System

Abstract

A system is provided.SOLUTION: A system includes a means for acquiring food material information input by a user, a means for specifying food materials in a refrigerator by image analysis, a means for generating a plurality of recipes in a generation AI based on the specified food materials, and a means for providing the generated recipes to 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] The challenges are that it is difficult for restaurant owners and chefs to optimize ingredient inventory, and that cooking at home tends to be monotonous. Food waste is also common, leading to over-purchasing and wasting ingredients in the refrigerator. Furthermore, users have to manually search for and suggest recipes to increase the variety of ingredients, which is a hassle, making it difficult to cook efficiently. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for acquiring ingredient information entered by a user, a means for identifying ingredients in a refrigerator through image analysis, a means for generating multiple recipes using a generation AI based on the identified ingredients, and a means for providing the generated recipes to the user. The system also includes a means for selecting the optimal recipe based on the user's preference information, a means for managing ingredient inventory status, and a means for automatically linking inventory data, thereby reducing ingredient waste and increasing the variety of dishes available. The system also supports mobile ordering services and the operation of bento shops that specialize in discarded ingredients, thereby enabling efficient use of ingredients in restaurants and homes.

[0006] "User" refers to any individual or organization that uses the system or service.

[0007] "Ingredient information" refers to detailed data about ingredients owned by the user, specifically including the type, quantity, and storage condition of the ingredients.

[0008] "Means" refers to the methods or technical components used to achieve a particular purpose.

[0009] "Acquire" refers to gathering or receiving specific information or data.

[0010] "Image analysis" refers to the technology of processing image data to identify and recognize the objects and features contained within it.

[0011] "Food in the refrigerator" refers to all food and ingredients stored in the refrigerator.

[0012] "Identifying" refers to identifying and selecting one in particular from multiple options or candidates.

[0013] "Generative AI" refers to algorithms or systems that use artificial intelligence techniques to generate new data or information (e.g., recipes).

[0014] A "recipe" refers to information that includes instructions and a list of ingredients for making a particular dish.

[0015] "Providing" refers to making a service or information available to a user.

[0016] "Inventory status" refers to the latest data regarding the quantity and type of ingredients, products, etc. currently in stock.

[0017] "Management" refers to planning, organizing, and monitoring information and resources to achieve specific objectives.

[0018] "Automatically" means that the system or machine performs the action on its own, without the need for human intervention. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

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

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The purpose of this invention is to realize a system that acquires ingredient information entered by a user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user. This system is designed to support inventory management in restaurants and diversify cooking at home.

[0041] The program and processing of this system can be explained as follows.

[0042] Program processing

[0043] Users can take a photo of the inside of their refrigerator and upload it to the system using their smartphone or tablet. At the same time, they can also manually enter ingredient information. The device then sends the captured image or manually entered ingredient information to the server.

[0044] The server launches an AI image analysis module to analyze the image sent. This module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the list as is.

[0045] Next, the server launches a generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list. This generation process also takes into account the user's preferences and allergy information. The server then sends the generated recipes to the terminal to be provided to the user.

[0046] Examples:

[0047] When a user takes a photo of the contents of their refrigerator with their smartphone and uploads it, the server analyzes the image and identifies chicken, carrots, and cabbage.The server then uses generative AI to generate recipes such as "Chicken and Carrot Stew" or "Cabbage and Chicken Stir-fry" from these ingredients and notifies the user of these recipes.The user then creates a dish based on the suggested recipes.

[0048] As a function for restaurants, the server can link with the restaurant's inventory management system and update the stock status of ingredients in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and requests a "grilled dish," the server generates an optimal recipe based on the generative AI and sends it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[0049] Furthermore, it also makes effective use of discarded food ingredients. When restaurants and households send data on food ingredients that are scheduled to be discarded to the server, the server uses generative AI to generate recipes based on these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[0050] To prevent overbuying, the server periodically checks the food data in the user's refrigerator, generates warning messages about duplicate or unused food items, and sends them to the device. This function reduces food waste and allows for proper food management.

[0051] As described above, this system offers a wide range of functions, is highly convenient for users, and enables effective ingredient management and recipe provision. It can also contribute to reducing food waste.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to their device via the app.

[0055] Step 2:

[0056] The device uploads the saved image to the server. At this time, even if the user manually inputs ingredient information, the data is also sent to the server.

[0057] Step 3:

[0058] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[0059] Step 4:

[0060] The server receives the analysis results from the AI ​​image analysis module and stores the list of identified ingredients (e.g., "chicken," "carrots," and "cabbage") in a database.

[0061] Step 5:

[0062] The server launches the generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list.

[0063] Step 6:

[0064] The server compares the user's preference information and allergy information with the generated recipes and selects the most suitable recipe.

[0065] Step 7:

[0066] The server transmits the selected recipe list to the user's terminal.

[0067] Step 8:

[0068] The terminal displays the received recipe list to the user, and the user selects from the suggested recipes and starts cooking.

[0069] Step 9:

[0070] The restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time.

[0071] Step 10:

[0072] The server generates optimal recipes based on restaurant inventory data to accommodate mobile orders from users.

[0073] Step 11:

[0074] The kitchen terminal of the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[0075] Step 12:

[0076] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[0077] Step 13:

[0078] The server uses AI to generate recipes that can be effectively used based on ingredients that are scheduled to be discarded, and notifies affiliated bento shops.

[0079] Step 14:

[0080] The server periodically checks the food ingredient data in the user's refrigerator and generates a warning message about duplicate or unused food ingredients.

