

[0848] Input: Face image data

[0849] Output: Emotion data (happiness, sadness, etc.)

[0850] How it works: The server sends facial image data to an emotion recognition engine, such as Microsoft Azure's Emotion API. The emotion recognition engine analyzes the facial image and returns the user's emotional data.

[0851] Step 4:

[0852] The server generates optimal meal options for the user based on the recognized emotion data.

[0853] Input: Emotion data

[0854] Output: A list of meal options

[0855] Specific operation: The server performs conditional branching based on the emotion data and generates meal options that match the user's emotion. For example, if the emotion of joy is recognized, cake and a celebratory dinner will be listed as options.

[0856] Step 5:

[0857] The server presents the generated meal options on a user interface.

[0858] Input: List of meal options

[0859] Output: Meal options displayed on the user interface

[0860] Specific operation: The server sends the generated list of meal options to the device and displays it on the user interface. The user can then check the options on the screen of their smartphone or smart glasses.

[0861] Step 6:

[0862] The user makes a final selection from the presented meal options.

[0863] Input: List of meal options

[0864] Output: User's meal selection

[0865] Specific operation: The user selects one of the meal options presented on the user interface. The selected meal information is sent from the terminal to the server.

[0866] Step 7:

[0867] The server orders the selected meal through a food delivery service.

[0868] Input: User's meal selection

[0869] Output: Order information for food delivery service

[0870] Specific behavior: The server uses a food delivery service API (e.g., Uber Eats or DoorDash) to order the meal selected by the user. The order information is sent to the food delivery service, which then arranges for delivery.

[0871] 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.

[0872] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0873] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0874] 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.

[0875] [Second embodiment]

[0876] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0877] 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.

[0878] 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).

[0879] 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.

[0880] 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.

[0881] 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).

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0888] "Example 1"

[0889] In one embodiment of the present invention, a user interface allows for personal dietary preferences and restrictions.

[0890] There are systems that collect user preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.) that users input and the system collects.

[0891] "Example 2"

[0892] Based on the collected information, a system can generate meal suggestions that everyone can agree on. Specifically, it takes into account everyone's preferences and restrictions and suggests meal options that are predicted to be most agreeable. For example, if everyone likes fish dishes and no one is allergic to fish, the system can suggest a fish restaurant.

[0893] "Example 3"

[0894] There is a system that presents suggested meal options to users and leaves the final choice to the user. Specifically, the system presents the suggested options on a user interface, and the user makes the final choice from among them. This allows for a fair selection process that reflects everyone's opinions.

[0895] The processing flow of each embodiment will be described below.

[0896] "Example 1"

[0897] Step 1: The user accesses the system's user interface.

[0898] Step 2: The user enters their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[0899] Step 3: The system collects the information entered by the user and stores it in a database.

[0900] "Example 2"

[0901] Step 1: The system retrieves everyone's dietary preferences and restrictions from a database.

[0902] Step 2: Based on the information obtained, the system generates meal options that are predicted to be most likely to gain consensus.

[0903] Step 3: Present the generated meal options to the user.

[0904] "Example 3"

[0905] Step 1: The user reviews the meal options presented by the system.

[0906] Step 2: The user makes their final meal selection.

[0907] Step 3: The system receives the user's selection and stores the results.

[0908] Example 1

[0909] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0910] Conventional meal plan proposal systems have difficulty in properly reflecting each individual's dietary preferences and restrictions, making it difficult to provide a meal plan that satisfies the user. In addition, when generating a meal plan that takes into account the opinions of multiple people, it is difficult to make proposals that everyone can agree on.

[0911] 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.

[0912] In this invention, the server includes a means for collecting each individual's dietary preferences and restrictions, a means for storing the collected information in a database, a means for sending a prompt to the generative AI model based on the stored information, a means for the generative AI model to generate a meal plan suitable for the user, and a means for displaying the generated meal plan to the user. This makes it possible to provide a meal plan that appropriately reflects each individual's dietary preferences and restrictions. Furthermore, when generating a meal plan that takes into account the opinions of multiple people, it is possible to make proposals that are acceptable to all.

[0913] "Means for collecting individual dietary preferences and restrictions" means a means for providing an interface for users to input their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[0914] The "means for storing collected information in a database" refers to a means for storing information about dietary preferences and restrictions entered by a user in a database.

[0915] "Means for sending prompt sentences to the generative AI model based on stored information" refers to means for generating and sending appropriate prompt sentences to the generative AI model based on user information stored in the database.

[0916] "Means by which the generative AI model generates a meal plan appropriate for the user" refers to means by which the generative AI model analyzes the prompt sentence and generates an appropriate meal plan based on the user's dietary preferences and restrictions.

[0917] "Means for displaying the generated meal plan to the user" refers to means for displaying the meal plan generated by the generative AI model on the user's interface.

[0918] This invention is a system for collecting individual dietary preferences and restrictions and generating an appropriate meal plan based on the collected information. The system includes a user interface for a user to input the dietary preferences and restrictions, a server for storing the collected information in a database, a server for sending prompts to a generative AI model based on the stored information, a means for the generative AI model to generate a meal plan appropriate for the user, and a means for displaying the generated meal plan to the user.

[0919] Hardware and software used

[0920] Server: Uses the Django framework to host the web application.

[0921] Database: PostgreSQL is used to store user information.

[0922] Generative AI model: Use an appropriate generative AI model to generate the meal plan for the user.

[0923] Specific operation of the system

[0924] Users access the system through a web browser and enter their dietary preferences and restrictions into the user interface. Specifically, users enter allergy information, likes and dislikes, health restrictions, etc. For example, suppose a user enters the following information:

[0925] Allergy Information: Nuts

[0926] Likes and dislikes: I hate tomatoes

[0927] Health Restrictions: Low Carbohydrate

[0928] This information is entered as follows:

[0929] Allergy Information: Nuts

[0930] Likes and dislikes: I hate tomatoes

[0931] Health Restrictions: Low Carb

[0932] The device sends the information entered by the user to a server, which stores the received information in a database that is later used to generate the user's meal plan.

[0933] The server then sends prompts to the generative AI model based on the stored information, including the user's dietary preferences and restrictions. For example, the following prompts might be generated:

[0934] Generate an appropriate meal plan based on the user's dietary preferences and restrictions. Here is the user's information:

[0935] Allergy Information: Nuts

[0936] Likes and dislikes: I hate tomatoes

[0937] Health Restrictions: Low Carbohydrate

[0938] The generative AI model generates a meal plan suitable for the user based on the received prompt. The generated meal plan is returned to the server, which displays the generated meal plan in the user interface. The user can view the meal plan through their browser.

[0939] In this way, it is possible to provide meal plans that appropriately reflect each individual's dietary preferences and restrictions.In addition, when generating meal plans that take into account the opinions of multiple people, it is possible to make proposals that everyone can agree on.

[0940] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0941] Step 1:

[0942] The user inputs their dietary preferences and restrictions.

[0943] Users access the system through a web browser and enter their dietary preferences and restrictions into the user interface, including allergy information, likes and dislikes, and health restrictions.

[0944] Input: User's dietary preferences and restrictions (e.g., nut allergy, dislike of tomatoes, low carb)

[0945] Output: The entered information is displayed in the form.

[0946] Specific Action: A user enters "nuts" in the "Allergy Information" field, "dislikes tomatoes" in the "Likes and Dislikes" field, and "low carb" in the "Health Restrictions" field.

[0947] Step 2:

[0948] The terminal transmits the input information to the server.

[0949] When the user completes the input and clicks the send button, the terminal sends the input information to the server as an HTTP POST request.

[0950] Input: User-entered dietary preferences and restrictions

[0951] Output: HTTP POST request sent to the server

[0952] Specific operation: The device sends a POST request to the " / submit_preferences" endpoint and includes the information entered by the user in the request body.

[0953] Step 3:

[0954] The server stores the received information in a database.

[0955] The server processes the incoming requests and stores the user's dietary preferences and restrictions in a database, which uses PostgreSQL.

[0956] Input: The user's dietary preferences and restrictions received by the server.

[0957] Output: User information stored in the database

[0958] What happens: The server extracts the user's information from the request body and runs an SQL query to connect to a PostgreSQL database and save the information.

[0959] Step 4:

[0960] The server sends a prompt to the generative AI model based on the stored information.

[0961] The server uses the stored information to generate prompts to send to the generative AI model, including the user's dietary preferences and restrictions.

[0962] Input: User information stored in the database

[0963] Output: The prompt sent to the generative AI model

[0964] Specific operation: The server retrieves user information from the database, generates a prompt sentence based on the retrieved information, and sends the generated prompt sentence to the generative AI model.

[0965] Step 5:

[0966] A generative AI model generates a meal plan tailored to the user.

[0967] The generative AI model generates a meal plan suitable for the user based on the received prompt, and the generated meal plan is returned to the server.

[0968] Input: The prompt sent to the generative AI model

[0969] Output: The generated meal plan

[0970] Specific operation: The generative AI model analyzes the prompt, generates a meal plan based on the user's preferences and restrictions, and returns the generated meal plan to the server.

[0971] Step 6:

[0972] The server displays the generated meal plan to the user.

[0973] The server receives the meal plan returned by the generative AI model and displays it in a user interface, where the user can view the meal plan through their browser.

[0974] Input: Meal plan returned from a generative AI model

[0975] Output: Meal plan displayed in the user interface

[0976] Specific operation: The server receives the meal plan returned by the generative AI model, converts the meal plan into HTML format, sends the converted HTML to the user's browser, and the user views the meal plan in the browser.

[0977] (Application example 1)

[0978] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0979] Conventional food delivery systems have difficulty proposing menus that fully consider the dietary preferences and restrictions of individual users, and it has been particularly difficult to make proposals that reflect the opinions of multiple people or that everyone can agree on. Furthermore, users have to input their own dietary preferences and restrictions, which is time-consuming, and there has been a lack of a way to efficiently collect and manage this information.

[0980] 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.

[0981] In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple users, means for making suggestions that take into account the opinions of all users, means for providing services for groups, means for collecting each individual's dietary preferences and restrictions, means for proposing an optimal menu based on the collected information, and means for ordering from the suggested menu. This makes it possible to efficiently collect users' dietary preferences and restrictions and to propose optimal menus for each user and the entire group.

[0982] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that makes meal suggestions that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[0983] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively evaluates the collected information about each individual's dietary preferences and restrictions, and generates meal suggestions that everyone can agree on.

[0984] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[0985] "Means for collecting individual dietary preferences and restrictions" refers to a function that allows users to input their own dietary preferences and restrictions (such as allergy information, likes and dislikes, health restrictions, etc.) and the system collects them.

[0986] "Means for suggesting the most suitable menu based on collected information" refers to a function for selecting and suggesting the most suitable menu based on the user's collected dietary preferences and restrictions.

[0987] The "means of ordering from the proposed menu" is a function that allows the user to select from the proposed menu and actually place an order.

[0988] As an embodiment of the present invention, the following system is constructed.

[0989] System Configuration

[0990] The system consists of a server, user terminals, and a network. The server plays a central role in collecting users' dietary preferences and restrictions and proposing optimal menus. The user terminals are devices such as smartphones and tablets that provide an interface for users to input their dietary preferences and restrictions.

[0991] Hardware and software used

[0992] Hardware: Servers, smartphones, tablets

[0993] Software: Python 3.x, JSON library, database management system (e.g., MySQL)

[0994] Data processing and calculation

[0995] 1. Collecting your dietary preferences and restrictions:

[0996] Through the user terminal, the user inputs their dietary preferences and restrictions (allergy information, likes and dislikes, health restrictions, etc.), which are sent to the server in JSON format and stored in a database.

[0997] 2. Optimal menu suggestions:

[0998] The server selects the optimal menu based on the user's dietary preferences and restrictions. Specifically, it filters out menus that do not include the user's allergies or disliked foods, and prioritizes menus that include the user's favorite foods.

[0999] 3. Menu Viewing and Ordering:

[1000] The suggested menu is displayed on the user's terminal, and the user can select from it and place an order. The order information is then sent back to the server for processing.

[1001] Specific examples

[1002] For example, if a user inputs "tomato" as their allergy information, "chicken" as their favorite food, and "fish" as their least favorite food, the server will suggest the most suitable menu based on this information. Specifically, it may suggest a menu item such as "chicken curry."

[1003] Prompt Sentence Examples

[1004] An example of a prompt to be input to the generative AI model is as follows:

[1005] Build an application that collects a user's dietary preferences and restrictions and suggests the best menu items. Users enter allergies, likes, dislikes, and health restrictions, and filter the menu items based on this. For example, if a user enters "I'm allergic to tomatoes," "I like chicken," and "I don't like fish," suggest "Chicken Curry."

[1006] In this way, users' dietary preferences and restrictions can be efficiently collected and optimal menus can be suggested for individual users and for the group as a whole.

[1007] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1008] Step 1:

[1009] The user uses the device to input their dietary preferences and restrictions. Specifically, they input allergy information, favorite foods, disliked foods, health restrictions, etc. The input data is sent to the server in JSON format. Examples of input data include "allergy information: tomato," "favorite food: chicken," and "disliked food: fish."

[1010] Step 2:

[1011] The server receives the JSON format data sent from the device and stores it in a database. Specifically, it stores allergy information, likes and dislikes, and health restrictions along with the user ID in the database. The input data is in JSON format, and the output is saved in the database.

[1012] Step 3:

[1013] The server selects the optimal menu based on the user's dietary preferences and restrictions stored in the database. Specifically, it filters out menus that do not include allergy information or disliked foods, and prioritizes menus that include favorite foods. The input is the user's preferences and restrictions obtained from the database, and the output is a filtered menu list.

[1014] Step 4:

[1015] The server sends the filtered menu list to the user terminal. Specifically, it sends the selected menu to the terminal in JSON format. The input is the filtered menu list, and the output is the transmission to the terminal.

