System

Abstract

To provide a system.SOLUTION: A system includes: means for a user to input a menu for a fixed period; means for proposing a side dish for supplementing the nutritional balance of the input menu and replacement of the menu; and means for identifying a feeling state of the user using a feeling engine. The means for proposing generates a menu to be proposed using a generative AI model on the basis of a prompt sentence for instructing the generation of the menu on the basis of the feeling state of the user.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] People living alone or in dual-income households often don't have the time to think about meal plans that cater to their preferences and are nutritionally balanced. Even if they want to try a new genre of food, they often don't know what kind of menu to make. [Means for solving the problem]

[0005] By inputting menus for a certain period of time, the system will suggest side dishes and menu changes to improve nutritional balance. Furthermore, it will use generative AI to provide a service that can accommodate personal preferences and new genres that users want to try. This AI will learn from the user's past menu input history and make menu suggestions based on the results. It will also receive feedback from users and learn from that feedback to improve the accuracy of its menu suggestions. [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 Embodiment 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 disclosed technique will be described below with reference to the accompanying drawings.

[0008] do.

[0009] First, the terms used in the following description will be explained.

[0010] 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)).

[0011] 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.

[0012] In the following embodiments, the coded storage is one or more nonvolatile storage devices that store various programs, various parameters, etc. Examples of nonvolatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0013] 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.

[0014] 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."

[0015] [First embodiment]

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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 includes an optical system including a lens, an aperture, and a shutter, and a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or CC

[0022] It is a small digital camera equipped with an imaging element such as a D (Charge Coupled Device) image sensor.

[0023] 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.

[0024] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0029] "Example 1"

[0030] The system of the present invention provides an interface for users to input menus for a certain period of time. This interface can be used, for example, on a web page or a smartphone application.

[0031] This is achieved by: The user inputs a menu, for example, "Monday's dinner is grilled salted salmon, and Tuesday's dinner is curry rice."

[0032] "Example 2"

[0033] The system then suggests side dishes or menu changes to improve nutritional balance. For example, if a user inputs "Curry rice for dinner on Tuesday," the system might suggest, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[0034] "Example 3"

[0035] Furthermore, the system uses generative AI to provide a service that can accommodate individual preferences and new genres that users want to try. This AI learns from the user's past menu input history and makes menu suggestions based on the results. For example, if a user has often input "grilled salted salmon" in the past, the AI ​​will suggest something like, "Why not try grilled salted mackerel, which has a similar flavor to grilled salted salmon?"

[0036] "Example 4"

[0037] The AI ​​also receives feedback from users and learns from that feedback to improve the accuracy of its menu suggestions. For example, if a user gives a "good rating" to the suggestion "grilled salted mackerel," the AI ​​will increase the probability of suggesting dishes similar to "grilled salted mackerel."

[0038] The processing flow of each embodiment will be described below.

[0039] "Example 1"

[0040] Step 1: The user inputs a menu for a certain period of time through the system's interface. This interface can be implemented on a web page or a smartphone application, and the user inputs a menu in the form of "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday."

[0041] "Example 2"

[0042] Step 1: The system receives menu input from the user.

[0043] Step 2: The system suggests side dishes or menu changes to improve nutritional balance. For example, if a user inputs "Curry rice for dinner on Tuesday," the system will suggest something like, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[0044] "Example 3"

[0045] Step 1: The system uses generative AI to provide services that cater to individual preferences and new genres that people want to try.

[0046] Step 2: The AI ​​learns from the user's past menu entry history and makes menu suggestions based on the results. For example, if the user has often entered "grilled salted salmon" in the past, the AI ​​will suggest something like, "Why not try grilled salted mackerel, which has a similar flavor to grilled salted salmon?"

[0047] "Example 4"

[0048] Step 1: The system receives feedback from the user.

[0049] Step 2: The AI ​​learns from that feedback and improves the accuracy of the menu suggestions. For example, if a user gives a "good rating" to the suggestion "grilled salted mackerel," the AI ​​will increase the probability of suggesting menu items similar to "grilled salted mackerel."

[0050] Example 1

[0051] 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."

[0052] Conventional menu management systems require users to manually input menus and consider nutritional balance, which is time-consuming and inefficient. They also lack the flexibility to accommodate individual preferences and new genres. Furthermore, they lack the functionality to suggest menus using users' past history and feedback, making it difficult to increase user satisfaction.

[0053] 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.

[0054] In this invention, the server includes a means for users to input menus for a certain period of time, a means for saving the input menu data in a database, a means for sending prompts to the generative AI model based on the saved data, a means for receiving responses from the generative AI model and displaying them to the user, a means for suggesting side dishes or menu changes to improve nutritional balance, and a means for using the generative AI model to provide a service that can accommodate personal preferences or new genres that users want to try. This allows users to efficiently manage their menus and receive menu suggestions that match their personal preferences or new genres. Furthermore, by utilizing past history and feedback, more accurate menu suggestions can be achieved.

[0055] "User" refers to an individual or organization that uses the system to input menus and receive suggestions.

[0056] "Menu" refers to the contents of meals for a certain period of time, and specifically includes the menu of meals such as breakfast, lunch, and dinner.

[0057] "Interface" refers to the screen or application through which users access the system and input menu plans.

[0058] A "server" refers to a computer system that receives requests from users, stores data, and communicates with generative AI models.

[0059] "Database" refers to a data management system that stores menu data entered by users and allows searching and updating as needed.

[0060] A "generative AI model" refers to an artificial intelligence model that suggests recipes and nutritional values ​​based on menu data entered by the user.

[0061] A "prompt" is an instruction sent to the generative AI model, including menu information entered by the user.

[0062] "Response" refers to the recipe or nutritional information that the generative AI model generates based on the prompt.

[0063] "Nutritional balance" refers to the balance of nutrients contained in food, and is an important element for maintaining a healthy diet.

[0064] A "side dish" is a food that is served as a supplement to the main dish and plays a role in supplementing the nutritional balance.

[0065] "Suggestion" refers to the system making suggestions or advice to the user.

[0066] "Feedback" refers to opinions and evaluations provided by users to the system, which are used to improve and learn from the system.

[0067] This invention is a system that allows users to input menus for a certain period of time, and then uses a generative AI model to suggest recipes and nutritional values ​​based on the input. Specific embodiments of this system are described below.

[0068] Users access the system's interface using a web browser or smartphone application. The interface is built using web technologies such as HTML, CSS, and JavaScript (registered trademark). When a user accesses the interface, the server displays a menu entry screen.

[0069] For example, a user inputs a menu such as "Grilled salmon for dinner on Monday, and curry rice for dinner on Tuesday." The input data is sent from the terminal to the server as an HTTP POST request. The server analyzes the received data and stores it in a database (for example, MySQL (registered trademark) or PostgreSQL).

[0070] Based on the stored data, the server sends a prompt to the generative AI model. For example, OpenAI's GPT-3 (registered trademark) is used as the generative AI model. The prompt includes the menu information entered by the user. Specific examples of prompts include:

[0071] The user entered the following menu:

[0072] Monday's dinner is grilled salmon

[0073] Tuesday dinner is curry rice

[0074] Based on this, suggest recipes and nutritional values ​​for each menu item.

[0075] The generative AI model receives this prompt and generates detailed recipes and nutritional information for each menu item. The generated information is returned to the server, which converts it into HTML for display to the user. This displays the detailed recipes and nutritional information on the user's device.

[0076] The server also has the ability to suggest side dishes and menu changes to improve nutritional balance. The generative AI model learns from the user's past menu input history and makes menu suggestions based on the results. It also receives feedback from the user and learns based on that feedback to improve the accuracy of menu suggestions.

[0077] This system allows users to efficiently manage their menus and receive menu suggestions that cater to their personal preferences and new genres. It also makes use of past history and feedback to provide more accurate menu suggestions.

[0078] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0079] Step 1:

[0080] The user accesses the interface

[0081] Users access the system interface using a web browser or smartphone application. Specifically, users enter a URL in the browser or launch an app, which displays the system homepage or app home screen. The input is the URL or app icon, and the output is the homepage or home screen.

[0082] Step 2:

[0083] The server displays the menu entry screen.

[0084] The server receives the user's request and sends a menu entry screen built using HTML, CSS, and JavaScript to the user's device. Specifically, the server analyzes the HTTP request and returns the corresponding HTML file. The input is the user's request, and the output is the menu entry screen.

[0085] Step 3:

[0086] The user inputs the menu

[0087] The user inputs a menu into the displayed menu entry screen, for example, "Monday's dinner is grilled salted salmon, and Tuesday's dinner is curry rice." Input is done using text boxes and drop-down menus. The input is the menu data entered by the user, and the output is the data displayed in the input form.

[0088] Step 4:

[0089] The device sends the input data to the server

[0090] When the user has finished entering the menu, they click the "Submit" button, which causes the device to send the entered data to the server as an HTTP POST request. The input is the menu data entered by the user, and the output is the HTTP request sent to the server.

[0091] Step 5:

[0092] The server saves the data to a database

[0093] The server parses the received data and stores it in a database (e.g., MySQL or PostgreSQL). Specifically, the server establishes a database connection and executes SQL queries to insert the data. The input is the menu data received from the HTTP request, and the output is the data stored in the database.

[0094] Step 6:

[0095] The server sends a prompt to the generative AI model

[0096] The server generates prompts based on the stored data. For example, a prompt such as "The user has entered the following menu: grilled salmon for dinner on Monday, curry rice for dinner on Tuesday. Based on this, please suggest recipes and nutritional values ​​for each menu item" is sent to the generative AI model. The input is the menu data stored in the database, and the output is the prompt sent to the generative AI model.

[0097] Step 7:

[0098] A generative AI model generates a response

[0099] A generative AI model (such as OpenAI's GPT-3) generates a response based on the prompt it receives. The response includes detailed recipes and nutritional information for each meal. The input is the prompt, and the output is the generated response data.

[0100] Step 8:

[0101] The server displays the generated information to the user

[0102] The server analyzes the response received from the generative AI model and generates HTML to display to the user. Specifically, the server embeds the response data into an HTML template and sends it to the user's device. The input is the response data from the generative AI model, and the output is the HTML displayed on the user's device.

[0103] (Application example 1)

[0104] 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."

[0105] Conventional menu management systems allow users to input menus for a certain period of time, but they lack the ability to suggest side dishes that take nutritional balance into consideration, or to suggest new menus that meet individual preferences. Furthermore, they do not provide a way to list ingredients needed based on the menu and to purchase them efficiently. This means that users have to spend a lot of time and effort purchasing ingredients.

[0106] 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.

[0107] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can respond to personal preferences and new genres that users want to try using generative AI, and a means for listing necessary ingredients based on the menu and ordering those ingredients through a food delivery service.This allows users to efficiently manage their menus and easily purchase the necessary ingredients.

[0108] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[0109] "Means of suggesting side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[0110] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative AI to suggest menus that suit individual preferences and new cooking genres based on the user's past data and feedback.

[0111] "A means of listing ingredients needed based on a menu and ordering those ingredients through a food delivery service" is a function that automatically lists ingredients needed based on a menu entered by the user and orders ingredients through a food delivery service based on that list.

[0112] A system for carrying out this invention includes a server, a user terminal, and a food delivery service. The server includes means for inputting menus for a certain period of time, means for suggesting side dishes or menu changes to supplement nutritional balance, means for providing a service that can accommodate personal preferences or new genres that users want to try using generative AI, and means for listing ingredients needed based on the menu and ordering the ingredients through a food delivery service.

[0113] The user terminal is a device such as a smartphone or PC, and provides an interface for users to input menus. For example, a user might input a menu such as "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday." This input data is sent to the server.

[0114] The server uses the Flask framework to build a web server and provides an endpoint for users to input menu plans for a certain period of time. When a user inputs a menu plan, a list of ingredients required based on the menu is created and returned in JSON format. Specifically, the server searches for ingredients in the menu database, eliminating duplicates before creating a list.

[0115] The generative AI learns from the user's past menu input history and makes menu suggestions based on the results. It also receives feedback from the user, learns based on that feedback, and improves the accuracy of the menu suggestions. This allows users to receive menu suggestions that match their personal preferences and new genres they want to try.

[0116] Furthermore, the server lists the ingredients needed based on the menu and orders them through a food delivery service based on that list. This function allows users to efficiently purchase the ingredients they need.

[0117] As a specific example, consider the case where the user inputs the following menu:

[0118] Monday: Grilled Salmon

[0119] Tuesday: Curry rice

[0120] In this case, the server generates a prompt like this:

[0121] "Monday's dinner is grilled salmon, and Tuesday's dinner is curry rice."

[0122] The generated shopping list looks like this:

[0123] "Salmon, salt, curry roux, rice, meat, vegetables"

[0124] Based on this list, you can order the ingredients you need through a food delivery service.

[0125] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0126] Step 1:

[0127] A user inputs a menu for a certain period of time using a terminal.

[0128] Input: The user inputs a menu such as "Grilled salted salmon for dinner on Monday, and curry rice for dinner on Tuesday" into an interface for inputting menu items.

[0129] Output: The entered menu data is sent from the terminal to the server.

[0130] Step 2:

[0131] The server analyzes the received menu data and lists the necessary ingredients.

[0132] Input: Menu data sent from the device.

[0133] Data processing: The server refers to the menu database and searches for ingredients that correspond to each menu.

[0134] Output: A list of listed ingredients.

[0135] Step 3:

[0136] The server orders ingredients through a food delivery service based on the list of ingredients.

[0137] Input: A list of listed ingredients.

[0138] Data calculation: The server calls the API of the food delivery service and sends the list of ingredients as order data.

[0139] Output: Order confirmation from food delivery service.

[0140] Step 4:

[0141] The generative AI learns from the user's past menu input history and reflects this in the next menu suggestion.

[0142] Input: User's past menu entry history.

[0143] Data processing: Generative AI analyzes past data to learn user preferences and patterns.

[0144] Output: Learning results that will be reflected in the next menu suggestion.

[0145] Step 5:

[0146] Users provide feedback, and the generative AI learns based on that feedback.

[0147] Input: Feedback data from users.

[0148] Data computation: Generative AI analyzes feedback data and learns to improve the accuracy of suggestions.

[0149] Output: Improved menu suggestions for your next meal.

[0150] Example 2

[0151] 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."

[0152] Planning nutritionally balanced meals is a difficult task in today's busy lifestyles. In particular, considering side dishes and menu changes to compensate for individual nutrient deficiencies requires specialized knowledge and is difficult for average users. There is also a demand for menu suggestions that reflect individual preferences and new genres that people want to try, but doing this manually takes time and effort. Furthermore, it is important to utilize the user's past menu history and feedback to make more accurate suggestions.

[0153] 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.

[0154] In this invention, the server includes a means for the user to input menus for a certain period of time, a means for the terminal to send the input data to the server, a means for the server to analyze the data and obtain nutritional components, a means for the server to evaluate nutritional balance, a means for the server to input prompts to the generative AI model, a means for the server to return the generated suggestions to the user, and a means for using the generative AI model to provide a service that can accommodate personal preferences or new genres that the user wants to try, thereby enabling users to easily create menus that take nutritional balance into consideration.

[0155] "User" refers to an individual who uses the system to input menu information and receive nutritional balance suggestions.

[0156] "Terminal" refers to a device used by a user, such as a computer or smartphone, that is used to input data into the system and receive suggestions.

[0157] "Server" refers to the central processing unit that receives data sent by users and performs analysis and uses generated AI models.

[0158] A "menu" refers to a meal plan or menu for a certain period of time, and is information that a user inputs into the system.

[0159] "Nutritional components" refers to nutrients such as vitamins, minerals, proteins, lipids, and carbohydrates contained in food.

[0160] "Nutritional balance" refers to the appropriate distribution of nutrients in a diet, and is an essential element for maintaining good health.

[0161] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate suggestions based on user input.

[0162] A "prompt" is an instruction given to a generative AI model, including a question or command to generate a specific suggestion.

[0163] "Suggestions" refers to side dishes or menu substitutions that the system suggests to the user.

[0164] "Feedback" refers to the opinions and evaluations users provide to the system, and is information used to train the generative AI model.

[0165] This invention is a system that suggests side dishes and menu changes to improve nutritional balance based on menu information entered by a user. The system is implemented using a user's terminal, a server, and a generative AI model.

[0166] Hardware and software used

[0167] Hardware: User devices (PCs, smartphones, etc.), servers

[0168] Software: Generative AI models (e.g., GPT-4®), database management systems (e.g., MySQL), web application frameworks (e.g., Django)

[0169] Data processing and calculation

[0170] 1. User input: The user uses a terminal to enter menu information, such as "Curry rice for dinner on Tuesday," into the input form of the web application.

[0171] 2. Data transmission: The device sends the input data to the server as an HTTP request. The data is sent in JSON format.

[0172] 3. Data analysis: The server analyzes the received data and retrieves the nutritional information for curry rice from a database (e.g., MySQL). Specifically, it queries the database for the nutritional information for curry rice.

[0173] 4. Nutritional Balance Assessment: The server assesses the nutritional content of the curry rice based on the acquired nutritional information. For example, it identifies a lack of vitamin A.

[0174] 5. Use of generative AI model: The server inputs a prompt to the generative AI model (e.g., GPT-4). An example of a prompt is, "Curry rice is low in vitamin A, so what side dish should I add?"

[0175] 6. Suggestion generation: The server receives the suggestions obtained from the generative AI model and returns them to the user. Specifically, it returns an HTTP response with a message such as, "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish."

[0176] Specific examples

[0177] User input: "Curry rice for dinner on Tuesday"

[0178] Example prompt: "Curry rice is low in vitamin A, so what side dish should you add?"

[0179] Suggestion output: "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0180] In this way, users can easily create menus that take nutritional balance into consideration. The system can also learn from the user's past menu input history and feedback to provide more accurate suggestions.

[0181] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0182] Step 1:

[0183] The user inputs a menu for a certain period of time.

[0184] Specific operation: The user uses the terminal to enter menu information such as "Curry rice for dinner on Tuesday" into the input form of the web application.

[0185] Input: Menu information entered by the user.

[0186] Output: Menu information entered into the terminal.

[0187] Step 2:

[0188] The terminal sends the input data to the server.

[0189] Specific operation: The device sends the menu information entered by the user to the server as an HTTP request. The data is sent in JSON format.

[0190] Input: Menu information entered into the device.

[0191] Output: Menu information sent to the server.

[0192] Step 3:

[0193] The server analyzes the data and obtains the nutritional information.

[0194] Specific operation: The server analyzes the received data and retrieves the nutritional information of curry rice from a database (e.g., MySQL). Specifically, it executes a query about the nutritional information of curry rice against the database.

[0195] Input: Menu information sent to the server.

[0196] Output: Nutritional information retrieved from the database.

[0197] Step 4:

[0198] The server evaluates the nutritional balance.

[0199] Specific operation: The server evaluates the nutrients contained in curry rice based on the acquired nutritional information. For example, it identifies that it is lacking in vitamin A.

[0200] Input: Nutrition information retrieved from the database.

[0201] Output: Nutritional balance assessment (e.g. Vitamin A deficiency).

[0202] Step 5:

[0203] The server inputs a prompt sentence into the generative AI model.

[0204] Specific operation: The server inputs a prompt to the generative AI model (e.g., GPT-4). An example of a prompt is, "Curry rice is low in vitamin A, so what side dish should I add?"

[0205] Input: Nutritional balance assessment results.

[0206] Output: The prompt sentence fed into the generative AI model.

[0207] Step 6:

[0208] The server returns the generated suggestions to the user.

[0209] Specific operation: The server receives the suggestions obtained from the generative AI model and returns them to the user. Specifically, it returns an HTTP response with a message such as "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish."

[0210] Input: Suggestions obtained from a generative AI model.

[0211] Output: The suggestion message returned to the user.

[0212] (Application example 2)

[0213] 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."

[0214] Conventional menu suggestion systems can suggest side dishes or menu substitutions to improve the nutritional balance of the menu entered by the user, but they lack the functionality to suggest side dishes or additional menu items that take nutritional balance into account for the dish the user is about to order. This makes it difficult for users to select meals that take nutritional balance into account when eating out or ordering food delivery.

[0215] 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.

[0216] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to compensate for nutritional balance, a means for providing a service that can respond to personal preferences and new genres that the user wants to try using generative AI, and a means for suggesting side dishes and additional menu items that take nutritional balance into consideration for the dish the user is about to order. This enables the user to select meals that take nutritional balance into consideration even when eating out or using food delivery.

[0217] A "means for inputting meal plans for a specified period of time" is an interface or device that allows a user to input meal plans for a specified period of time.

[0218] "Means for suggesting side dishes or menu changes to compensate for nutritional imbalance" refers to algorithms or systems that suggest side dishes or alternative menu items to compensate for missing nutrients for the menu entered by the user.

[0219] "A means of using generative AI to provide services that can accommodate individual preferences and new genres that users want to try" is a technology that uses a generative AI model to learn from users' past data and feedback, and provides services that accommodate individual users' preferences and new cuisine genres.

[0220] "A means of suggesting side dishes and additional menu items that take into consideration the nutritional balance of the dish that the user is about to order" is a system that suggests side dishes and additional menu items that will supplement the nutritional balance of the dish that the user is about to order via food delivery or eating out.

[0221] The system for implementing this invention allows users to input menus for a certain period of time and provides a function to suggest side dishes and menu changes to supplement nutritional balance. It also uses generative AI to provide a service that can respond to personal preferences and new genres that users want to try, and has a function to suggest side dishes and additional menu items that take nutritional balance into consideration for the dish the user is about to order.

[0222] System configuration

[0223] The system consists of the following main components:

[0224] 1. User device: A device such as a smartphone or tablet that users use to input menu plans.

[0225] 2. Server: A central system for processing and storing data, where the generative AI model runs.

[0226] 3. Generative AI model: An AI model that learns from user input data, past history, and feedback to provide appropriate suggestions.

[0227] Program processing

[0228] The server receives the menu data sent from the user's device and uses a generative AI model to suggest side dishes and menu changes to improve nutritional balance. Specifically, the following process is performed:

[0229] 1. Data entry: The user enters a menu for a certain period of time. For example, the user enters "Curry rice for dinner on Tuesday."

[0230] 2. Data processing: The server receives the input menu data and sends it to the generative AI model.

[0231] 3. Suggestion generation: Based on the input menu data, the generative AI model suggests side dishes or menu changes to improve nutritional balance. For example, it might say, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0232] Hardware and software used

[0233] Hardware: smartphones, tablets, servers

[0234] Software: Python (registered trademark), OpenAI (registered trademark) API

[0235] Specific examples

[0236] For example, if a user wants to order "curry rice," the following prompt sentence is input to the generative AI model:

[0237] A user is trying to order "Curry rice." Please suggest a side dish to supplement the nutrients that are lacking in this dish.

[0238] Example response from a generative AI model:

[0239] Since curry rice is low in vitamin A, we suggest adding a carrot salad as a side dish.