[0081] Step 15:

[0082] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] In modern society, food management has become increasingly complex in homes and restaurants, and efficient inventory management and recipe selection are required. In particular, it is a challenge to provide optimal cooking methods that take into account the user's preferences and allergies while minimizing food waste.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes a means for acquiring ingredient information entered by the user, a means for identifying ingredients in the storage device through image analysis, a means for generating multiple recipes using a generation AI based on the identified ingredients, and a means for providing the generated recipes to the user, thereby improving the efficiency of ingredient management and making it possible to provide optimal recipes that take into account the user's preferences and allergies.

[0088] "User" refers to any individual or entity that uses the System.

[0089] "Food information" refers to data such as the type, quantity, and expiration date of food stored in a refrigerator or storage device.

[0090] "Storage equipment" refers to equipment such as refrigerators, freezers, and pantries for storing food ingredients.

[0091] "Image analysis" refers to the technology of analyzing image data captured by a camera or smartphone and recognizing specific objects (e.g., food ingredients) contained within it.

[0092] "Generative AI" refers to artificial intelligence that generates new information or content (e.g., cooking methods) based on specified input data.

[0093] "Cooking instructions" refers to recipes that describe how to prepare a dish based on specific ingredients.

[0094] "Preference information" is data relating to the user's preferences, including preferences for seasonings and ingredients of specific dishes.

[0095] "Allergy Information" means data regarding specific ingredients to which a user is allergic.

[0096] "Stock status" refers to information such as the quantity and type of ingredients stored in the storage device.

[0097] "Inventory data" means data that records inventory status.

[0098] This system allows users to efficiently manage ingredient information stored in a storage device and provides optimal recipes using a generative AI model. This system aims to support ingredient inventory management and recipe selection, particularly in homes and restaurants.

[0099] System configuration

[0100] User actions

[0101] Users can use the camera on their smartphone or tablet to take photos of ingredients in their refrigerator or storage unit, then upload the images to the system via their device. Users can also manually enter ingredient information.

[0102] Terminal handling

[0103] The device sends the image acquired from the user or the manually entered ingredient information to the server. When uploading the image, a network communication method such as an HTTP POST request is used.

[0104] Server Processing

[0105] The server launches an AI image analysis module (e.g., TensorFlow, OpenCV) to analyze the received image data. This image analysis module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the ingredient list as is.

[0106] Next, the server launches a generative AI module (e.g., GPT-3, BERT) and provides it with the identified ingredient list and the user's preference and allergy information as input. The generative AI module generates multiple recipes based on the input data. The generated recipes are sent from the server to the device and provided to the user.

[0107] Hardware and software used

[0108] This system uses the following hardware and software:

[0109] Hardware: smartphones, tablets, servers

[0110] Software: TensorFlow for image analysis, OpenCV, GPT-3 for generative AI, BERT, network library for HTTP communication

[0111] Specific examples

[0112] 1. The user takes a photo of the inside of the refrigerator with their smartphone and uploads the image to the server via the application.

[0113] 2. The server uses TensorFlow to analyze the image and identify chicken, carrots, and cabbage.

[0114] 3. The server inputs the following prompt to GPT-3: "Could you come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy."

[0115] 4. Recipes generated by GPT-3, such as "Chicken and carrot stew" or "Cabbage and chicken stir-fry," are sent to the user's device.

[0116] 5. Users can create dishes based on these recipes.

[0117] This system, configured in this way, not only provides convenience to users but also contributes to effective ingredient management and the reduction of food waste. For restaurants, linking it to an inventory management system will enable real-time updates of inventory status, which is expected to lead to more efficient operations.

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

[0119] Step 1:

[0120] The user takes a photo of the inside of the refrigerator using the camera on their smartphone or tablet. The user then launches the camera app and takes a photo of the food from any position within the storage device. The captured image is saved to the device's photo library.

[0121] Input: Image taken with the camera app

[0122] Output: Image files saved in the device's photo library

[0123] Step 2:

[0124] The user opens the application on the device, selects the image they have taken, and presses the upload button. The user then clicks the "Upload Image" button in the application and selects the image file they have just taken from the file selection dialog. The selected image is then sent to the server via the Internet.

[0125] Input: An image file selected by the user.

[0126] Output: Image data sent to the server

[0127] Step 3:

[0128] The server launches an AI image analysis module to analyze the image data it receives. The server saves the image data received via the HTTP request in a specified directory, and launches an image analysis library such as TensorFlow or OpenCV with the path as an argument.

[0129] Input: Image data received via HTTP request

[0130] Output: Image analysis module is launched

[0131] Step 4:

[0132] The server uses an image analysis module to identify ingredients in the image. The module uses an object detection algorithm (e.g., YOLO, SSD) to identify the ingredients in the image and generate a list of items such as "chicken," "carrot," and "cabbage." The server outputs the location and label of each ingredient in the image as the analysis result.

[0133] Input: The path of the image file passed to the image analysis module

[0134] Output: List of identified ingredients (e.g. "chicken", "carrot", "cabbage")

[0135] Step 5:

[0136] The server starts the generation AI module and provides the identified ingredients list and the user's preference and allergy information as input. The server generates a prompt and calls the GPT-3 or BERT API to request recipe generation.

[0137] Input: List of identified ingredients, user preferences and allergy information

[0138] Output: The generative AI module is triggered

[0139] Step 6:

[0140] The generative AI module generates recipes. For example, it responds to a prompt such as, "Could you think of a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy." It then generates and returns multiple recipes in JSON format.

[0141] Input: Prompt text (e.g., "Could you please come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy.")

[0142] Output: The generated recipe (e.g. "Chicken and carrot stew", "Cabbage and chicken stir fry")

[0143] Step 7:

[0144] The server sends the generated recipe to the terminal. The generated recipe is sent to the terminal in JSON format, and the terminal receives it and displays it on the user interface.

[0145] Input: JSON data of the recipe returned by the generation AI module

[0146] Output: Sends JSON data to the terminal and displays it in the user interface.

[0147] Through each of the above steps, users can effectively manage ingredients and easily obtain multiple cooking methods using the generative AI model.