[1016] Step 5:

[1017] The user selects the desired menu from the menu list displayed on the terminal and places an order. Specifically, by confirming the selected menu and pressing the order button, the order information is sent to the server. The input is the menu selected by the user, and the output is the order information sent to the server.

[1018] Step 6:

[1019] The server processes the received order information and confirms the order. Specifically, it stores the order information in a database and arranges cooking and delivery as necessary. The input is the order information sent by the user, and the output is the confirmation of the order and related arrangements.

[1020] Through the above steps, the optimal menu is proposed and ordered, taking into consideration the user's dietary preferences and restrictions.

[1021] Example 2

[1022] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1023] Conventional meal recommendation systems have difficulty effectively reflecting the opinions and preferences of multiple people, making it difficult to make recommendations that everyone can agree on. Furthermore, there is a problem with insufficient data collection and analysis to take into account individual dietary preferences and restrictions, resulting in low accuracy of recommendations.

[1024] 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.

[1025] In this invention, the server includes a means for inputting user information, a means for collecting and storing the input user information, a means for analyzing the collected user information, a means for generating meal suggestions based on the analysis results, and a means for providing the generated suggestions to the user, thereby effectively reflecting the opinions and preferences of multiple people and making meal suggestions that everyone can agree on.

[1026] A "means for inputting user information" is a device or software that provides an interface for a user to input their dietary preferences and restrictions.

[1027] The "means for collecting and storing input user information" refers to a device or software for transmitting the information input by the user to a server and storing it in a database.

[1028] "Means for analyzing collected user information" refers to a device or software that performs data analysis based on collected user information and generates results that take into account the user's preferences and limitations.

[1029] The "means for generating meal suggestions based on the analysis results" refers to a device or software for generating optimal meal suggestions for a user based on the results of the data analysis.

[1030] The "means for providing generated suggestions to a user" is a device or software that transmits the generated meal suggestions to a user's terminal and allows the user to review the suggestions.

[1031] A "generative AI model" is an artificial intelligence model used to analyze data and generate optimal suggestions, taking into account user preferences and limitations.

[1032] A "prompt" is an instruction given to a generative AI model, containing instructions for achieving a specific result.

[1033] MODE FOR CARRYING OUT THE INVENTION

[1034] The present invention relates to a system that takes into account the dietary preferences and restrictions of users and generates meal proposals that everyone can agree on. A specific embodiment of this system will be described below.

[1035] 1. System Configuration

[1036] The system consists of the following major components:

[1037] A way to enter user information

[1038] A means of collecting and storing input user information

[1039] A means of analyzing collected user information

[1040] A means of generating meal suggestions based on the analysis results

[1041] A means for providing generated suggestions to the user

[1042] 2. Hardware and Software Used

[1043] Server: A central processing unit for collecting, storing, analyzing data, and generating recommendations. It uses MySQL as its database.

[1044] Device: The device (smartphone, PC, etc.) where the user enters information and receives suggestions.

[1045] Generative AI model: An artificial intelligence model (e.g., GPT-4) used to analyze data and generate optimal recommendations, taking into account user preferences and limitations.

[1046] 3. System Operation

[1047] Enter your user information:

[1048] Users use the terminal to input their dietary preferences and restrictions. For example, User A inputs, "I like fish dishes, I have no allergies."

[1049] Data collection and storage:

[1050] The terminal sends the information entered by the user to the server. The server saves the received data in a database (MySQL). For example, User A's information "I like fish dishes, I have no allergies" is saved in the database.

[1051] Data analysis:

[1052] The server retrieves all user information stored in the database and inputs it into a generative AI model (GPT-4). The generative AI model analyzes the data, taking into account the user's preferences and limitations. For example, it verifies that everyone likes fish dishes and that no one is allergic to fish.

[1053] Proposal generation:

[1054] The server generates meal recommendations that are most likely to gain consensus based on the analysis results obtained from the generative AI model, such as suggesting restaurants serving fish.

[1055] Providing suggestions:

[1056] The server sends the generated suggestions to the user's device. The user can check and select the suggestions through the device. For example, user A checks and selects "fish restaurants" on the device.

[1057] 4. Examples of concrete examples and prompts

[1058] Examples:

[1059] User A: I like fish dishes and I don't have any allergies

[1060] User B: I like fish dishes and I don't have any allergies

[1061] User C: I like fish dishes and I have no allergies

[1062] In this case, the server suggests a fish restaurant.

[1063] Example prompt sentence:

[1064] Generate meal suggestions that everyone can agree on, taking into account the user's dietary preferences and restrictions. Use the following information to make suggestions:

[1065] User A: I like fish dishes and I don't have any allergies

[1066] User B: I like fish dishes and I don't have any allergies

[1067] User C: I like fish dishes and I have no allergies

[1068] In this way, meal suggestions that everyone can agree on are generated and provided to the user.

[1069] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1070] Step 1:

[1071] Entering user information

[1072] Users use the terminal to input their dietary preferences and restrictions. For example, User A inputs, "I like fish dishes, I have no allergies."

[1073] Input: User's dietary preferences and restrictions (e.g., "I like fish dishes, no allergies")

[1074] Output: The entered user information is saved on the device.

[1075] Step 2:

[1076] Data collection and storage

[1077] The terminal transmits the information entered by the user to the server.

[1078] The server stores the received data in a database (MySQL). For example, user A's information "likes fish dishes, no allergies" is stored in the database.

[1079] Input: Information entered by the user (e.g., "I like fish dishes, I have no allergies")

[1080] Output: User information stored in the database

[1081] Step 3:

[1082] Analyzing the data

[1083] The server retrieves all user information stored in a database.

[1084] The server uses a generative AI model (GPT-4) to analyze the data, taking into account user preferences and restrictions, for example, ensuring that everyone likes fish dishes and that no one is allergic to fish.

[1085] Input: All user information stored in the database

[1086] Output: Analysis results from the generative AI model (e.g., "Everyone likes fish dishes, and no one is allergic to fish")

[1087] Step 4:

[1088] Proposal Generation

[1089] The server generates meal recommendations that are most likely to gain consensus based on the analysis results obtained from the generative AI model, such as suggesting restaurants serving fish.

[1090] Input: Analysis results from generative AI model

[1091] Output: Dining suggestions (e.g. "fish restaurants")

[1092] Step 5:

[1093] Providing suggestions

[1094] The server transmits the generated proposal to the user's terminal.

[1095] The user can check the suggestions through the terminal and select one. For example, user A checks and selects "fish restaurants" on the terminal.

[1096] Input: Dining suggestions (e.g., "fish restaurants")

[1097] Output: Proposal displayed on the user's device

[1098] In this way, meal suggestions that everyone can agree on are generated and provided to the user.

[1099] (Application example 2)

[1100] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1101] With conventional food delivery services, it was difficult to suggest meals that took into account the preferences and dietary restrictions of multiple people, making it difficult to find options that would satisfy everyone. Furthermore, manual adjustments were required, making it difficult to make efficient suggestions. This made meal selections for groups cumbersome, resulting in lower satisfaction.

[1102] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1103] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for generating meal suggestions using a generative AI model, and a means for generating prompt sentences and making suggestions, thereby enabling efficient and satisfying meal suggestions that take into account the preferences and dietary restrictions of multiple people.

[1104] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that suggests meal options that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[1105] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively analyzes the collected information about each individual's dietary preferences and restrictions, and generates meal suggestions that everyone can agree on.

[1106] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[1107] "Means for generating meal suggestions using a generative AI model" means a function that uses an artificial intelligence model to automatically generate meal suggestions that take into account a user's preferences and restrictions.

[1108] "Means for generating prompt sentences and making suggestions" is a function that generates sentences to give appropriate instructions to the generative AI model based on the information input by the user, and makes meal suggestions based on the results.

[1109] To implement this invention, a server, a user terminal, and a generative AI model are used. Specific embodiments are described below.

[1110] System Configuration

[1111] The server includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing services for groups, means for generating meal suggestions using a generative AI model, and means for generating prompt sentences and making suggestions.

[1112] The user terminal is a mobile device such as a smartphone or tablet that provides an interface for the user to input their dietary preferences and restrictions.

[1113] Program processing

[1114] The server receives each individual's dietary preferences and restrictions from the user's device and stores them in a database. The server then uses a generative AI model to generate meal suggestions that everyone can agree on. The server also generates prompts and provides appropriate instructions to the generative AI model.

[1115] The server is a computer system with a high-performance processor and large memory capacity, and the user devices are ordinary smartphones or tablets. The software used is OpenAI's API for the generative AI model, and the program is implemented in Python.

[1116] Specific examples

[1117] For example, suppose user A likes fish and vegetables, dislikes meat, and has a nut allergy. User B likes meat and fish, dislikes vegetables, and has no allergies. User C likes vegetables and fruit, dislikes fish, and is allergic to dairy products. Based on this information, the server generates a prompt like the following:

[1118] Example prompt sentence:

[1119] Generate meal suggestions that everyone can agree on, taking into account user preferences and restrictions. User info: [{"name": "User A", "likes": ["fish", "vegetables"], "dislikes": ["meat"], "allergies": ["nuts"]}, {"name": "User B", "likes": ["meat", "fish"], "dislikes": ["vegetables"], "allergies": []}, {"name": "User C", "likes": ["vegetables", "fruit"], "dislikes": ["fish"], "allergies": ["dairy"]}]

[1120] This prompt is then fed into a generative AI model to generate satisfying meal suggestions, which are then sent to the user's device and displayed to the user.

[1121] In this way, it becomes possible to propose efficient and satisfying meals that take into account the preferences and dietary restrictions of multiple people.

[1122] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1123] Step 1:

[1124] The user uses the terminal to input their dietary preferences and restrictions.

[1125] Input: User preferences (e.g., fish, vegetables), disliked ingredients (e.g., meat), allergy information (e.g., nut allergy)

[1126] Output: The entered information is sent from the terminal to the server.

[1127] Specific actions: The user enters their dietary preferences and restrictions through the smartphone app interface and presses the submit button.

[1128] Step 2:

[1129] The server receives each individual's dietary preferences and restriction information sent from the device and stores it in a database.

[1130] Input: User preferences and restrictions sent from the device

[1131] Output: User information stored in the database

[1132] Specific operation: The server analyzes the received data and stores each user's information in a database.

[1133] Step 3:

[1134] The server retrieves each individual's dietary preferences and restrictions from a database and generates a prompt.

[1135] Input: User information stored in the database

[1136] Output: Generated prompt statement

[1137] Specific operation: The server uses a Python program to generate a prompt based on the user information. For example, it generates the following prompt:

[1138] Generate meal suggestions that everyone can agree on, taking into account user preferences and restrictions. User info: [{"name": "User A", "likes": ["fish", "vegetables"], "dislikes": ["meat"], "allergies": ["nuts"]}, {"name": "User B", "likes": ["meat", "fish"], "dislikes": ["vegetables"], "allergies": []}, {"name": "User C", "likes": ["vegetables", "fruit"], "dislikes": ["fish"], "allergies": ["dairy"]}]

[1139] Step 4:

[1140] The server inputs prompts into the generative AI model to generate meal suggestions.

[1141] Input: Generated prompt statement

[1142] Output: Meal suggestions from a generative AI model

[1143] How it works: The server uses the OpenAI API to send the generated prompt to the AI ​​model and receive meal suggestions.

[1144] Step 5:

[1145] The server transmits the generated meal suggestions to the user terminal.

[1146] Input: Meal suggestions from a generative AI model

[1147] Output: Meal suggestions displayed on the user's device

[1148] Specific operation: The server sends the received meal suggestions to the user's device, allowing the user to review the suggestions through the app.

[1149] Step 6:

[1150] The user uses the terminal to review the suggested meals and place an order.

[1151] Input: Meal suggestions sent by the server

[1152] Output: User's order information

[1153] Specific actions: The user reviews the suggested meals through the app and presses the order button to confirm the order.

[1154] In this way, it is possible to propose and order meals that are efficient and satisfying, taking into account the preferences and dietary restrictions of multiple people.

[1155] Example 3

[1156] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1157] Conventional meal recommendation systems have difficulty providing meal options that fully consider individual users' preferences and allergy information, making it difficult to provide meal options that satisfy everyone. Furthermore, they lack a mechanism for effectively reflecting users' selection results, resulting in problems with reduced recommendation accuracy and satisfaction. This has led to an increasing need for a fair and personalized meal recommendation system to increase user satisfaction.

[1158] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1159] In this invention, the server includes means for receiving requests from users, means for collecting the user's past dietary history and allergy information, means for generating prompt sentences to be input to the generative AI model based on the collected data, means for generating meal options using the generative AI model, means for sending the generated meal options to a user interface, means for displaying the meal options on the user interface, means for sending the user's selection results to the server, and means for saving the user's selection results in a database. This enables personalized meal suggestions that take into account the individual preferences and restrictions of each user, thereby realizing fair selections that everyone can agree on.

[1160] The "means for receiving a request from a user" is a function that allows a user to send a request for meal suggestions to the system and for the server to receive the request.

[1161] "Means for collecting the user's past dietary history and allergy information" is a function for retrieving and collecting information about the meals and allergies selected by the user in the past from a database.

[1162] The "means for generating prompt sentences to be input into the generative AI model" is a function that creates instructions (prompt sentences) for the generative AI model to generate appropriate meal options based on collected data.

[1163] "Means for generating meal options using a generative AI model" refers to a function for inputting a prompt sentence into a generative AI model and generating multiple meal options as a result.

[1164] "Means for transmitting the generated meal options to a user interface" means a function for transmitting the meal options generated by the generative AI model to a user interface so that the user can review them.

[1165] The "means for displaying meal options on the user interface" is a function for visually displaying the meal options generated on the user interface so that the user can confirm them.

[1166] The "means for transmitting the results of the user's selection to the server" is a function for transmitting the results of the meal the user has selected on the user interface to the server.

[1167] "Means for saving the user's selection results in a database" is a function for saving the results of the user's meal selection in a database and reflecting them in future suggestions.