[0240] In this way, nutritionally balanced side dishes and additional menu items can be suggested for the dish the user is about to order.

[0241] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0242] Step 1:

[0243] The user inputs a menu for a certain period of time.

[0244] Input: A user uses a device such as a smartphone or tablet to input a meal plan for a specific period of time. For example, they input "Curry and rice for dinner on Tuesday."

[0245] Output: The entered menu data is saved on the terminal and sent to the server.

[0246] Specific operation: The user inputs the menu through the application interface and presses the submit button to send the data to the server.

[0247] Step 2:

[0248] The server receives the input menu data.

[0249] Input: Menu data sent from the user's device.

[0250] Output: Menu data saved on the server.

[0251] Specific operation: The server receives the data sent from the user terminal and stores it in a database.

[0252] Step 3:

[0253] The server sends the menu data to the generative AI model.

[0254] Input: Menu data stored on the server.

[0255] Output: The prompt sent to the generative AI model.

[0256] Specific operation: The server generates a prompt based on the menu data and sends it to the generative AI model. For example, it generates a prompt such as, "The user is about to order 'Curry Rice'. Please suggest a side dish to supplement the nutrients that are lacking in this dish."

[0257] Step 4:

[0258] A generative AI model generates suggestions based on the prompt.

[0259] Input: The prompt sent to the generative AI model.

[0260] Output: Suggested results from the generative AI model.

[0261] Specific operation: The generative AI model analyzes the prompt sentence and suggests appropriate side dishes or menu changes. For example, it generates a result such as, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0262] Step 5:

[0263] The server receives the suggested results from the generative AI model.

[0264] Input: Suggested results from a generative AI model.

[0265] Output: Suggested results stored on the server.

[0266] Specific operation: The server receives the suggestion results sent from the generative AI model and stores them in a database.

[0267] Step 6:

[0268] The server sends the suggestion results to the user's device.

[0269] Input: Suggested results stored on the server.

[0270] Output: Suggested results displayed on the user's device.

[0271] Specific operation: The server sends the saved suggestion results to the user's device and displays them to the user. For example, a message such as "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish" is displayed.

[0272] Example 3

[0273] 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 smart device 14 will be referred to as a "terminal."

[0274] Conventional menu suggestion systems have difficulty in proposing meals that reflect individual user preferences or new challenges, and have been unable to effectively utilize user feedback to improve the accuracy of suggestions. This has made it difficult to increase user satisfaction.

[0275] 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.

[0276] In this invention, the server includes a means for a user to input a menu, a means for the server to save the menu data, a means for the server to learn the data using a generative AI model, a means for the user to request a new menu, a means for the server to suggest a menu using the generative AI model, a means for the user to provide feedback on the suggested menu, and a means for the server to save the feedback data and re-train the generative AI model. This makes it possible to propose menus that reflect the user's individual preferences and new challenges, and further makes it possible to improve the accuracy of the suggestions by utilizing feedback from the user.

[0277] "Menu" refers to a meal menu or a combination of dishes.

[0278] "Generative AI" is a type of artificial intelligence that refers to a model that has the ability to generate new data and suggestions based on specific data.

[0279] "User" refers to an individual who uses the system to input or request menu items.

[0280] "Server" refers to a computer system that receives data from users, stores it, processes it, and uses generative AI models to learn and make recommendations.

[0281] "Database" refers to an information management system for storing menu data and feedback data from users.

[0282] "Feedback" refers to the evaluation or opinion provided by the user regarding the suggested menu.

[0283] "Learning" refers to data processing by the generative AI to improve the accuracy of future suggestions based on the user's past menu input history and feedback data.

[0284] "Suggestion" refers to the act of generative AI proposing new menus based on the user's preferences and requests.

[0285] A "request" refers to an action in which a user asks the system to suggest a new menu.

[0286] MODE FOR CARRYING OUT THE INVENTION

[0287] This invention relates to a menu suggestion system that utilizes generative AI to accommodate personal preferences and new genres that customers want to try. Specific embodiments of this system are described below.

[0288] Hardware and software used

[0289] Hardware: Server, user terminal (PC, smartphone)

[0290] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), feedback collection systems

[0291] System Overview

[0292] The system learns from the menu data entered by the user in the past and suggests new menus based on the results. Furthermore, it retrains the generative AI model based on user feedback to improve the accuracy of its suggestions.

[0293] Data processing and calculation

[0294] 1. Data collection: The user uses the device to input a past menu. For example, they input "grilled salmon with salt."

[0295] 2. Data storage: The server receives the menu data sent by the user and stores it in the database management system. Specifically, it adds a new record to the "Menu" table in the database.

[0296] 3. Data learning: The server periodically retrieves menu data from the database and uses the generative AI model to learn from it, allowing the model to understand user preferences and patterns.

[0297] 4. Suggestion generation: When a user sends a request for a new menu item from their device, the server uses the generative AI model to suggest an appropriate menu item. For example, it might suggest, "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?"

[0298] 5. Feedback collection: The user tries the suggested menu and provides feedback on the results. For example, they give a "good rating" to "grilled salted mackerel."

[0299] 6. Accuracy Improvement: The server retrains the generative AI model based on the feedback data to improve the accuracy of suggestions.

[0300] Specific examples

[0301] User's past menu entry: "Grilled Salmon"

[0302] Example suggestion: "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?"

[0303] Feedback example: A user gives a "good rating" to "Grilled salted mackerel"

[0304] Prompt Sentence Examples

[0305] Prompt: "Suggest new menu items based on the user's past menu entries. Please consider the user's preferences and new genres they would like to try."

[0306] This system aims to enrich the user's dietary habits by learning the user's preferences and proposing more appropriate menus. The flow of the specification process in the third embodiment will be described with reference to FIG.

[0307] Step 1:

[0308] The user inputs the menu

[0309] The user uses a device (PC or smartphone) to input past menu items into the system interface. For example, they might input "grilled salmon with salt." The input data is then sent from the device to the server.

[0310] Step 2:

[0311] The server stores the menu data

[0312] The server receives the menu data sent by the user and stores it in a database management system (e.g., MySQL). Specifically, it adds a new record to the "Menu" table in the database. The input is the menu data from the user, and the output is the record stored in the database.

[0313] Step 3:

[0314] The server uses a generative AI model to learn the data.

[0315] The server periodically retrieves menu data from the database and trains it using a generative AI model (e.g., GPT-4). This allows the model to understand user preferences and patterns. The input is the menu data retrieved from the database, and the output is the trained generative AI model.

[0316] Step 4:

[0317] A user requests a new menu

[0318] A user uses a terminal to request the system to suggest a new menu. For example, they might input, "Please suggest a new fish dish." The input is a request from the user, and the output is the request data sent to the server.

[0319] Step 5:

[0320] The server uses a generative AI model to suggest menus

[0321] The server receives the user's request and generates an appropriate menu using a generative AI model. For example, it might suggest, "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?" The input is the user's request and the trained generative AI model, and the output is the suggested menu.

[0322] Step 6:

[0323] Users provide feedback on suggested menu items

[0324] The user tries the suggested menu and provides feedback on the results. For example, the user gives a "good rating" to "grilled salted mackerel." The input is the user's feedback, and the output is the feedback data to the server.

[0325] Step 7:

[0326] The server stores the feedback data and retrains the generative AI model.

[0327] The server receives feedback from users and stores it in a database. It then retrains the generative AI model based on the feedback data to improve the accuracy of suggestions. The input is the feedback data from users, and the output is the retrained generative AI model.

[0328] (Application example 3)

[0329] 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."

[0330] Conventional menu suggestion systems do not adequately consider user preferences or new challenges. They also lack a mechanism to effectively utilize user feedback to improve the accuracy of suggestions. Furthermore, food delivery services do not suggest new dishes based on users' past ordering history, making it difficult to increase user satisfaction.

[0331] 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.

[0332] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences and new genres that the user wants to try, a means for learning from the user's past order history and suggesting new dishes that suit the user's preferences, and a means for receiving feedback from the user, learning based on that feedback, and improving the accuracy of the suggestions. This makes it possible to suggest menus and dishes that take into account the user's preferences and new challenges, thereby increasing user satisfaction.

[0333] The "means for inputting menus for a certain period of time" is an interface that allows a user to input menu information planned for a specific period of time into the system.

[0334] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that takes into consideration the nutritional balance of the menu entered by the user and suggests appropriate side dishes or alternative menu items.

[0335] "A means of using generative AI to provide services that can accommodate individual preferences and new genres that users want to try" is a function that uses generative artificial intelligence to provide services that accommodate individual preferences and new genres based on users' past data and feedback.

[0336] "Means of learning the user's past order history and suggesting new dishes that suit the user's preferences" is a function that analyzes the history of dishes that the user has ordered in the past and uses that data to suggest new dishes that suit the user's preferences.

[0337] "Means for receiving feedback from users, learning based on that feedback, and improving the accuracy of suggestions" refers to a function that collects feedback information provided by users, allows the system to learn based on that information, and improves the accuracy of suggestions from the next time onwards.

[0338] The system for implementing this invention has the function of learning the user's past order history and suggesting new dishes that suit the user's preferences. The system is realized using the following hardware and software.

[0339] Hardware

[0340] Server: A server for storing and processing data.

[0341] User device: A mobile device such as a smartphone or tablet.

[0342] software

[0343] Generative AI model: An AI model that learns from a user's past order history and suggests new dishes. Specifically, it uses Python and its libraries (scikit-learn, numpy, etc.).

[0344] Database: A database to store user order history and feedback.

[0345] User Interface: The interface through which users can enter their order history and provide feedback.

[0346] Data processing and calculation

[0347] The server retrieves the user's past order history from the database and uses a generative AI model to learn from that data. Specifically, it performs the following processes:

[0348] 1. Data Acquisition: Retrieve the user's past order history from the database.

[0349] 2. Data preprocessing: Convert the acquired data into TF-IDF vectors.

[0350] 3. Similarity calculation: Calculate the similarity between the user's order history and the menu items using cosine similarity.

[0351] 4. Suggestion generation: Suggests similar menu items to the user.

[0352] 5. Feedback learning: Receive feedback from users and retrain the generative AI model based on that feedback.

[0353] Specific examples

[0354] For example, if a user has previously ordered a "Margherita pizza" and a "Pepperoni pizza," the generative AI model can learn from this data and suggest a "Quattro Formaggi pizza."

[0355] Example prompts to input to a generative AI model:

[0356] Suggest new menu items based on the user's past order history, which is "Margherita Pizza" and "Pepperoni Pizza."

[0357] In this way, it becomes possible to suggest menus and dishes that take into account the user's preferences and new challenges, thereby increasing user satisfaction.

[0358] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0359] Step 1:

[0360] The server retrieves the user's past order history from a database.

[0361] Input: User ID

[0362] Output: User's past order history data

[0363] What happens: The server queries the database to retrieve the order history for the specified user ID. This data includes the order date and time, dish name, rating, etc.

[0364] Step 2:

[0365] The server preprocesses the acquired order history data and converts it into a TF-IDF vector.

[0366] Input: User's past order history data

[0367] Output: TF-IDF vector

[0368] What happens: The server converts the order history data into text format and uses scikit-learn's TfidfVectorizer to create a TF-IDF vector. This vector quantifies the features of each dish.

[0369] Step 3:

[0370] The server converts the list of menu items into TF-IDF vectors.

[0371] Input: A list of menu items

[0372] Output: TF-IDF vectors of menu items

[0373] Specific operation: The server converts the list of menu items into text format and also converts it into a TF-IDF vector, which is a numerical representation of the features of each menu item.

[0374] Step 4:

[0375] The server calculates the cosine similarity between the user's order history vector and the menu item vector.

[0376] Input: TF-IDF vector of user's order history, TF-IDF vector of menu items

[0377] Output: Cosine similarity score

[0378] How it works: The server uses scikit-learn's cosine_similarity function to calculate the cosine similarity between the user's order history vector and each menu item vector. This score indicates how close each menu item is to the user's preferences.

[0379] Step 5:

[0380] The server suggests the most similar menu items to the user based on the cosine similarity scores.

[0381] Input: Cosine similarity score

[0382] Output: Suggested menu items

[0383] Specific operation: The server compares the calculated cosine similarity scores, selects the menu item with the highest score, and sends this menu item to the user device to suggest to the user.

[0384] Step 6:

[0385] The user provides feedback on the suggested menu items.

[0386] Input: Suggested menu item

[0387] Output: User feedback

[0388] Specific behavior: The user reviews the suggested menu items and provides feedback, such as a positive or negative rating. This feedback is sent from the user device to the server.

[0389] Step 7:

[0390] The server receives feedback from users and retrains the generative AI model based on that feedback.

[0391] Input: User feedback

[0392] Output: An updated generative AI model

[0393] How it works: The server stores the feedback received from users in a database and uses that data to retrain the generative AI model, improving the accuracy of future suggestions.

[0394] 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.

[0395] "Example 1"

[0396] In one embodiment of the present invention, a system is provided that includes an emotion engine that recognizes a user's emotions. The system grasps the user's emotional state and provides meal suggestions based on the emotional state. Specifically, when the user is feeling joy, the system suggests a meal that will enhance that joy. For example, the system may suggest a special meal on the day the user receives a promotion.

[0397] "Example 2"

[0398] The emotion engine also analyzes user behavioral data and feedback to understand a user's emotional state. Specifically, it analyzes the user's behavior after eating a particular meal and their evaluation of the meal to understand how that meal affected the user's emotions. For example, if a user becomes more active after eating a particular meal, it can determine that that meal is likely to increase the user's joy.

[0399] "Example 3"

[0400] Furthermore, the emotion engine learns the user's emotional state to improve the accuracy of menu suggestions according to the user's emotional state. Specifically, it learns the relationship between the user's past emotional state and the menu at that time, and makes menu suggestions based on that result. For example, if a user tends to prefer a particular meal when feeling happy, the accuracy of suggestions can be improved by suggesting that meal when the user is in a similar emotional state.

[0401] "Example 4"

[0402] In this way, the system of the present invention enriches the user's dining experience by providing menu suggestions that take the user's emotional state into account. Furthermore, by learning the user's emotional state, the system can deepen its understanding of the user's emotions and provide a more personalized service.

[0403] The processing flow of each embodiment will be described below.

[0404] "Example 1"

[0405] Step 1: The emotion engine understands the user's emotional state.

[0406] Step 2: Based on the emotional state, the generative AI generates a menu.

[0407] Step 3: The generated menu is presented to the user.

[0408] "Example 2"

[0409] Step 1: User behavioral data and feedback are input into the emotion engine.

[0410] Step 2: The emotion engine analyzes the input data and understands the user's emotional state.

[0411] Step 3: Based on the emotional state, the generative AI generates a menu and presents it to the user.

[0412] "Example 3"

[0413] Step 1: The emotion engine learns the relationship between the user's past emotional state and the menu at that time.

[0414] Step 2: Based on the learning results, the emotion engine understands the current emotional state of the user.

[0415] Step 3: Based on the emotional state, the generative AI generates a menu and presents it to the user.

[0416] "Example 4"

[0417] Step 1: The user's emotional state is understood by the emotion engine.

[0418] Step 2: Based on the emotional state, the generative AI generates a menu.

[0419] Step 3: The generated menu is presented to the user, enriching their dining experience.

[0420] Example 1

[0421] 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."

[0422] Conventional menu suggestion systems suggest menus without considering the user's emotional state, making it difficult to enhance the user's psychological satisfaction. Furthermore, while suggestions are made based on nutritional balance and personal preferences, there is a lack of special suggestions tailored to the user's emotions. This presents a problem in that it is difficult for users to select an appropriate menu for a special day or a specific emotional state. The specification process by the specification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0423] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can accommodate personal preferences and new genres that the user wants to try using generative AI, a means for recognizing the user's emotional state and suggesting menus based on that emotional state, and a means for integrating and analyzing the user's emotional data and menu data. This makes it possible to provide the optimal menu according to the user's emotional state and increase psychological satisfaction.

[0424] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[0425] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[0426] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses a generative AI model to suggest menus that suit individual preferences and new cooking genres based on the user's past data and feedback.

[0427] "Means of recognizing the user's emotional state and suggesting menus based on that emotional state" is a function that uses an emotion engine to analyze the user's emotions and suggests appropriate menus based on the results.

[0428] "Means for integrating and analyzing user emotional data and menu data" is a function that combines and analyzes the menu data entered by the user with the emotional data obtained from the emotion engine to generate the optimal menu.

[0429] MODE FOR CARRYING OUT THE INVENTION

[0430] This invention is a system that allows a user to input menus for a certain period of time, and based on that data, suggests optimal menus that take into account nutritional balance, personal preferences, and even the user's emotional state. Specific embodiments of this system are described below.

[0431] Providing a user interface

[0432] The server provides an interface for users to input menu plans for a certain period of time. This interface is implemented on a web page or smartphone application. Specifically, the web page is generated using HTML, CSS, and JavaScript, and for smartphone applications, frameworks such as React Native or Flutter (registered trademark) are used.

[0433] User menu entry

[0434] The user inputs a menu into a text box through the provided interface. For example, they might input "grilled salted salmon for dinner on Monday, and curry rice for dinner on Tuesday." The input data is sent to the server and stored in a database.

[0435] Collecting Emotional Data

[0436] The server collects the user's emotional state using an emotion engine. This emotion engine recognizes emotions by analyzing the user's input, actions, and external data (e.g., social media posts). Specific software used is the emotion analysis API from IBM Watson (registered trademark) or Microsoft (registered trademark) Azure (registered trademark).

[0437] Data integration and analysis

[0438] The server integrates the menu data entered by the user with the emotion data obtained from the emotion engine. Based on this integrated data, it uses a generative AI model to suggest optimal menus. Specifically, the model is implemented using Python and TENSORFLOW (registered trademark) and the data is analyzed.

[0439] Menu suggestions

[0440] Based on the analysis results of the generative AI model, the server suggests the optimal menu based on the user's emotional state. For example, if a user receives a promotion, it might suggest a steak dinner as a special meal.

[0441] Displaying suggestions

[0442] The device displays the suggestions sent from the server to the user. The user can then review the suggested menu and make any necessary corrections or approvals. The menu is displayed in a visually easy-to-understand format using HTML and CSS.

[0443] Examples and prompts

[0444] Specific examples

[0445] A user types "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday" on a web page. The emotion engine detects that the user posted on social media, "I got promoted!" and suggests "steak dinner" as a special meal.

[0446] Prompt Sentence Examples

[0447] "Please suggest the best meal based on the meal data and sentiment data entered by the user. If the user gets promoted, please suggest a special meal."

[0448] In this way, a system is realized that provides optimal menus according to the user's emotional state.

[0449] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0450] Step 1:

[0451] The server provides an interface for users to input menus for a certain period of time. On a web page or smartphone application, users input their menus, for example, "Monday's dinner is grilled salted salmon, and Tuesday's dinner is curry rice." The input data is sent to the server and stored in a database. The input is the user's menu data, and the output is the menu data stored in the database.

[0452] Step 2:

[0453] The server uses an emotion engine to collect the user's emotional state. The emotion engine recognizes emotions by analyzing user input and behavior, as well as external data (e.g., social media posts). Specific software used is the emotion analysis API from IBM Watson or Microsoft Azure. The input is user behavior data and external data, and the output is analyzed emotional data.

[0454] Step 3:

[0455] The server integrates the menu data entered by the user with the emotion data obtained from the emotion engine. Based on this integrated data, a generative AI model is used to suggest optimal menus. Specifically, the model is implemented using Python and TensorFlow to analyze the data. The input is the integrated menu data and emotion data, and the output is a menu suggested by the generative AI model.

[0456] Step 4:

[0457] The server uses the analysis results of the generative AI model to suggest the optimal menu based on the user's emotional state. For example, if a user is promoted, it might suggest a "steak dinner" as a special meal. The input is the analysis results of the generative AI model, and the output is the suggested menu.

[0458] Step 5:

[0459] The terminal displays the suggestions sent from the server to the user. The user checks the suggested menu and makes any necessary corrections or approvals. The display is provided in a visually easy-to-understand format using HTML and CSS. The input is the suggestions sent from the server, and the output is the menu displayed to the user.

[0460] (Application example 1)

[0461] 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."

[0462] Conventional menu suggestion systems can suggest menus based on the user's nutritional balance and personal preferences, but they do not suggest menus that take into account the user's emotional state. As a result, they are unable to provide appropriate meals according to the user's emotions, making it difficult to increase user satisfaction. In addition, they are unable to suggest special menus that correspond to specific emotional states, such as when the user is tired or on special occasions.

[0463] 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 a means for inputting menus for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences or new genres that the user wants to try, and a means for recognizing the user's emotional state and suggesting menus based on those emotions. This makes it possible to propose appropriate menus according to the user's emotional state, thereby increasing user satisfaction.

[0464] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[0465] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[0466] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative AI to learn from users' past data and feedback, and suggests menus that match individual users' preferences and new cooking genres.

[0467] "Means for recognizing the user's emotional state and suggesting menus based on those emotions" is a function that detects the user's emotions and suggests appropriate menus based on those emotions.

[0468] A system for implementing this invention includes a means for a user to input menu items for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences or new genres that the user wants to try, and a means for recognizing the user's emotional state and suggesting menu items based on those emotions.

[0469] System Program

[0470] This system uses the following hardware and software:

[0471] Hardware: Smartphone

[0472] Software: Python, emotion recognition API (e.g. Microsoft Azure Emotion API)

[0473] Program processing explanation

[0474] The server provides an interface for users to input menus for a certain period of time. This interface can be implemented on a web page or a smartphone application. For example, users can input menus in the form of "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday."

[0475] The server then uses an emotion recognition API to recognize the user's emotional state. The user can input their emotional state or detect emotions through camera or voice input. This emotional data is sent to the server and analyzed by generative AI.

[0476] The generative AI learns from the user's past menu input history and feedback, and then makes menu suggestions based on the results. For example, it might suggest a relaxing meal when the user is tired, or a special meal when the user is happy.

[0477] Specific examples

[0478] For example, if a user inputs "I'm tired," the server will recognize this emotion through an emotion recognition API, and the generative AI will suggest "a relaxing meal." This suggestion is based on the user's past data and feedback.

[0479] Example prompts to input to a generative AI model:

[0480] A user says they're tired. Suggest a relaxing meal.

[0481] Using this prompt, the generative AI model can suggest appropriate menu items.

[0482] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0483] Step 1:

[0484] The user inputs a menu for a certain period of time through a smartphone application. For example, the user might input a menu such as "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday." The input data is then sent to the server.

[0485] Step 2:

[0486] The server uses the emotion recognition API to recognize the user's emotional state. The user inputs their emotional state or detects emotions through camera or voice input. The emotion recognition API analyzes the input data and identifies the user's emotional state. This emotional data is sent to the server.

[0487] Step 3:

[0488] The server uses generative AI to learn from the user's past menu entry history and feedback. Based on this data, the generative AI identifies the user's preferences and new genres they would like to try. The results of this learning are stored on the server.