[0148] (Application example 1)

[0149] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0150] Conventional systems were able to suggest recipes based on food stored in a home storage device, but no system existed that could instantly analyze food combinations purchased in stores and suggest appropriate recipes to consumers. As a result, when consumers purchased food in stores, they sometimes did not know how to cook the food, which discouraged their desire to purchase it. In addition, there were insufficient methods for managing food inventory in stores and for effectively utilizing discarded food. A new system was needed to solve these problems.

[0151] 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.

[0152] In this invention, the server includes a means for acquiring ingredient information entered by a user, a means for identifying foods in the storage device through image analysis, a means for generating multiple recipe suggestions using AI based on the identified foods, a means for providing the generated recipe suggestions to the user, and a means for customers to acquire and analyze images of food on shelves in a store and provide recipe suggestions. This enables optimal recipe suggestions based on food at home and in stores. It also effectively manages food inventory in stores and reduces food waste.

[0153] The "means for acquiring ingredient information entered by the user" is a function that allows ingredient information manually entered by the user using a smartphone, tablet device, etc. to be sent to the server, and for that information to be received by the system.

[0154] "Means for identifying food in a storage device through image analysis" refers to a function that processes photographic data taken by a user in a storage device using an image analysis algorithm to automatically recognize and identify food in the photograph.

[0155] "Means for generating multiple dish suggestions using generative AI based on identified foods" refers to a function that automatically generates multiple dish suggestions using a generative AI model based on a food list obtained through image analysis or user input.

[0156] The "means for providing the generated recipe suggestions to the user" is a function that notifies the user's terminal of the recipe suggestions generated by the system, allowing the user to view the information.

[0157] "A means for customers to acquire, analyze, and suggest dishes from images of food on store shelves" refers to a function that allows customers to take photos of store shelves with their smartphones and upload those images to the system, which then identifies and analyzes the food on the shelves and generates and provides optimal dish suggestions based on the results.

[0158] The system that realizes this application example automatically recognizes and analyzes food items in refrigerators and on store shelves, and then makes recipe suggestions based on that information. The system consists of a user terminal, an image analysis module, a generative AI module, and a server.

[0159] First, users take a photo of the storage device or store shelves using their smartphone or tablet device, and then upload the photo to the server. Users can also manually enter ingredient information. The server uses an image analysis module to identify foods based on the provided photo. High-performance analysis algorithms such as OpenCV and YOLOv3 are used for image analysis.

[0160] After the food items are identified, the server passes this information to a generative AI module, which then makes recipe suggestions based on food information in supermarkets and home storage devices. For this purpose, a natural language generation model such as GPT-2 is used as the generative AI model. The generated recipe suggestions also take into account the user's preferences and allergies. The server then sends the generated recipe suggestions to the user's device, where they can be viewed by the user.

[0161] As a concrete example, consider the following case:

[0162] 1. A customer takes a photo of a supermarket shelf with their smartphone, opens the application and uploads the photo.

[0163] 2. The server analyzes the image and identifies tomatoes, chicken, cabbage, etc.

[0164] 3. The generative AI module generates dish suggestions based on these ingredients, such as "chicken stew with tomatoes."

[0165] 4. The recipe suggestions are sent to the user's device, and the user can then purchase the food based on the suggestions.

[0166] An example of a prompt for a generative AI model is:

[0167] Generate a recipe using the following ingredients: chicken, tomatoes, carrots, cabbage, and onions.

[0168] This system allows users to instantly receive appropriate recipe suggestions based on the food they have in stores or at home, contributing to increased purchasing motivation and reduced food waste.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] A user uses a smartphone or tablet to take a photo of the storage device or the shelves in the store. This photo becomes the input data. The user can also manually input ingredient information. The input data includes image data and manually entered ingredient information.

[0172] Step 2:

[0173] The terminal transmits the photos taken by the user and the food ingredient information entered by the user to the server. In this transmission process, image data and manually entered text data are sent to the server.

[0174] Step 3:

[0175] The server passes the received image data to an image analysis module, which uses algorithms such as OpenCV and YOLOv3. The image analysis module identifies each ingredient in the image. As a result of the analysis, a list of identified ingredients is generated.

[0176] Step 4:

[0177] If there is any manually entered ingredient information, the server adds it to the ingredient list as is. The final ingredient list is completed. The output at this stage is the identified ingredient list.

[0178] Step 5:

[0179] The server passes the identified ingredient list to a generative AI module, which uses a pre-trained generative AI model (e.g., GPT-2) to generate multiple recipe suggestions. In this process, the ingredient list is used as input, and the generative AI outputs a recipe based on it.

[0180] Step 6:

[0181] The server selects the most suitable recipe from multiple recipe suggestions generated based on the user's preferences and allergies. This selection process uses a filtering function to output a list of recipes that suit the user.

[0182] Step 7:

[0183] The server sends the optimal recipe suggestions to the user device, which then notifies the user and makes the information available for viewing. The final output is a recipe suggestion that is displayed on the user device.

[0184] Step 8:

[0185] Users can then take the suggestions provided, select the appropriate ingredients, and prepare their meal, which will increase purchasing motivation and encourage behavior that contributes to reducing food waste.

[0186] 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.

[0187] This invention is a system that acquires ingredient information entered by the user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user, in addition to a system that combines an emotion engine that recognizes the user's emotions. This system is designed to realize inventory management for restaurants, diversify cooking at home, and respond to user emotions.

[0188] Program processing

[0189] The program process in this system begins when the user takes a photo of the inside of the refrigerator and uploads the image and their emotional state to the system via their terminal. The user can also manually input ingredient information, and simultaneously use the emotion engine to obtain their current emotional state (e.g., joy, sadness, stress).