[1168] The present invention is a system that provides a user with personalized meal suggestions and leaves the final selection up to the user. Specific embodiments of this system will be described below.

[1169] Hardware and Software Configuration

[1170] server

[1171] The server receives user requests and has a database for collecting the user's past dietary history and allergy information. The server generates meal options using a generative AI model and sends the generated options to the user interface. Specifically, the server uses the following software and hardware:

[1172] Database Management System (DBMS): Stores and manages users' past dietary history and allergy information.

[1173] Generative AI model: A machine learning model that generates meal options based on user data.

[1174] Web Server: A server that sends data to the user interface.

[1175] Terminal

[1176] The terminal is a device used by the user that receives the meal options sent from the server and displays them on a user interface. The terminal uses software such as:

[1177] Web browser or mobile application: Provides the user interface and allows users to view and select their meal options.

[1178] User

[1179] The user accesses the system through a terminal and makes a final selection from the proposed meal options. The user's selection is sent to the server through the terminal and stored in a database.

[1180] Data processing and calculation

[1181] When the server receives a request from a user, it first collects the user's past dietary history and allergy information from a database. Then, based on the collected data, it generates a prompt sentence to be input into the generative AI model. For example, it generates a prompt sentence like the following:

[1182] Example prompt sentence:

[1183] "Generate suggestions for tonight's dinner, taking into account the user's past eating history and allergy information."

[1184] Based on this prompt, the generative AI model generates meal options such as "curry rice," "chicken salad," and "pasta." The generated options are sent from the server to the user interface.

[1185] The device receives the meal options sent from the server and displays them on the user interface. The user makes a final selection from the displayed options and sends the result to the server via the device. The server stores the user's selection in a database and reflects it in future suggestions.

[1186] Specific examples

[1187] For example, if a user requests "today's dinner suggestions," the server might do the following:

[1188] 1. Request received: The server receives a request for "today's dinner suggestions."

[1189] 2. Data collection: The server collects the user's past dietary history and allergy information from the database.

[1190] 3. Prompt generation: The server generates a prompt saying, "Please generate suggestions for today's dinner, taking into account the user's past eating history and allergy information."

[1191] 4. Option generation: The server inputs the prompt sentence into the generative AI model, generating options such as "curry rice," "chicken salad," and "pasta."

[1192] 5. Sending choices: The server sends the generated choices to the user interface.

[1193] 6. Display options: The terminal displays the received options on the user interface.

[1194] 7. User selection: The user selects "curry rice."

[1195] 8. Sending selection results: The device sends the user's selection results to the server.

[1196] 9. Data storage: The server stores the user's selection in a database for future recommendations.

[1197] In this way, the system provides personalized meal suggestions to the user and leaves the final selection up to the user, thereby achieving fair and satisfying meal selection. The flow of the specification process in Example 3 will be described with reference to FIG. 15.

[1198] Step 1:

[1199] Receiving a user request

[1200] Subject: Server

[1201] The server receives a request from a user. For example, a request for "tonight's dinner suggestions" is input. The server analyzes this request and extracts the information needed for the next processing step. The input is the user's request, and the output is the analyzed request information.

[1202] Step 2:

[1203] Data collection

[1204] Subject: Server

[1205] The server collects the user's past dietary history and allergy information from a database. The input is the parsed request information, and the output is the collected user's dietary history and allergy information. Specifically, it executes a database query to obtain the required data.

[1206] Step 3:

[1207] Generate prompt statement

[1208] Subject: Server

[1209] The server generates a prompt sentence to be input into the generative AI model based on the collected data. The input is the collected user's dietary history and allergy information, and the output is the generated prompt sentence. Specifically, it creates a prompt sentence in the format "Please generate suggestions for tonight's dinner, taking into account the user's past dietary history and allergy information."

[1210] Step 4:

[1211] Meal Choice Generation

[1212] Subject: Server

[1213] The server inputs a prompt sentence into the generative AI model to generate meal options. The input is the generated prompt sentence, and the output is the generated meal options. Specifically, the generative AI model generates options such as "curry rice," "chicken salad," and "pasta."

[1214] Step 5:

[1215] Submit your choices

[1216] Subject: Server

[1217] The server sends the generated meal options to the user interface. The input is the generated meal options, and the output is the data sent to the user interface. Specifically, the data is sent using an HTTP request.

[1218] Step 6:

[1219] Displaying options

[1220] Subject: Terminal

[1221] The device receives the meal options sent from the server and displays them on a user interface. The input is the data sent from the server, and the output is the meal options displayed on the user interface. Specifically, the options are displayed in a web browser or a mobile application.

[1222] Step 7:

[1223] User Selection

[1224] Subject: User

[1225] The user checks the proposed meal options through the device's user interface and makes a final selection. The input is the meal options displayed on the user interface, and the output is the user's selection. Specifically, the user selects "curry rice."

[1226] Step 8:

[1227] Sending the selection results

[1228] Subject: Terminal

[1229] The terminal sends the results of the user's selection to the server. The input is the user's selection, and the output is the data sent to the server. Specifically, the data is sent using an HTTP request.

[1230] Step 9:

[1231] Saving and updating data

[1232] Subject: Server

[1233] The server receives the user's final selection and stores it in a database. The input is the data sent to the server, and the output is the selection stored in the database. Specifically, it adds a new record to the database and reflects it in future suggestions.

[1234] (Application example 3)

[1235] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1236] With conventional food delivery systems, when multiple people order a meal together, it is difficult to fairly reflect everyone's opinions. It is also difficult to propose a meal that satisfies everyone while taking into account each individual's dietary preferences and restrictions. This makes meal selection for groups complicated, resulting in a decrease in satisfaction.

[1237] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1238] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for presenting suggested meal options on a user interface so that the user can make a final selection from among them, and a means for determining the option that receives the most votes as the final selection. This makes it possible to make meal suggestions that fairly reflect the opinions of all people and take into account each individual's preferences and restrictions, making it possible to smoothly select meals for a group.

[1239] "Means for providing meal suggestions that reflect the opinions of multiple users" refers to a function that generates appropriate meal options based on dietary preferences and restrictions collected from multiple users.

[1240] "A means of making suggestions that take everyone's opinions into consideration" is a function that makes meal suggestions that everyone can agree on based on the opinions and restrictions collected from each user.

[1241] A "means for providing services for groups" is a function that provides services that are intended for use by multiple users together.

[1242] "A means for presenting suggested meal options on a user interface and allowing the user to make a final selection" refers to a function that displays meal options generated by the system to the user and provides an interface for the user to make a selection from among them.

[1243] The "means of determining the option with the most votes as the final selection" is a function that aggregates the results of users' votes and determines the option with the most votes as the final selection.

[1244] To implement the present invention, a system including a server, a user terminal, and a user interface is required. Specific embodiments are described below.

[1245] System Configuration

[1246] 1. Server:

[1247] The server includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing service for groups, means for presenting suggested meal options on a user interface and allowing the user to make a final selection from among them, and means for determining the option that receives the most votes as the final selection.

[1248] 2. User Device:

[1249] The user terminal is a device such as a smartphone or tablet, and is used by the user to check meal options and cast a vote through an interface provided by the server.

[1250] 3. User Interface:

[1251] The user interface provides a screen for the user to review and vote on the suggested meal options. The interface is designed to be easy for the user to operate.

[1252] Program processing

[1253] The server performs the following process.

[1254] 1. Menu suggestions:

[1255] The server randomly selects three menus from predefined menu options and presents them to the user's device using the Python random.sample module.

[1256] 2. Vote Collection:

[1257] The server collects votes from each user. The user makes a selection from a menu of suggestions and sends that selection to the server. If an invalid selection is made, the user is prompted to select again.

[1258] 3. Final Selection:

[1259] The server tallies the collected votes and determines the menu with the most votes as the final choice, using the Python collections.Counter module.

[1260] Specific examples

[1261] For example, when user 1, user 2, and user 3 order a meal together, the server suggests "pizza," "sushi," and "curry." Each user votes for their preference, and the menu with the most votes is selected as the final menu item.

[1262] Example prompt sentence:

[1263] "User 1, please choose from the following menu: ['Pizza', 'Sushi', 'Curry']:"

[1264] "User 2, please choose from the following menu: ['Pizza', 'Sushi', 'Curry']:"

[1265] "User 3, please choose from the following menu: ['Pizza', 'Sushi', 'Curry']:"

[1266] In this way, it is possible to fairly reflect everyone's opinions and propose meals that take into account each individual's preferences and restrictions, making it easier for groups to choose meals.

[1267] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1268] Step 1:

[1269] The server randomly selects three menus from a predefined menu of options.

[1270] Input: A list of predefined menu options.

[1271] Data processing: Using Python's random.sample module, three menus are randomly selected from the list.

[1272] Output: The three selected menus.

[1273] What happens: The server reads the list of menu options and randomly selects three from it.

[1274] Step 2:

[1275] The server transmits the selected three menus to the user terminal and presents them to the user.

[1276] Input: 3 selected menus.

[1277] Data processing: Converts the selected menu into a format for display on the user interface.

[1278] Output: The menu choices displayed on the user's terminal.

[1279] Specific operation: The server converts the selected menu into a format suitable for the user interface and sends it to the user terminal, which receives it and displays it on the screen.

[1280] Step 3:

[1281] The user selects one from the presented menu and sends it to the server.

[1282] Input: The menu selected by the user.

[1283] Data processing: Converting the user's selection into a data format for sending to the server.

[1284] Output: The user's selection data that is sent to the server.

[1285] Specific operation: The user selects one item from a menu presented through the user interface and sends that selection to the server.

[1286] Step 4:

[1287] The server collects selection data from each user and prompts them to make a selection again if an invalid selection is made.

[1288] Input: Selection data submitted by each user.

[1289] Data processing: Check the validity of the selected data, and if an invalid selection is made, prompt the user to select again.

[1290] Output: A list of valid selections.

[1291] Specific operation: The server receives the selection data sent by each user and checks its validity. If any selection is invalid, it sends a message to the user prompting them to select again.

[1292] Step 5:

[1293] The server tallys the collected selection data and determines the menu with the most votes as the final selection.

[1294] Input: A list of valid selection data.

[1295] Data processing: Use the Python collections.Counter module to count the number of votes for each menu item.

[1296] Output: The menu with the most votes.

[1297] Specific operation: The server aggregates the collected selection data and counts the number of votes for each menu item. The menu item with the most votes is determined as the final selection and notified to the user.

[1298] 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.

[1299] "Example 1"

[1300] In one embodiment of the present invention, a system is provided that includes an emotion engine that recognizes a user's emotions. The system recognizes emotions from the user's facial expressions, tone of voice, text input, etc., and reflects this information in meal recommendations. For example, if a user expresses a happy emotion, the system suggests meals that are predicted to be enjoyed by the user. Alternatively, if a user expresses a sad emotion, the system suggests meals that are predicted to comfort the user.

[1301] "Example 2"

[1302] In another embodiment, a system is provided in which the means for making suggestions that take into account everyone's opinions is based on an emotion engine that recognizes users' emotions and generates meal suggestions that everyone can agree on. This system recognizes the emotions of each user and makes meal suggestions based on those emotions. For example, if everyone is expressing joy, the system suggests meals that are predicted to be liked by everyone. Also, if some users are expressing sadness, the system suggests meals that comfort the user and that other users can agree on.

[1303] "Example 3"

[1304] In yet another embodiment, the means for providing group-oriented services is based on the user's emotions.

[1305] A system is provided that provides services to users based on an emotion engine that recognizes emotions. This system recognizes the emotions of each user and provides services based on those emotions. For example, if a user is expressing happiness, the system provides the user with a service that is predicted to increase the user's happiness. Also, if a user is expressing sadness, the system provides the user with a service that is predicted to reduce the user's sadness.

[1306] The processing flow of each embodiment will be described below.

[1307] "Example 1"

[1308] Step 1: Recognize emotions from the user's facial expressions, tone of voice, text input, etc.

[1309] Step 2: Analyze the recognized emotions and determine the user's current emotional state.

[1310] Step 3: Based on the determined emotional state, suggest meals that the user is likely to like.

[1311] Step 1: Recognize each user's emotions.

[1312] Step 2: Analyze the recognized emotions and determine each user's current emotional state.

[1313] Step 3: Generate meal suggestions that everyone can agree on based on the determined emotional state.

[1314] "Example 3"

[1315] Step 1: Recognize each user's emotions.

[1316] Step 2: Analyze the recognized emotions and determine each user's current emotional state.

[1317] Step 3: Providing services to the user based on the determined emotional state.

[1318] Example 1

[1319] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1320] Conventional meal recommendation systems have difficulty taking into account the dietary preferences and restrictions of individual users, and are unable to make suggestions that reflect the user's emotions. Therefore, in order to increase user satisfaction, meal recommendations that take into account individual preferences, restrictions, and emotions are required. It is also difficult to make meal recommendations that reflect the opinions of multiple people or that take into account the opinions of everyone. A system that can solve these issues is needed.

[1321] 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.

[1322] In this invention, the server includes means for collecting each individual's dietary preferences and restrictions, means for recognizing the user's emotions, means for generating meal suggestions based on the collected dietary preferences, restrictions, and emotion information, means for presenting the generated meal suggestions to the user, means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, and means for providing services for groups. This makes it possible to make meal suggestions that take into account the preferences, restrictions, and emotions of each individual user, and also makes suggestions that reflect the opinions of multiple people or that take into account the opinions of all people.

[1323] A "means for collecting individual dietary preferences and restrictions" is a system that includes an interface and database for users to input and collect their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[1324] The "means for recognizing user emotions" refers to a system that includes machine learning models and algorithms for analyzing and recognizing emotions from a user's facial expressions, tone of voice, text input, etc.

[1325] "Means for generating meal suggestions based on collected dietary preferences, restrictions, and emotional information" means a system that includes a generative AI model or algorithm for generating appropriate meal suggestions based on data collected from a user.