[0489] Step 4:

[0490] The server suggests appropriate menus based on the user's emotional state and past data. For example, if the user is recognized as "tired," the generative AI will suggest "relaxing meals." These suggestions are displayed on the user's smartphone application.

[0491] Step 5:

[0492] The user provides feedback on the suggested menu, which is entered through a smartphone application and sent to the server.

[0493] Step 6:

[0494] The server receives feedback from users, and the generative AI learns based on that feedback. This improves the accuracy of menu suggestions. The learning results are saved on the server and reflected in the next suggestions.

[0495] Example 2

[0496] 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."

[0497] Conventional menu suggestion systems have difficulty in appropriately suggesting side dishes and menu changes that take into account the user's nutritional balance. Furthermore, they are unable to take into account the user's emotional state, which makes it difficult to increase user satisfaction. Furthermore, there is a need to improve the accuracy of suggestions by utilizing the user's past behavioral data and feedback.

[0498] 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.

[0499] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to compensate for nutritional balance, a means for providing a service that can respond to personal preferences and new genres that users want to try using a generative AI model, and a means for collecting user behavioral data and feedback and understanding the user's emotional state using an emotion engine. This enables appropriate menu suggestions that take the user's nutritional balance into consideration, and by making suggestions that take the user's emotional state into account, user satisfaction can be increased. In addition, the accuracy of suggestions can be improved by utilizing the user's past behavioral data and feedback.

[0500] A "means for inputting a menu for a certain period of time" is a device or software that provides an interface for a user to input meal contents for a specific period of time.

[0501] A "means for suggesting side dishes or menu changes to compensate for nutritional imbalance" is a device or software that analyzes the nutritional components of an input menu and suggests side dishes or alternative menu items to compensate for missing nutrients.

[0502] "A means of using a generative AI model to provide a service that can respond to individual preferences and new genres that users want to try" refers to a device or software that uses a generative AI model to learn from a user's past data and preferences, and then suggests new menus and side dishes based on that data.

[0503] "Means for collecting user behavioral data and feedback and understanding the user's emotional state using an emotion engine" refers to a device or software that collects the user's behavior and evaluation after consuming a meal, analyzes it using an emotion engine, and evaluates the user's emotional state.

[0504] MODE FOR CARRYING OUT THE INVENTION

[0505] This invention is a system that suggests side dishes and menu changes to supplement nutritional balance based on the user's diet. It also uses an emotion engine to analyze the user's behavioral data and feedback and understand the user's emotional state.

[0506] Hardware and software used

[0507] Hardware: Servers, user devices (PCs, smartphones)

[0508] Software: Generative AI model, emotion engine, database management system (DBMS)

[0509] Specific operation of the system

[0510] 1. User Input

[0511] The user uses the device to input the details of the meal, for example, "Curry rice for dinner on Tuesday."

[0512] 2. Analysis of dietary content

[0513] The server analyzes the entered meal details. Using a generative AI model, the server analyzes the entered text and extracts the specific details of the meal. For example, it recognizes the keyword "curry rice."

[0514] 3. Evaluation of nutritional balance

[0515] The server accesses the database and retrieves the nutritional information for the curry rice. Based on the retrieved information, the server evaluates the nutritional balance of the curry rice. For example, it identifies a deficiency of vitamin A.

[0516] 4. Generating Suggestions

[0517] The server generates suggestions for side dishes and menu items to complement nutritional balance. It uses a generative AI model to suggest appropriate side dishes. For example, it suggests, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0518] 5. Collecting behavioral data

[0519] The server collects user behavior data, specifically, the user's actions after eating a meal (e.g., exercise or rest) and their evaluation of the meal (e.g., "delicious" or "satisfied") are recorded in a database.

[0520] 6. Analysis by Emotion Engine

[0521] The server uses an emotion engine to analyze the collected behavioral data and feedback. For example, if a user starts exercising after eating curry rice, the server analyzes the behavioral data and evaluates the impact of the meal on the user's emotions.

[0522] 7. Understanding your emotional state

[0523] The server uses the analysis results of the emotion engine to understand the user's emotional state. For example, if a user becomes active after eating curry rice, it will determine that the meal increased the user's joy.

[0524] Specific examples

[0525] Example user input: "Curry rice for dinner on Tuesday"

[0526] Server analysis example: "Curry rice is low in vitamin A"

[0527] Example suggestion: "Suggest adding carrot salad as a side dish."

[0528] Example of behavioral data collection: "User started exercising after eating curry rice."

[0529] Example of emotion engine analysis: "Curry rice increased user activity"

[0530] Example of grasping emotional state: "Curry rice increased the user's joy"

[0531] Prompt Sentence Examples

[0532] "Tuesday's dinner is curry rice. Please suggest a side dish to make it more nutritious."

[0533] "A user starts exercising after eating curry rice. Analyze the effect of this meal on the user's emotions."

[0534] The above is an embodiment of the present invention.

[0535] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0536] Step 1:

[0537] The user inputs the meal details.

[0538] Input: A user uses a terminal to input a meal description in text format. For example, they might input "Curry rice for dinner on Tuesday."

[0539] Output: The entered meal details are sent to the server.

[0540] Specific operation: The user enters the meal details into the input form on the device and presses the send button, which sends the data to the server.

[0541] Step 2:

[0542] The server analyzes the meal contents.

[0543] Input: Text data of meal details submitted by the user.

[0544] Output: Specific meal items (e.g. curry rice) are extracted.

[0545] What happens: The server uses the generative AI model to analyze the input text and extract specific details about the meal, for example, recognizing the keyword "curry rice."

[0546] Step 3:

[0547] The server evaluates the nutritional balance.

[0548] Input: Extracted meal details (e.g. curry rice).

[0549] Output: Nutritional information of the meal and its evaluation results.

[0550] Specific operation: The server accesses the database and obtains the nutritional information of curry rice. Based on the obtained information, it evaluates the nutritional balance of curry rice and identifies, for example, a lack of vitamin A.

[0551] Step 4:

[0552] The server generates suggestions for side dishes and menu items.

[0553] Input: Nutritional balance assessment result (e.g. Vitamin A deficiency).

[0554] Output: Suggested side dishes and menu items to complement nutritional balance.

[0555] What it does: The server uses a generative AI model to suggest appropriate side dishes, such as "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0556] Step 5:

[0557] The server collects user behavior data.

[0558] Input: User behavioral data after consuming a meal and their evaluation of the meal.

[0559] Output: Collected behavioral data and evaluations are recorded in a database.

[0560] Specific operation: The server collects the user's behavioral data (e.g., exercise or rest after eating) and feedback (e.g., "It was delicious" or "I was satisfied") and records them in a database.

[0561] Step 6:

[0562] The server analyzes the data using an emotion engine.

[0563] Input: Collected behavioral data and feedback.

[0564] Output: Analysis results about the user's emotional state.

[0565] Specific operation: The server uses the emotion engine to analyze the collected behavioral data and feedback. For example, if a user starts exercising after eating curry rice, the behavioral data is analyzed to evaluate the impact of the meal on the user's emotions.

[0566] Step 7:

[0567] The server grasps the user's emotional state.

[0568] Input: Sentiment engine analysis results.

[0569] Output: Information about the user's emotional state.

[0570] Specific operation: The server understands the user's emotional state based on the analysis results of the emotion engine. For example, if the user becomes active after eating curry rice, it determines that the meal increased the user's joy.

[0571] (Application example 2)

[0572] 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."

[0573] Conventional menu suggestion systems did not adequately consider nutritional balance when selecting side dishes or changing menu items, making it difficult to contribute to users' health management. Furthermore, menu suggestions did not take into account the user's emotional state, making it difficult to increase user satisfaction. Furthermore, there was a lack of means to effectively utilize user behavioral data and feedback, resulting in low suggestion accuracy.

[0574] 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.

[0575] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can respond to personal preferences and new genres that the user wants to try using generative AI, a means for analyzing the user's behavioral data and feedback to understand their emotional state, and a means for suggesting the next menu taking the user's emotional state into consideration, which contributes to the user's health management and makes it possible to increase satisfaction.

[0576] The "means for inputting menus" is an interface that allows users to input meal plans for a certain period of time into the system.

[0577] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that takes into consideration the nutritional balance of the input menu and suggests appropriate side dishes or menu changes.

[0578] "A means of using generative AI to provide services that can respond to individual preferences and new genres that users want to try" is a function that uses generative AI to learn from users' past data and preferences and make suggestions for new meals.

[0579] "Means of analyzing user behavioral data and feedback to understand emotional state" is a function that analyzes the feedback and behavioral data provided by the user after eating to understand the user's emotional state.

[0580] "Means for suggesting the next menu taking into account the user's emotional state" is a function that makes suggestions for the next meal based on the user's emotional state.

[0581] The system for implementing this invention includes an interface that allows users to input menu plans for a certain period of time, a function that suggests side dishes and menu changes to supplement nutritional balance, a function that uses generative AI to provide services that can accommodate personal preferences and new genres that users want to try, a function that analyzes user behavioral data and feedback to understand their emotional state, and a function that takes their emotional state into consideration to suggest the next menu plan.

[0582] Program processing

[0583] The server receives menu data entered by the user for a certain period of time and suggests side dishes or menu changes to improve nutritional balance. For example, if a user enters "Curry rice for dinner on Tuesday," the server will make a suggestion such as, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[0584] Furthermore, the server uses generative AI to learn from the user's past menu input history and makes menu suggestions based on the results. For example, if a user has previously ordered a "hamburger steak," the next time the server suggests "sauteed spinach, which goes well with the hamburger steak."

[0585] To analyze user behavioral data and feedback, the server analyzes the feedback and behavioral data provided by the user after eating to understand the user's emotional state. For example, if the user feedbacks that the meal is "delicious," the server determines that the meal is likely to increase the user's pleasure.

[0586] Finally, the server considers the user's emotional state to suggest the next meal. For example, if the user gives feedback that they are "satisfied," the server will suggest the next meal based on that emotional state.

[0587] Hardware and software used

[0588] In this system, users input their menus using devices such as smartphones or tablets, and the server analyzes the data using programming languages ​​such as Python. Data processing and calculations are performed by saving and analyzing the user's order history and feedback in JSON format.

[0589] Specific examples

[0590] For example, if a user orders "curry rice," the system will display a message saying, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish." If the user gives feedback that the meal is "delicious," the system will determine that the meal has the potential to increase the user's pleasure.

[0591] Example prompts to input to a generative AI model:

[0592] A user has ordered "Curry rice." Please suggest a side dish that takes nutritional balance into consideration. Also, please analyze the user's feedback "Delicious" to understand their emotional state.

[0593] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0594] Step 1:

[0595] The user inputs a menu for a certain period of time.

[0596] Users use devices such as smartphones and tablets to input menu plans for a certain period of time into the application interface, and the input data is sent to the server.

[0597] Input: Menu data entered by the user

[0598] Output: Menu data sent to the server

[0599] Step 2:

[0600] The server will suggest side dishes or menu changes to improve nutritional balance.

[0601] The server analyzes the received menu data and suggests appropriate side dishes or menu changes, taking nutritional balance into consideration. For example, if a user inputs "Tuesday's dinner is curry rice," the server will suggest, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[0602] Input: Menu data

[0603] Output: Suggested side dishes and menu items

[0604] Step 3:

[0605] The server uses generative AI to learn from the user's past menu entry history.

[0606] The server analyzes the user's past menu input history and uses generative AI to learn from it, thereby understanding the user's preferences and trends and reflecting them in the next menu suggestion.

[0607] Input: Past menu input history

[0608] Output: Learning results

[0609] Step 4:

[0610] The server analyzes the user's behavioral data and feedback to understand their emotional state.

[0611] The server analyzes the feedback and behavioral data provided by the user after eating to understand the user's emotional state. For example, if the user gives feedback that the meal was "delicious," the server determines that the meal is likely to increase the user's pleasure.

[0612] Input: Feedback and behavioral data

[0613] Output: Emotional state analysis results

[0614] Step 5:

[0615] The server takes into account the user's emotional state and suggests the next menu.

[0616] The server will suggest the next meal based on the analysis of the user's emotional state. For example, if the user gives feedback of "satisfied," the server will suggest the next meal based on that emotional state.

[0617] Input: Emotional state analysis results

[0618] Output: Next menu suggestion

[0619] Specific examples

[0620] For example, if a user orders "curry rice," the system will display, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish." If the user gives feedback that the meal is "delicious," the system will determine that the meal has the potential to increase the user's enjoyment.

[0621] Example prompts to input to a generative AI model:

[0622] A user has ordered "Curry rice." Please suggest a side dish that takes nutritional balance into consideration. Also, please analyze the user's feedback "Delicious" to understand their emotional state.

[0623] Example 3

[0624] 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."

[0625] Conventional menu suggestion systems have difficulty in making suggestions that fully take into account the user's individual preferences and emotional state, and have been unable to increase user satisfaction. Furthermore, they lack a mechanism for effectively utilizing user feedback to improve the accuracy of suggestions. This has led to a demand for systems that can further enrich users' dining experiences.

[0626] 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.

[0627] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences and new genres that the user wants to try, a means for analyzing the user's emotional state and suggesting menus based on that emotional state, and a means for collecting user feedback, allowing the generative AI to learn based on that feedback and improve the accuracy of the menu suggestions. This enables personalized menu suggestions that take into account the user's individual preferences and emotional state, thereby enriching the user's dining experience.

[0628] The "menu input means" is a means for a user to input menus for a certain period of time.

[0629] "Nutritional balance support measures" are measures that suggest side dishes or menu changes to supplement nutritional balance.

[0630] "Generative AI" is artificial intelligence that provides services that can respond to individual preferences and new genres that people want to try.

[0631] The "emotional state analysis means" is a means for analyzing the user's emotional state and suggesting a menu based on that emotional state.

[0632] The "feedback collection method" is a method for collecting user feedback, allowing the generative AI to learn based on that feedback and improve the accuracy of menu suggestions.

[0633] "Database" refers to a data storage system that stores users' past menu entry history and feedback.

[0634] A "user terminal" is a device that allows a user to input menu items and check suggested menu items.

[0635] A "server" is a central system that receives and processes data sent from user terminals.

[0636] A "prompt" is an instruction given to a generative AI to perform a specific task.

[0637] MODE FOR CARRYING OUT THE INVENTION

[0638] This invention is a system that uses generative AI to provide a menu suggestion service that can accommodate personal preferences and new genres that users want to try. The system learns from the user's past menu input history, feedback, and emotional state, and then suggests optimal menus based on that.

[0639] Hardware and software used

[0640] Hardware: Servers, user devices (PCs, smartphones)

[0641] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL®), emotion engines (e.g., Affectiva)

[0642] Specific operation of the system

[0643] 1. User menu entry

[0644] The user uses the device to input a previously prepared menu. For example, the user opens the app and inputs "grilled salmon with salt."

[0645] 2. Data storage

[0646] The device sends the entered menu data to the server, which saves this data in a database. For example, the device sends the data "grilled salmon with salt" to the server, and the server saves this data in a database.

[0647] 3. Generating menu suggestions

[0648] The server retrieves the user's past menu history from the database and inputs it into a generative AI model (e.g., GPT-4). For example, the server retrieves the history of "grilled salmon" and sends a prompt to the generative AI model saying, "Please suggest a new menu based on the menu history entered by the user in the past."

[0649] 4. Providing suggestions

[0650] The server receives the menu suggestions generated by the generative AI model and sends them to the device. For example, the generative AI model suggests "grilled salted mackerel," and the server sends this suggestion to the device. The device then displays to the user, "Why not try grilled salted mackerel?"

[0651] 5. Collecting User Feedback

[0652] Users can provide feedback on suggested menu items. For example, a user can give a "good rating" to "grilled salted mackerel."

[0653] 6. Learning Feedback

[0654] The server stores the user's feedback in a database and provides the feedback data to the generative AI model. For example, the server stores the feedback of "good rating" in the database and sends a prompt to the generative AI model saying, "Please improve the accuracy of the next menu suggestion based on the user's feedback."

[0655] 7. Emotional state analysis

[0656] The server uses an emotion engine (e.g., Affectiva) to analyze the user's emotional state. For example, the server inputs the user's facial expressions and voice data into the emotion engine and obtains the analysis result that "the user is feeling happy."

[0657] 8. Generating Suggestions Based on Emotions

[0658] The server sends new prompts to the generative AI model based on the user's emotional state and past menu data, generating emotion-based menu suggestions. For example, the server might send a prompt to the generative AI model saying, "If the user tends to like a particular meal when they are feeling happy, please suggest that meal when they are in a similar emotional state." The generative AI model then suggests "a meal the user likes when they are feeling happy," and the server sends this suggestion to the device.

[0659] In this way, the system learns the user's past data and emotional state and provides more personalized menu suggestions, thereby enriching the user's dining experience. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[0660] Step 1:

[0661] User menu entry

[0662] The user uses the device to input a menu they have previously created. Specifically, the user opens the app and inputs "grilled salmon with salt." The input data is sent from the device to the server. The input data is "Menu name: grilled salmon with salt."

[0663] Step 2:

[0664] Data storage

[0665] The server receives the menu data sent from the terminal and saves it in the database. Specifically, the server saves the data "grilled salmon with salt" in the database. The input data is "Menu name: grilled salmon with salt", and the output is the state saved in the database.

[0666] Step 3:

[0667] Generate menu suggestions

[0668] The server retrieves the user's past menu history from the database and inputs it into a generative AI model (e.g., GPT-4). Specifically, the server retrieves the history of "grilled salmon" and sends the generative AI model a prompt saying, "Please suggest a new menu based on the menu history entered by the user in the past." The input data is "Past menu history: grilled salmon," and the output is the generated suggestion, "grilled mackerel with salt."

[0669] Step 4:

[0670] Providing suggestions

[0671] The server receives the menu suggestions generated by the generative AI model and sends them to the device. Specifically, the generative AI model suggests "grilled salted mackerel," and the server sends this suggestion to the device. The device then displays to the user, "Why not try grilled salted mackerel?" The input data is "generated suggestion: grilled salted mackerel," and the output is what is presented to the user.

[0672] Step 5:

[0673] Collecting user feedback

[0674] The user provides feedback on the suggested menu. Specifically, the user gives a "good rating" to "grilled salted mackerel." The input data is "suggested menu: grilled salted mackerel," and the output is "feedback: good rating."

[0675] Step 6:

[0676] Learning Feedback

[0677] The server stores the user's feedback in a database and provides the feedback data to the generative AI model. Specifically, the server stores the "good rating" feedback in the database and sends the generative AI model a prompt saying, "Please improve the accuracy of the next menu suggestion based on the user's feedback." The input data is "Feedback: good rating," and the output is the "trained model."

[0678] Step 7:

[0679] Emotional state analysis

[0680] The server uses an emotion engine (e.g., Affectiva) to analyze the user's emotional state. Specifically, the server inputs the user's facial and voice data into the emotion engine, and obtains the analysis result that "the user is feeling happy." The input data is "facial and voice data," and the output is "emotional state: happy."

[0681] Step 8:

[0682] Generating Suggestions Based on Emotions

[0683] The server sends a new prompt to the generative AI model based on the emotional state and past menu data, generating emotion-based menu suggestions. Specifically, the server sends the prompt to the generative AI model: "If the user tends to prefer a particular meal when feeling happy, please suggest that meal when the user is in a similar emotional state." The generative AI model suggests "a meal that the user prefers when feeling happy," and the server sends this suggestion to the device. The input data are "emotional state: joy" and "past menu data," and the output is "emotion-based suggestions."

[0684] (Application example 3)

[0685] 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."

[0686] Conventional menu suggestion systems are limited to suggestions based on the user's past menu input history and feedback, and have the problem of being unable to provide personalized suggestions that take the user's emotional state into account. They also do not adequately address users' preferences or their desire to try new genres. Furthermore, food delivery services require optimal dish suggestions based on the user's past ordering history and feedback, but there has been a lack of effective ways to achieve this.

[0687] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences and new genres that the user wants to try, a means for learning the user's past order history, feedback, and emotional state to suggest optimal dishes, and a means for generating the next suggested dish using a generative AI model. This enables personalized menu suggestions that take the user's emotional state into consideration, and optimal dish suggestions for food delivery services.

[0688] The "means for inputting a menu for a certain period of time" is an interface that allows a user to input into the system the meal contents planned for a specific period of time.

[0689] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[0690] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative artificial intelligence to suggest individual preferences and new genres of cuisine based on the user's past data and feedback.

[0691] "Means of learning from a user's past order history, feedback, and emotional state to suggest the most suitable dish" refers to a function that analyzes the dishes a user has ordered in the past, the feedback they received at the time, and their emotional state, and then suggests the next best dish.

[0692] "Means for generating the next suggested dish using a generative AI model" is a function that uses a generative artificial intelligence model to generate the next suggested dish based on user data.

[0693] The system for implementing this invention provides a food delivery application that learns a user's past order history, feedback, and emotional state, and suggests the most suitable dishes. A specific embodiment of this system is described below.

[0694] System Configuration

[0695] This system mainly uses the following hardware and software:

[0696] Hardware: Smartphone

[0697] Software: Python, OpenAI API

[0698] Program processing explanation

[0699] Retrieving User Data

[0700] The server retrieves the user's past order history and feedback from the database, which allows it to understand what dishes the user has ordered in the past and what ratings they have given.

[0701] Acquiring emotional state

[0702] The server provides an interface for obtaining the user's emotional state. For example, the user can input the emotional state within the application, or the emotional state can be inferred using sensors on the smartphone.

[0703] AI suggestions

[0704] The server uses a generative AI model to generate the next dish suggestion based on the acquired user data and emotional state, using OpenAI's API to input the user's data as a prompt sentence to generate the optimal dish.

[0705] Specific examples

[0706] For example, if a user has frequently ordered "pizza" in the past and has given "pizza" a "good" rating, the next suggested dish when the emotional state is "happy" may be "calzone."

[0707] Prompt Sentence Examples

[0708] Below are some example prompts to input to the generative AI model:

[0709] User's past orders: ["Pizza", "Pasta"]

[0710] Feedback: {"pizza": "good", "pasta": "average"}

[0711] Emotional state: Joy

[0712] What dish would you suggest next?

[0713] By inputting this prompt into a generative AI model, the next suggested dish can be generated.

[0714] effect

[0715] This system will enable personalized menu suggestions that take into account the user's emotional state, as well as optimal dish suggestions for food delivery services, thereby enriching the user's dining experience and increasing satisfaction.

[0716] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0717] Step 1:

[0718] The server retrieves the user's past order history and feedback from the database. Specifically, it sends a query to the database using the user ID as a key to retrieve a list of past orders and their ratings. The input for this step is the user ID, and the output is the past order history and feedback data.

[0719] Step 2:

[0720] The server acquires the user's emotional state. Specifically, it collects the emotional state input by the user within the application and emotional data inferred using the smartphone's sensors. The input of this step is the input data of the user's emotional state, and the output is the emotional state information.