[0190] The specific program process is as follows:

[0191] Users can take pictures of the inside of their refrigerator using their smartphones, and the image data is saved on the device using the app. Users can also manually enter ingredient information and simultaneously input emotions by launching an emotion engine within the app.

[0192] The device uploads the saved images and manually entered data to the server, along with the emotion data.

[0193] The server launches an AI image analysis module to analyze the received image, which identifies the ingredients in the image and generates a list of ingredients such as "chicken," "carrots," and "cabbage."

[0194] The server receives the ingredient list as the analysis result and stores it in a database. It also records the received emotion data.

[0195] The server then launches a generative AI module, which receives the identified ingredient list and emotional data as input. The generative AI generates multiple recipes based on the ingredient list and emotional data. For example, if the user is recognized as "tired," a particularly easy and relaxing recipe is generated.

[0196] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in the selection of a recipe that is most appropriate for the user.

[0197] The server sends the selected recipe list to the user's terminal.

[0198] The device displays the received recipe list to the user, who can then select a recipe from the suggested recipes and begin cooking.

[0199] As a function for restaurants, the restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and indicates "stress," the AI ​​generator will suggest a recipe with a particularly relaxing effect and send it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[0200] Furthermore, it also enables the effective use of discarded food ingredients. When food data for food items to be discarded is sent to the server from restaurants and households, the server uses generative AI to generate recipes that can effectively use these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[0201] To prevent overbuying, the server periodically checks the food data in the user's refrigerator and generates and sends warning messages to the device about duplicate or unused food items. This function reduces food waste and allows for proper food management.

[0202] By incorporating user emotion recognition, this system goes beyond simply proposing recipes and can also suggest optimal ways to use ingredients and dishes based on the user's emotional state, thereby increasing the user's psychological satisfaction and supporting a healthier diet.

[0203] The processing flow will be explained below.

[0204] Step 1:

[0205] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to the device through the app. At the same time, the app activates an emotion engine and inputs the user's current emotional state (e.g., joy, stress, etc.).

[0206] Step 2:

[0207] The device uploads the saved images, emotion data, and manually entered ingredient information to the server, along with the user's emotion information.

[0208] Step 3:

[0209] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[0210] Step 4:

[0211] The server receives the analysis results from the AI ​​image analysis module and stores the identified ingredients (e.g., "chicken," "carrot," "cabbage") in a database. The received emotion data is also recorded at the same time.

[0212] Step 5:

[0213] The server launches a generative AI module, which receives the identified ingredients and the user's emotional data as input. The generative AI generates multiple recipes based on this data.

[0214] Step 6:

[0215] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in a recipe that is more suitable for the user.

[0216] Step 7:

[0217] The server transmits the selected recipe list to the terminal.

[0218] Step 8:

[0219] The device displays the received recipe list to the user, who then selects a recipe from the suggested recipes and begins cooking.

[0220] As a concrete example, if a user is recognized as being in a "stressed" state and there are "chicken," "carrots," and "cabbage" in the refrigerator, the generative AI will suggest recipes that are effective in reducing stress, such as "easy stewed chicken and carrots."

[0221] Step 9:

[0222] A restaurant's inventory management system periodically sends inventory data to a server and updates the database in real time.

[0223] Step 10:

[0224] A user inputs his / her preferences for ingredients and dishes and his / her emotional state through the mobile ordering service and sends an order request to the server.

[0225] Step 11:

[0226] The server uses generative AI to select the optimal recipe based on the order request and inventory data, and sends it to the restaurant's kitchen terminal.

[0227] Step 12:

[0228] The kitchen terminal in the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[0229] Step 13:

[0230] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[0231] Step 14:

[0232] The server uses AI to generate recipes that can be effectively used based on data on ingredients that are scheduled to be discarded, and notifies the system of affiliated bento shops of these recipes.

[0233] Step 15:

[0234] The server periodically checks the food ingredient data in the user's refrigerator, generates warning messages about duplicated or unused food ingredients, and sends them to the terminal.

[0235] Step 16:

[0236] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[0237] Example 2

[0238] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0239] In recent years, the effective use and management of ingredients has become increasingly important in homes and restaurants. However, conventional recipe suggestion systems have difficulty in proposing recipes that take into account the user's emotional state, and they are unable to handle ingredient inventory management and allergy information in an integrated manner. Therefore, there is a need for an efficient system that provides optimal recipes that reflect the user's emotional state and preference information, and also includes ingredient inventory management.

[0240] 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.

[0241] In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients and the user's emotional state, and means for providing the generated recipes to the user. This enables efficient ingredient management by integrating optimal recipe suggestions that take the user's emotional state into consideration and ingredient inventory management and allergy information.

[0242] "Ingredient information" is data about the food and ingredients present in the refrigerator, which is manually entered by the user or obtained through image analysis.

[0243] "Image analysis" is the process by which an AI module recognizes and identifies specific ingredients from images taken with a camera or smartphone.

[0244] "Generative AI" refers to artificial intelligence that generates new information (in this case, recipes) based on input data, typically using natural language processing techniques.

[0245] "Emotional state" is data that indicates the type of emotion the user is currently feeling (e.g., stress, fatigue, joy).

[0246] "Preference information" is information about the types of foods the user likes and foods they want to avoid.

[0247] "Allergy information" is information about the user's food allergies, specifically a list of ingredients that may cause allergies.

[0248] "Inventory control" is the process of monitoring and managing the quantity and type of food ingredients stored in refrigerators and within a restaurant.

[0249] A "recipe" is a list of instructions or ingredients for making a dish using specific ingredients.

[0250] A "prompt sentence" is an input sentence that provides specific information to the generative AI and produces a desired output.

[0251] "Terminal" means a hardware device (e.g., smartphone, tablet, or PC) used by a User to access the System.