[1326] "Means for presenting generated meal suggestions to a user" refers to a system for displaying the generated meal suggestions to a user through a user interface.

[1327] The "means for making meal suggestions that reflect the opinions of multiple people" is a system that generates meal suggestions that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[1328] The "means for making suggestions that take everyone's opinions into consideration" is a system that generates meal suggestions that everyone can agree on based on the collected information about each individual's dietary preferences and restrictions.

[1329] A "group service offering" is a system for providing meal suggestions or other services that can be used by multiple users together.

[1330] The present invention relates to a meal recommendation system that takes into account a user's dietary preferences, dietary restrictions, and emotions. Specific embodiments of this system will be described below.

[1331] System configuration

[1332] This system consists of three main components: a server, a terminal, and a user.

[1333] server

[1334] The server has the following functions:

[1335] 1. Data collection: Collect each individual's dietary preferences and restrictions through a user interface. Use a relational database such as MySQL or PostgreSQL.

[1336] 2. Emotion Recognition: Use machine learning frameworks such as TensorFlow and PyTorch to recognize emotions from the user's facial expressions, tone of voice, text input, etc.

[1337] 3. Meal suggestion generation: Based on the collected data, meal suggestions are generated using a generative AI model (e.g., OpenAI's GPT-3).

[1338] 4. Providing suggestions: The generated meal suggestions are sent to the terminal to be presented to the user.

[1339] Terminal

[1340] A terminal is a device such as a smartphone or computer that has the following functions:

[1341] 1. Data Entry: Provide an interface for users to enter their dietary preferences and restrictions.

[1342] 2. Emotional data collection: Using a camera and microphone to capture the user's facial expressions and tone of voice, as well as text input.

[1343] 3. Display suggestions: Display meal suggestions sent from the server to the user.

[1344] User

[1345] Users use the system to input their dietary preferences, restrictions, and emotions, and then review suggested meals.

[1346] Specific examples

[1347] Here is a concrete example of how the system works:

[1348] 1. Data entry: The user opens the smartphone application and enters information such as "I have a nut allergy," "I like spicy food," and "I would like to eat a low-calorie diet."

[1349] 2. Emotion data collection: When a user smiles at the camera, the device captures their facial expression and sends it to the server. Also, when a user types "I'm tired today," that data is also sent to the server.

[1350] 3. Emotion Recognition: The server passes the received data to the emotion engine to recognize the user's emotions. For example, it recognizes the emotion "joy" from a smiling face and the emotion "fatigue" from text input.

[1351] 4. Meal suggestion generation: The server generates meal suggestions using a generative AI model based on the collected data. An example of a prompt sentence is, "The user has a nut allergy, likes spicy food, and wants a low-calorie diet. Furthermore, their current emotion is joy. What kind of meal would you suggest?"

[1352] 5. Suggestion presentation: The generated meal suggestion (e.g., "How about your favorite sushi?") is sent to the terminal and displayed to the user.

[1353] In this way, the system can provide meal suggestions tailored to the user's individual needs and emotions.

[1354] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1355] Step 1:

[1356] Users open an application on their smartphone or computer and enter their dietary preferences and restrictions, such as "I have a nut allergy," "I like spicy food," or "I prefer a low-calorie diet."

[1357] Input: Information about the user's dietary preferences and restrictions

[1358] Output: The entered information is saved on the device and sent to the server.

[1359] Step 2:

[1360] The device collects emotion data such as the user's facial expressions, tone of voice, and text input. For example, it uses a camera to capture the user's smile and a microphone to record the tone of voice. If the user inputs text such as "I'm tired today," that data is also collected.

[1361] Input: User facial expressions, tone of voice, and text input

[1362] Output: The collected emotion data is sent to the server.

[1363] Step 3:

[1364] The server receives the dietary preferences, restrictions, and emotional data sent from the device and stores it in a database using a relational database such as MySQL or PostgreSQL.

[1365] Input: Food preferences, restrictions, and emotional data sent from the device

[1366] Output: User information stored in the database

[1367] Step 4:

[1368] The server passes the stored emotion data to the emotion engine, which then recognizes the user's emotion. The emotion engine uses machine learning frameworks such as TensorFlow and PyTorch to analyze emotions from the user's facial expressions, tone of voice, and text input. For example, it can recognize the emotion "joy" from a smiling face and the emotion "fatigue" from text input.

[1369] Input: Stored emotion data

[1370] Output: Recognized user emotion information

[1371] Step 5:

[1372] The server generates meal suggestions using a generative AI model based on the collected dietary preferences and restrictions and the recognized emotion information. For example, the following prompt sentence is input to the generative AI model: "The user has a nut allergy, likes spicy food, and wishes to eat a low-calorie diet. Furthermore, their current emotion is joy. What meal would you suggest?"

[1373] Input: Food preferences and restrictions, perceived emotional information

[1374] Output: Generated meal suggestions

[1375] Step 6:

[1376] The server transmits the generated meal suggestions to the terminal.

[1377] Input: Generated meal suggestions

[1378] Output: Meal suggestions sent to the device

[1379] Step 7:

[1380] The device displays the meal suggestions sent from the server to the user. For example, it displays "How about your favorite sushi?" on the smartphone screen.

[1381] Input: Meal suggestions sent from the server

[1382] Output: Meal suggestions displayed to the user

[1383] In this way, the system can provide meal suggestions tailored to the user's individual needs and emotions.

[1384] (Application example 1)

[1385] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1386] Conventional meal recommendation systems can take into account a user's dietary preferences and restrictions, but they cannot make recommendations that reflect the user's emotions. As a result, they are unable to make optimal meal recommendations based on the user's emotional state, making it difficult to increase user satisfaction. In addition, when making meal recommendations that reflect the opinions of multiple people, it is difficult to generate recommendations that take into account everyone's opinions, making it impossible to increase the satisfaction of the entire group.

[1387] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing services for groups, means for collecting each individual's dietary preferences and restrictions, means for recognizing the user's emotions, and means for making meal suggestions based on the recognized emotions. This makes it possible to make optimal meal suggestions based on the user's emotional state, and by making suggestions that take into account the opinions of multiple people, it is possible to increase the satisfaction of the entire group.

[1388] "Means for suggesting meals that reflect the opinions of multiple people" is a function that suggests meals that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[1389] The "means of making suggestions that take everyone's opinions into consideration" is a function that generates meal suggestions that everyone can agree on based on the collected information about each individual's dietary preferences and restrictions.

[1390] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[1391] "Means for collecting individual dietary preferences and restrictions" refers to a function that allows users to input their own dietary preferences, allergy information, health restrictions, etc., and the system collects this information.

[1392] "Means for recognizing user emotions" refers to a function for recognizing emotions from the user's facial expressions, tone of voice, text input, etc.

[1393] The "means for suggesting meals based on recognized emotions" is a function for suggesting optimal meals according to the user's emotional state.

[1394] A system for implementing the present invention includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing service for groups, means for collecting each individual's dietary preferences and restrictions, means for recognizing a user's emotions, and means for making meal suggestions based on the recognized emotions.

[1395] Hardware and Software Configuration

[1396] The server uses the following hardware and software:

[1397] Hardware: Smartphone (camera, microphone)

[1398] Software: OpenCV (image processing library), Keras (deep learning library), SpeechRecognition (speech recognition library), TextBlob (text analysis library)

[1399] Data processing and calculation

[1400] 1. Image processing: The image of the user's face taken with the smartphone camera is read, converted to grayscale, and input into the emotion recognition model. This allows the emotion to be recognized from the user's facial expression.

[1401] 2. Speech processing: Converts speech recorded by a smartphone microphone into text and analyzes the sentiment of the text, thereby recognizing emotions from the user's tone of voice.

[1402] 3. Emotion recognition: Integrates emotional information obtained from images and audio to determine the final emotion.

[1403] 4. Meal Suggestion: Based on the determined emotions, appropriate meals are suggested.

[1404] Specific examples

[1405] If the user smiles into the smartphone camera, the system recognizes this as "happy" and suggests meals like sushi or pizza. If the user has a sad expression, the system recognizes this as "sad" and suggests meals like chocolate or soup.

[1406] Prompt Sentence Examples

[1407] Design a system that recognizes emotions from a user's facial and vocal expressions and suggests appropriate meals based on those emotions. For example, if a user expresses happiness, it suggests meals such as sushi or pizza, and if a user expresses sadness, it suggests meals such as chocolate or soup.

[1408] In this way, it is possible to make optimal meal suggestions based on the user's emotional state, and by making suggestions that take into account the opinions of multiple people, it is possible to increase the satisfaction of the entire group.

[1409] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1410] Step 1:

[1411] The user takes a picture of their face in front of the smartphone camera. The input is the user's face image, and the output is image data. The smartphone camera is used to capture the user's face image and save it as image data.

[1412] Step 2:

[1413] The server receives the facial image and converts it to grayscale using OpenCV. The input is facial image data and the output is grayscale image data. The server converts the received facial image to grayscale using the OpenCV library and processes it into a format suitable for the emotion recognition model.

[1414] Step 3:

[1415] The server uses Keras to input grayscale images into an emotion recognition model to recognize emotions. The input is grayscale image data, and the output is the recognized emotion label. The server uses the Keras library to input grayscale images into an emotion recognition model to predict the user's emotion.

[1416] Step 4:

[1417] The user records audio using the smartphone's microphone. The input is the user's voice and the output is audio data. The smartphone's microphone is used to capture the user's voice and save it as audio data.

[1418] Step 5:

[1419] The server receives the voice data and converts it to text using SpeechRecognition. The input is voice data and the output is text data. The server converts the received voice data to text using the SpeechRecognition library.

[1420] Step 6:

[1421] The server analyzes the sentiment of text data using TextBlob. The input is text data and the output is the recognized sentiment label. The server uses the TextBlob library to analyze the sentiment of the text data and predict the user's sentiment.

[1422] Step 7:

[1423] The server integrates the emotional information obtained from the image and audio and determines the final emotion. The input is the emotion label from the image and the emotion label from the audio, and the output is the final emotion label. The server integrates the emotional information obtained from the image and the audio and determines the most appropriate emotion.

[1424] Step 8:

[1425] The server suggests meals based on the final emotion. The input is the final emotion label, and the output is a suggested meal list. The server references a database for suggesting appropriate meals based on the final emotion label and generates a meal list to suggest to the user.

[1426] Step 9:

[1427] The user checks the suggested meal list on their smartphone and selects a meal. The input is the suggested meal list, and the output is the meal selected by the user. The user checks the suggested meal list on the smartphone screen and selects the meal they want.

[1428] Step 10:

[1429] The server sends the user's selected meal to the delivery service and confirms the order. The input is the user's selected meal and the output is the order information for the delivery service. The server sends the user's selected meal to the delivery service and confirms the order.

[1430] Example 2

[1431] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1432] Conventional meal recommendation systems have difficulty reflecting the opinions of multiple people, making it difficult to make recommendations that everyone can agree on. Furthermore, they are unable to take user emotions into account when making recommendations, making it impossible to make optimal recommendations for specific situations. This creates the problem of being unable to increase satisfaction for the entire group.

[1433] 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.

[1434] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for recognizing the emotions of each individual, and a means for generating meal suggestions based on the emotions, thereby enabling optimal meal suggestions that take into account the opinions and emotions of multiple people.

[1435] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that makes meal suggestions that everyone can agree on based on the dietary preferences and restrictions collected from multiple users.

[1436] "Means for making suggestions that take everyone's opinions into consideration" is a function that generates meal suggestions that everyone can agree on based on the collected dietary preferences and restrictions of each user.

[1437] "Means for providing services to groups" refers to a function for providing meal suggestions and other related services to groups of multiple users.

[1438] "Means for recognizing each individual's emotions" is a function that analyzes the user's facial expressions, voice, etc. to understand their emotional state.

[1439] The "means for generating meal suggestions based on emotions" is a function for generating optimal meal suggestions based on the recognized emotional state of the user.

[1440] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions, voice, etc. to recognize their emotional state.

[1441] A "generative AI model" is an artificial intelligence model that generates suggestions and answers in natural language based on input data.

[1442] A "prompt" is an instruction given to a generative AI model to obtain a specific output.

[1443] MODE FOR CARRYING OUT THE INVENTION

[1444] The present invention is a system for proposing a meal plan that satisfies all of the opinions and feelings of multiple people. A specific embodiment of this system will be described below.

[1445] Information gathering

[1446] The server collects user preferences and allergy information. Specifically, it stores the questionnaire results entered by the user via their device and past dietary history in a database. The software used is a database management system (e.g., MySQL).

[1447] Specific behavior:

[1448] The user enters "I like fish dishes" and "I don't have any allergies" into the questionnaire form displayed on the device screen.

[1449] The terminal transmits the input information to the server.

[1450] The server stores the received information in a MySQL database.

[1451] Data analysis

[1452] The server then performs data analysis on the collected information, specifically using Python's Pandas library to identify meal options that everyone is likely to like.

[1453] Specific behavior:

[1454] The server retrieves information such as "I like fish dishes" and "I have no allergies" from the MySQL database.

[1455] The server uses the Pandas library to identify everyone's preferred meal options.

[1456] Proposal generation

[1457] The server then uses the analysis results to generate meal recommendations that everyone can agree on, using a generative AI model (e.g., OpenAI's GPT-3) to create the recommendations.

[1458] Specific behavior:

[1459] Based on the analysis result that "everyone likes fish dishes," the server sends a prompt to GPT-3.

[1460] GPT-3 generates the result "Suggest a restaurant that serves fish."

[1461] The server sends the generated proposal to the terminal.

[1462] Emotion Recognition (Alternative Embodiment)

[1463] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the user's facial expressions and voice through a camera and microphone to understand their emotional state. The hardware used is a camera and microphone, and the software used is an emotion recognition engine (e.g., Microsoft Azure's Emotion API).

[1464] Specific behavior:

[1465] The user smiles into the device's camera.

[1466] The device sends the video captured by the camera to the server.