[0721] Step 3:

[0722] The server generates prompts based on the acquired user data and emotional state. Specifically, it combines past order history, feedback, and emotional state to create prompts to input into the generative AI model. The inputs for this step are past order history, feedback, and emotional state, and the output is the generated prompt.

[0723] Step 4:

[0724] The server uses the generative AI model to generate the next dish suggestion. Specifically, it sends the generated prompt to OpenAI's API and receives a response from the AI ​​model. The input of this step is the generated prompt, and the output is the suggested dish from the AI ​​model.

[0725] Step 5:

[0726] The server presents the suggested dishes to the user by displaying them in the application interface and allowing the user to select them as their next dish to order. The input to this step is the suggested dishes from the AI ​​model, and the output is the information about the dishes presented to the user.

[0727] 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.

[0728] 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.

[0729] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0730] 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.

[0731] [Second embodiment]

[0732] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0733] 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.

[0734] 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).

[0735] 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.

[0736] 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.

[0737] 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).

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0744] "Example 1"

[0745] The system of the present invention provides an interface that allows users to input menus for a certain period of time. This interface can be implemented, for example, on a web page or a smartphone application. For example, a user inputs a menu in the form of "Monday's dinner is grilled salmon with salt, and Tuesday's dinner is curry rice."

[0746] "Example 2"

[0747] The system then suggests side dishes or menu changes to improve nutritional balance. For example, if a user inputs "Curry rice for dinner on Tuesday," the system might suggest, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[0748] "Example 3"

[0749] Furthermore, the system uses generative AI to provide a service that can accommodate individual preferences and new genres that users want to try. This AI learns from the user's past menu input history and makes menu suggestions based on the results. For example, if a user has often input "grilled salted salmon" in the past, the AI ​​will suggest something like, "Why not try grilled salted mackerel, which has a similar flavor to grilled salted salmon?"

[0750] "Example 4"

[0751] The AI ​​also receives feedback from users and learns from that feedback to improve the accuracy of its menu suggestions. For example, if a user gives a "good rating" to the suggestion "grilled salted mackerel," the AI ​​will increase the probability of suggesting dishes similar to "grilled salted mackerel."

[0752] The processing flow of each embodiment will be described below.

[0753] "Example 1"

[0754] Step 1: The user inputs a menu for a certain period of time through the system's interface. This interface can be implemented on a web page or a smartphone application, and the user inputs a menu in the form of "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday."

[0755] "Example 2"

[0756] Step 1: The system receives menu input from the user.

[0757] Step 2: The system suggests side dishes or menu changes to improve nutritional balance. For example, if a user inputs "Curry rice for dinner on Tuesday," the system will suggest something like, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[0758] "Example 3"

[0759] Step 1: The system uses generative AI to provide services that cater to individual preferences and new genres that people want to try.

[0760] Step 2: The AI ​​learns from the user's past menu entry history and makes menu suggestions based on the results. For example, if the user has often entered "grilled salted salmon" in the past, the AI ​​will suggest something like, "Why not try grilled salted mackerel, which has a similar flavor to grilled salted salmon?"

[0761] "Example 4"

[0762] Step 1: The system receives feedback from the user.

[0763] Step 2: The AI ​​learns from that feedback and improves the accuracy of the menu suggestions. For example, if a user gives a "good rating" to the suggestion "grilled salted mackerel," the AI ​​will increase the probability of suggesting menu items similar to "grilled salted mackerel."

[0764] Example 1

[0765] 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."

[0766] Conventional menu management systems require users to manually input menus and consider nutritional balance, which is time-consuming and inefficient. They also lack the flexibility to accommodate individual preferences and new genres. Furthermore, they lack the functionality to suggest menus using users' past history and feedback, making it difficult to increase user satisfaction.

[0767] 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.

[0768] In this invention, the server includes a means for users to input menus for a certain period of time, a means for saving the input menu data in a database, a means for sending prompts to the generative AI model based on the saved data, a means for receiving responses from the generative AI model and displaying them to the user, a means for suggesting side dishes or menu changes to improve nutritional balance, and a means for using the generative AI model to provide a service that can accommodate personal preferences or new genres that users want to try. This allows users to efficiently manage their menus and receive menu suggestions that match their personal preferences or new genres. Furthermore, by utilizing past history and feedback, more accurate menu suggestions can be achieved.

[0769] "User" refers to an individual or organization that uses the system to input menus and receive suggestions.

[0770] "Menu" refers to the contents of meals for a certain period of time, and specifically includes the menu of meals such as breakfast, lunch, and dinner.

[0771] "Interface" refers to the screen or application through which users access the system and input menu plans.

[0772] A "server" refers to a computer system that receives requests from users, stores data, and communicates with generative AI models.

[0773] "Database" refers to a data management system that stores menu data entered by users and allows searching and updating as needed.

[0774] A "generative AI model" refers to an artificial intelligence model that suggests recipes and nutritional values ​​based on menu data entered by the user.

[0775] A "prompt" is an instruction sent to the generative AI model, including menu information entered by the user.

[0776] "Response" refers to the recipe or nutritional information that the generative AI model generates based on the prompt.

[0777] "Nutritional balance" refers to the balance of nutrients contained in food, and is an important element for maintaining a healthy diet.

[0778] A "side dish" is a food that is served as a supplement to the main dish and plays a role in supplementing the nutritional balance.

[0779] "Suggestion" refers to the system making suggestions or advice to the user.

[0780] "Feedback" refers to opinions and evaluations provided by users to the system, which are used to improve and learn from the system.

[0781] This invention is a system that allows users to input menus for a certain period of time, and then uses a generative AI model to suggest recipes and nutritional values ​​based on the input. Specific embodiments of this system are described below.

[0782] Users access the system's interface using a web browser or smartphone application. The interface is built using web technologies such as HTML, CSS, and JavaScript. When a user accesses the interface, the server displays a menu entry screen.

[0783] For example, a user inputs a menu such as "Grilled salmon for dinner on Monday, and curry rice for dinner on Tuesday." The input data is sent from the device to the server as an HTTP POST request. The server analyzes the received data and stores it in a database (for example, MySQL or PostgreSQL).

[0784] Based on the stored data, the server sends a prompt to the generative AI model. For example, OpenAI's GPT-3 is used as the generative AI model. The prompt includes the menu information entered by the user. Specific examples of prompts include:

[0785] The user entered the following menu:

[0786] Monday's dinner is grilled salmon

[0787] Tuesday dinner is curry rice

[0788] Based on this, suggest recipes and nutritional values ​​for each menu item.

[0789] The generative AI model receives this prompt and generates detailed recipes and nutritional information for each menu item. The generated information is returned to the server, which converts it into HTML for display to the user. This displays the detailed recipes and nutritional information on the user's device.

[0790] The server also has the ability to suggest side dishes and menu changes to improve nutritional balance. The generative AI model learns from the user's past menu input history and makes menu suggestions based on the results. It also receives feedback from the user and learns based on that feedback to improve the accuracy of menu suggestions.

[0791] This system allows users to efficiently manage their menus and receive menu suggestions that cater to their personal preferences and new genres. It also makes use of past history and feedback to provide more accurate menu suggestions.

[0792] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0793] Step 1:

[0794] The user accesses the interface

[0795] Users access the system interface using a web browser or smartphone application. Specifically, users enter a URL in the browser or launch an app, which displays the system homepage or app home screen. The input is the URL or app icon, and the output is the homepage or home screen.

[0796] Step 2:

[0797] The server displays the menu entry screen.

[0798] The server receives the user's request and sends a menu entry screen built using HTML, CSS, and JavaScript to the user's device. Specifically, the server analyzes the HTTP request and returns the corresponding HTML file. The input is the user's request, and the output is the menu entry screen.

[0799] Step 3:

[0800] The user inputs the menu

[0801] The user inputs a menu into the displayed menu entry screen, for example, "Monday's dinner is grilled salted salmon, and Tuesday's dinner is curry rice." Input is done using text boxes and drop-down menus. The input is the menu data entered by the user, and the output is the data displayed in the input form.

[0802] Step 4:

[0803] The device sends the input data to the server

[0804] When the user has finished entering the menu, they click the "Submit" button, which causes the device to send the entered data to the server as an HTTP POST request. The input is the menu data entered by the user, and the output is the HTTP request sent to the server.

[0805] Step 5:

[0806] The server saves the data to a database

[0807] The server parses the received data and stores it in a database (e.g., MySQL or PostgreSQL). Specifically, the server establishes a database connection and executes SQL queries to insert the data. The input is the menu data received from the HTTP request, and the output is the data stored in the database.

[0808] Step 6:

[0809] The server sends a prompt to the generative AI model

[0810] The server generates prompts based on the stored data. For example, a prompt such as "The user has entered the following menu: grilled salmon for dinner on Monday, curry rice for dinner on Tuesday. Based on this, please suggest recipes and nutritional values ​​for each menu item" is sent to the generative AI model. The input is the menu data stored in the database, and the output is the prompt sent to the generative AI model.

[0811] Step 7:

[0812] A generative AI model generates a response

[0813] A generative AI model (such as OpenAI's GPT-3) generates a response based on the prompt it receives. The response includes detailed recipes and nutritional information for each meal. The input is the prompt, and the output is the generated response data.

[0814] Step 8:

[0815] The server displays the generated information to the user

[0816] The server analyzes the response received from the generative AI model and generates HTML to display to the user. Specifically, the server embeds the response data into an HTML template and sends it to the user's device. The input is the response data from the generative AI model, and the output is the HTML displayed on the user's device.

[0817] (Application example 1)

[0818] 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."

[0819] Conventional menu management systems allow users to input menus for a certain period of time, but they lack the ability to suggest side dishes that take nutritional balance into consideration, or to suggest new menus that meet individual preferences. Furthermore, they do not provide a way to list ingredients needed based on the menu and to purchase them efficiently. This means that users have to spend a lot of time and effort purchasing ingredients.

[0820] 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.

[0821] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can respond to personal preferences and new genres that users want to try using generative AI, and a means for listing necessary ingredients based on the menu and ordering those ingredients through a food delivery service.This allows users to efficiently manage their menus and easily purchase the necessary ingredients.

[0822] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[0823] "Means of suggesting side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[0824] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative AI to suggest menus that suit individual preferences and new cooking genres based on the user's past data and feedback.

[0825] "A means of listing ingredients needed based on a menu and ordering those ingredients through a food delivery service" is a function that automatically lists ingredients needed based on a menu entered by the user and orders ingredients through a food delivery service based on that list.

[0826] A system for carrying out this invention includes a server, a user terminal, and a food delivery service. The server includes means for inputting menus for a certain period of time, means for suggesting side dishes or menu changes to supplement nutritional balance, means for providing a service that can respond to personal preferences or new genres that users want to try using generative AI, and means for listing ingredients needed based on the menu and ordering the ingredients through a food delivery service.

[0827] The user terminal is a device such as a smartphone or PC, and provides an interface for users to input menus. For example, a user might input a menu such as "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday." This input data is sent to the server.

[0828] The server uses the Flask framework to build a web server and provides an endpoint for users to input menu plans for a certain period of time. When a user inputs a menu plan, a list of ingredients required based on the menu is created and returned in JSON format. Specifically, the server searches for ingredients in the menu database, eliminating duplicates before creating a list.

[0829] The generative AI learns from the user's past menu input history and makes menu suggestions based on the results. It also receives feedback from the user, learns based on that feedback, and improves the accuracy of the menu suggestions. This allows users to receive menu suggestions that match their personal preferences and new genres they want to try.

[0830] Furthermore, the server lists the ingredients needed based on the menu and orders them through a food delivery service based on that list. This function allows users to efficiently purchase the ingredients they need.

[0831] As a specific example, consider the case where the user inputs the following menu:

[0832] Monday: Grilled Salmon

[0833] Tuesday: Curry rice

[0834] In this case, the server generates a prompt like this:

[0835] "Monday's dinner is grilled salmon, and Tuesday's dinner is curry rice."

[0836] The generated shopping list looks like this:

[0837] "Salmon, salt, curry roux, rice, meat, vegetables"

[0838] Based on this list, you can order the ingredients you need through a food delivery service.

[0839] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0840] Step 1:

[0841] A user inputs a menu for a certain period of time using a terminal.

[0842] Input: The user inputs a menu such as "Grilled salted salmon for dinner on Monday, and curry rice for dinner on Tuesday" into an interface for inputting menu items.

[0843] Output: The entered menu data is sent from the terminal to the server.

[0844] Step 2:

[0845] The server analyzes the received menu data and lists the necessary ingredients.

[0846] Input: Menu data sent from the device.

[0847] Data processing: The server refers to the menu database and searches for ingredients that correspond to each menu.

[0848] Output: A list of listed ingredients.

[0849] Step 3:

[0850] The server orders ingredients through a food delivery service based on the list of ingredients.

[0851] Input: A list of listed ingredients.

[0852] Data calculation: The server calls the API of the food delivery service and sends the list of ingredients as order data.

[0853] Output: Order confirmation from food delivery service.

[0854] Step 4:

[0855] The generative AI learns from the user's past menu input history and reflects this in the next menu suggestion.

[0856] Input: User's past menu entry history.

[0857] Data processing: Generative AI analyzes past data to learn user preferences and patterns.

[0858] Output: Learning results that will be reflected in the next menu suggestion.

[0859] Step 5:

[0860] Users provide feedback, and the generative AI learns based on that feedback.

[0861] Input: Feedback data from users.

[0862] Data computation: Generative AI analyzes feedback data and learns to improve the accuracy of suggestions.

[0863] Output: Improved menu suggestions for your next meal.

[0864] Example 2

[0865] 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."

[0866] Planning nutritionally balanced meals is a difficult task in today's busy lifestyles. In particular, considering side dishes and menu changes to compensate for individual nutrient deficiencies requires specialized knowledge and is difficult for average users. There is also a demand for menu suggestions that reflect individual preferences and new genres that people want to try, but doing this manually takes time and effort. Furthermore, it is important to utilize the user's past menu history and feedback to make more accurate suggestions.

[0867] 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.

[0868] In this invention, the server includes a means for the user to input menus for a certain period of time, a means for the terminal to send the input data to the server, a means for the server to analyze the data and obtain nutritional components, a means for the server to evaluate nutritional balance, a means for the server to input prompts to the generative AI model, a means for the server to return the generated suggestions to the user, and a means for using the generative AI model to provide a service that can accommodate personal preferences or new genres that the user wants to try, thereby enabling users to easily create menus that take nutritional balance into consideration.

[0869] "User" refers to an individual who uses the system to input menu information and receive nutritional balance suggestions.

[0870] "Terminal" refers to a device used by a user, such as a computer or smartphone, that is used to input data into the system and receive suggestions.

[0871] "Server" refers to the central processing unit that receives data sent by users and performs analysis and uses generated AI models.

[0872] A "menu" refers to a meal plan or menu for a certain period of time, and is information that a user inputs into the system.

[0873] "Nutritional components" refers to nutrients such as vitamins, minerals, proteins, lipids, and carbohydrates contained in food.

[0874] "Nutritional balance" refers to the appropriate distribution of nutrients in a diet, and is an essential element for maintaining good health.

[0875] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate suggestions based on user input.

[0876] A "prompt" is an instruction given to a generative AI model, including a question or command to generate a specific suggestion.

[0877] "Suggestions" refers to side dishes or menu substitutions that the system suggests to the user.

[0878] "Feedback" refers to the opinions and evaluations users provide to the system, and is information used to train the generative AI model.

[0879] This invention is a system that suggests side dishes and menu changes to improve nutritional balance based on menu information entered by a user. The system is implemented using a user's terminal, a server, and a generative AI model.

[0880] Hardware and software used

[0881] Hardware: User devices (PCs, smartphones, etc.), servers

[0882] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), web application frameworks (e.g., Django)

[0883] Data processing and calculation

[0884] 1. User input: The user uses a terminal to enter menu information, such as "Curry rice for dinner on Tuesday," into the input form of the web application.

[0885] 2. Data transmission: The device sends the input data to the server as an HTTP request. The data is sent in JSON format.

[0886] 3. Data analysis: The server analyzes the received data and retrieves the nutritional information for curry rice from a database (e.g., MySQL). Specifically, it queries the database for the nutritional information for curry rice.

[0887] 4. Nutritional Balance Assessment: The server assesses the nutritional content of the curry rice based on the acquired nutritional information. For example, it identifies a lack of vitamin A.

[0888] 5. Use of generative AI model: The server inputs a prompt to the generative AI model (e.g., GPT-4). An example of a prompt is, "Curry rice is low in vitamin A, so what side dish should I add?"

[0889] 6. Suggestion generation: The server receives the suggestions obtained from the generative AI model and returns them to the user. Specifically, it returns an HTTP response with a message such as, "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish."

[0890] Specific examples

[0891] User input: "Curry rice for dinner on Tuesday"

[0892] Example prompt: "Curry rice is low in vitamin A, so what side dish should you add?"

[0893] Suggestion output: "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0894] In this way, users can easily create menus that take nutritional balance into consideration. The system can also learn from the user's past menu input history and feedback to provide more accurate suggestions.

[0895] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0896] Step 1:

[0897] The user inputs a menu for a certain period of time.

[0898] Specific operation: The user uses the terminal to enter menu information such as "Curry rice for dinner on Tuesday" into the input form of the web application.

[0899] Input: Menu information entered by the user.

[0900] Output: Menu information entered into the terminal.

[0901] Step 2:

[0902] The terminal sends the input data to the server.

[0903] Specific operation: The device sends the menu information entered by the user to the server as an HTTP request. The data is sent in JSON format.

[0904] Input: Menu information entered into the device.

[0905] Output: Menu information sent to the server.

[0906] Step 3:

[0907] The server analyzes the data and obtains the nutritional information.

[0908] Specific operation: The server analyzes the received data and retrieves the nutritional information of curry rice from a database (e.g., MySQL). Specifically, it executes a query about the nutritional information of curry rice against the database.

[0909] Input: Menu information sent to the server.

[0910] Output: Nutritional information retrieved from the database.

[0911] Step 4:

[0912] The server evaluates the nutritional balance.

[0913] Specific operation: The server evaluates the nutrients contained in curry rice based on the acquired nutritional information. For example, it identifies that it is lacking in vitamin A.

[0914] Input: Nutrition information retrieved from the database.

[0915] Output: Nutritional balance assessment (e.g. Vitamin A deficiency).

[0916] Step 5:

[0917] The server inputs a prompt sentence into the generative AI model.

[0918] Specific operation: The server inputs a prompt to the generative AI model (e.g., GPT-4). An example of a prompt is, "Curry rice is low in vitamin A, so what side dish should I add?"

[0919] Input: Nutritional balance assessment results.

[0920] Output: The prompt sentence fed into the generative AI model.

[0921] Step 6:

[0922] The server returns the generated suggestions to the user.

[0923] Specific operation: The server receives the suggestions obtained from the generative AI model and returns them to the user. Specifically, it returns an HTTP response with a message such as, "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish."

[0924] Input: Suggestions obtained from a generative AI model.

[0925] Output: The suggestion message returned to the user.

[0926] (Application example 2)

[0927] 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."

[0928] Conventional menu suggestion systems can suggest side dishes or menu substitutions to improve the nutritional balance of the menu entered by the user, but they lack the functionality to suggest side dishes or additional menu items that take nutritional balance into account for the dish the user is about to order. This makes it difficult for users to select meals that take nutritional balance into account when eating out or ordering food delivery.

[0929] 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.

[0930] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to compensate for nutritional balance, a means for providing a service that can respond to personal preferences and new genres that the user wants to try using generative AI, and a means for suggesting side dishes and additional menu items that take nutritional balance into consideration for the dish the user is about to order. This enables the user to select meals that take nutritional balance into consideration even when eating out or using food delivery.

[0931] A "means for inputting meal plans for a specified period of time" is an interface or device that allows a user to input meal plans for a specified period of time.

[0932] "Means for suggesting side dishes or menu changes to compensate for nutritional imbalance" refers to algorithms or systems that suggest side dishes or alternative menu items to compensate for missing nutrients for the menu entered by the user.

[0933] "A means of using generative AI to provide services that can accommodate individual preferences and new genres that users want to try" is a technology that uses a generative AI model to learn from users' past data and feedback, and provides services that accommodate individual users' preferences and new cuisine genres.

[0934] "A means of suggesting side dishes and additional menu items that take into consideration the nutritional balance of the dish that the user is about to order" is a system that suggests side dishes and additional menu items that will supplement the nutritional balance of the dish that the user is about to order via food delivery or eating out.

[0935] The system for implementing this invention allows users to input menus for a certain period of time and provides a function to suggest side dishes and menu changes to supplement nutritional balance. It also uses generative AI to provide a service that can respond to personal preferences and new genres that users want to try, and has a function to suggest side dishes and additional menu items that take nutritional balance into consideration for the dish the user is about to order.

[0936] System configuration

[0937] The system consists of the following main components:

[0938] 1. User device: A device such as a smartphone or tablet that users use to input menu plans.

[0939] 2. Server: A central system for processing and storing data, where the generative AI model runs.

[0940] 3. Generative AI model: An AI model that learns from user input data, past history, and feedback to provide appropriate suggestions.

[0941] Program processing

[0942] The server receives the menu data sent from the user's device and uses a generative AI model to suggest side dishes and menu changes to improve nutritional balance. Specifically, the following process is performed:

[0943] 1. Data entry: The user enters a menu for a certain period of time. For example, the user enters "Curry rice for dinner on Tuesday."

[0944] 2. Data processing: The server receives the input menu data and sends it to the generative AI model.

[0945] 3. Suggestion generation: Based on the input menu data, the generative AI model suggests side dishes or menu changes to improve nutritional balance. For example, it might say, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0946] Hardware and software used

[0947] Hardware: smartphones, tablets, servers

[0948] Software: Python, OpenAI API

[0949] Specific examples

[0950] For example, if a user wants to order "curry rice," the following prompt sentence is input to the generative AI model:

[0951] A user is trying to order "Curry rice." Please suggest a side dish to supplement the nutrients that are lacking in this dish.

[0952] Example response from a generative AI model:

[0953] Since curry rice is low in vitamin A, we suggest adding a carrot salad as a side dish.

[0954] In this way, nutritionally balanced side dishes and additional menu items can be suggested for the dish the user is about to order.

[0955] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0956] Step 1:

[0957] The user inputs a menu for a certain period of time.

[0958] Input: A user uses a device such as a smartphone or tablet to input a meal plan for a specific period of time. For example, they input "Curry and rice for dinner on Tuesday."

[0959] Output: The entered menu data is saved on the terminal and sent to the server.

[0960] Specific operation: The user inputs the menu through the application interface and presses the submit button to send the data to the server.

[0961] Step 2:

[0962] The server receives the input menu data.

[0963] Input: Menu data sent from the user's device.

[0964] Output: Menu data saved on the server.

[0965] Specific operation: The server receives the data sent from the user terminal and stores it in a database.