[0252] The "database" is a system for efficiently storing and managing information such as ingredients, emotional state, preference information, allergy information, and inventory data.

[0253] The present invention is a system in which a user inputs information about ingredients in the refrigerator and their emotional state into the system, and a generation AI generates and provides multiple recipes based on that information. This system is designed to handle inventory management for restaurants, the diversification of home cooking, and the user's emotions. Below, we will explain in detail how to implement this system.

[0254] First, the user takes a photo of the contents of the refrigerator using a device such as a smartphone. This image data is then saved on the device using a dedicated app. The user can also manually enter information about ingredients, such as "two carrots and 300g of chicken." At the same time, the user can input their current emotional state (e.g., "stressed" or "tired") using the emotion engine built into the app.

[0255] The device then uploads the stored image data, manually entered ingredient information, and emotion data to a server using the HTTPS protocol, and the data may be compressed before transmission.

[0256] The server launches an AI image analysis module (e.g., Google Cloud Vision API) to analyze the received image data. This module identifies ingredients in the image and generates a list of ingredients, such as "chicken," "carrot," and "cabbage." The analysis results are returned to the server in JSON format.

[0257] The server then stores the ingredient list and emotion data resulting from this analysis in a database, which stores ingredient information, emotion data, user preference information, allergy information, and other information.

[0258] The server runs a generative AI (e.g., OpenAI GPT-4) that generates multiple recipes based on the identified ingredients and emotional data. Example prompts include:

[0259] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[0260] Based on this prompt, the AI ​​generates recipes such as "chicken and carrot soup" or "cabbage and chicken stir-fry." The server filters the generated recipes based on the user's preferences and allergies to select the most suitable recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded.

[0261] The selected recipe list is sent from the server to the device in JSON format, which the device parses and displays to the user. The user can then select a recipe from the displayed list and start cooking.

[0262] It also has functions for restaurants, and the inventory management system periodically sends inventory data to the server, allowing for real-time inventory management. The created recipes are also sent to devices used in the restaurant's kitchen, allowing for efficient food preparation.

[0263] In this way, the present invention is a system that provides optimal recipes by utilizing the user's emotional state and information about ingredients in the refrigerator, thereby improving the efficiency of ingredient management and diversifying cooking options. Furthermore, by selecting recipes that reflect food allergies and preferences, it is possible to increase user satisfaction.

[0264] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0265] Step 1:

[0266] User takes a photo of the inside of the refrigerator

[0267] The user takes a photo of the inside of the refrigerator using their smartphone. This image data is saved on the device using a dedicated app. The input is the photo of the inside of the refrigerator, and the output is the saved image data.

[0268] Step 2:

[0269] Input of ingredient information and emotion data

[0270] The user manually inputs ingredient information into the app, such as "2 carrots, 300g of chicken," and then uses the app's emotion engine to input their current emotional state (e.g., "stressed"). The input is the manually entered ingredient information and emotion data, and the output is the saved ingredient information and emotion data.

[0271] Step 3:

[0272] Uploading image data and input data

[0273] The device uploads the stored image data, manually entered ingredient information, and emotion data to the server. The upload uses the HTTPS protocol, and the data may be compressed. The input is the image data, ingredient information, and emotion data, and the output is the data sent to the server.

[0274] Step 4:

[0275] Identifying ingredients through image analysis

[0276] The server performs image analysis using the Google Cloud Vision API. Through this analysis, it recognizes ingredients in the image and generates a list of ingredients such as "chicken," "carrot," and "cabbage." The input is the uploaded image data, and the output is the list of ingredients.

[0277] Step 5:

[0278] Saving to a database

[0279] The server stores the ingredient list and emotional data as the analysis results in a database. The data includes ingredient information, emotional data, user preference information, allergy information, etc. The input is the generated ingredient list and emotional data, and the output is the data stored in the database.

[0280] Step 6:

[0281] Recipe Generation

[0282] The server runs a generative AI (e.g., OpenAI GPT-4) to generate multiple recipes using the identified ingredients list and emotion data. Example prompts include:

[0283] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[0284] The input is an ingredient list and emotion data, and the output is the generated recipe.

[0285] Step 7:

[0286] Recipe Selection

[0287] The server filters the generated recipes taking into account the user's preference and allergy information to select the optimal recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded. The input is the generated recipe and the user's preference and allergy information, and the output is the selected optimal recipe.

[0288] Step 8:

[0289] Recipe provided

[0290] The server sends the selected recipe list in JSON format to the terminal, which parses it and displays it to the user. The user can select a recipe from the displayed recipe and start cooking. The input is the selected recipe list, and the output is the recipe displayed on the terminal.

[0291] (Application example 2)

[0292] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0293] In conventional restaurants, it has been difficult to properly manage ingredients in the refrigerator and efficiently check inventory status. In addition, recipe suggestions based on emotions are rare, making it difficult to provide dishes that take into account the emotional state of the customer. This has led to a decline in customer satisfaction and the need for more efficient ingredient management.

[0294] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients, means for providing the generated recipes to the user, means for recognizing the user's emotions, and means for selecting an appropriate recipe based on the emotion data. This improves the efficiency of ingredient management in the refrigerator and enables optimal recipe suggestions based on the customer's emotions.

[0295] The "means for acquiring ingredient information entered by the user" is a function for collecting information about ingredients provided by the user manually or digitally.

[0296] "Means for identifying ingredients in a refrigerator through image analysis" refers to a technology for analyzing images of ingredients in a refrigerator and identifying the type of ingredients.

[0297] "Means for generating multiple recipes using generative AI based on identified ingredients" refers to a function that automatically generates multiple recipes using generative AI based on ingredient information identified through image analysis.

[0298] "Means for providing the generated recipe to the user" refers to means for providing the recipe generated by the generation AI in a form that the user can use.