[1467] The server uses Microsoft Azure's Emotion API to recognize when the user is expressing the emotion "joy."

[1468] Emotion-based suggestions

[1469] The server then uses the emotion recognition results to make meal recommendations that everyone can agree on. Specifically, it uses a generative AI model to create recommendations based on the emotional state of the person.

[1470] Specific behavior:

[1471] Based on the emotion recognition result that "everyone is showing the emotion of joy," the server sends a prompt message to GPT-3.

[1472] GPT-3 generates the result "Suggesting meals that are predicted to be enjoyed by everyone."

[1473] The server sends the generated proposal to the terminal.

[1474] Examples and prompts

[1475] Examples:

[1476] User A: I like fish dishes and I have no allergies.

[1477] User B: I like fish dishes and I don't have any allergies.

[1478] User C: I like fish dishes and I have no allergies.

[1479] Example prompt sentence:

[1480] Generate meal suggestions that everyone can agree on based on user preferences and allergies. Consider the following information:

[1481] User A: I like fish dishes and I have no allergies.

[1482] User B: I like fish dishes and I don't have any allergies.

[1483] User C: I like fish dishes and I have no allergies.

[1484] By feeding this prompt into a generative AI model, we can get meal suggestions that everyone can agree on.

[1485] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1486] Program processing flow

[1487] Step 1: Gather information

[1488] Specific description:

[1489] The server collects information about the user's preferences and allergies, specifically, the results of a questionnaire entered by the user via their device and past meal history, and stores this information in a database.

[1490] Input: Preferences and allergy information you enter into your device.

[1491] Output: User preferences and allergy information stored in a database.

[1492] Specific behavior:

[1493] The user enters "I like fish dishes" and "I don't have any allergies" into the questionnaire form displayed on the terminal screen.

[1494] The terminal transmits the input information to the server.

[1495] The server stores the received information in a MySQL database.

[1496] Step 2: Data analysis

[1497] Specific description:

[1498] The server then performs data analysis on the collected information, specifically using Python's Pandas library to identify meal options that everyone is likely to like.

[1499] Input: User preferences and allergy information retrieved from a database.

[1500] Output: Meal options that everyone is likely to like.

[1501] Specific behavior:

[1502] The server retrieves information such as "I like fish dishes" and "I have no allergies" from the MySQL database.

[1503] The server uses the Pandas library to identify everyone's preferred meal options.

[1504] Step 3: Proposal Generation

[1505] Specific description:

[1506] The server then uses the analysis results to generate meal recommendations that everyone can agree on, using a generative AI model (e.g., OpenAI's GPT-3) to create the recommendations.

[1507] Input: Data analysis results.

[1508] Output: Meal suggestions that everyone can agree on.

[1509] Specific behavior:

[1510] The server sends a prompt to GPT-3 based on the analysis result that "everyone likes fish dishes."

[1511] GPT-3 generates the result "Suggest a restaurant that serves fish."

[1512] The server transmits the generated proposal to the terminal.

[1513] Step 4: Emotion Recognition (Alternative Embodiment)

[1514] Specific description:

[1515] The server uses an emotion engine to recognize the user's emotions. Specifically, it analyzes the user's facial expressions and voice through a camera and microphone to understand their emotional state.

[1516] Input: User facial expressions and voice captured from camera and microphone.

[1517] Output: Perceived emotional state of the user.

[1518] Specific behavior:

[1519] The user smiles into the device's camera.

[1520] The terminal transmits the video captured by the camera to the server.

[1521] The server uses an emotion recognition engine to recognize that the user is expressing the emotion "happiness."

[1522] Step 5: Emotion-based suggestions

[1523] Specific description:

[1524] The server then uses the emotion recognition results to make meal recommendations that everyone can agree on. Specifically, it uses a generative AI model to create recommendations based on the emotional state of the person.

[1525] Input: Emotion recognition results.

[1526] Output: Food suggestions based on emotional state.

[1527] Specific behavior:

[1528] The server sends a prompt message to GPT-3 based on the emotion recognition result that "everyone is showing the emotion of joy."

[1529] GPT-3 generates the result: "Suggest meals that are predicted to be enjoyed by everyone."

[1530] The server transmits the generated proposal to the terminal.

[1531] (Application example 2)

[1532] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1533] Conventional meal recommendation systems have difficulty reflecting the opinions of multiple users, making it difficult to find meal options that everyone can agree on. Furthermore, because suggestions do not take user emotions into account, satisfaction may decrease in certain situations. Furthermore, when generating suggestions, individual preferences and restrictions may not be fully reflected, making it impossible to make optimal suggestions. To solve these issues, a system is needed that recognizes user emotions and uses a generative AI model to make meal recommendations that everyone can agree on.

[1534] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1535] In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple users, means for making suggestions that take into account the opinions of all users, means for providing group services, means for recognizing user emotions, means for making meal suggestions based on the emotions, means for generating meal suggestions using a generative AI model based on collected information, and means for outputting the generated suggestions as prompt sentences. This makes it possible to make meal suggestions that everyone can agree on while taking into account the emotions of users.

[1536] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that suggests meal options that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[1537] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively analyzes each user's collected dietary preferences and restrictions and generates meal suggestions that everyone can agree on.

[1538] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[1539] "Means for recognizing user emotions" refers to a function for recognizing emotions in real time from the user's facial expressions, voice, etc.

[1540] The "means for suggesting meals based on emotions" is a function for suggesting optimal meals by taking into account the recognized emotions of the user.

[1541] "Means for generating meal suggestions using a generative AI model based on collected information" refers to a function that uses a generative AI model to generate optimal meal suggestions based on information such as a user's preferences, restrictions, and emotions.

[1542] "Means for outputting generated suggestions as prompt sentences" refers to a function for outputting meal suggestions generated by a generative AI model in a format that is easy for the user to understand.

[1543] The system for carrying out the present invention proposes meals that are satisfactory to all users based on information collected from multiple users. A specific embodiment of this system will be described below.

[1544] Hardware and software used

[1545] Hardware: Smartphones, smart glasses

[1546] Software: Emotion recognition engine (e.g., Affectiva SDK), database (e.g., Firebase), generative AI model (e.g., GPT-4)

[1547] System configuration

[1548] 1. Collection of User Information

[1549] The camera on a smartphone or smart glasses is used to capture the user's facial expressions in real time.

[1550] An emotion recognition engine is used to extract emotion data from the captured facial expressions.

[1551] Store user dietary preferences and allergy information in your Firebase database.

[1552] 2. Generating Meal Suggestions

[1553] Based on the collected user information and emotional data, prompts are input into a generative AI model (GPT-4).

[1554] A generative AI model generates optimal meal suggestions.

[1555] 3. Order Optimization

[1556] It presents suggested meals to users and provides an easy ordering interface.

[1557] Run algorithms to optimize delivery times and costs.

[1558] Specific examples

[1559] scenario

[1560] Three users are trying to order food together. User A likes pizza, User B is a vegetarian, and User C is allergic to fish. Users A and B show happy emotions, while User C shows sad emotions.

[1561] Prompt Sentence Examples

[1562] User A likes: Pizza

[1563] User B's preference: Vegetarian

[1564] User C's preference: Fish allergy

[1565] User A's emotion: Joy

[1566] User B's emotion: joy

[1567] User C's emotion: Sadness

[1568] Generate meal suggestions that everyone can agree on.

[1569] This prompt can then be fed into a generative AI model, which can generate suggestions such as "vegetarian pizza" or "fish-free pasta dishes," making it possible to create meal recommendations that everyone can agree on.

[1570] Processing flow

[1571] The server recognizes the user's emotions and generates meal suggestions using a generative AI model based on the collected information. The generated suggestions are output as prompts and presented to the user. This makes it possible to provide meal suggestions that everyone can agree on while taking into account the user's emotions.

[1572] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1573] Step 1:

[1574] Users use their smartphones or smart glasses to input their dietary preferences and allergy information, which then collects personalized information about the user and stores it in a Firebase database.

[1575] Step 2:

[1576] The device captures the user's facial expressions in real time using a smartphone or smart glasses camera, and the captured facial data is sent to an emotion recognition engine (e.g., Affectiva SDK).

[1577] Step 3:

[1578] The server uses an emotion recognition engine to extract the user's emotions from the captured facial expression data, and the extracted emotion data is stored in the Firebase database.

[1579] Step 4:

[1580] The server retrieves the user's dietary preferences, allergy information, and emotional data collected from the Firebase database, which is used to generate prompts that are fed into a generative AI model (e.g., GPT-4).

[1581] Step 5:

[1582] The server inputs a prompt sentence into the generative AI model to generate optimal meal suggestions, which are then output as prompt sentences.

[1583] Step 6:

[1584] The terminal presents the generated meal suggestions to the user, who can then review the suggested meal suggestions and place an order.

[1585] Step 7:

[1586] The server receives the user's order information, executes an algorithm to optimize delivery time and cost, and notifies the user of the optimized delivery information.

[1587] Step 8:

[1588] The user checks the optimized delivery information and finalizes the order. The server then sends the order information to the restaurant or delivery service, which then arranges for the meal to be delivered.

[1589] Example 3

[1590] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1591] Conventional systems have problems in that they do not adequately reflect the opinions of multiple people when proposing meals or providing services based on the user's emotions. They also face the challenge of accurately recognizing the emotions of individual users and providing appropriate services based on those emotions. This can lead to a decrease in user satisfaction.

[1592] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1593] In this invention, the server includes means for generating suggestions, means for presenting the generated suggestions, means for accepting a user's selection, means for recognizing the user's emotion, and means for providing a service based on the recognized emotion, thereby enabling meal suggestions that reflect the opinions of multiple people and the provision of a service based on the user's emotion.

[1594] The "means for generating a proposal" is a device or program having a function for generating a proposal to a user.

[1595] The "means for presenting the generated proposal" is a device or program having a function for visually or audibly presenting the generated proposal to the user.

[1596] The "means for accepting a user's selection" is a device or program that has the function of accepting a selection when the user makes a selection from the presented suggestions.

[1597] The "means for recognizing a user's emotions" refers to a device or program that has the function of detecting and recognizing a user's emotions.

[1598] The "means for providing a service based on the recognized emotion" is a device or program having a function for providing an appropriate service based on the recognized emotion of the user.

[1599] A "generative AI model" is a model that uses artificial intelligence to generate suggestions.

[1600] An "emotion engine" is software or hardware that recognizes a user's emotions.

[1601] The present invention provides a system for generating and presenting suggestions to a user, accepting the user's selection, recognizing the user's emotions, and providing services based on those emotions. Specific embodiments of this system are described below.

[1602] Hardware and software used

[1603] Server: A server for data processing and proposal generation. For example, a virtual server of a cloud service is used.

[1604] Device: The device on which the user interface is displayed. For example, a smartphone or tablet.

[1605] Emotion engine: Software for recognizing user emotions. For example, using an emotion recognition API.

[1606] Generative AI model: An AI model for generating suggestions. For example, we use a natural language processing model.

[1607] Explanation of program processing

[1608] 1. Proposal generation

[1609] The server uses the generative AI model to generate suggested meal options for the user.

[1610] The server sends a prompt to the generative AI model, for example, "Suggest the following food options for the user: sushi, pizza, salad."

[1611] The generative AI model generates meal options based on the prompt and returns them to the server.

[1612] The server stores the generated suggestions in a database.

[1613] 2. Presenting the proposal

[1614] The server instructs the terminal to display the generated meal options on a user interface.

[1615] The device presents suggestions to the user through a user interface, specifically displaying the options "sushi," "pizza," and "salad" in the form of buttons on the screen.

[1616] 3. User Choice

[1617] The user makes a final choice from the presented options. For example, the user clicks the "Sushi" button.

[1618] The terminal transmits the user's selection to the server, specifically, data including information about the selected "sushi" to the server.

[1619] 4. Emotion recognition

[1620] The server uses an emotion engine to recognize the user's emotion.

[1621] The server sends the user's facial image and voice data to the emotion engine and receives the emotion analysis results. For example, the emotion "joy" is recognized from the user's facial image.

[1622] 5. Provision of Services

[1623] The server uses a generative AI model to suggest appropriate services based on the recognized emotions. Example: "Please suggest services to increase the user's joy."

[1624] The generative AI model generates a service based on the prompt and returns it to the server, suggesting, for example, a "discount coupon for sushi."

[1625] The server transmits the generated service to the terminal.

[1626] The device presents users with services based on their emotions, such as displaying a "sushi discount coupon" on the screen.

[1627] Examples of concrete examples and prompts

[1628] Example 1: Food options

[1629] The server sends the generative AI model a prompt: "Suggest the following food options for the user: sushi, pizza, salad."

[1630] The generative AI model generates the options "sushi," "pizza," and "salad" and returns them to the server.

[1631] The server stores these choices in a database and sends them to the device.

[1632] The device displays the options "Sushi," "Pizza," and "Salad" on the user interface.

[1633] Example 2: Emotion-based service delivery

[1634] The user selects "sushi" and the device sends that information to the server.

[1635] The server sends the user's facial image to the emotion engine, which recognizes the emotion of "joy."

[1636] The server sends a prompt to the generative AI model: "Please suggest a service to increase user joy."

[1637] The generative AI model generates a "sushi discount coupon" and returns it to the server.

[1638] The server sends this service to the terminal, which then displays a "sushi discount coupon" to the user.

[1639] The above is a specific embodiment for carrying out the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1640] Step 1:

[1641] Proposal generation

[1642] The server sends a prompt to the generative AI model, using as input a prompt to generate suggested meal options for the user (e.g., "Please suggest the following meal options for the user: sushi, pizza, salad.").

[1643] The generative AI model generates meal options based on the prompt sentence and returns the options "sushi," "pizza," and "salad" to the server as output.

[1644] The server saves the generated suggestions in a database. As a specific operation, it writes the generated options to the database.

[1645] Step 2:

[1646] Presenting the proposal

[1647] The server instructs the terminal to display the generated meal options on a user interface, using the options stored in the database as input.