[0966] Step 3:

[0967] The server sends the menu data to the generative AI model.

[0968] Input: Menu data stored on the server.

[0969] Output: The prompt sent to the generative AI model.

[0970] Specific operation: The server generates a prompt based on the menu data and sends it to the generative AI model. For example, it generates a prompt such as, "The user is about to order 'curry rice.' Please suggest a side dish to supplement the nutrients that are lacking in this dish."

[0971] Step 4:

[0972] A generative AI model generates suggestions based on the prompt.

[0973] Input: The prompt sent to the generative AI model.

[0974] Output: Suggested results from the generative AI model.

[0975] Specific operation: The generative AI model analyzes the prompt and suggests appropriate side dishes or menu changes. For example, it generates a result such as, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[0976] Step 5:

[0977] The server receives the suggested results from the generative AI model.

[0978] Input: Suggested results from a generative AI model.

[0979] Output: Suggested results stored on the server.

[0980] Specific operation: The server receives the suggestion results sent from the generative AI model and stores them in a database.

[0981] Step 6:

[0982] The server sends the suggestion results to the user's device.

[0983] Input: Suggested results stored on the server.

[0984] Output: Suggested results displayed on the user's device.

[0985] Specific operation: The server sends the saved suggestion results to the user's device and displays them to the user. For example, a message such as "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish" is displayed.

[0986] Example 3

[0987] 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."

[0988] Conventional menu suggestion systems have difficulty in proposing meals that reflect individual user preferences or new challenges, and have been unable to effectively utilize user feedback to improve the accuracy of suggestions. This has made it difficult to increase user satisfaction.

[0989] 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.

[0990] In this invention, the server includes a means for a user to input a menu, a means for the server to save the menu data, a means for the server to learn the data using a generative AI model, a means for the user to request a new menu, a means for the server to suggest a menu using the generative AI model, a means for the user to provide feedback on the suggested menu, and a means for the server to save the feedback data and re-train the generative AI model. This makes it possible to propose menus that reflect the user's individual preferences and new challenges, and further makes it possible to improve the accuracy of the suggestions by utilizing feedback from the user.

[0991] "Menu" refers to a meal menu or a combination of dishes.

[0992] "Generative AI" is a type of artificial intelligence that refers to a model that has the ability to generate new data and suggestions based on specific data.

[0993] "User" refers to an individual who uses the system to input or request menu items.

[0994] "Server" refers to a computer system that receives data from users, stores it, processes it, and uses generative AI models to learn and make recommendations.

[0995] "Database" refers to an information management system for storing menu data and feedback data from users.

[0996] "Feedback" refers to the evaluation or opinion provided by the user regarding the suggested menu.

[0997] "Learning" refers to data processing by the generative AI to improve the accuracy of future suggestions based on the user's past menu input history and feedback data.

[0998] "Suggestion" refers to the act of generative AI proposing new menus based on the user's preferences and requests.

[0999] A "request" refers to an action in which a user asks the system to suggest a new menu.

[1000] MODE FOR CARRYING OUT THE INVENTION

[1001] This invention relates to a menu suggestion system that utilizes generative AI to accommodate personal preferences and new genres that customers want to try. Specific embodiments of this system are described below.

[1002] Hardware and software used

[1003] Hardware: Server, user terminal (PC, smartphone)

[1004] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), feedback collection systems

[1005] System Overview

[1006] The system learns from the menu data entered by the user in the past and suggests new menus based on the results. Furthermore, it retrains the generative AI model based on user feedback to improve the accuracy of its suggestions.

[1007] Data processing and calculation

[1008] 1. Data collection: The user uses the device to input a past menu. For example, they input "grilled salmon with salt."

[1009] 2. Data storage: The server receives the menu data sent by the user and stores it in the database management system. Specifically, it adds a new record to the "Menu" table in the database.

[1010] 3. Data learning: The server periodically retrieves menu data from the database and uses the generative AI model to learn from it, allowing the model to understand user preferences and patterns.

[1011] 4. Suggestion generation: When a user sends a request for a new menu item from their device, the server uses the generative AI model to suggest an appropriate menu item. For example, it might suggest, "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?"

[1012] 5. Feedback collection: The user tries the suggested menu and provides feedback on the results. For example, they give a "good rating" to "grilled salted mackerel."

[1013] 6. Accuracy Improvement: The server retrains the generative AI model based on the feedback data to improve the accuracy of suggestions.

[1014] Specific examples

[1015] User's past menu entry: "Grilled Salmon"

[1016] Example suggestion: "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?"

[1017] Feedback example: A user gives a "good rating" to "Grilled salted mackerel"

[1018] Prompt Sentence Examples

[1019] Prompt: "Suggest new menu items based on the user's past menu entries. Please consider the user's preferences and new genres they would like to try."

[1020] This system aims to enrich the user's dietary habits by learning the user's preferences and proposing more appropriate menus. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1021] Step 1:

[1022] The user inputs the menu

[1023] The user uses a device (PC or smartphone) to input past menu items into the system interface. For example, they might input "grilled salmon with salt." The input data is then sent from the device to the server.

[1024] Step 2:

[1025] The server stores the menu data

[1026] The server receives the menu data sent by the user and stores it in a database management system (e.g., MySQL). Specifically, it adds a new record to the "Menu" table in the database. The input is the menu data from the user, and the output is the record stored in the database.

[1027] Step 3:

[1028] The server uses a generative AI model to learn the data.

[1029] The server periodically retrieves menu data from the database and trains it using a generative AI model (e.g., GPT-4). This allows the model to understand the user's preferences and patterns. The input is the menu data retrieved from the database, and the output is the trained generative AI model.

[1030] Step 4:

[1031] A user requests a new menu

[1032] A user uses a terminal to request the system to suggest a new menu. For example, they might input, "Please suggest a new fish dish." The input is a request from the user, and the output is the request data sent to the server.

[1033] Step 5:

[1034] The server uses a generative AI model to suggest menus

[1035] The server receives the user's request and generates an appropriate menu using a generative AI model. For example, it might suggest, "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?" The input is the user's request and the trained generative AI model, and the output is the suggested menu.

[1036] Step 6:

[1037] Users provide feedback on suggested menu items

[1038] The user tries the suggested menu and provides feedback on the results. For example, the user gives a "good rating" to "grilled salted mackerel." The input is the user's feedback, and the output is feedback data to the server.

[1039] Step 7:

[1040] The server stores the feedback data and retrains the generative AI model.

[1041] The server receives feedback from users and stores it in a database. It then retrains the generative AI model based on the feedback data to improve the accuracy of suggestions. The input is the feedback data from users, and the output is the retrained generative AI model.

[1042] (Application example 3)

[1043] 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."

[1044] Conventional menu suggestion systems do not adequately consider user preferences or new challenges. They also lack a mechanism to effectively utilize user feedback to improve the accuracy of suggestions. Furthermore, food delivery services do not suggest new dishes based on users' past ordering history, making it difficult to increase user satisfaction.

[1045] 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.

[1046] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences and new genres that the user wants to try, a means for learning from the user's past order history and suggesting new dishes that suit the user's preferences, and a means for receiving feedback from the user, learning based on that feedback, and improving the accuracy of the suggestions. This makes it possible to suggest menus and dishes that take into account the user's preferences and new challenges, thereby increasing user satisfaction.

[1047] The "means for inputting menus for a certain period of time" is an interface that allows a user to input menu information planned for a specific period of time into the system.

[1048] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that takes into consideration the nutritional balance of the menu entered by the user and suggests appropriate side dishes or alternative menu items.

[1049] "A means of using generative AI to provide services that can accommodate individual preferences and new genres that users want to try" is a function that uses generative artificial intelligence to provide services that accommodate individual preferences and new genres based on users' past data and feedback.

[1050] "Means of learning the user's past order history and suggesting new dishes that suit the user's preferences" is a function that analyzes the history of dishes that the user has ordered in the past and uses that data to suggest new dishes that suit the user's preferences.

[1051] "Means for receiving feedback from users, learning based on that feedback, and improving the accuracy of suggestions" refers to a function that collects feedback information provided by users, allows the system to learn based on that information, and improves the accuracy of suggestions from the next time onwards.

[1052] The system for implementing this invention has the function of learning the user's past order history and suggesting new dishes that suit the user's preferences. The system is realized using the following hardware and software.

[1053] Hardware

[1054] Server: A server for storing and processing data.

[1055] User device: A mobile device such as a smartphone or tablet.

[1056] software

[1057] Generative AI model: An AI model that learns from a user's past order history and suggests new dishes. Specifically, it uses Python and its libraries (scikit-learn, numpy, etc.).

[1058] Database: A database to store user order history and feedback.

[1059] User Interface: The interface through which users can enter their order history and provide feedback.

[1060] Data processing and calculation

[1061] The server retrieves the user's past order history from a database and uses a generative AI model to learn from that data. Specifically, it performs the following processes:

[1062] 1. Data Acquisition: Retrieve the user's past order history from the database.

[1063] 2. Data preprocessing: Convert the acquired data into TF-IDF vectors.

[1064] 3. Similarity calculation: Calculate the similarity between the user's order history and the menu items using cosine similarity.

[1065] 4. Suggestion generation: Suggests similar menu items to the user.

[1066] 5. Feedback learning: Receive feedback from users and retrain the generative AI model based on that feedback.

[1067] Specific examples

[1068] For example, if a user has previously ordered a "Margherita pizza" and a "Pepperoni pizza," the generative AI model can learn from this data and suggest a "Quattro Formaggi pizza."

[1069] Example prompts to input to a generative AI model:

[1070] Suggest new menu items based on the user's past order history, which is "Margherita Pizza" and "Pepperoni Pizza."

[1071] In this way, it becomes possible to suggest menus and dishes that take into account the user's preferences and new challenges, thereby increasing user satisfaction.

[1072] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1073] Step 1:

[1074] The server retrieves the user's past order history from a database.

[1075] Input: User ID

[1076] Output: User's past order history data

[1077] What happens: The server queries the database to retrieve the order history for the specified user ID. This data includes the order date and time, dish name, rating, etc.

[1078] Step 2:

[1079] The server preprocesses the acquired order history data and converts it into a TF-IDF vector.

[1080] Input: User's past order history data

[1081] Output: TF-IDF vector

[1082] What happens: The server converts the order history data into text format and uses scikit-learn's TfidfVectorizer to create a TF-IDF vector. This vector quantifies the features of each dish.

[1083] Step 3:

[1084] The server converts the list of menu items into TF-IDF vectors.

[1085] Input: A list of menu items

[1086] Output: TF-IDF vectors of menu items

[1087] Specific operation: The server converts the list of menu items into text format and also converts it into a TF-IDF vector, which is a numerical representation of the features of each menu item.

[1088] Step 4:

[1089] The server calculates the cosine similarity between the user's order history vector and the menu item vector.

[1090] Input: TF-IDF vector of user's order history, TF-IDF vector of menu items

[1091] Output: Cosine similarity score

[1092] How it works: The server uses scikit-learn's cosine_similarity function to calculate the cosine similarity between the user's order history vector and each menu item vector. This score indicates how close each menu item is to the user's preferences.

[1093] Step 5:

[1094] The server suggests the most similar menu items to the user based on the cosine similarity scores.

[1095] Input: Cosine similarity score

[1096] Output: Suggested menu items

[1097] Specific operation: The server compares the calculated cosine similarity scores, selects the menu item with the highest score, and sends this menu item to the user device to suggest to the user.

[1098] Step 6:

[1099] The user provides feedback on the suggested menu items.

[1100] Input: Suggested menu item

[1101] Output: User feedback

[1102] Specific behavior: The user reviews the suggested menu items and provides feedback, such as a positive or negative rating. This feedback is sent from the user device to the server.

[1103] Step 7:

[1104] The server receives feedback from users and retrains the generative AI model based on that feedback.

[1105] Input: User feedback

[1106] Output: An updated generative AI model

[1107] How it works: The server stores the feedback received from users in a database and uses that data to retrain the generative AI model, improving the accuracy of future suggestions.

[1108] 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.

[1109] "Example 1"

[1110] In one embodiment of the present invention, a system is provided that includes an emotion engine that recognizes a user's emotions. The system grasps the user's emotional state and provides meal suggestions based on the emotional state. Specifically, when the user is feeling joy, the system suggests a meal that will enhance that joy. For example, the system may suggest a special meal on the day the user receives a promotion.

[1111] "Example 2"

[1112] The emotion engine also analyzes user behavioral data and feedback to understand a user's emotional state. Specifically, it analyzes the user's behavior after eating a particular meal and their evaluation of the meal to understand how that meal affected the user's emotions. For example, if a user becomes more active after eating a particular meal, it can determine that that meal is likely to increase the user's joy.

[1113] "Example 3"

[1114] Furthermore, the emotion engine learns the user's emotional state to improve the accuracy of menu suggestions according to the user's emotional state. Specifically, it learns the relationship between the user's past emotional state and the menu at that time, and makes menu suggestions based on that result. For example, if a user tends to prefer a particular meal when feeling happy, the accuracy of suggestions can be improved by suggesting that meal when the user is in a similar emotional state.

[1115] "Example 4"

[1116] In this way, the system of the present invention enriches the user's dining experience by providing menu suggestions that take the user's emotional state into account. Furthermore, by learning the user's emotional state, the system can deepen its understanding of the user's emotions and provide a more personalized service.

[1117] The processing flow of each embodiment will be described below.

[1118] "Example 1"

[1119] Step 1: The emotion engine understands the user's emotional state.

[1120] Step 2: Based on the emotional state, the generative AI generates a menu.

[1121] Step 3: The generated menu is presented to the user.

[1122] "Example 2"

[1123] Step 1: User behavioral data and feedback are input into the emotion engine.

[1124] Step 2: The emotion engine analyzes the input data and understands the user's emotional state.

[1125] Step 3: Based on the emotional state, the generative AI generates a menu and presents it to the user.

[1126] "Example 3"

[1127] Step 1: The emotion engine learns the relationship between the user's past emotional state and the menu at that time.

[1128] Step 2: Based on the learning results, the emotion engine understands the current emotional state of the user.

[1129] Step 3: Based on the emotional state, the generative AI generates a menu and presents it to the user.

[1130] "Example 4"

[1131] Step 1: The user's emotional state is understood by the emotion engine.

[1132] Step 2: Based on the emotional state, the generative AI generates a menu.

[1133] Step 3: The generated menu is presented to the user, enriching their dining experience.

[1134] Example 1

[1135] 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."

[1136] Conventional menu suggestion systems suggest menus without considering the user's emotional state, making it difficult to enhance the user's psychological satisfaction. Furthermore, while suggestions are made based on nutritional balance and personal preferences, there is a lack of special suggestions tailored to the user's emotions. This presents a problem in that it is difficult for users to select an appropriate menu for a special day or a specific emotional state. The specification process by the specification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1137] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can accommodate personal preferences and new genres that the user wants to try using generative AI, a means for recognizing the user's emotional state and suggesting menus based on that emotional state, and a means for integrating and analyzing the user's emotional data and menu data. This makes it possible to provide the optimal menu according to the user's emotional state and increase psychological satisfaction.

[1138] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[1139] "Means of suggesting side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[1140] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses a generative AI model to suggest menus that suit individual preferences and new cooking genres based on the user's past data and feedback.

[1141] "Means of recognizing the user's emotional state and suggesting menus based on that emotional state" is a function that uses an emotion engine to analyze the user's emotions and suggests appropriate menus based on the results.

[1142] "Means for integrating and analyzing user emotional data and menu data" is a function that combines and analyzes the menu data entered by the user with the emotional data obtained from the emotion engine to generate the optimal menu.

[1143] MODE FOR CARRYING OUT THE INVENTION

[1144] This invention is a system that allows a user to input menus for a certain period of time, and based on that data, suggests optimal menus that take into account nutritional balance, personal preferences, and even the user's emotional state. Specific embodiments of this system are described below.

[1145] Providing a user interface

[1146] The server provides an interface for users to input menu plans for a certain period of time. This interface is implemented as a web page or smartphone application. Specifically, web pages are generated using HTML, CSS, and JavaScript, while smartphone applications use frameworks such as React Native or Flutter.

[1147] User menu entry

[1148] The user inputs a menu into a text box through the provided interface. For example, they might input "grilled salted salmon for dinner on Monday, and curry rice for dinner on Tuesday." The input data is sent to the server and stored in a database.

[1149] Collecting Emotional Data

[1150] The server collects the user's emotional state using an emotion engine. This emotion engine recognizes emotions by analyzing user input, behavior, and external data (e.g., social media posts). Specific software used is the emotion analysis API from IBM Watson or Microsoft Azure.

[1151] Data integration and analysis

[1152] The server integrates the menu data entered by the user with the emotion data obtained from the emotion engine. Based on this integrated data, it uses a generative AI model to suggest optimal menus. Specifically, the model is implemented using Python and TensorFlow and the data is analyzed.

[1153] Menu suggestions

[1154] Based on the analysis results of the generative AI model, the server suggests the optimal menu based on the user's emotional state. For example, if a user receives a promotion, it might suggest a steak dinner as a special meal.

[1155] Displaying suggestions

[1156] The device displays the suggestions sent from the server to the user. The user can then review the suggested menu and make any necessary corrections or approvals. The menu is displayed in a visually easy-to-understand format using HTML and CSS.

[1157] Examples and prompts

[1158] Specific examples

[1159] A user types "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday" on a web page. The emotion engine detects that the user posted on social media, "I got promoted!" and suggests "steak dinner" as a special meal.

[1160] Prompt Sentence Examples

[1161] "Please suggest the best meal based on the menu data and sentiment data entered by the user. If the user gets promoted, please suggest a special meal."

[1162] In this way, a system is realized that provides optimal menus according to the user's emotional state.

[1163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1164] Step 1:

[1165] The server provides an interface for users to input menus for a certain period of time. On a web page or smartphone application, users input menus, for example, "Monday's dinner is grilled salted salmon, and Tuesday's dinner is curry rice." The input data is sent to the server and stored in a database. The input is the user's menu data, and the output is the menu data stored in the database.

[1166] Step 2:

[1167] The server uses an emotion engine to collect the user's emotional state. The emotion engine recognizes emotions by analyzing user input and behavior, as well as external data (e.g., social media posts). Specific software used is the emotion analysis API from IBM Watson or Microsoft Azure. The input is user behavior data and external data, and the output is analyzed emotional data.

[1168] Step 3:

[1169] The server integrates the menu data entered by the user with the emotion data obtained from the emotion engine. Based on this integrated data, a generative AI model is used to suggest optimal menus. Specifically, the model is implemented using Python and TensorFlow to analyze the data. The input is the integrated menu data and emotion data, and the output is a menu suggested by the generative AI model.

[1170] Step 4:

[1171] The server uses the analysis results of the generative AI model to suggest the optimal menu based on the user's emotional state. For example, if a user is promoted, it might suggest a "steak dinner" as a special meal. The input is the analysis results of the generative AI model, and the output is the suggested menu.

[1172] Step 5:

[1173] The terminal displays the suggestions sent from the server to the user. The user checks the suggested menu and makes any necessary corrections or approvals. The display is provided in a visually easy-to-understand format using HTML and CSS. The input is the suggestions sent from the server, and the output is the menu displayed to the user.

[1174] (Application example 1)

[1175] 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."

[1176] Conventional menu suggestion systems can suggest menus based on the user's nutritional balance and personal preferences, but they do not suggest menus that take into account the user's emotional state. As a result, they are unable to provide appropriate meals according to the user's emotions, making it difficult to increase user satisfaction. In addition, they are unable to suggest special menus that correspond to specific emotional states, such as when the user is tired or on special occasions.

[1177] 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 a means for inputting menus for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences or new genres that the user wants to try, and a means for recognizing the user's emotional state and suggesting menus based on those emotions. This makes it possible to propose appropriate menus according to the user's emotional state, thereby increasing user satisfaction.

[1178] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[1179] "Means of suggesting side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[1180] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative AI to learn from users' past data and feedback, and suggests menus that match individual users' preferences and new cooking genres.

[1181] "Means for recognizing the user's emotional state and suggesting menus based on those emotions" is a function that detects the user's emotions and suggests appropriate menus based on those emotions.

[1182] A system for implementing this invention includes a means for a user to input menu items for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences or new genres that the user wants to try, and a means for recognizing the user's emotional state and suggesting menu items based on those emotions.

[1183] System Program

[1184] This system uses the following hardware and software:

[1185] Hardware: Smartphone

[1186] Software: Python, emotion recognition API (e.g. Microsoft Azure Emotion API)

[1187] Program processing explanation

[1188] The server provides an interface for users to input menus for a certain period of time. This interface can be implemented on a web page or a smartphone application. For example, users can input menus in the form of "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday."

[1189] The server then uses an emotion recognition API to recognize the user's emotional state. The user can input their emotional state or detect emotions through camera or voice input. This emotional data is sent to the server and analyzed by the generative AI.

[1190] The generative AI learns from the user's past menu input history and feedback, and then makes menu suggestions based on the results. For example, it might suggest a relaxing meal when the user is tired, or a special meal when the user is happy.

[1191] Specific examples

[1192] For example, if a user inputs "I'm tired," the server will recognize this emotion through an emotion recognition API, and the generative AI will suggest "a relaxing meal." This suggestion is based on the user's past data and feedback.

[1193] Example prompts to input to a generative AI model:

[1194] A user says they're tired. Suggest a relaxing meal.

[1195] Using this prompt, the generative AI model can suggest appropriate menu items.

[1196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1197] Step 1:

[1198] The user inputs a menu for a certain period of time through a smartphone application. For example, the user might input a menu such as "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday." The input data is then sent to the server.

[1199] Step 2:

[1200] The server uses the emotion recognition API to recognize the user's emotional state. The user inputs their emotional state or detects emotions through camera or voice input. The emotion recognition API analyzes the input data and identifies the user's emotional state. This emotional data is sent to the server.

[1201] Step 3:

[1202] The server uses generative AI to learn from the user's past menu entry history and feedback. Based on this data, the generative AI identifies the user's preferences and new genres they would like to try. The results of this learning are stored on the server.

[1203] Step 4:

[1204] The server suggests appropriate menus based on the user's emotional state and past data. For example, if the user is recognized as "tired," the generative AI will suggest "relaxing meals." These suggestions are displayed on the user's smartphone application.

[1205] Step 5:

[1206] The user provides feedback on the suggested menu, which is entered through a smartphone application and sent to the server.

[1207] Step 6:

[1208] The server receives feedback from users, and the generative AI learns based on that feedback. This improves the accuracy of menu suggestions. The learning results are saved on the server and reflected in the next suggestions.

[1209] Example 2

[1210] 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."

[1211] Conventional menu suggestion systems have difficulty in appropriately suggesting side dishes and menu changes that take into account the user's nutritional balance. Furthermore, they are unable to take into account the user's emotional state, which makes it difficult to increase user satisfaction. Furthermore, there is a need to improve the accuracy of suggestions by utilizing the user's past behavioral data and feedback.

[1212] 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.