[0299] The "means for recognizing user's emotions" is a function for recognizing and analyzing the user's current emotional state (e.g., joy, sadness, stress).

[0300] The "means for selecting an appropriate recipe based on emotional data" is a technology that takes into consideration the recognized emotional data of a user and selects a recipe that is appropriate for that emotional state.

[0301] "Means for selecting an optimal recipe taking into consideration user preference information and allergy information" refers to a technology that refers to information about a user's individual preferences and allergies and selects an optimal recipe.

[0302] "Means for managing food ingredient inventory and automatically linking inventory data" refers to a management system that monitors food ingredient inventory and automatically links the necessary information to a database, etc.

[0303] This invention is a system for efficiently managing ingredients and proposing recipes in restaurants and homes.

[0304] The user starts by taking a photo of the ingredients in the refrigerator using a device such as a smartphone. The device then uploads the captured image data and the ingredient information manually entered by the user to the server. The user also inputs their current emotional state (e.g., joy, sadness, stress) using the emotion engine.

[0305] The server then launches an AI image analysis module (such as OpenCV) on the received image data to identify the ingredients in the refrigerator. This generates an ingredient list, such as "chicken," "carrots," and "cabbage." The server then stores this ingredient list as a result of this analysis in a database, and simultaneously records the received emotion data.

[0306] Next, the server invokes a generative AI model (e.g., HuggingFace's Transformer library) and provides the identified ingredient list and emotion data as input. This generative AI generates prompts based on the given ingredient list and emotion data, and generates multiple recipes. For example, if the user is recognized as "stressed," a particularly easy and relaxing recipe is generated.

[0307] The generated recipes are compared with the user's preference and allergy information to select the most suitable recipe. The selected recipe list is sent to the user's device, and the user can choose from the suggested recipes and start cooking.

[0308] As a concrete example, the following prompt is input to the generator AI:

[0309] "Generate recipes using chicken, carrots, and cabbage when you're feeling stressed."

[0310] Another example of application for restaurants is that store employees can take photos of the inside of the refrigerator with their smartphones and upload them to an app, which can help streamline inventory management. If an employee feels tired, the generative AI can suggest a relaxing recipe, such as "Easy Chicken and Cabbage Consommé Soup," which can then be immediately made available on the menu.

[0311] In this way, by combining emotion recognition with ingredient information, it becomes possible to suggest recipes that meet the user's psychological and physical needs, thereby improving customer satisfaction and streamlining ingredient management.

[0312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0313] Step 1:

[0314] The user takes a photo of the contents of the refrigerator using a smartphone and manually inputs the ingredients. This data is stored on the smartphone, and the user also inputs their current emotional state (e.g., stress, joy) through the device. The input data includes the photo data, manually input ingredients, and emotional data.

[0315] Step 2:

[0316] The device uploads the photo data, manually entered ingredient information, and emotion data entered by the user to the server, which then sends the data as a package to the server, where it is stored.

[0317] Step 3:

[0318] The server passes the received photo data to an AI image analysis module to identify the ingredients in the refrigerator. This analysis process uses an image processing library such as OpenCV to generate a list of ingredients such as "chicken," "carrots," and "cabbage." The input data is the photo data, and the output data is the list of identified ingredients.

[0319] Step 4:

[0320] The server stores the identified ingredient list in a database and simultaneously records the received emotion data. This recorded data is used for later recipe generation. The input data is the ingredient list and emotion data, and the output data is the result stored in the database.

[0321] Step 5:

[0322] The server inputs the saved ingredient list and emotion data into a generative AI model to generate an appropriate recipe. Using a generative AI model (e.g., HuggingFace's Transformer library), a prompt based on the ingredient list and emotion data is generated, and the recipe is generated by sending the prompt to the model. The input data is the ingredient list and emotion data, and the output data is the generated recipe list. Example: Prompt: "Please generate a recipe using chicken, carrots, and cabbage for when I'm feeling stressed."

[0323] Step 6:

[0324] The server compares the generated recipe list with the user's preference and allergy information to select the most suitable recipe. In this comparison process, the server compares the user information in the database with the generated recipes to select the most suitable candidates. The input data is the generated recipe list and the user's preference and allergy information, and the output data is the list of suitable recipes.

[0325] Step 7:

[0326] The server sends the optimal recipe list to the user's device. The user can view the received recipe list through the device, select a desired recipe, and start cooking. The input data is the optimal recipe list, and the output data is the recipe list displayed on the user's device.

[0327] In this way, a system is constructed that can suggest optimal recipes based on the user's emotional state and ingredient information.

[0328] 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.

[0329] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0330] 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.

[0331] [Second embodiment]

[0332] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0333] 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.

[0334] 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).

[0335] 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.

[0336] 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.

[0337] 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).

[0338] 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.

[0339] 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.

[0340] 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.

[0341] 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.

[0342] 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.

[0343] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0344] The purpose of this invention is to realize a system that acquires ingredient information entered by a user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user. This system is designed to support inventory management in restaurants and diversify cooking at home.

[0345] The program and processing of this system can be explained as follows.

[0346] Program processing

[0347] Users can take a photo of the inside of their refrigerator and upload it to the system using their smartphone or tablet. At the same time, they can also manually enter ingredient information. The device then sends the captured image or manually entered ingredient information to the server.

[0348] The server launches an AI image analysis module to analyze the image sent. This module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the list as is.

[0349] Next, the server launches a generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list. This generation process also takes into account the user's preferences and allergy information. The server then sends the generated recipes to the terminal to be provided to the user.

[0350] Examples:

[0351] When a user takes a photo of the contents of their refrigerator with their smartphone and uploads it, the server analyzes the image and identifies chicken, carrots, and cabbage.The server then uses generative AI to generate recipes such as "Chicken and Carrot Stew" or "Cabbage and Chicken Stir-fry" from these ingredients and notifies the user of these recipes.The user then creates a dish based on the suggested recipes.