[1648] The device presents suggestions to the user through a user interface. Specifically, the options "Sushi," "Pizza," and "Salad" are displayed in the form of buttons on the screen. As an output, the user is presented with a visual representation of the options.

[1649] Step 3:

[1650] User Selection

[1651] The user makes the final choice from the presented options, using the button the user selects (e.g., "Sushi") as input.

[1652] The terminal transmits the user's selection to the server. Specifically, it transmits data including information about the selected "sushi" to the server. As an output, the user's selection information is transmitted to the server.

[1653] Step 4:

[1654] emotion recognition

[1655] The server uses an emotion engine to recognize the user's emotions, using the user's facial image and voice data as input.

[1656] The server sends the user's facial image and voice data to the emotion engine and receives the emotion analysis results. Specifically, the server sends data to the emotion engine and receives the analysis results. The output is the user's emotion (e.g., "joy").

[1657] Step 5:

[1658] Service provision

[1659] The server uses a generative AI model to suggest appropriate services based on the recognized emotion, using the recognized emotion (e.g., "joy") and a prompt sentence (e.g., "Please suggest services to increase the user's joy.") as input.

[1660] The generative AI model generates a service based on the prompt sentence and returns "Sushi discount coupon" to the server as output.

[1661] The server transmits the generated service to the terminal, specifically, transmitting the generated service information to the terminal.

[1662] The device presents services based on the user's emotions. Specifically, it displays a "sushi discount coupon" on the screen. The output is a visual representation of the service to the user.

[1663] (Application example 3)

[1664] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1665] Conventional meal recommendation systems have difficulty making fair recommendations that reflect the opinions of multiple people, and do not provide services that take user emotions into consideration. This makes it difficult to increase user satisfaction. Furthermore, when presenting meal options, they are unable to make optimal recommendations based on the user's emotions, resulting in a lack of service that meets the user's needs. This makes it difficult to make recommendations that satisfy everyone, especially when choosing meals for a group.

[1666] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1667] In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple users, means for making suggestions that take into account the opinions of all users, means for providing group services, means for recognizing a user's emotions, means for suggesting meal options based on the recognized emotions, means for presenting the suggested meal options on a user interface and allowing the user to make a final selection, and means for ordering the selected meal through a delivery service. This enables optimal meal suggestions that take into account the user's emotions, making it possible to realize meal selections that satisfy everyone.

[1668] "Means for making meal suggestions that reflect the opinions of multiple people" refers to a function that generates meal options that reflect everyone's opinions based on the dietary preferences and restrictions collected from multiple users.

[1669] "Means for making suggestions that take everyone's opinions into consideration" is a function that generates meal suggestions that everyone can agree on based on the collected information about each individual's dietary preferences and restrictions.

[1670] A "means for providing group services" is a function for providing common services to multiple users.

[1671] "Means for recognizing user emotions" refers to a function that analyzes data such as the user's face and voice and identifies their emotions.

[1672] "Means for suggesting meal options based on recognized emotions" refers to a function that generates meal options appropriate to a user's emotions based on their emotional data.

[1673] "A means for presenting suggested meal options on a user interface and allowing the user to make a final selection" is a function that displays meal options through a user interface and allows the user to make a final selection from among them.

[1674] "Means for ordering selected meals through a delivery service" refers to a function that allows a user to order selected meals using a delivery service.

[1675] A system for implementing the present invention includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing service for groups, means for recognizing a user's emotion, means for suggesting meal options based on the recognized emotion, means for presenting the suggested meal options on a user interface and allowing the user to make a final selection, and means for ordering the selected meal through a delivery service.

[1676] Hardware and software used

[1677] Hardware: Smartphones, smart glasses, cameras

[1678] Software: Emotion recognition engines (e.g., Microsoft Azure's Emotion API), food delivery service APIs (e.g., Uber Eats and DoorDash), user interface (UI) frameworks

[1679] Data processing and calculation

[1680] 1. Emotion recognition:

[1681] The server scans the user's face using the camera on the smartphone or smart glasses, and then uses an emotion recognition engine to recognize the user's emotions. Specifically, it uses Microsoft Azure's Emotion API to obtain emotional data from the user's facial image.

[1682] 2. Meal Suggestions:

[1683] The server generates optimal meal options for the user based on the recognized emotion data, for example, suggesting special desserts or celebratory meals if the user expresses joy.

[1684] 3. User Interface:

[1685] The server displays the suggested meal options on a user interface, which is provided via a smartphone or smart glasses display, from which the user makes a final selection.

[1686] 4. Delivery arrangements:

[1687] The server orders the meal selected by the user through a food delivery service API, for example, Uber Eats or DoorDash, and arranges for the selected meal to be delivered.

[1688] Specific examples

[1689] Example 1:

[1690] When a user takes a photo of their face with their smartphone and the app recognizes the emotion "joy," it suggests "cake" or "celebration dinner." The user selects "cake" from the suggested options on their smartphone screen, and the app automatically completes the order through a food delivery service.

[1691] Example 2:

[1692] When the user is wearing the smart glasses, the glasses' camera scans the user's face and similarly recognizes emotions to suggest meals, and the user reviews the options on the glasses' display and makes the final selection via voice command.

[1693] Prompt Sentence Examples

[1694] "Write a Python program that recognizes a user's emotions and suggests the best meal options based on those emotions. Use Microsoft Azure's Emotion API for emotion recognition and use conditional branching based on the emotion data to suggest meals."

[1695] The above is an embodiment of the present invention.

[1696] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1697] Step 1:

[1698] A user takes a picture of their face using the camera on their smartphone or smart glasses.

[1699] Input: User's face image

[1700] Output: Face image data

[1701] Specific operation: The user activates the camera on their smartphone or smart glasses and takes a picture of their face. The captured image is then stored on the device.

[1702] Step 2:

[1703] The terminal transmits the captured facial image to the server.

[1704] Input: Face image data

[1705] Output: Facial image data sent to the server

[1706] Specific operation: The device uploads the captured facial image data to a server via the Internet. The server stores the received facial image data.

[1707] Step 3:

[1708] The server transmits the facial image data to an emotion recognition engine to recognize the emotion of the user.

[1709] Input: Face image data

[1710] Output: Emotion data (happiness, sadness, etc.)

[1711] How it works: The server sends facial image data to an emotion recognition engine, such as Microsoft Azure's Emotion API. The emotion recognition engine analyzes the facial image and returns the user's emotional data.

[1712] Step 4:

[1713] The server generates optimal meal options for the user based on the recognized emotion data.

[1714] Input: Emotion data

[1715] Output: A list of meal options

[1716] Specific operation: The server performs conditional branching based on the emotion data and generates meal options that match the user's emotion. For example, if the emotion of joy is recognized, cake and a celebratory dinner will be listed as options.

[1717] Step 5:

[1718] The server presents the generated meal options on a user interface.

[1719] Input: List of meal options

[1720] Output: Meal options displayed on the user interface

[1721] Specific operation: The server sends the generated list of meal options to the device and displays it on the user interface. The user can then check the options on the screen of their smartphone or smart glasses.

[1722] Step 6:

[1723] The user makes a final selection from the presented meal options.

[1724] Input: List of meal options

[1725] Output: User's meal selection

[1726] Specific operation: The user selects one of the meal options presented on the user interface. The selected meal information is sent from the terminal to the server.

[1727] Step 7:

[1728] The server orders the selected meal through a food delivery service.

[1729] Input: User's meal selection

[1730] Output: Order information for food delivery service

[1731] Specific behavior: The server uses a food delivery service API (e.g., Uber Eats or DoorDash) to order the meal selected by the user. The order information is sent to the food delivery service, which then arranges for delivery.

[1732] 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.

[1733] 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> ) 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.

[1734] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1735] 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.

[1736] [Third embodiment]

[1737] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1738] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1739] 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).

[1740] 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.

[1741] 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.

[1742] 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).

[1743] 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.

[1744] 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.

[1745] 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.

[1746] 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.

[1747] In the headset type terminal 314, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is executed by the processor 46 on the RAM 48.

[1748] This is realized by operating as the control unit 46A in accordance with the reception output program 60.

[1749] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1750] "Example 1"

[1751] One embodiment of the present invention is a system that collects individual dietary preferences and restrictions through a user interface, where the user inputs and the system collects their preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[1752] "Example 2"

[1753] Based on the collected information, a system can generate meal suggestions that everyone can agree on. Specifically, it takes into account everyone's preferences and restrictions and suggests meal options that are predicted to be most agreeable. For example, if everyone likes fish dishes and no one is allergic to fish, the system can suggest a fish restaurant.

[1754] "Example 3"

[1755] There is a system that presents suggested meal options to users and leaves the final choice to the user. Specifically, the system presents the suggested options on a user interface, and the user makes the final choice from among them. This allows for a fair selection process that reflects everyone's opinions.

[1756] The processing flow of each embodiment will be described below.

[1757] "Example 1"

[1758] Step 1: The user accesses the system's user interface.

[1759] Step 2: The user enters their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[1760] Step 3: The system collects the information entered by the user and stores it in a database.

[1761] "Example 2"

[1762] Step 1: The system retrieves everyone's dietary preferences and restrictions from a database.

[1763] Step 2: Based on the information obtained, the system generates meal options that are predicted to be most likely to gain consensus.

[1764] Step 3: Present the generated meal options to the user.

[1765] "Example 3"

[1766] Step 1: The user reviews the meal options presented by the system.

[1767] Step 2: The user makes their final meal selection.

[1768] Step 3: The system receives the user's selection and stores the results.

[1769] Example 1

[1770] Next, a description will be given of Example 1 of Form 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."

[1771] Conventional meal plan proposal systems have difficulty in properly reflecting each individual's dietary preferences and restrictions, making it difficult to provide a meal plan that satisfies the user. In addition, when generating a meal plan that takes into account the opinions of multiple people, it is difficult to make proposals that everyone can agree on.

[1772] 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.

[1773] In this invention, the server includes a means for collecting each individual's dietary preferences and restrictions, a means for storing the collected information in a database, a means for sending a prompt to the generative AI model based on the stored information, a means for the generative AI model to generate a meal plan suitable for the user, and a means for displaying the generated meal plan to the user. This makes it possible to provide a meal plan that appropriately reflects each individual's dietary preferences and restrictions. Furthermore, when generating a meal plan that takes into account the opinions of multiple people, it is possible to make proposals that are acceptable to all.

[1774] "Means for collecting individual dietary preferences and restrictions" means a means for providing an interface for users to input their dietary preferences and restrictions (e.g., allergy information, likes and dislikes, health restrictions, etc.).

[1775] The "means for storing collected information in a database" refers to a means for storing information about dietary preferences and restrictions entered by a user in a database.

[1776] "Means for sending prompt sentences to the generative AI model based on stored information" refers to means for generating and sending appropriate prompt sentences to the generative AI model based on user information stored in the database.

[1777] "Means by which the generative AI model generates a meal plan appropriate for the user" refers to means by which the generative AI model analyzes the prompt sentence and generates an appropriate meal plan based on the user's dietary preferences and restrictions.

[1778] "Means for displaying the generated meal plan to the user" refers to means for displaying the meal plan generated by the generative AI model on the user's interface.

[1779] This invention is a system for collecting individual dietary preferences and restrictions and generating an appropriate meal plan based on the collected information. The system includes a user interface for a user to input the dietary preferences and restrictions, a server for storing the collected information in a database, a server for sending prompts to a generative AI model based on the stored information, a means for the generative AI model to generate a meal plan appropriate for the user, and a means for displaying the generated meal plan to the user.

[1780] Hardware and software used

[1781] Server: Uses the Django framework to host the web application.

[1782] Database: PostgreSQL is used to store user information.

[1783] Generative AI model: Use an appropriate generative AI model to generate the meal plan for the user.

[1784] Specific operation of the system

[1785] Users access the system through a web browser and enter their dietary preferences and restrictions into the user interface. Specifically, users enter allergy information, likes and dislikes, health restrictions, etc. For example, suppose a user enters the following information:

[1786] Allergy Information: Nuts

[1787] Likes and dislikes: I hate tomatoes

[1788] Health Restrictions: Low Carbohydrate

[1789] This information is entered as follows:

[1790] Allergy Information: Nuts

[1791] Likes and dislikes: I hate tomatoes

[1792] Health Restrictions: Low Carb

[1793] The device sends the information entered by the user to a server, which stores the received information in a database that is later used to generate the user's meal plan.

[1794] The server then sends prompts to the generative AI model based on the stored information, including the user's dietary preferences and restrictions. For example, the following prompts might be generated:

[1795] Generate an appropriate meal plan based on the user's dietary preferences and restrictions. Here is the user's information:

[1796] Allergy Information: Nuts

[1797] Likes and dislikes: I hate tomatoes

[1798] Health Restrictions: Low Carbohydrate

[1799] The generative AI model generates a meal plan suitable for the user based on the received prompt. The generated meal plan is returned to the server, which displays the generated meal plan in the user interface. The user can view the meal plan through their browser.

[1800] In this way, it is possible to provide meal plans that appropriately reflect each individual's dietary preferences and restrictions.In addition, when generating meal plans that take into account the opinions of multiple people, it is possible to make proposals that everyone can agree on.

[1801] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1802] Step 1:

[1803] The user inputs their dietary preferences and restrictions.

[1804] Users access the system through a web browser and enter their dietary preferences and restrictions into the user interface, including allergy information, likes and dislikes, and health restrictions.

[1805] Input: User's dietary preferences and restrictions (e.g., nut allergy, dislike of tomatoes, low carb)

[1806] Output: The entered information is displayed in the form.

[1807] Specific Action: A user enters "nuts" in the "Allergy Information" field, "dislikes tomatoes" in the "Likes and Dislikes" field, and "low carb" in the "Health Restrictions" field.

[1808] Step 2:

[1809] The terminal transmits the input information to the server.

[1810] When the user completes the input and clicks the send button, the terminal sends the input information to the server as an HTTP POST request.