[1213] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to compensate for nutritional balance, a means for providing a service that can respond to personal preferences and new genres that users want to try using a generative AI model, and a means for collecting user behavioral data and feedback and understanding the user's emotional state using an emotion engine. This enables appropriate menu suggestions that take the user's nutritional balance into consideration, and by making suggestions that take the user's emotional state into account, user satisfaction can be increased. In addition, the accuracy of suggestions can be improved by utilizing the user's past behavioral data and feedback.

[1214] A "means for inputting a menu for a certain period of time" is a device or software that provides an interface for a user to input meal contents for a specific period of time.

[1215] A "means for suggesting side dishes or menu changes to compensate for nutritional imbalance" is a device or software that analyzes the nutritional components of an input menu and suggests side dishes or alternative menu items to compensate for missing nutrients.

[1216] "A means of using a generative AI model to provide a service that can respond to individual preferences and new genres that users want to try" refers to a device or software that uses a generative AI model to learn from a user's past data and preferences, and then suggests new menus and side dishes based on that data.

[1217] "Means for collecting user behavioral data and feedback and understanding the user's emotional state using an emotion engine" refers to a device or software that collects the user's behavior and evaluation after consuming a meal, analyzes it using an emotion engine, and evaluates the user's emotional state.

[1218] MODE FOR CARRYING OUT THE INVENTION

[1219] This invention is a system that suggests side dishes and menu changes to supplement nutritional balance based on the user's diet. It also uses an emotion engine to analyze the user's behavioral data and feedback and understand the user's emotional state.

[1220] Hardware and software used

[1221] Hardware: Servers, user devices (PCs, smartphones)

[1222] Software: Generative AI model, emotion engine, database management system (DBMS)

[1223] Specific operation of the system

[1224] 1. User Input

[1225] The user uses the device to input the details of the meal, for example, "Curry rice for dinner on Tuesday."

[1226] 2. Analysis of dietary content

[1227] The server analyzes the entered meal details. Using a generative AI model, the server analyzes the entered text and extracts the specific details of the meal. For example, it recognizes the keyword "curry rice."

[1228] 3. Evaluation of nutritional balance

[1229] The server accesses the database and retrieves the nutritional information for the curry rice. Based on the retrieved information, the server evaluates the nutritional balance of the curry rice. For example, it identifies a deficiency of vitamin A.

[1230] 4. Generating Suggestions

[1231] The server generates suggestions for side dishes and menu items to complement nutritional balance. It uses a generative AI model to suggest appropriate side dishes. For example, it suggests, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[1232] 5. Collecting behavioral data

[1233] The server collects user behavior data, specifically, the user's actions after eating a meal (e.g., exercise or rest) and their evaluation of the meal (e.g., "delicious" or "satisfied") are recorded in a database.

[1234] 6. Analysis by Emotion Engine

[1235] The server uses an emotion engine to analyze the collected behavioral data and feedback. For example, if a user starts exercising after eating curry rice, the behavioral data is analyzed to evaluate the impact of the meal on the user's emotions.

[1236] 7. Understanding your emotional state

[1237] The server uses the analysis results of the emotion engine to understand the user's emotional state. For example, if a user becomes active after eating curry rice, it will determine that the meal increased the user's joy.

[1238] Specific examples

[1239] Example user input: "Curry rice for dinner on Tuesday"

[1240] Server analysis example: "Curry rice is low in vitamin A"

[1241] Example suggestion: "Suggest adding carrot salad as a side dish."

[1242] Example of behavioral data collection: "User started exercising after eating curry rice."

[1243] Example of emotion engine analysis: "Curry rice increased user activity"

[1244] Example of grasping emotional state: "Curry rice increased the user's joy"

[1245] Prompt Sentence Examples

[1246] "Tuesday's dinner is curry rice. Please suggest a side dish to make it more nutritious."

[1247] "A user starts exercising after eating curry rice. Analyze the effect of this meal on the user's emotions."

[1248] The above is an embodiment of the present invention.

[1249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1250] Step 1:

[1251] The user inputs the meal details.

[1252] Input: A user uses a terminal to input a meal description in text format. For example, they might input "Curry rice for dinner on Tuesday."

[1253] Output: The entered meal details are sent to the server.

[1254] Specific operation: The user enters the meal details into the input form on the device and presses the send button, which sends the data to the server.

[1255] Step 2:

[1256] The server analyzes the meal contents.

[1257] Input: Text data of meal details submitted by the user.

[1258] Output: Specific meal items (e.g. curry rice) are extracted.

[1259] What happens: The server uses the generative AI model to analyze the input text and extract specific meal details, for example, recognizing the keyword "curry rice."

[1260] Step 3:

[1261] The server evaluates the nutritional balance.

[1262] Input: Extracted meal details (e.g. curry rice).

[1263] Output: Nutritional information of the meal and its evaluation results.

[1264] Specific operation: The server accesses the database and obtains the nutritional information of curry rice. Based on the obtained information, it evaluates the nutritional balance of curry rice and identifies, for example, a lack of vitamin A.

[1265] Step 4:

[1266] The server generates suggestions for side dishes and menu items.

[1267] Input: Nutritional balance assessment result (e.g. Vitamin A deficiency).

[1268] Output: Suggested side dishes and menu items to complement nutritional balance.

[1269] What it does: The server uses a generative AI model to suggest appropriate side dishes, such as "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[1270] Step 5:

[1271] The server collects user behavior data.

[1272] Input: User behavioral data after consuming a meal and their evaluation of the meal.

[1273] Output: Collected behavioral data and evaluations are recorded in a database.

[1274] Specific operation: The server collects the user's behavioral data (e.g., exercise or rest after eating) and feedback (e.g., "It was delicious" or "I was satisfied") and records them in a database.

[1275] Step 6:

[1276] The server analyzes the data using an emotion engine.

[1277] Input: Collected behavioral data and feedback.

[1278] Output: Analysis results about the user's emotional state.

[1279] Specific operation: The server uses the emotion engine to analyze the collected behavioral data and feedback. For example, if a user starts exercising after eating curry rice, the behavioral data is analyzed to evaluate the impact of the meal on the user's emotions.

[1280] Step 7:

[1281] The server grasps the user's emotional state.

[1282] Input: Sentiment engine analysis results.

[1283] Output: Information about the user's emotional state.

[1284] Specific operation: The server understands the user's emotional state based on the analysis results of the emotion engine. For example, if the user becomes active after eating curry rice, it determines that the meal increased the user's joy.

[1285] (Application example 2)

[1286] 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."

[1287] Conventional menu suggestion systems did not adequately consider nutritional balance when selecting side dishes or changing menu items, making it difficult to contribute to users' health management. Furthermore, menu suggestions did not take into account the user's emotional state, making it difficult to increase user satisfaction. Furthermore, there was a lack of means to effectively utilize user behavioral data and feedback, resulting in low suggestion accuracy.

[1288] 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.

[1289] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can respond to personal preferences and new genres that the user wants to try using generative AI, a means for analyzing the user's behavioral data and feedback to understand their emotional state, and a means for suggesting the next menu taking the user's emotional state into consideration, which contributes to the user's health management and makes it possible to increase satisfaction.

[1290] The "means for inputting menus" is an interface that allows users to input meal plans for a certain period of time into the system.

[1291] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that takes into consideration the nutritional balance of the input menu and suggests appropriate side dishes or menu changes.

[1292] "A means of using generative AI to provide services that can respond to individual preferences and new genres that users want to try" is a function that uses generative AI to learn from users' past data and preferences and suggests new meals.

[1293] "Means of analyzing user behavioral data and feedback to understand emotional state" is a function that analyzes the feedback and behavioral data provided by the user after eating to understand the user's emotional state.

[1294] "Means for suggesting the next menu taking into account the user's emotional state" is a function that makes suggestions for the next meal based on the user's emotional state.

[1295] The system for implementing this invention includes an interface that allows users to input menu plans for a certain period of time, a function that suggests side dishes and menu changes to supplement nutritional balance, a function that uses generative AI to provide services that can accommodate personal preferences and new genres that users want to try, a function that analyzes user behavioral data and feedback to understand their emotional state, and a function that takes their emotional state into consideration to suggest the next menu plan.

[1296] Program processing

[1297] The server receives menu data entered by the user for a certain period of time and suggests side dishes or menu changes to improve nutritional balance. For example, if a user enters "Curry rice for dinner on Tuesday," the server will make a suggestion such as, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[1298] Furthermore, the server uses generative AI to learn from the user's past menu input history and makes menu suggestions based on the results. For example, if a user has previously ordered a "hamburger steak," the next time the server suggests "sauteed spinach, which goes well with the hamburger steak."

[1299] To analyze user behavioral data and feedback, the server analyzes the feedback and behavioral data provided by the user after eating to understand the user's emotional state. For example, if the user feedbacks that the meal is "delicious," the server determines that the meal is likely to increase the user's pleasure.

[1300] Finally, the server considers the user's emotional state to suggest the next meal. For example, if the user gives feedback that they are "satisfied," the server will suggest the next meal based on that emotional state.

[1301] Hardware and software used

[1302] In this system, users input their menus using devices such as smartphones or tablets, and the server analyzes the data using programming languages ​​such as Python. Data processing and calculations are performed by saving and analyzing the user's order history and feedback in JSON format.

[1303] Specific examples

[1304] For example, if a user orders "curry rice," the system will display a message saying, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish." If the user gives feedback that the meal is "delicious," the system will determine that the meal has the potential to increase the user's pleasure.

[1305] Example prompts to input to a generative AI model:

[1306] A user has ordered "Curry rice." Please suggest a side dish that takes nutritional balance into consideration. Also, please analyze the user's feedback "Delicious" to understand their emotional state.

[1307] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1308] Step 1:

[1309] The user inputs a menu for a certain period of time.

[1310] Users use devices such as smartphones and tablets to input menu plans for a certain period of time into the application interface, and the input data is sent to the server.

[1311] Input: Menu data entered by the user

[1312] Output: Menu data sent to the server

[1313] Step 2:

[1314] The server will suggest side dishes or menu changes to improve nutritional balance.

[1315] The server analyzes the received menu data and suggests appropriate side dishes or menu changes, taking into account nutritional balance. For example, if a user inputs "Tuesday's dinner is curry rice," the server will suggest, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[1316] Input: Menu data

[1317] Output: Side dish and menu suggestions

[1318] Step 3:

[1319] The server uses generative AI to learn from the user's past menu entry history.

[1320] The server analyzes the user's past menu input history and uses generative AI to learn from it, thereby understanding the user's preferences and trends and reflecting them in the next menu suggestion.

[1321] Input: Past menu input history

[1322] Output: Learning results

[1323] Step 4:

[1324] The server analyzes the user's behavioral data and feedback to understand their emotional state.

[1325] The server analyzes the feedback and behavioral data provided by the user after eating to understand the user's emotional state. For example, if the user gives feedback that the meal was "delicious," the server determines that the meal is likely to increase the user's joy.

[1326] Input: Feedback and behavioral data

[1327] Output: Emotional state analysis results

[1328] Step 5:

[1329] The server takes into account the user's emotional state and suggests the next menu.

[1330] The server will suggest the next meal based on the analysis of the user's emotional state. For example, if the user gives feedback of "satisfied," the server will suggest the next meal based on that emotional state.

[1331] Input: Emotional state analysis results

[1332] Output: Next menu suggestion

[1333] Specific examples

[1334] For example, if a user orders "curry rice," the system will display, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish." If the user gives feedback that the meal is "delicious," the system will determine that the meal has the potential to increase the user's enjoyment.

[1335] Example prompts to input to a generative AI model:

[1336] A user has ordered "Curry rice." Please suggest a side dish that takes nutritional balance into consideration. Also, please analyze the user's feedback "Delicious" to understand their emotional state.

[1337] Example 3

[1338] 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."

[1339] Conventional menu suggestion systems have difficulty in making suggestions that fully take into account the user's individual preferences and emotional state, and have been unable to increase user satisfaction. Furthermore, they lack a mechanism for effectively utilizing user feedback to improve the accuracy of suggestions. This has led to a demand for systems that can further enrich users' dining experiences.

[1340] 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.

[1341] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences and new genres that the user wants to try, a means for analyzing the user's emotional state and suggesting menus based on that emotional state, and a means for collecting user feedback, allowing the generative AI to learn based on that feedback and improve the accuracy of the menu suggestions. This enables personalized menu suggestions that take into account the user's individual preferences and emotional state, thereby enriching the user's dining experience.

[1342] The "menu input means" is a means for a user to input menus for a certain period of time.

[1343] "Nutritional balance support measures" are measures that suggest side dishes or menu changes to supplement nutritional balance.

[1344] "Generative AI" is artificial intelligence that provides services that can respond to individual preferences and new genres that people want to try.

[1345] The "emotional state analysis means" is a means for analyzing the user's emotional state and suggesting a menu based on that emotional state.

[1346] The "feedback collection method" is a method for collecting user feedback, allowing the generative AI to learn based on that feedback and improve the accuracy of menu suggestions.

[1347] "Database" refers to a data storage system that stores users' past menu entry history and feedback.

[1348] A "user terminal" is a device that allows a user to input menu items and check suggested menu items.

[1349] A "server" is a central system that receives and processes data sent from user terminals.

[1350] A "prompt" is an instruction given to a generative AI to perform a specific task.

[1351] MODE FOR CARRYING OUT THE INVENTION

[1352] This invention is a system that uses generative AI to provide a menu suggestion service that can accommodate personal preferences and new genres that users want to try. The system learns from the user's past menu input history, feedback, and emotional state, and then suggests optimal menus based on that.

[1353] Hardware and software used

[1354] Hardware: Servers, user devices (PCs, smartphones)

[1355] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), emotion engines (e.g., Affectiva)

[1356] Specific operation of the system

[1357] 1. User menu entry

[1358] The user uses the device to input a previously prepared menu. For example, the user opens the app and inputs "grilled salmon with salt."

[1359] 2. Data storage

[1360] The device sends the entered menu data to the server, which saves this data in a database. For example, the device sends the data "grilled salmon with salt" to the server, and the server saves this data in a database.

[1361] 3. Generating menu suggestions

[1362] The server retrieves the user's past menu history from the database and inputs it into a generative AI model (e.g., GPT-4). For example, the server retrieves the history of "grilled salmon" and sends a prompt to the generative AI model saying, "Please suggest a new menu based on the menu history entered by the user in the past."

[1363] 4. Providing suggestions

[1364] The server receives the menu suggestions generated by the generative AI model and sends them to the device. For example, the generative AI model suggests "grilled salted mackerel," and the server sends this suggestion to the device. The device then displays to the user, "Why not try grilled salted mackerel?"

[1365] 5. Collecting User Feedback

[1366] Users can provide feedback on suggested menu items. For example, a user can give a "good rating" to "grilled salted mackerel."

[1367] 6. Learning Feedback

[1368] The server stores the user's feedback in a database and provides the feedback data to the generative AI model. For example, the server stores the feedback of "good rating" in the database and sends a prompt to the generative AI model saying, "Please improve the accuracy of the next menu suggestion based on the user's feedback."

[1369] 7. Emotional state analysis

[1370] The server uses an emotion engine (e.g., Affectiva) to analyze the user's emotional state. For example, the server inputs the user's facial expressions and voice data into the emotion engine, and the analysis result is "the user is feeling happy."

[1371] 8. Generating Suggestions Based on Emotions

[1372] The server sends new prompts to the generative AI model based on the user's emotional state and past menu data, generating emotion-based menu suggestions. For example, the server might send a prompt to the generative AI model saying, "If the user tends to like a particular meal when they are feeling happy, please suggest that meal when they are in a similar emotional state." The generative AI model then suggests "a meal the user likes when they are feeling happy," and the server sends this suggestion to the device.

[1373] In this way, the system learns the user's past data and emotional state and provides more personalized menu suggestions, thereby enriching the user's dining experience. The flow of the identification process in Example 3 will be described with reference to FIG. 21.

[1374] Step 1:

[1375] User menu entry

[1376] The user uses the device to input a menu they have previously created. Specifically, the user opens the app and inputs "grilled salmon with salt." The input data is sent from the device to the server. The input data is "Menu name: grilled salmon with salt."

[1377] Step 2:

[1378] Data storage

[1379] The server receives the menu data sent from the terminal and saves it in the database. Specifically, the server saves the data "grilled salmon with salt" in the database. The input data is "Menu name: grilled salmon with salt", and the output is the state saved in the database.

[1380] Step 3:

[1381] Generate menu suggestions

[1382] The server retrieves the user's past menu history from the database and inputs it into a generative AI model (e.g., GPT-4). Specifically, the server retrieves the history of "grilled salmon" and sends the generative AI model a prompt saying, "Please suggest a new menu based on the menu history entered by the user in the past." The input data is "Past menu history: grilled salmon," and the output is the generated suggestion, "grilled mackerel with salt."

[1383] Step 4:

[1384] Providing suggestions

[1385] The server receives the menu suggestions generated by the generative AI model and sends them to the device. Specifically, the generative AI model suggests "grilled salted mackerel," and the server sends this suggestion to the device. The device then displays to the user, "Why not try grilled salted mackerel?" The input data is "generated suggestion: grilled salted mackerel," and the output is what is presented to the user.

[1386] Step 5:

[1387] Collecting user feedback

[1388] The user provides feedback on the suggested menu. Specifically, the user gives a "good rating" to "grilled salted mackerel." The input data is "suggested menu: grilled salted mackerel," and the output is "feedback: good rating."

[1389] Step 6:

[1390] Learning Feedback

[1391] The server stores the user's feedback in a database and provides the feedback data to the generative AI model. Specifically, the server stores the "good rating" feedback in the database and sends the generative AI model a prompt saying, "Please improve the accuracy of the next menu suggestion based on the user's feedback." The input data is "Feedback: good rating," and the output is the "trained model."

[1392] Step 7:

[1393] Emotional state analysis

[1394] The server uses an emotion engine (e.g., Affectiva) to analyze the user's emotional state. Specifically, the server inputs the user's facial and voice data into the emotion engine, and obtains the analysis result that "the user is feeling happy." The input data is "facial and voice data," and the output is "emotional state: happy."

[1395] Step 8:

[1396] Generating Suggestions Based on Emotions

[1397] The server sends a new prompt to the generative AI model based on the emotional state and past menu data, generating emotion-based menu suggestions. Specifically, the server sends the prompt to the generative AI model: "If the user tends to prefer a particular meal when feeling happy, please suggest that meal when the user is in a similar emotional state." The generative AI model suggests "a meal that the user prefers when feeling happy," and the server sends this suggestion to the device. The input data are "emotional state: joy" and "past menu data," and the output is "emotion-based suggestions."

[1398] (Application example 3)

[1399] 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."

[1400] Conventional menu suggestion systems are limited to suggestions based on the user's past menu input history and feedback, and have the problem of being unable to provide personalized suggestions that take the user's emotional state into account. They also do not adequately address users' preferences or their desire to try new genres. Furthermore, food delivery services require optimal dish suggestions based on the user's past ordering history and feedback, but there has been a lack of effective ways to achieve this.

[1401] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences and new genres that the user wants to try, a means for learning the user's past order history, feedback, and emotional state to suggest optimal dishes, and a means for generating the next suggested dish using a generative AI model. This enables personalized menu suggestions that take the user's emotional state into consideration, and optimal dish suggestions for food delivery services.

[1402] The "means for inputting a menu for a certain period of time" is an interface that allows a user to input into the system the meal contents planned for a specific period of time.

[1403] "Means of suggesting side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[1404] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative artificial intelligence to suggest individual preferences and new genres of cuisine based on the user's past data and feedback.

[1405] "Means of learning from a user's past order history, feedback, and emotional state to suggest the most suitable dish" refers to a function that analyzes the dishes a user has ordered in the past, the feedback they received at the time, and their emotional state, and then suggests the next best dish.

[1406] "Means for generating the next suggested dish using a generative AI model" is a function that uses a generative artificial intelligence model to generate the next suggested dish based on user data.

[1407] The system for implementing this invention provides a food delivery application that learns a user's past order history, feedback, and emotional state, and suggests the most suitable dishes. A specific embodiment of this system is described below.

[1408] System Configuration

[1409] This system mainly uses the following hardware and software:

[1410] Hardware: Smartphone

[1411] Software: Python, OpenAI API

[1412] Program processing explanation

[1413] Retrieving User Data

[1414] The server retrieves the user's past order history and feedback from the database, which allows it to understand what dishes the user has ordered in the past and what ratings they have given.

[1415] Acquiring emotional state

[1416] The server provides an interface for obtaining the user's emotional state. For example, the user can input the emotional state within the application, or the emotional state can be inferred using sensors on the smartphone.

[1417] AI suggestions

[1418] The server uses a generative AI model to generate the next dish suggestion based on the acquired user data and emotional state, using OpenAI's API to input the user's data as a prompt sentence to generate the optimal dish.

[1419] Specific examples

[1420] For example, if a user has frequently ordered "pizza" in the past and has given "pizza" a "good" rating, the next suggested dish when the emotional state is "happy" may be "calzone."

[1421] Prompt Sentence Examples

[1422] Below are some example prompts to input to the generative AI model:

[1423] User's past orders: ["Pizza", "Pasta"]

[1424] Feedback: {"pizza": "good", "pasta": "average"}

[1425] Emotional state: Joy

[1426] What dish would you suggest next?

[1427] By inputting this prompt into a generative AI model, the next suggested dish can be generated.

[1428] effect

[1429] This system will enable personalized menu suggestions that take into account the user's emotional state, as well as optimal dish suggestions for food delivery services, thereby enriching the user's dining experience and increasing satisfaction.

[1430] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1431] Step 1:

[1432] The server retrieves the user's past order history and feedback from the database. Specifically, it sends a query to the database using the user ID as a key to retrieve a list of past orders and their ratings. The input for this step is the user ID, and the output is the past order history and feedback data.

[1433] Step 2:

[1434] The server acquires the user's emotional state. Specifically, it collects the emotional state input by the user within the application and emotional data inferred using the smartphone's sensors. The input of this step is the input data of the user's emotional state, and the output is the emotional state information.

[1435] Step 3:

[1436] The server generates prompts based on the acquired user data and emotional state. Specifically, it combines past order history, feedback, and emotional state to create prompts to input into the generative AI model. The inputs for this step are past order history, feedback, and emotional state, and the output is the generated prompts.

[1437] Step 4:

[1438] The server uses the generative AI model to generate the next dish suggestion. Specifically, it sends the generated prompt to OpenAI's API and receives a response from the AI ​​model. The input of this step is the generated prompt, and the output is the suggested dish from the AI ​​model.

[1439] Step 5:

[1440] The server presents the suggested dishes to the user by displaying them in the application interface and allowing the user to select them as their next dish to order. The input to this step is the suggested dishes from the AI ​​model, and the output is the information about the dishes presented to the user.

[1441] 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.

[1442] 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.

[1443] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1444] 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.

[1445] [Third embodiment]

[1446] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1447] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1448] 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).