[0352] As a function for restaurants, the server can link with the restaurant's inventory management system and update the stock status of ingredients in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and requests a "grilled dish," the server generates an optimal recipe based on the generative AI and sends it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[0353] Furthermore, it also makes effective use of discarded food ingredients. When restaurants and households send data on food ingredients that are scheduled to be discarded to the server, the server uses generative AI to generate recipes based on these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[0354] To prevent overbuying, the server periodically checks the food data in the user's refrigerator, generates warning messages about duplicate or unused food items, and sends them to the device. This function reduces food waste and allows for proper food management.

[0355] As described above, this system offers a wide range of functions, is highly convenient for users, and enables effective ingredient management and recipe provision. It can also contribute to reducing food waste.

[0356] The processing flow will be explained below.

[0357] Step 1:

[0358] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to their device via the app.

[0359] Step 2:

[0360] The device uploads the saved image to the server. At this time, even if the user manually inputs ingredient information, the data is also sent to the server.

[0361] Step 3:

[0362] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[0363] Step 4:

[0364] The server receives the analysis results from the AI ​​image analysis module and stores the list of identified ingredients (e.g., "chicken," "carrots," and "cabbage") in a database.

[0365] Step 5:

[0366] The server launches the generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list.

[0367] Step 6:

[0368] The server compares the user's preference information and allergy information with the generated recipes and selects the most suitable recipe.

[0369] Step 7:

[0370] The server transmits the selected recipe list to the user's terminal.

[0371] Step 8:

[0372] The terminal displays the received recipe list to the user, and the user selects from the suggested recipes and starts cooking.

[0373] Step 9:

[0374] The restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time.

[0375] Step 10:

[0376] The server generates optimal recipes based on restaurant inventory data to accommodate mobile orders from users.

[0377] Step 11:

[0378] The kitchen terminal of the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[0379] Step 12:

[0380] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[0381] Step 13:

[0382] The server uses AI to generate recipes that can be effectively used based on ingredients that are scheduled to be discarded, and notifies affiliated bento shops.

[0383] Step 14:

[0384] The server periodically checks the food ingredient data in the user's refrigerator and generates a warning message about duplicate or unused food ingredients.

[0385] Step 15:

[0386] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[0387] Example 1

[0388] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0389] In modern society, food management has become increasingly complex in homes and restaurants, and efficient inventory management and recipe selection are required. In particular, it is a challenge to provide optimal cooking methods that take into account the user's preferences and allergies while minimizing food waste.

[0390] 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.

[0391] In this invention, the server includes a means for acquiring ingredient information entered by the user, a means for identifying ingredients in the storage device through image analysis, a means for generating multiple recipes using a generation AI based on the identified ingredients, and a means for providing the generated recipes to the user, thereby improving the efficiency of ingredient management and making it possible to provide optimal recipes that take into account the user's preferences and allergies.

[0392] "User" refers to any individual or entity that uses the System.

[0393] "Food information" refers to data such as the type, quantity, and expiration date of food stored in a refrigerator or storage device.

[0394] "Storage equipment" refers to equipment such as refrigerators, freezers, and pantries for storing food ingredients.

[0395] "Image analysis" refers to the technology of analyzing image data captured by a camera or smartphone and recognizing specific objects (e.g., food ingredients) contained within it.

[0396] "Generative AI" refers to artificial intelligence that generates new information or content (e.g., cooking methods) based on specified input data.

[0397] "Cooking instructions" refers to recipes that describe how to prepare a dish based on specific ingredients.

[0398] "Preference information" is data relating to the user's preferences, including preferences for seasonings and ingredients of specific dishes.

[0399] "Allergy Information" means data regarding specific ingredients to which a user is allergic.

[0400] "Stock status" refers to information such as the quantity and type of ingredients stored in the storage device.

[0401] "Inventory data" means data that records inventory status.

[0402] This system allows users to efficiently manage ingredient information stored in a storage device and provides optimal recipes using a generative AI model. This system aims to support ingredient inventory management and recipe selection, particularly in homes and restaurants.

[0403] System configuration

[0404] User actions

[0405] Users can use the camera on their smartphone or tablet to take photos of ingredients in their refrigerator or storage unit, then upload the images to the system via their device. Users can also manually enter ingredient information.

[0406] Terminal handling

[0407] The device sends the image acquired from the user or the manually entered ingredient information to the server. When uploading the image, a network communication method such as an HTTP POST request is used.

[0408] Server Processing

[0409] The server launches an AI image analysis module (e.g., TensorFlow, OpenCV) to analyze the received image data. This image analysis module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the ingredient list as is.

[0410] Next, the server launches a generative AI module (e.g., GPT-3, BERT) and provides it with the identified ingredient list and the user's preference and allergy information as input. The generative AI module generates multiple recipes based on the input data. The generated recipes are sent from the server to the device and provided to the user.

[0411] Hardware and software used

[0412] This system uses the following hardware and software:

[0413] Hardware: smartphones, tablets, servers

[0414] Software: TensorFlow for image analysis, OpenCV, GPT-3 for generative AI, BERT, network library for HTTP communication

[0415] Specific examples

[0416] 1. The user takes a photo of the inside of the refrigerator with their smartphone and uploads the image to the server via the application.

[0417] 2. The server uses TensorFlow to analyze the image and identify chicken, carrots, and cabbage.

[0418] 3. The server inputs the following prompt to GPT-3: "Could you come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy."

[0419] 4. Recipes generated by GPT-3, such as "Chicken and carrot stew" or "Cabbage and chicken stir-fry," are sent to the user's device.

[0420] 5. Users can create dishes based on these recipes.