[1811] Input: User-entered dietary preferences and restrictions

[1812] Output: HTTP POST request sent to the server

[1813] Specific operation: The device sends a POST request to the " / submit_preferences" endpoint and includes the information entered by the user in the request body.

[1814] Step 3:

[1815] The server stores the received information in a database.

[1816] The server processes the incoming requests and stores the user's dietary preferences and restrictions in a database, which uses PostgreSQL.

[1817] Input: The user's dietary preferences and restrictions received by the server.

[1818] Output: User information stored in the database

[1819] What happens: The server extracts the user's information from the request body and runs an SQL query to connect to a PostgreSQL database and save the information.

[1820] Step 4:

[1821] The server sends a prompt to the generative AI model based on the stored information.

[1822] The server uses the stored information to generate prompts to send to the generative AI model, including the user's dietary preferences and restrictions.

[1823] Input: User information stored in the database

[1824] Output: The prompt sent to the generative AI model

[1825] Specific operation: The server retrieves user information from the database, generates a prompt sentence based on the retrieved information, and sends the generated prompt sentence to the generative AI model.

[1826] Step 5:

[1827] A generative AI model generates a meal plan tailored to the user.

[1828] The generative AI model generates a meal plan suitable for the user based on the received prompt, and the generated meal plan is returned to the server.

[1829] Input: The prompt sent to the generative AI model

[1830] Output: The generated meal plan

[1831] Specific operation: The generative AI model analyzes the prompt, generates a meal plan based on the user's preferences and restrictions, and returns the generated meal plan to the server.

[1832] Step 6:

[1833] The server displays the generated meal plan to the user.

[1834] The server receives the meal plan returned by the generative AI model and displays it in a user interface, where the user can view the meal plan through their browser.

[1835] Input: Meal plan returned from a generative AI model

[1836] Output: Meal plan displayed in the user interface

[1837] Specific operation: The server receives the meal plan returned by the generative AI model, converts the meal plan into HTML format, sends the converted HTML to the user's browser, and the user views the meal plan in the browser.

[1838] (Application example 1)

[1839] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1840] Conventional food delivery systems have difficulty proposing menus that fully consider the dietary preferences and restrictions of individual users, and it has been particularly difficult to make proposals that reflect the opinions of multiple people or that everyone can agree on. Furthermore, users have to input their own dietary preferences and restrictions, which is time-consuming, and there has been a lack of a way to efficiently collect and manage this information.

[1841] 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.

[1842] In this invention, the server includes means for making meal suggestions that reflect the opinions of multiple users, means for making suggestions that take into account the opinions of all users, means for providing services for groups, means for collecting each individual's dietary preferences and restrictions, means for proposing an optimal menu based on the collected information, and means for ordering from the suggested menu. This makes it possible to efficiently collect users' dietary preferences and restrictions and to propose optimal menus for each user and the entire group.

[1843] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that makes meal suggestions that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[1844] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively evaluates the collected information about each individual's dietary preferences and restrictions, and generates meal suggestions that everyone can agree on.

[1845] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[1846] "Means for collecting individual dietary preferences and restrictions" refers to a function that allows users to input their own dietary preferences and restrictions (such as allergy information, likes and dislikes, health restrictions, etc.) and the system collects them.

[1847] "Means for suggesting the most suitable menu based on collected information" refers to a function for selecting and suggesting the most suitable menu based on the user's collected dietary preferences and restrictions.

[1848] The "means of ordering from the proposed menu" is a function that allows the user to select from the proposed menu and actually place an order.

[1849] As an embodiment of the present invention, the following system is constructed.

[1850] System Configuration

[1851] The system consists of a server, user terminals, and a network. The server plays a central role in collecting users' dietary preferences and restrictions and proposing optimal menus. The user terminals are devices such as smartphones and tablets that provide an interface for users to input their dietary preferences and restrictions.

[1852] Hardware and software used

[1853] Hardware: Servers, smartphones, tablets

[1854] Software: Python 3.x, JSON library, database management system (e.g., MySQL)

[1855] Data processing and calculation

[1856] 1. Collecting your dietary preferences and restrictions:

[1857] Through the user terminal, the user inputs their dietary preferences and restrictions (allergy information, likes and dislikes, health restrictions, etc.), which are sent to the server in JSON format and stored in a database.

[1858] 2. Optimal menu suggestions:

[1859] The server selects the optimal menu based on the user's dietary preferences and restrictions. Specifically, it filters out menus that do not include the user's allergies or disliked foods, and prioritizes menus that include the user's favorite foods.

[1860] 3. Menu Viewing and Ordering:

[1861] The suggested menu is displayed on the user's terminal, and the user can select from it and place an order. The order information is then sent back to the server for processing.

[1862] Specific examples

[1863] For example, if a user inputs "tomato" as their allergy information, "chicken" as their favorite food, and "fish" as their least favorite food, the server will suggest the most suitable menu based on this information. Specifically, it may suggest a menu item such as "chicken curry."

[1864] Prompt Sentence Examples

[1865] An example of a prompt to be input to the generative AI model is as follows:

[1866] Build an application that collects a user's dietary preferences and restrictions and suggests the best menu items. Users enter allergies, likes, dislikes, and health restrictions, and filter the menu items based on this. For example, if a user enters "I'm allergic to tomatoes," "I like chicken," and "I don't like fish," suggest "Chicken Curry."

[1867] In this way, users' dietary preferences and restrictions can be efficiently collected and optimal menus can be suggested for individual users and for the group as a whole.

[1868] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1869] Step 1:

[1870] The user uses the device to input their dietary preferences and restrictions. Specifically, they input allergy information, favorite foods, disliked foods, health restrictions, etc. The input data is sent to the server in JSON format. Examples of input data include "allergy information: tomato," "favorite food: chicken," and "disliked food: fish."

[1871] Step 2:

[1872] The server receives the JSON format data sent from the device and stores it in a database. Specifically, it stores allergy information, likes and dislikes, and health restrictions along with the user ID in the database. The input data is in JSON format, and the output is saved in the database.

[1873] Step 3:

[1874] The server selects the optimal menu based on the user's dietary preferences and restrictions stored in the database. Specifically, it filters out menus that do not include allergy information or disliked foods, and prioritizes menus that include favorite foods. The input is the user's preferences and restrictions obtained from the database, and the output is a filtered menu list.

[1875] Step 4:

[1876] The server sends the filtered menu list to the user terminal. Specifically, it sends the selected menu to the terminal in JSON format. The input is the filtered menu list, and the output is the transmission to the terminal.

[1877] Step 5:

[1878] The user selects the desired menu from the menu list displayed on the terminal and places an order. Specifically, by confirming the selected menu and pressing the order button, the order information is sent to the server. The input is the menu selected by the user, and the output is the order information sent to the server.

[1879] Step 6:

[1880] The server processes the received order information and confirms the order. Specifically, it stores the order information in a database and arranges cooking and delivery as necessary. The input is the order information sent by the user, and the output is the confirmation of the order and related arrangements.

[1881] Through the above steps, the optimal menu is proposed and ordered, taking into consideration the user's dietary preferences and restrictions.

[1882] Example 2

[1883] Next, a description will be given of Example 2 of Form 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."

[1884] Conventional meal recommendation systems have difficulty effectively reflecting the opinions and preferences of multiple people, making it difficult to make recommendations that everyone can agree on. Furthermore, there is a problem with insufficient data collection and analysis to take into account individual dietary preferences and restrictions, resulting in low accuracy of recommendations.

[1885] 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.

[1886] In this invention, the server includes a means for inputting user information, a means for collecting and storing the input user information, a means for analyzing the collected user information, a means for generating meal suggestions based on the analysis results, and a means for providing the generated suggestions to the user, thereby effectively reflecting the opinions and preferences of multiple people and making meal suggestions that everyone can agree on.

[1887] A "means for inputting user information" is a device or software that provides an interface for a user to input their dietary preferences and restrictions.

[1888] The "means for collecting and storing input user information" refers to a device or software for transmitting the information input by the user to a server and storing it in a database.

[1889] "Means for analyzing collected user information" refers to a device or software that performs data analysis based on collected user information and generates results that take into account the user's preferences and limitations.

[1890] The "means for generating meal suggestions based on the analysis results" refers to a device or software for generating optimal meal suggestions for a user based on the results of the data analysis.

[1891] The "means for providing generated suggestions to a user" is a device or software that transmits the generated meal suggestions to a user's terminal and allows the user to review the suggestions.

[1892] A "generative AI model" is an artificial intelligence model used to analyze data and generate optimal suggestions, taking into account user preferences and limitations.

[1893] A "prompt" is an instruction given to a generative AI model, containing instructions for achieving a specific result.

[1894] MODE FOR CARRYING OUT THE INVENTION

[1895] The present invention relates to a system that takes into account the dietary preferences and restrictions of users and generates meal proposals that everyone can agree on. A specific embodiment of this system will be described below.

[1896] 1. System Configuration

[1897] The system consists of the following major components:

[1898] A way to enter user information

[1899] A means of collecting and storing input user information

[1900] A means of analyzing collected user information

[1901] A means of generating meal suggestions based on the analysis results

[1902] A means for providing generated suggestions to the user

[1903] 2. Hardware and Software Used

[1904] Server: A central processing unit for collecting, storing, analyzing data, and generating recommendations. It uses MySQL as its database.

[1905] Device: The device (smartphone, PC, etc.) where the user enters information and receives suggestions.

[1906] Generative AI model: An artificial intelligence model (e.g., GPT-4) used to analyze data and generate optimal recommendations, taking into account user preferences and limitations.

[1907] 3. System Operation

[1908] Enter your user information:

[1909] Users use the terminal to input their dietary preferences and restrictions. For example, User A inputs, "I like fish dishes, I have no allergies."

[1910] Data collection and storage:

[1911] The terminal sends the information entered by the user to the server. The server saves the received data in a database (MySQL). For example, User A's information "I like fish dishes, I have no allergies" is saved in the database.

[1912] Data analysis:

[1913] The server retrieves all user information stored in the database and inputs it into a generative AI model (GPT-4). The generative AI model analyzes the data, taking into account the user's preferences and limitations. For example, it verifies that everyone likes fish dishes and that no one is allergic to fish.

[1914] Proposal generation:

[1915] The server generates meal recommendations that are most likely to gain consensus based on the analysis results obtained from the generative AI model, such as suggesting restaurants serving fish.

[1916] Providing suggestions:

[1917] The server sends the generated suggestions to the user's device. The user can check and select the suggestions through the device. For example, user A checks and selects "fish restaurants" on the device.

[1918] 4. Examples of concrete examples and prompts

[1919] Examples:

[1920] User A: I like fish dishes and I don't have any allergies

[1921] User B: I like fish dishes and I don't have any allergies

[1922] User C: I like fish dishes and I have no allergies

[1923] In this case, the server suggests a fish restaurant.

[1924] Example prompt sentence:

[1925] Generate meal suggestions that everyone can agree on, taking into account the user's dietary preferences and restrictions. Use the following information to make suggestions:

[1926] User A: I like fish dishes and I don't have any allergies

[1927] User B: I like fish dishes and I don't have any allergies

[1928] User C: I like fish dishes and I have no allergies

[1929] In this way, meal suggestions that everyone can agree on are generated and provided to the user.

[1930] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1931] Step 1:

[1932] Entering user information

[1933] Users use the terminal to input their dietary preferences and restrictions. For example, User A inputs, "I like fish dishes, I have no allergies."

[1934] Input: User's dietary preferences and restrictions (e.g., "I like fish dishes, no allergies")

[1935] Output: The entered user information is saved on the device.

[1936] Step 2:

[1937] Data collection and storage

[1938] The terminal transmits the information entered by the user to the server.

[1939] The server stores the received data in a database (MySQL). For example, user A's information "likes fish dishes, no allergies" is stored in the database.

[1940] Input: Information entered by the user (e.g., "I like fish dishes, I have no allergies")

[1941] Output: User information stored in the database

[1942] Step 3:

[1943] Analyzing the data

[1944] The server retrieves all user information stored in a database.

[1945] The server uses a generative AI model (GPT-4) to analyze the data, taking into account user preferences and restrictions, for example, ensuring that everyone likes fish dishes and that no one is allergic to fish.

[1946] Input: All user information stored in the database

[1947] Output: Analysis results from the generative AI model (e.g., "Everyone likes fish dishes, and no one is allergic to fish")

[1948] Step 4:

[1949] Proposal Generation

[1950] The server generates meal recommendations that are most likely to gain consensus based on the analysis results obtained from the generative AI model, such as suggesting restaurants serving fish.

[1951] Input: Analysis results from generative AI model

[1952] Output: Dining suggestions (e.g. "fish restaurants")

[1953] Step 5:

[1954] Providing suggestions

[1955] The server transmits the generated proposal to the user's terminal.

[1956] The user can check the suggestions through the terminal and select one. For example, user A checks and selects "fish restaurants" on the terminal.

[1957] Input: Dining suggestions (e.g., "fish restaurants")

[1958] Output: Proposal displayed on the user's device

[1959] In this way, meal suggestions that everyone can agree on are generated and provided to the user.

[1960] (Application example 2)

[1961] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1962] With conventional food delivery services, it was difficult to suggest meals that took into account the preferences and dietary restrictions of multiple people, making it difficult to find options that would satisfy everyone. Furthermore, manual adjustments were required, making it difficult to make efficient suggestions. This made meal selections for groups cumbersome, resulting in lower satisfaction.

[1963] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1964] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for generating meal suggestions using a generative AI model, and a means for generating prompt sentences and making suggestions, thereby enabling efficient and satisfying meal suggestions that take into account the preferences and dietary restrictions of multiple people.

[1965] "Means for making meal suggestions that reflect the opinions of multiple people" is a function that suggests meal options that will satisfy everyone based on the dietary preferences and restrictions collected from multiple users.

[1966] The "means of making suggestions that take everyone's opinions into consideration" is a function that comprehensively analyzes the collected information about each individual's dietary preferences and restrictions, and generates meal suggestions that everyone can agree on.