[1449] 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.

[1450] 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.

[1451] 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).

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1457] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1458] "Example 1"

[1459] The system of the present invention provides an interface that allows users to input menus for a certain period of time. This interface can be implemented, for example, on a web page or a smartphone application. For example, a user inputs a menu in the form of "Monday's dinner is grilled salmon with salt, and Tuesday's dinner is curry rice."

[1460] "Example 2"

[1461] The system then suggests side dishes or menu changes to improve nutritional balance. For example, if a user inputs "Curry rice for dinner on Tuesday," the system might suggest, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[1462] "Example 3"

[1463] Furthermore, the system uses generative AI to provide a service that can accommodate individual preferences and new genres that users want to try. This AI learns from the user's past menu input history and makes menu suggestions based on the results. For example, if a user has often input "grilled salted salmon" in the past, the AI ​​will suggest something like, "Why not try grilled salted mackerel, which has a similar flavor to grilled salted salmon?"

[1464] "Example 4"

[1465] The AI ​​also receives feedback from users and learns from that feedback to improve the accuracy of its menu suggestions. For example, if a user gives a "good rating" to the suggestion "grilled salted mackerel," the AI ​​will increase the probability of suggesting dishes similar to "grilled salted mackerel."

[1466] The processing flow of each embodiment will be described below.

[1467] "Example 1"

[1468] Step 1: The user inputs a menu for a certain period of time through the system's interface. This interface can be implemented on a web page or a smartphone application, and the user inputs a menu in the form of "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday."

[1469] "Example 2"

[1470] Step 1: The system receives menu input from the user.

[1471] Step 2: The system suggests side dishes or menu changes to improve nutritional balance. For example, if a user inputs "Curry rice for dinner on Tuesday," the system will suggest something like, "Curry rice is low in vitamin A, so I suggest adding a carrot salad as a side dish."

[1472] "Example 3"

[1473] Step 1: The system uses generative AI to provide services that cater to individual preferences and new genres that people want to try.

[1474] Step 2: The AI ​​learns from the user's past menu entry history and makes menu suggestions based on the results. For example, if the user has often entered "grilled salted salmon" in the past, the AI ​​will suggest something like, "Why not try grilled salted mackerel, which has a similar flavor to grilled salted salmon?"

[1475] "Example 4"

[1476] Step 1: The system receives feedback from the user.

[1477] Step 2: The AI ​​learns from that feedback and improves the accuracy of the menu suggestions. For example, if a user gives a "good rating" to the suggestion "grilled salted mackerel," the AI ​​will increase the probability of suggesting menu items similar to "grilled salted mackerel."

[1478] Example 1

[1479] 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."

[1480] Conventional menu management systems require users to manually input menus and consider nutritional balance, which is time-consuming and inefficient. They also lack the flexibility to accommodate individual preferences and new genres. Furthermore, they lack the functionality to suggest menus using users' past history and feedback, making it difficult to increase user satisfaction.

[1481] 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.

[1482] In this invention, the server includes a means for users to input menus for a certain period of time, a means for saving the input menu data in a database, a means for sending prompts to the generative AI model based on the saved data, a means for receiving responses from the generative AI model and displaying them to the user, a means for suggesting side dishes or menu changes to improve nutritional balance, and a means for using the generative AI model to provide a service that can accommodate personal preferences or new genres that users want to try. This allows users to efficiently manage their menus and receive menu suggestions that match their personal preferences or new genres. Furthermore, by utilizing past history and feedback, more accurate menu suggestions can be achieved.

[1483] "User" refers to an individual or organization that uses the system to input menus and receive suggestions.

[1484] "Menu" refers to the contents of meals for a certain period of time, and specifically includes the menu of meals such as breakfast, lunch, and dinner.

[1485] "Interface" refers to the screen or application through which users access the system and input menu plans.

[1486] A "server" refers to a computer system that receives requests from users, stores data, and communicates with generative AI models.

[1487] "Database" refers to a data management system that stores menu data entered by users and allows searching and updating as needed.

[1488] A "generative AI model" refers to an artificial intelligence model that suggests recipes and nutritional values ​​based on menu data entered by the user.

[1489] A "prompt" is an instruction sent to the generative AI model, including menu information entered by the user.

[1490] "Response" refers to the recipe or nutritional information that the generative AI model generates based on the prompt.

[1491] "Nutritional balance" refers to the balance of nutrients contained in food, and is an important element for maintaining a healthy diet.

[1492] A "side dish" is a food that is served as a supplement to the main dish and plays a role in supplementing the nutritional balance.

[1493] "Suggestion" refers to the system making suggestions or advice to the user.

[1494] "Feedback" refers to opinions and evaluations provided by users to a system, which are used to improve and learn from the system.

[1495] This invention is a system that allows users to input menus for a certain period of time, and then uses a generative AI model to suggest recipes and nutritional values ​​based on the input. Specific embodiments of this system are described below.

[1496] Users access the system's interface using a web browser or smartphone application. The interface is built using web technologies such as HTML, CSS, and JavaScript. When a user accesses the interface, the server displays a menu entry screen.

[1497] For example, a user inputs a menu such as "Grilled salmon for dinner on Monday, and curry rice for dinner on Tuesday." The input data is sent from the device to the server as an HTTP POST request. The server analyzes the received data and stores it in a database (for example, MySQL or PostgreSQL).

[1498] Based on the stored data, the server sends a prompt to the generative AI model. For example, OpenAI's GPT-3 is used as the generative AI model. The prompt includes the menu information entered by the user. Specific examples of prompts include:

[1499] The user entered the following menu:

[1500] Monday's dinner is grilled salmon

[1501] Tuesday dinner is curry rice

[1502] Based on this, suggest recipes and nutritional values ​​for each menu item.

[1503] The generative AI model receives this prompt and generates detailed recipes and nutritional information for each menu item. The generated information is returned to the server, which converts it into HTML for display to the user. This displays the detailed recipes and nutritional information on the user's device.

[1504] The server also has the ability to suggest side dishes and menu changes to improve nutritional balance. The generative AI model learns from the user's past menu input history and makes menu suggestions based on the results. It also receives feedback from the user and learns based on that feedback to improve the accuracy of menu suggestions.

[1505] This system allows users to efficiently manage their menus and receive menu suggestions that cater to their personal preferences and new genres. It also makes use of past history and feedback to provide more accurate menu suggestions.

[1506] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1507] Step 1:

[1508] The user accesses the interface

[1509] Users access the system interface using a web browser or smartphone application. Specifically, users enter a URL in the browser or launch an app, which displays the system homepage or app home screen. The input is the URL or app icon, and the output is the homepage or home screen.

[1510] Step 2:

[1511] The server displays the menu entry screen.

[1512] The server receives the user's request and sends a menu entry screen built using HTML, CSS, and JavaScript to the user's device. Specifically, the server analyzes the HTTP request and returns the corresponding HTML file. The input is the user's request, and the output is the menu entry screen.

[1513] Step 3:

[1514] The user inputs the menu

[1515] The user inputs a menu into the displayed menu entry screen, for example, "Monday's dinner is grilled salted salmon, and Tuesday's dinner is curry rice." Input is done using text boxes and drop-down menus. The input is the menu data entered by the user, and the output is the data displayed in the input form.

[1516] Step 4:

[1517] The device sends the input data to the server

[1518] When the user has finished entering the menu, they click the "Submit" button, which causes the device to send the entered data to the server as an HTTP POST request. The input is the menu data entered by the user, and the output is the HTTP request sent to the server.

[1519] Step 5:

[1520] The server saves the data to a database

[1521] The server parses the received data and stores it in a database (e.g., MySQL or PostgreSQL). Specifically, the server establishes a database connection and executes SQL queries to insert the data. The input is the menu data received from the HTTP request, and the output is the data stored in the database.

[1522] Step 6:

[1523] The server sends a prompt to the generative AI model

[1524] The server generates prompts based on the stored data. For example, a prompt such as "The user has entered the following menu: grilled salmon for dinner on Monday, curry rice for dinner on Tuesday. Based on this, please suggest recipes and nutritional values ​​for each menu item" is sent to the generative AI model. The input is the menu data stored in the database, and the output is the prompt sent to the generative AI model.

[1525] Step 7:

[1526] A generative AI model generates a response

[1527] A generative AI model (such as OpenAI's GPT-3) generates a response based on the prompt it receives. The response includes detailed recipes and nutritional information for each dish. The input is the prompt, and the output is the generated response data.

[1528] Step 8:

[1529] The server displays the generated information to the user

[1530] The server analyzes the response received from the generative AI model and generates HTML to display to the user. Specifically, the server embeds the response data into an HTML template and sends it to the user's device. The input is the response data from the generative AI model, and the output is the HTML displayed on the user's device.

[1531] (Application example 1)

[1532] 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."

[1533] Conventional menu management systems allow users to input menus for a certain period of time, but they lack the ability to suggest side dishes that take nutritional balance into consideration, or to suggest new menus that meet individual preferences. Furthermore, they do not provide a way to list ingredients needed based on the menu and to purchase them efficiently. This means that users have to spend a lot of time and effort purchasing ingredients.

[1534] 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.

[1535] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can respond to personal preferences and new genres that users want to try using generative AI, and a means for listing necessary ingredients based on the menu and ordering those ingredients through a food delivery service.This allows users to efficiently manage their menus and easily purchase the necessary ingredients.

[1536] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[1537] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[1538] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative AI to suggest menus that suit individual preferences and new cooking genres based on the user's past data and feedback.

[1539] "A means of listing ingredients needed based on a menu and ordering those ingredients through a food delivery service" is a function that automatically lists ingredients needed based on a menu entered by the user and orders ingredients through a food delivery service based on that list.

[1540] A system for carrying out this invention includes a server, a user terminal, and a food delivery service. The server includes means for inputting menus for a certain period of time, means for suggesting side dishes or menu changes to supplement nutritional balance, means for providing a service that can accommodate personal preferences or new genres that users want to try using generative AI, and means for listing ingredients needed based on the menu and ordering the ingredients through a food delivery service.

[1541] The user terminal is a device such as a smartphone or PC, and provides an interface for users to input menus. For example, a user might input a menu such as "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday." This input data is sent to the server.

[1542] The server uses the Flask framework to build a web server and provides an endpoint for users to input menu plans for a certain period of time. When a user inputs a menu plan, a list of ingredients required based on the menu is created and returned in JSON format. Specifically, the server searches for ingredients in the menu database, eliminating duplicates before creating a list.

[1543] The generative AI learns from the user's past menu input history and makes menu suggestions based on the results. It also receives feedback from the user, learns based on that feedback, and improves the accuracy of the menu suggestions. This allows users to receive menu suggestions that match their personal preferences and new genres they want to try.

[1544] Furthermore, the server lists the ingredients needed based on the menu and orders them through a food delivery service based on that list. This function allows users to efficiently purchase the ingredients they need.

[1545] As a specific example, consider the case where the user inputs the following menu:

[1546] Monday: Grilled Salmon

[1547] Tuesday: Curry rice

[1548] In this case, the server generates a prompt like this:

[1549] "Monday's dinner is grilled salmon, and Tuesday's dinner is curry rice."

[1550] The generated shopping list looks like this:

[1551] "Salmon, salt, curry roux, rice, meat, vegetables"

[1552] Based on this list, you can order the ingredients you need through a food delivery service.

[1553] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1554] Step 1:

[1555] A user inputs a menu for a certain period of time using a terminal.

[1556] Input: The user inputs a menu such as "Grilled salted salmon for dinner on Monday, and curry rice for dinner on Tuesday" into an interface for inputting menu items.

[1557] Output: The entered menu data is sent from the terminal to the server.

[1558] Step 2:

[1559] The server analyzes the received menu data and lists the necessary ingredients.

[1560] Input: Menu data sent from the device.

[1561] Data processing: The server refers to the menu database and searches for ingredients that correspond to each menu.

[1562] Output: A list of listed ingredients.

[1563] Step 3:

[1564] The server orders ingredients through a food delivery service based on the list of ingredients.

[1565] Input: A list of listed ingredients.

[1566] Data calculation: The server calls the API of the food delivery service and sends the list of ingredients as order data.

[1567] Output: Order confirmation from food delivery service.

[1568] Step 4:

[1569] The generative AI learns from the user's past menu input history and reflects this in the next menu suggestion.

[1570] Input: User's past menu entry history.

[1571] Data processing: Generative AI analyzes past data to learn user preferences and patterns.

[1572] Output: Learning results that will be reflected in the next menu suggestion.

[1573] Step 5:

[1574] Users provide feedback, and the generative AI learns based on that feedback.

[1575] Input: Feedback data from users.

[1576] Data computation: Generative AI analyzes feedback data and learns to improve the accuracy of suggestions.

[1577] Output: Improved menu suggestions for your next meal.

[1578] Example 2

[1579] 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."

[1580] Planning nutritionally balanced meals is a difficult task in today's busy lifestyles. In particular, considering side dishes and menu changes to compensate for individual nutrient deficiencies requires specialized knowledge and is difficult for average users. There is also a demand for menu suggestions that reflect individual preferences and new genres that people want to try, but doing this manually takes time and effort. Furthermore, it is important to utilize the user's past menu history and feedback to make more accurate suggestions.

[1581] 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.

[1582] In this invention, the server includes a means for the user to input menus for a certain period of time, a means for the terminal to send the input data to the server, a means for the server to analyze the data and obtain nutritional components, a means for the server to evaluate nutritional balance, a means for the server to input prompts to the generative AI model, a means for the server to return the generated suggestions to the user, and a means for using the generative AI model to provide a service that can accommodate personal preferences or new genres that the user wants to try, thereby enabling users to easily create menus that take nutritional balance into consideration.

[1583] "User" refers to an individual who uses the system to input menu information and receive nutritional balance suggestions.

[1584] "Terminal" refers to a device used by a user, such as a computer or smartphone, that is used to input data into the system and receive suggestions.

[1585] "Server" refers to the central processing unit that receives data sent by users and performs analysis and uses generated AI models.

[1586] A "menu" refers to a meal plan or menu for a certain period of time, and is information that a user inputs into the system.

[1587] "Nutritional components" refers to nutrients such as vitamins, minerals, proteins, lipids, and carbohydrates contained in food.

[1588] "Nutritional balance" refers to the appropriate distribution of nutrients in a diet, and is an essential element for maintaining good health.

[1589] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate suggestions based on user input.

[1590] A "prompt" is an instruction given to a generative AI model, including a question or command to generate a specific suggestion.

[1591] "Suggestions" refers to side dishes or menu substitutions that the system suggests to the user.

[1592] "Feedback" refers to the opinions and evaluations users provide to the system, and is information used to train the generative AI model.

[1593] This invention is a system that suggests side dishes and menu changes to improve nutritional balance based on menu information entered by a user. The system is implemented using a user's terminal, a server, and a generative AI model.

[1594] Hardware and software used

[1595] Hardware: User devices (PCs, smartphones, etc.), servers

[1596] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), web application frameworks (e.g., Django)

[1597] Data processing and calculation

[1598] 1. User input: The user uses a terminal to enter menu information, such as "Curry rice for dinner on Tuesday," into the input form of the web application.

[1599] 2. Data transmission: The device sends the input data to the server as an HTTP request. The data is sent in JSON format.

[1600] 3. Data analysis: The server analyzes the received data and retrieves the nutritional information for curry rice from a database (e.g., MySQL). Specifically, it queries the database for the nutritional information for curry rice.

[1601] 4. Nutritional Balance Assessment: The server assesses the nutritional content of the curry rice based on the acquired nutritional information. For example, it identifies a lack of vitamin A.

[1602] 5. Use of generative AI model: The server inputs a prompt to the generative AI model (e.g., GPT-4). An example of a prompt is, "Curry rice is low in vitamin A, so what side dish should I add?"

[1603] 6. Suggestion generation: The server receives the suggestions obtained from the generative AI model and returns them to the user. Specifically, it returns an HTTP response with a message such as, "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish."

[1604] Specific examples

[1605] User input: "Curry rice for dinner on Tuesday"

[1606] Example prompt: "Curry rice is low in vitamin A, so what side dish should you add?"

[1607] Suggestion output: "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[1608] In this way, users can easily create menus that take nutritional balance into consideration. The system can also learn from the user's past menu input history and feedback to provide more accurate suggestions.

[1609] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1610] Step 1:

[1611] The user inputs a menu for a certain period of time.

[1612] Specific operation: The user uses the terminal to enter menu information such as "Curry rice for dinner on Tuesday" into the input form of the web application.

[1613] Input: Menu information entered by the user.

[1614] Output: Menu information entered into the terminal.

[1615] Step 2:

[1616] The terminal sends the input data to the server.

[1617] Specific operation: The device sends the menu information entered by the user to the server as an HTTP request. The data is sent in JSON format.

[1618] Input: Menu information entered into the device.

[1619] Output: Menu information sent to the server.

[1620] Step 3:

[1621] The server analyzes the data and obtains the nutritional information.

[1622] Specific operation: The server analyzes the received data and retrieves the nutritional information of curry rice from a database (e.g., MySQL). Specifically, it executes a query about the nutritional information of curry rice against the database.

[1623] Input: Menu information sent to the server.

[1624] Output: Nutritional information retrieved from the database.

[1625] Step 4:

[1626] The server evaluates the nutritional balance.

[1627] Specific operation: The server evaluates the nutrients contained in curry rice based on the acquired nutritional information. For example, it identifies that it is lacking in vitamin A.

[1628] Input: Nutrition information retrieved from the database.

[1629] Output: Nutritional balance assessment (e.g. Vitamin A deficiency).

[1630] Step 5:

[1631] The server inputs a prompt sentence into the generative AI model.

[1632] Specific operation: The server inputs a prompt to the generative AI model (e.g., GPT-4). An example of a prompt is, "Curry rice is low in vitamin A, so what side dish should I add?"

[1633] Input: Nutritional balance assessment results.

[1634] Output: The prompt sentence fed into the generative AI model.

[1635] Step 6:

[1636] The server returns the generated suggestions to the user.

[1637] Specific operation: The server receives the suggestions obtained from the generative AI model and returns them to the user. Specifically, it returns an HTTP response with a message such as, "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish."

[1638] Input: Suggestions obtained from a generative AI model.

[1639] Output: The suggestion message returned to the user.

[1640] (Application example 2)

[1641] 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."

[1642] Conventional menu suggestion systems can suggest side dishes or menu substitutions to improve the nutritional balance of the menu entered by the user, but they lack the functionality to suggest side dishes or additional menu items that take nutritional balance into account for the dish the user is about to order. This makes it difficult for users to select meals that take nutritional balance into account when eating out or ordering food delivery.

[1643] 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.

[1644] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to compensate for nutritional balance, a means for providing a service that can respond to personal preferences and new genres that the user wants to try using generative AI, and a means for suggesting side dishes and additional menu items that take nutritional balance into consideration for the dish the user is about to order. This enables the user to select meals that take nutritional balance into consideration even when eating out or using food delivery.

[1645] A "means for inputting meal plans for a specified period of time" is an interface or device that allows a user to input meal plans for a specified period of time.

[1646] "Means for suggesting side dishes or menu changes to compensate for nutritional imbalance" refers to algorithms or systems that suggest side dishes or alternative menu items to compensate for missing nutrients for the menu entered by the user.

[1647] "A means of using generative AI to provide services that can accommodate individual preferences and new genres that users want to try" is a technology that uses a generative AI model to learn from users' past data and feedback, and provides services that accommodate individual users' preferences and new cuisine genres.

[1648] "A means of suggesting side dishes and additional menu items that take into consideration the nutritional balance of the dish that the user is about to order" is a system that suggests side dishes and additional menu items that will supplement the nutritional balance of the dish that the user is about to order via food delivery or eating out.

[1649] The system for implementing this invention allows users to input menus for a certain period of time and provides a function to suggest side dishes and menu changes to supplement nutritional balance. It also uses generative AI to provide a service that can respond to personal preferences and new genres that users want to try, and has a function to suggest side dishes and additional menu items that take nutritional balance into consideration for the dish the user is about to order.

[1650] System configuration

[1651] The system consists of the following main components:

[1652] 1. User device: A device such as a smartphone or tablet that users use to input menu plans.

[1653] 2. Server: A central system for processing and storing data, where the generative AI model runs.

[1654] 3. Generative AI model: An AI model that learns from user input data, past history, and feedback to provide appropriate suggestions.

[1655] Program processing

[1656] The server receives the menu data sent from the user's device and uses a generative AI model to suggest side dishes and menu changes to improve nutritional balance. Specifically, the following process is performed:

[1657] 1. Data entry: The user enters a menu for a certain period of time. For example, the user enters "Curry rice for dinner on Tuesday."

[1658] 2. Data processing: The server receives the input menu data and sends it to the generative AI model.

[1659] 3. Suggestion generation: Based on the input menu data, the generative AI model suggests side dishes or menu changes to improve nutritional balance. For example, it might say, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[1660] Hardware and software used

[1661] Hardware: smartphones, tablets, servers

[1662] Software: Python, OpenAI API

[1663] Specific examples

[1664] For example, if a user wants to order "curry rice," the following prompt sentence is input to the generative AI model:

[1665] A user is trying to order "Curry rice." Please suggest a side dish to supplement the nutrients that are lacking in this dish.

[1666] Example response from a generative AI model:

[1667] Since curry rice is low in vitamin A, we suggest adding a carrot salad as a side dish.

[1668] In this way, nutritionally balanced side dishes and additional menu items can be suggested for the dish the user is about to order.

[1669] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1670] Step 1:

[1671] The user inputs a menu for a certain period of time.

[1672] Input: A user uses a device such as a smartphone or tablet to input a meal plan for a specific period of time. For example, they input "Curry and rice for dinner on Tuesday."

[1673] Output: The entered menu data is saved on the terminal and sent to the server.

[1674] Specific operation: The user inputs the menu through the application interface and presses the submit button to send the data to the server.

[1675] Step 2:

[1676] The server receives the input menu data.

[1677] Input: Menu data sent from the user's device.

[1678] Output: Menu data saved on the server.

[1679] Specific operation: The server receives the data sent from the user terminal and stores it in a database.

[1680] Step 3:

[1681] The server sends the menu data to the generative AI model.

[1682] Input: Menu data stored on the server.

[1683] Output: The prompt sent to the generative AI model.

[1684] Specific operation: The server generates a prompt based on the menu data and sends it to the generative AI model. For example, it generates a prompt such as, "The user is about to order 'Curry Rice'. Please suggest a side dish to supplement the nutrients that are lacking in this dish."

[1685] Step 4:

[1686] A generative AI model generates suggestions based on the prompt.

[1687] Input: The prompt sent to the generative AI model.

[1688] Output: Suggested results from the generative AI model.

[1689] Specific operation: The generative AI model analyzes the prompt sentence and suggests appropriate side dishes or menu changes. For example, it generates a result such as, "Curry rice is low in vitamin A, so we suggest adding a carrot salad as a side dish."

[1690] Step 5:

[1691] The server receives the suggested results from the generative AI model.

[1692] Input: Suggested results from a generative AI model.

[1693] Output: Suggested results stored on the server.

[1694] Specific operation: The server receives the suggestion results sent from the generative AI model and stores them in a database.

[1695] Step 6:

[1696] The server sends the suggestion results to the user's device.

[1697] Input: Suggested results stored on the server.

[1698] Output: Suggested results displayed on the user's device.

[1699] Specific operation: The server sends the saved suggestion results to the user's device and displays them to the user. For example, a message such as "Curry rice is low in vitamin A, so we suggest adding carrot salad as a side dish" is displayed.

[1700] Example 3

[1701] 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."

[1702] Conventional menu suggestion systems have difficulty in proposing meals that reflect individual user preferences or new challenges, and have been unable to effectively utilize user feedback to improve the accuracy of suggestions. This has made it difficult to increase user satisfaction.

[1703] 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.

[1704] In this invention, the server includes a means for a user to input a menu, a means for the server to save the menu data, a means for the server to learn the data using a generative AI model, a means for the user to request a new menu, a means for the server to suggest a menu using the generative AI model, a means for the user to provide feedback on the suggested menu, and a means for the server to save the feedback data and re-train the generative AI model. This makes it possible to propose menus that reflect the user's individual preferences and new challenges, and further makes it possible to improve the accuracy of the suggestions by utilizing feedback from the user.

[1705] "Menu" refers to a meal menu or a combination of dishes.

[1706] "Generative AI" is a type of artificial intelligence that refers to a model that has the ability to generate new data and suggestions based on specific data.

[1707] "User" refers to an individual who uses the system to input or request menu items.

[1708] "Server" refers to a computer system that receives data from users, stores it, processes it, and uses generative AI models to learn and make recommendations.

[1709] "Database" refers to an information management system for storing menu data and feedback data from users.

[1710] "Feedback" refers to the evaluation or opinion provided by the user regarding the suggested menu.

[1711] "Learning" refers to data processing by the generative AI to improve the accuracy of future suggestions based on the user's past menu input history and feedback data.

[1712] "Suggestion" refers to the act of generative AI proposing new menus based on the user's preferences and requests.

[1713] A "request" refers to an action in which a user asks the system to suggest a new menu.

[1714] MODE FOR CARRYING OUT THE INVENTION

[1715] This invention relates to a menu suggestion system that utilizes generative AI to accommodate personal preferences and new genres that users want to try. Specific embodiments of this system are described below.

[1716] Hardware and software used

[1717] Hardware: Server, user terminal (PC, smartphone)

[1718] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), feedback collection systems

[1719] System Overview

[1720] The system learns from the menu data entered by the user in the past and suggests new menus based on the results. Furthermore, it retrains the generative AI model based on user feedback to improve the accuracy of its suggestions.

[1721] Data processing and calculation

[1722] 1. Data collection: The user uses the device to input a past menu. For example, they input "grilled salmon with salt."

[1723] 2. Data storage: The server receives the menu data sent by the user and stores it in the database management system. Specifically, it adds a new record to the "Menu" table in the database.

[1724] 3. Data learning: The server periodically retrieves menu data from the database and uses the generative AI model to learn from it, allowing the model to understand user preferences and patterns.

[1725] 4. Suggestion generation: When a user sends a request for a new menu item from their device, the server uses the generative AI model to suggest an appropriate menu item. For example, it might suggest, "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?"

[1726] 5. Feedback collection: The user tries the suggested menu and provides feedback on the results. For example, they give a "good rating" to "grilled salted mackerel."

[1727] 6. Accuracy Improvement: The server retrains the generative AI model based on the feedback data to improve the accuracy of suggestions.

[1728] Specific examples

[1729] User's past menu entry: "Grilled Salmon"

[1730] Example suggestion: "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?"

[1731] Feedback example: A user gives a "good rating" to "Grilled salted mackerel"

[1732] Prompt Sentence Examples

[1733] Prompt: "Suggest new menu items based on the user's past menu entries. Please consider the user's preferences and new genres they would like to try."

[1734] This system aims to enrich the user's dietary habits by learning the user's preferences and proposing more appropriate menus. The flow of the specification process in the third embodiment will be described with reference to FIG.

[1735] Step 1:

[1736] The user inputs the menu

[1737] The user uses a device (PC or smartphone) to input past menu items into the system interface. For example, they might input "grilled salmon with salt." The input data is then sent from the device to the server.

[1738] Step 2:

[1739] The server stores the menu data

[1740] The server receives the menu data sent by the user and stores it in a database management system (e.g., MySQL). Specifically, it adds a new record to the "Menu" table in the database. The input is the menu data from the user, and the output is the record stored in the database.

[1741] Step 3:

[1742] The server uses a generative AI model to learn the data.

[1743] The server periodically retrieves menu data from the database and trains it using a generative AI model (e.g., GPT-4). This allows the model to understand user preferences and patterns. The input is the menu data retrieved from the database, and the output is the trained generative AI model.

[1744] Step 4:

[1745] A user requests a new menu

[1746] A user uses a terminal to request the system to suggest a new menu. For example, they might input, "Please suggest a new fish dish." The input is a request from the user, and the output is the request data sent to the server.

[1747] Step 5:

[1748] The server uses a generative AI model to suggest menus

[1749] The server receives the user's request and generates an appropriate menu using a generative AI model. For example, it might suggest, "Why not try grilled salted mackerel, which tastes similar to grilled salted salmon?" The input is the user's request and the trained generative AI model, and the output is the suggested menu.

[1750] Step 6:

[1751] Users provide feedback on suggested menu items

[1752] The user tries the suggested menu and provides feedback on the results. For example, the user gives a "good rating" to "grilled salted mackerel." The input is the user's feedback, and the output is the feedback data to the server.

[1753] Step 7:

[1754] The server stores the feedback data and retrains the generative AI model.

[1755] The server receives feedback from users and stores it in a database. It then retrains the generative AI model based on the feedback data to improve the accuracy of suggestions. The input is the feedback data from users, and the output is the retrained generative AI model.

[1756] (Application example 3)

[1757] 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."

[1758] Conventional menu suggestion systems do not adequately consider user preferences or new challenges. They also lack a mechanism to effectively utilize user feedback to improve the accuracy of suggestions. Furthermore, food delivery services do not suggest new dishes based on users' past ordering history, making it difficult to increase user satisfaction.

[1759] 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.

[1760] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences and new genres that the user wants to try, a means for learning from the user's past order history and suggesting new dishes that suit the user's preferences, and a means for receiving feedback from the user, learning based on that feedback, and improving the accuracy of the suggestions. This makes it possible to suggest menus and dishes that take into account the user's preferences and new challenges, thereby increasing user satisfaction.

[1761] The "means for inputting menus for a certain period of time" is an interface that allows a user to input menu information planned for a specific period of time into the system.

[1762] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that takes into consideration the nutritional balance of the menu entered by the user and suggests appropriate side dishes or alternative menu items.

[1763] "A means of using generative AI to provide services that can accommodate individual preferences and new genres that users want to try" is a function that uses generative artificial intelligence to provide services that accommodate individual preferences and new genres based on users' past data and feedback.

[1764] "Means of learning the user's past order history and suggesting new dishes that suit the user's preferences" is a function that analyzes the history of dishes that the user has ordered in the past and uses that data to suggest new dishes that suit the user's preferences.

[1765] "Means for receiving feedback from users, learning based on that feedback, and improving the accuracy of suggestions" refers to a function that collects feedback information provided by users, allows the system to learn based on that information, and improves the accuracy of suggestions from the next time onwards.

[1766] The system for implementing this invention has the function of learning the user's past order history and suggesting new dishes that suit the user's preferences. The system is realized using the following hardware and software.

[1767] Hardware

[1768] Server: A server for storing and processing data.

[1769] User device: A mobile device such as a smartphone or tablet.

[1770] software

[1771] Generative AI model: An AI model that learns from a user's past order history and suggests new dishes. Specifically, it uses Python and its libraries (scikit-learn, numpy, etc.).

[1772] Database: A database to store user order history and feedback.

[1773] User Interface: The interface through which users can enter their order history and provide feedback.

[1774] Data processing and calculation

[1775] The server retrieves the user's past order history from a database and uses a generative AI model to learn from that data. Specifically, it performs the following processes:

[1776] 1. Data Acquisition: Retrieve the user's past order history from the database.

[1777] 2. Data preprocessing: Convert the acquired data into TF-IDF vectors.

[1778] 3. Similarity calculation: Calculate the similarity between the user's order history and the menu items using cosine similarity.

[1779] 4. Suggestion generation: Suggests similar menu items to the user.

[1780] 5. Feedback learning: Receive feedback from users and retrain the generative AI model based on that feedback.

[1781] Specific examples

[1782] For example, if a user has previously ordered a "Margherita pizza" and a "Pepperoni pizza," the generative AI model can learn from this data and suggest a "Quattro Formaggi pizza."

[1783] Example prompts to input to a generative AI model:

[1784] Suggest new menu items based on the user's past order history, which is "Margherita Pizza" and "Pepperoni Pizza."

[1785] In this way, it becomes possible to suggest menus and dishes that take into account the user's preferences and new challenges, thereby increasing user satisfaction.

[1786] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1787] Step 1:

[1788] The server retrieves the user's past order history from a database.

[1789] Input: User ID

[1790] Output: User's past order history data

[1791] What happens: The server queries the database to retrieve the order history for the specified user ID. This data includes the order date and time, dish name, rating, etc.

[1792] Step 2:

[1793] The server preprocesses the acquired order history data and converts it into a TF-IDF vector.

[1794] Input: User's past order history data

[1795] Output: TF-IDF vector

[1796] What happens: The server converts the order history data into text format and uses scikit-learn's TfidfVectorizer to create a TF-IDF vector. This vector quantifies the features of each dish.

[1797] Step 3:

[1798] The server converts the list of menu items into TF-IDF vectors.

[1799] Input: A list of menu items

[1800] Output: TF-IDF vectors of menu items

[1801] Specific operation: The server converts the list of menu items into text format and also converts it into a TF-IDF vector, which is a numerical representation of the features of each menu item.

[1802] Step 4:

[1803] The server calculates the cosine similarity between the user's order history vector and the menu item vector.

[1804] Input: TF-IDF vector of user's order history, TF-IDF vector of menu items

[1805] Output: Cosine similarity score

[1806] How it works: The server uses scikit-learn's cosine_similarity function to calculate the cosine similarity between the user's order history vector and each menu item vector. This score indicates how close each menu item is to the user's preferences.

[1807] Step 5:

[1808] The server suggests the most similar menu items to the user based on the cosine similarity scores.

[1809] Input: Cosine similarity score

[1810] Output: Suggested menu items

[1811] Specific operation: The server compares the calculated cosine similarity scores, selects the menu item with the highest score, and sends this menu item to the user device to suggest to the user.

[1812] Step 6:

[1813] The user provides feedback on the suggested menu items.

[1814] Input: Suggested menu item

[1815] Output: User feedback

[1816] Specific behavior: The user reviews the suggested menu items and provides feedback, such as a positive or negative rating. This feedback is sent from the user device to the server.

[1817] Step 7:

[1818] The server receives feedback from users and retrains the generative AI model based on that feedback.

[1819] Input: User feedback

[1820] Output: An updated generative AI model

[1821] How it works: The server stores the feedback received from users in a database and uses that data to retrain the generative AI model, improving the accuracy of future suggestions.

[1822] 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.

[1823] "Example 1"

[1824] In one embodiment of the present invention, a system is provided that includes an emotion engine that recognizes a user's emotions. The system grasps the user's emotional state and provides meal suggestions based on the emotional state. Specifically, when the user is feeling joy, the system suggests a meal that will enhance that joy. For example, the system may suggest a special meal on the day the user receives a promotion.

[1825] "Example 2"

[1826] The emotion engine also analyzes user behavioral data and feedback to understand a user's emotional state. Specifically, it analyzes the user's behavior after eating a particular meal and their evaluation of the meal to understand how that meal affected the user's emotions. For example, if a user becomes more active after eating a particular meal, it can determine that that meal is likely to increase the user's joy.

[1827] "Example 3"

[1828] Furthermore, the emotion engine learns the user's emotional state to improve the accuracy of menu suggestions according to the user's emotional state. Specifically, it learns the relationship between the user's past emotional state and the menu at that time, and makes menu suggestions based on that result. For example, if a user tends to prefer a particular meal when feeling happy, the accuracy of suggestions can be improved by suggesting that meal when the user is in a similar emotional state.

[1829] "Example 4"

[1830] In this way, the system of the present invention enriches the user's dining experience by providing menu suggestions that take the user's emotional state into account. Furthermore, by learning the user's emotional state, the system can deepen its understanding of the user's emotions and provide a more personalized service.

[1831] The processing flow of each embodiment will be described below.

[1832] "Example 1"

[1833] Step 1: The emotion engine understands the user's emotional state.

[1834] Step 2: Based on the emotional state, the generative AI generates a menu.

[1835] Step 3: The generated menu is presented to the user.

[1836] "Example 2"

[1837] Step 1: User behavioral data and feedback are input into the emotion engine.

[1838] Step 2: The emotion engine analyzes the input data and understands the user's emotional state.

[1839] Step 3: Based on the emotional state, the generative AI generates a menu and presents it to the user.

[1840] "Example 3"

[1841] Step 1: The emotion engine learns the relationship between the user's past emotional state and the menu at that time.

[1842] Step 2: Based on the learning results, the emotion engine understands the current emotional state of the user.

[1843] Step 3: Based on the emotional state, the generative AI generates a menu and presents it to the user.

[1844] "Example 4"

[1845] Step 1: The user's emotional state is understood by the emotion engine.

[1846] Step 2: Based on the emotional state, the generative AI generates a menu.

[1847] Step 3: The generated menu is presented to the user, enriching their dining experience.

[1848] Example 1

[1849] 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."

[1850] Conventional menu suggestion systems suggest menus without considering the user's emotional state, making it difficult to enhance the user's psychological satisfaction. Furthermore, while suggestions are made based on nutritional balance and personal preferences, there is a lack of special suggestions tailored to the user's emotions. This presents a problem in that it is difficult for users to select an appropriate menu for a special day or a specific emotional state. The specification process by the specification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1851] In this invention, the server includes a means for inputting menus for a certain period of time, a means for suggesting side dishes and menu changes to supplement nutritional balance, a means for providing a service that can accommodate personal preferences and new genres that the user wants to try using generative AI, a means for recognizing the user's emotional state and suggesting menus based on that emotional state, and a means for integrating and analyzing the user's emotional data and menu data. This makes it possible to provide the optimal menu according to the user's emotional state and increase psychological satisfaction.

[1852] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[1853] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[1854] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses a generative AI model to suggest menus that suit individual preferences and new cooking genres based on the user's past data and feedback.

[1855] "Means of recognizing the user's emotional state and suggesting menus based on that emotional state" is a function that uses an emotion engine to analyze the user's emotions and suggests appropriate menus based on the results.

[1856] "Means for integrating and analyzing user emotional data and menu data" is a function that combines and analyzes the menu data entered by the user with the emotional data obtained from the emotion engine to generate the optimal menu.

[1857] MODE FOR CARRYING OUT THE INVENTION

[1858] This invention is a system that allows a user to input menus for a certain period of time, and based on that data, suggests optimal menus that take into account nutritional balance, personal preferences, and even the user's emotional state. Specific embodiments of this system are described below.

[1859] Providing a user interface

[1860] The server provides an interface for users to input menu plans for a certain period of time. This interface is implemented as a web page or smartphone application. Specifically, web pages are generated using HTML, CSS, and JavaScript, while smartphone applications use frameworks such as React Native or Flutter.

[1861] User menu entry

[1862] The user inputs a menu into a text box through the provided interface. For example, they might input "grilled salted salmon for dinner on Monday, and curry rice for dinner on Tuesday." The input data is sent to the server and stored in a database.

[1863] Collecting Emotional Data

[1864] The server collects the user's emotional state using an emotion engine. This emotion engine recognizes emotions by analyzing user input, behavior, and external data (e.g., social media posts). Specific software used is the emotion analysis API from IBM Watson or Microsoft Azure.

[1865] Data integration and analysis

[1866] The server integrates the menu data entered by the user with the emotion data obtained from the emotion engine. Based on this integrated data, it uses a generative AI model to suggest optimal menus. Specifically, the model is implemented using Python and TensorFlow and the data is analyzed.

[1867] Menu suggestions

[1868] Based on the analysis results of the generative AI model, the server suggests the optimal menu based on the user's emotional state. For example, if a user receives a promotion, it might suggest a steak dinner as a special meal.

[1869] Displaying suggestions

[1870] The device displays the suggestions sent from the server to the user. The user can then review the suggested menu and make any necessary corrections or approvals. The menu is displayed in a visually easy-to-understand format using HTML and CSS.

[1871] Examples and prompts

[1872] Specific examples

[1873] A user types "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday" on a web page. The emotion engine detects that the user posted on social media, "I got promoted!" and suggests "steak dinner" as a special meal.

[1874] Prompt Sentence Examples

[1875] "Please suggest the best meal based on the meal data and sentiment data entered by the user. If the user gets promoted, please suggest a special meal."

[1876] In this way, a system is realized that provides optimal menus according to the user's emotional state.

[1877] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1878] Step 1:

[1879] The server provides an interface for users to input menus for a certain period of time. On a web page or smartphone application, users input their menus, for example, "Monday's dinner is grilled salted salmon, and Tuesday's dinner is curry rice." The input data is sent to the server and stored in a database. The input is the user's menu data, and the output is the menu data stored in the database.

[1880] Step 2:

[1881] The server uses an emotion engine to collect the user's emotional state. The emotion engine recognizes emotions by analyzing user input and behavior, as well as external data (e.g., social media posts). Specific software used is the emotion analysis API from IBM Watson or Microsoft Azure. The input is user behavior data and external data, and the output is analyzed emotional data.

[1882] Step 3:

[1883] The server integrates the menu data entered by the user with the emotion data obtained from the emotion engine. Based on this integrated data, a generative AI model is used to suggest optimal menus. Specifically, the model is implemented using Python and TensorFlow to analyze the data. The input is the integrated menu data and emotion data, and the output is a menu suggested by the generative AI model.

[1884] Step 4:

[1885] The server uses the analysis results of the generative AI model to suggest the optimal menu based on the user's emotional state. For example, if a user is promoted, it might suggest a "steak dinner" as a special meal. The input is the analysis results of the generative AI model, and the output is the suggested menu.

[1886] Step 5:

[1887] The terminal displays the suggestions sent from the server to the user. The user checks the suggested menu and makes any necessary corrections or approvals. The display is provided in a visually easy-to-understand format using HTML and CSS. The input is the suggestions sent from the server, and the output is the menu displayed to the user.

[1888] (Application example 1)

[1889] 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."

[1890] Conventional menu suggestion systems can suggest menus based on the user's nutritional balance and personal preferences, but they do not suggest menus that take into account the user's emotional state. As a result, they are unable to provide appropriate meals according to the user's emotions, making it difficult to increase user satisfaction. In addition, they are unable to suggest special menus that correspond to specific emotional states, such as when the user is tired or on special occasions.

[1891] 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 a means for inputting menus for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences or new genres that the user wants to try, and a means for recognizing the user's emotional state and suggesting menus based on those emotions. This makes it possible to propose appropriate menus according to the user's emotional state, thereby increasing user satisfaction.

[1892] "Means for inputting meal plans for a certain period of time" is a function that provides an interface for the user to input meal plans for a specific period of time.

[1893] "Means to suggest side dishes or menu changes to compensate for nutritional imbalance" is a function that suggests side dishes or alternative menu items that take nutritional balance into consideration for the menu items entered by the user.

[1894] "A means of using generative AI to provide a service that can accommodate individual preferences and new genres that users want to try" is a function that uses generative AI to learn from users' past data and feedback, and suggests menus that match individual users' preferences and new cooking genres.

[1895] "Means for recognizing the user's emotional state and suggesting menus based on those emotions" is a function that detects the user's emotions and suggests appropriate menus based on those emotions.

[1896] A system for implementing this invention includes a means for a user to input menu items for a certain period of time, a means for suggesting side dishes or menu changes to supplement nutritional balance, a means for using generative AI to provide a service that can accommodate personal preferences or new genres that the user wants to try, and a means for recognizing the user's emotional state and suggesting menu items based on those emotions.

[1897] System Program

[1898] This system uses the following hardware and software:

[1899] Hardware: Smartphone

[1900] Software: Python, emotion recognition API (e.g. Microsoft Azure Emotion API)

[1901] Program processing explanation

[1902] The server provides an interface for users to input menus for a certain period of time. This interface can be implemented on a web page or a smartphone application. For example, users can input menus in the form of "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday."

[1903] The server then uses an emotion recognition API to recognize the user's emotional state. The user can input their emotional state or detect emotions through camera or voice input. This emotional data is sent to the server and analyzed by the generative AI.

[1904] The generative AI learns from the user's past menu input history and feedback, and then makes menu suggestions based on the results. For example, it might suggest a relaxing meal when the user is tired, or a special meal when the user is happy.

[1905] Specific examples

[1906] For example, if a user inputs "I'm tired," the server will recognize this emotion through an emotion recognition API, and the generative AI will suggest "a relaxing meal." This suggestion is based on the user's past data and feedback.

[1907] Example prompts to input to a generative AI model:

[1908] A user says they're tired. Suggest a relaxing meal.

[1909] Using this prompt, the generative AI model can suggest appropriate menu items.

[1910] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1911] Step 1:

[1912] The user inputs a menu for a certain period of time through a smartphone application. For example, the user might input a menu such as "Grilled salmon for dinner on Monday, curry rice for dinner on Tuesday." The input data is then sent to the server.

[1913] Step 2:

[1914] The server uses the emotion recognition API to recognize the user's emotional state. The user inputs their emotional state or detects emotions through camera or voice input. The emotion recognition API analyzes the input data and identifies the user's emotional state. This emotional data is sent to the server.

[1915] Step 3:

[1916] The server uses generative AI to learn from the user's past menu entry history and feedback. Based on this data, the generative AI identifies the user's preferences and new genres they would like to try. The results of this learning are stored on the server.

[1917] Step 4:

[1918] The server s...

Claims

1. A means for users to input menus for a certain period of time; A means for suggesting a side dish or a change in the menu to supplement the nutritional balance of the input menu; means for determining an emotional state of the user using an emotion engine; Including, The proposed means comprises: The system uses a generative AI model to generate a suggested menu based on a prompt sentence that instructs the system to generate a menu based on the user's emotional state.

2. The proposed means comprises: The system learns the user's past menu input history, and generates a menu to be proposed using the generation AI model based on a prompt sentence that instructs the system to generate a menu based on the learning results. The system of claim 1 .

3. The proposed means comprises: The generative AI model receives feedback from the user, learns based on the feedback, and improves the accuracy of the menu suggestions. The system of claim 1 .

Images