[1967] "Means for providing services for groups" refers to a function for providing services that are intended to be used by multiple users together.

[1968] "Means for generating meal suggestions using a generative AI model" means a function that uses an artificial intelligence model to automatically generate meal suggestions that take into account a user's preferences and restrictions.

[1969] "Means for generating prompt sentences and making suggestions" is a function that generates sentences to give appropriate instructions to the generative AI model based on the information input by the user, and makes meal suggestions based on the results.

[1970] To implement this invention, a server, a user terminal, and a generative AI model are used. Specific embodiments are described below.

[1971] System Configuration

[1972] The server includes means for making meal suggestions that reflect the opinions of multiple people, means for making suggestions that take into account the opinions of all people, means for providing services for groups, means for generating meal suggestions using a generative AI model, and means for generating prompt sentences and making suggestions.

[1973] The user terminal is a mobile device such as a smartphone or tablet that provides an interface for the user to input their dietary preferences and restrictions.

[1974] Program processing

[1975] The server receives each individual's dietary preferences and restrictions from the user's device and stores them in a database. The server then uses a generative AI model to generate meal suggestions that everyone can agree on. The server also generates prompts and provides appropriate instructions to the generative AI model.

[1976] The server is a computer system with a high-performance processor and large memory capacity, and the user devices are ordinary smartphones or tablets. The software used is OpenAI's API for the generative AI model, and the program is implemented in Python.

[1977] Specific examples

[1978] For example, suppose user A likes fish and vegetables, dislikes meat, and has a nut allergy. User B likes meat and fish, dislikes vegetables, and has no allergies. User C likes vegetables and fruit, dislikes fish, and is allergic to dairy products. Based on this information, the server generates a prompt like the following:

[1979] Example prompt sentence:

[1980] Generate meal suggestions that everyone can agree on, taking into account user preferences and restrictions. User info: [{"name": "User A", "likes": ["fish", "vegetables"], "dislikes": ["meat"], "allergies": ["nuts"]}, {"name": "User B", "likes": ["meat", "fish"], "dislikes": ["vegetables"], "allergies": []}, {"name": "User C", "likes": ["vegetables", "fruit"], "dislikes": ["fish"], "allergies": ["dairy"]}]

[1981] This prompt is then fed into a generative AI model to generate satisfying meal suggestions, which are then sent to the user's device and displayed to the user.

[1982] In this way, it becomes possible to propose efficient and satisfying meals that take into account the preferences and dietary restrictions of multiple people.

[1983] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1984] Step 1:

[1985] The user uses the terminal to input their dietary preferences and restrictions.

[1986] Input: User preferences (e.g., fish, vegetables), disliked ingredients (e.g., meat), allergy information (e.g., nut allergy)

[1987] Output: The entered information is sent from the terminal to the server.

[1988] Specific actions: The user enters their dietary preferences and restrictions through the smartphone app interface and presses the submit button.

[1989] Step 2:

[1990] The server receives each individual's dietary preferences and restriction information sent from the device and stores it in a database.

[1991] Input: User preferences and restrictions sent from the device

[1992] Output: User information stored in the database

[1993] Specific operation: The server analyzes the received data and stores each user's information in a database.

[1994] Step 3:

[1995] The server retrieves each individual's dietary preferences and restrictions from a database and generates a prompt.

[1996] Input: User information stored in the database

[1997] Output: Generated prompt statement

[1998] Specific operation: The server uses a Python program to generate a prompt based on the user information. For example, it generates the following prompt:

[1999] Generate meal suggestions that everyone can agree on, taking into account user preferences and restrictions. User info: [{"name": "User A", "likes": ["fish", "vegetables"], "dislikes": ["meat"], "allergies": ["nuts"]}, {"name": "User B", "likes": ["meat", "fish"], "dislikes": ["vegetables"], "allergies": []}, {"name": "User C", "likes": ["vegetables", "fruit"], "dislikes": ["fish"], "allergies": ["dairy"]}]

[2000] Step 4:

[2001] The server inputs prompts into the generative AI model to generate meal suggestions.

[2002] Input: Generated prompt statement

[2003] Output: Meal suggestions from a generative AI model

[2004] How it works: The server uses the OpenAI API to send the generated prompt to the AI ​​model and receive meal suggestions.

[2005] Step 5:

[2006] The server transmits the generated meal suggestions to the user terminal.

[2007] Input: Meal suggestions from a generative AI model

[2008] Output: Meal suggestions displayed on the user's device

[2009] Specific operation: The server sends the received meal suggestions to the user's device, allowing the user to review the suggestions through the app.

[2010] Step 6:

[2011] The user uses the terminal to review the suggested meals and place an order.

[2012] Input: Meal suggestions sent by the server

[2013] Output: User's order information

[2014] Specific actions: The user reviews the suggested meals through the app and presses the order button to confirm the order.

[2015] In this way, it is possible to propose and order meals that are efficient and satisfying, taking into account the preferences and dietary restrictions of multiple people.

[2016] Example 3

[2017] Next, a third embodiment of the third embodiment will be described. 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."

[2018] Conventional meal recommendation systems have difficulty providing meal options that fully consider individual users' preferences and allergy information, making it difficult to provide meal options that satisfy everyone. Furthermore, they lack a mechanism for effectively reflecting users' selection results, resulting in problems with reduced recommendation accuracy and satisfaction. This has led to an increasing need for a fair and personalized meal recommendation system to increase user satisfaction.

[2019] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[2020] In this invention, the server includes means for receiving requests from users, means for collecting the user's past dietary history and allergy information, means for generating prompt sentences to be input to the generative AI model based on the collected data, means for generating meal options using the generative AI model, means for sending the generated meal options to a user interface, means for displaying the meal options on the user interface, means for sending the user's selection results to the server, and means for saving the user's selection results in a database. This enables personalized meal suggestions that take into account the individual preferences and restrictions of each user, thereby realizing fair selections that everyone can agree on.

[2021] The "means for receiving a request from a user" is a function that allows a user to send a request for meal suggestions to the system and for the server to receive the request.

[2022] "Means for collecting the user's past dietary history and allergy information" is a function for retrieving and collecting information about the meals and allergies selected by the user in the past from a database.

[2023] The "means for generating prompt sentences to be input into the generative AI model" is a function that creates instructions (prompt sentences) for the generative AI model to generate appropriate meal options based on collected data.

[2024] "Means for generating meal options using a generative AI model" refers to a function for inputting a prompt sentence into a generative AI model and generating multiple meal options as a result.

[2025] "Means for transmitting the generated meal options to a user interface" means a function for transmitting the meal options generated by the generative AI model to a user interface so that the user can review them.

[2026] The "means for displaying meal options on the user interface" is a function for visually displaying the meal options generated on the user interface so that the user can confirm them.

[2027] The "means for transmitting the results of the user's selection to the server" is a function for transmitting the results of the meal the user has selected on the user interface to the server.

[2028] "Means for saving the user's selection results in a database" is a function for saving the results of the user's meal selection in a database and reflecting them in future suggestions.

[2029] The present invention is a system that provides a user with personalized meal suggestions and leaves the final selection up to the user. Specific embodiments of this system will be described below.

[2030] Hardware and Software Configuration

[2031] server

[2032] The server receives user requests and has a database for collecting the user's past dietary history and allergy information. The server generates meal options using a generative AI model and sends the generated options to the user interface. Specifically, the server uses the following software and hardware:

[2033] Database Management System (DBMS): Stores and manages users' past dietary history and allergy information.

[2034] Generative AI model: A machine learning model that generates meal options based on user data.

[2035] Web Server: A server that sends data to the user interface.

[2036] Terminal

[2037] The terminal is a device used by the user that receives the meal options sent from the server and displays them on a user interface. The terminal uses software such as:

[2038] Web browser or mobile application: Provides the user interface and allows users to view and select their meal options.

[2039] User

[2040] The user accesses the system through a terminal and makes a final selection from the proposed meal options. The user's selection is sent to the server through the terminal and stored in a database.

[2041] Data processing and calculation

[2042] When the server receives a request from a user, it first collects the user's past dietary history and allergy information from a database. Then, based on the collected data, it generates a prompt sentence to be input into the generative AI model. For example, it generates a prompt sentence like the following:

[2043] Example prompt sentence:

[2044] "Generate suggestions for tonight's dinner, taking into account the user's past eating history and allergy information."

[2045] Based on this prompt, the generative AI model generates meal options such as "curry rice," "chicken salad," and "pasta." The generated options are sent from the server to the user interface.

[2046] The device receives the meal options sent from the server and displays them on the user interface. The user makes a final selection from the displayed options and sends the result to the server via the device. The server stores the user's selection in a database and reflects it in future suggestions.

[2047] Specific examples

[2048] For example, if a user requests "today's dinner suggestions," the server might do the following:

[2049] 1. Request received: The server receives a request for "today's dinner suggestions."

[2050] 2. Data collection: The server collects the user's past dietary history and allergy information from the database.

[2051] 3. Prompt generation: The server generates a prompt saying, "Please generate suggestions for today's dinner, taking into account the user's past eating history and allergy information."

[2052] 4. Option generation: The server inputs the prompt sentence into the generative AI model, generating options such as "curry rice," "chicken salad," and "pasta."

[2053] 5. Sending choices: The server sends the generated choices to the user interface.

[2054] 6. Display options: The terminal displays the received options on the user interface.

[2055] 7. User selection: The user selects "curry rice."

[2056] 8. Sending selection results: The device sends the user's selection results to the server.

[2057] 9. Data storage: The server stores the user's selection in a database for future recommendations.

[2058] In this way, the system provides personalized meal suggestions to the user and leaves the final selection up to the user, thereby achieving fair and satisfying meal selection. The flow of the specification process in Example 3 will be described with reference to FIG. 15.

[2059] Step 1:

[2060] Receiving a user request

[2061] Subject: Server

[2062] The server receives a request from a user. For example, a request for "tonight's dinner suggestions" is input. The server analyzes this request and extracts the information needed for the next processing step. The input is the user's request, and the output is the analyzed request information.

[2063] Step 2:

[2064] Data collection

[2065] Subject: Server

[2066] The server collects the user's past dietary history and allergy information from a database. The input is the parsed request information, and the output is the collected user's dietary history and allergy information. Specifically, it executes a database query to obtain the required data.

[2067] Step 3:

[2068] Generate prompt statement

[2069] Subject: Server

[2070] The server generates a prompt sentence to be input into the generative AI model based on the collected data. The input is the collected user's dietary history and allergy information, and the output is the generated prompt sentence. Specifically, it creates a prompt sentence in the format "Please generate suggestions for tonight's dinner, taking into account the user's past dietary history and allergy information."

[2071] Step 4:

[2072] Meal Choice Generation

[2073] Subject: Server

[2074] The server inputs a prompt sentence into the generative AI model to generate meal options. The input is the generated prompt sentence, and the output is the generated meal options. Specifically, the generative AI model generates options such as "curry rice," "chicken salad," and "pasta."

[2075] Step 5:

[2076] Submit your choices

[2077] Subject: Server

[2078] The server sends the generated meal options to the user interface. The input is the generated meal options, and the output is the data sent to the user interface. Specifically, the data is sent using an HTTP request.

[2079] Step 6:

[2080] Displaying options

[2081] Subject: Terminal

[2082] The device receives the meal options sent from the server and displays them on a user interface. The input is the data sent from the server, and the output is the meal options displayed on the user interface. Specifically, the options are displayed in a web browser or a mobile application.

[2083] Step 7:

[2084] User Selection

[2085] Subject: User

[2086] The user checks the proposed meal options through the device's user interface and makes a final selection. The input is the meal options displayed on the user interface, and the output is the user's selection. Specifically, the user selects "curry rice."

[2087] Step 8:

[2088] Sending the selection results

[2089] Subject: Terminal

[2090] The terminal sends the results of the user's selection to the server. The input is the user's selection, and the output is the data sent to the server. Specifically, the data is sent using an HTTP request.

[2091] Step 9:

[2092] Saving and updating data

[2093] Subject: Server

[2094] The server receives the user's final selection and stores it in a database. The input is the data sent to the server, and the output is the selection stored in the database. Specifically, it adds a new record to the database and reflects it in future suggestions.

[2095] (Application example 3)

[2096] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2097] With conventional food delivery systems, when multiple people order a meal together, it is difficult to fairly reflect everyone's opinions. It is also difficult to propose a meal that satisfies everyone while taking into account each individual's dietary preferences and restrictions. This makes meal selection for groups complicated, resulting in a decrease in satisfaction.

[2098] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[2099] In this invention, the server includes a means for making meal suggestions that reflect the opinions of multiple people, a means for making suggestions that take into account the opinions of all people, a means for providing services for groups, a means for presenting suggested meal options on a user interface so that the user can make a final selection from among them, and a means for determining the option that receives the most votes as the final selection. This makes it possible to make meal suggestions that fairly reflect the opinions of all people and take into account each individual's preferences and restrictions, making it possible to smoothly select meals for a group.

[2100] "Means for providing meal suggestions that reflect the opinions of multiple users" refers to a function that generates appropriate meal options based on dietary preferences and restrictions collected from multiple users.

[2101] "A means of making suggestions that take everyone's opinions into consideration" is a function that makes meal suggestions that everyone can agree on based on the opinions and restrictions collected from each user.

[2102] A "means for providing services for groups" is a function that provides services that are intended for use by mu...

Claims

1. A means for collecting opinions of a plurality of people and generating meal suggestions that reflect the collected opinions; means for transmitting the generated meal suggestions to a user; A means for recognizing a user's sentiment regarding the submitted meal suggestions; A means for generating universally acceptable meal suggestions based on the recognized emotions; and A system including:

2. The system of claim 1 , wherein the means for generating universal dining suggestions comprises means for collecting individual dietary restrictions.

3. The system of claim 1 , further comprising: means for suggesting services that amplify the recognized emotion.

Images