[0421] This system, configured in this way, not only provides convenience to users but also contributes to effective ingredient management and the reduction of food waste. For restaurants, linking it to an inventory management system will enable real-time updates of inventory status, which is expected to lead to more efficient operations.

[0422] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] The user takes a photo of the inside of the refrigerator using the camera on their smartphone or tablet. The user then launches the camera app and takes a photo of the food from any position within the storage device. The captured image is saved to the device's photo library.

[0425] Input: Image taken with the camera app

[0426] Output: Image files saved in the device's photo library

[0427] Step 2:

[0428] The user opens the application on the device, selects the image they have taken, and presses the upload button. The user then clicks the "Upload Image" button in the application and selects the image file they have just taken from the file selection dialog. The selected image is then sent to the server via the Internet.

[0429] Input: An image file selected by the user.

[0430] Output: Image data sent to the server

[0431] Step 3:

[0432] The server launches an AI image analysis module to analyze the image data it receives. The server saves the image data received via the HTTP request in a specified directory, and launches an image analysis library such as TensorFlow or OpenCV with the path as an argument.

[0433] Input: Image data received via HTTP request

[0434] Output: Image analysis module is launched

[0435] Step 4:

[0436] The server uses an image analysis module to identify ingredients in the image. The module uses an object detection algorithm (e.g., YOLO, SSD) to identify the ingredients in the image and generate a list of items such as "chicken," "carrot," and "cabbage." The server outputs the location and label of each ingredient in the image as the analysis result.

[0437] Input: The path of the image file passed to the image analysis module

[0438] Output: List of identified ingredients (e.g. "chicken", "carrot", "cabbage")

[0439] Step 5:

[0440] The server starts the generation AI module and provides the identified ingredients list and the user's preference and allergy information as input. The server generates a prompt and calls the GPT-3 or BERT API to request recipe generation.

[0441] Input: List of identified ingredients, user preferences and allergy information

[0442] Output: The generative AI module is triggered

[0443] Step 6:

[0444] The generative AI module generates recipes. For example, it responds to a prompt such as, "Could you think of a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy." It then generates and returns multiple recipes in JSON format.

[0445] Input: Prompt text (e.g., "Could you please come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy.")

[0446] Output: The generated recipe (e.g. "Chicken and carrot stew", "Cabbage and chicken stir fry")

[0447] Step 7:

[0448] The server sends the generated recipe to the terminal. The generated recipe is sent to the terminal in JSON format, and the terminal receives it and displays it on the user interface.

[0449] Input: JSON data of the recipe returned by the generation AI module

[0450] Output: Sends JSON data to the terminal and displays it in the user interface.

[0451] Through each of the above steps, users can effectively manage ingredients and easily obtain multiple cooking methods using the generative AI model.

[0452] (Application example 1)

[0453] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0454] Conventional systems were able to suggest recipes based on food stored in a home storage device, but no system existed that could instantly analyze food combinations purchased in stores and suggest appropriate recipes to consumers. As a result, when consumers purchased food in stores, they sometimes did not know how to cook the food, which discouraged their desire to purchase it. In addition, there were insufficient methods for managing food inventory in stores and for effectively utilizing discarded food. A new system was needed to solve these problems.

[0455] 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.

[0456] In this invention, the server includes a means for acquiring ingredient information entered by a user, a means for identifying foods in the storage device through image analysis, a means for generating multiple recipe suggestions using AI based on the identified foods, a means for providing the generated recipe suggestions to the user, and a means for customers to acquire and analyze images of food on shelves in a store and provide recipe suggestions. This enables optimal recipe suggestions based on food at home and in stores. It also effectively manages food inventory in stores and reduces food waste.

[0457] The "means for acquiring ingredient information entered by the user" is a function that allows ingredient information manually entered by the user using a smartphone, tablet device, etc. to be sent to the server, and for that information to be received by the system.

[0458] "Means for identifying food in a storage device through image analysis" refers to a function that processes photographic data taken by a user in a storage device using an image analysis algorithm to automatically recognize and identify food in the photograph.

[0459] "Means for generating multiple dish suggestions using generative AI based on identified foods" refers to a function that automatically generates multiple dish suggestions using a generative AI model based on a food list obtained through image analysis or user input.

[0460] The "means for providing the generated recipe suggestions to the user" is a function that notifies the user's terminal of the recipe suggestions generated by the system, allowing the user to view the information.

[0461] "A means for customers to acquire, analyze, and suggest dishes from images of food on store shelves" refers to a function that allows customers to take photos of store shelves with their smartphones and upload those images to the system, which then identifies and analyzes the food on the shelves and generates and provides optimal dish suggestions based on the results.

[0462] The system that realizes this application example automatically recognizes and analyzes food items in refrigerators and on store shelves, and then makes recipe suggestions based on that information. The system consists of a user terminal, an image analysis module, a generative AI module, and a server.

[0463] First, users take a photo of the storage device or store shelves using their smartphone or tablet device, and then upload the photo to the server. Users can also manually enter ingredient information. The server uses an image analysis module to identify foods based on the provided photo. High-performance analysis algorithms such as OpenCV and YOLOv3 are used for image analysis.

[0464] After the food items are identified, the server passes this information to a generative AI module, which then makes recipe suggestions based on food information in supermarkets and home storage devices. For this purpose, a natural language generation model such as GPT-2 is used as the generative AI model. The generated recipe suggestions also take into account the user's preferences and allergies. The server then sends the generated recipe suggestions to the user's device, where they can be viewed by the user.

[0465] As a concrete example, consider the following case:

[0466] 1. A customer takes a photo of a supermarket shelf with their smartphone, opens the application and uploads the photo.

[0467] 2. The server analyzes the image and identifies tomatoes, chicken, cabbage, etc.

[0468] 3. The generative AI module generates dish suggestions based on these ingredients, such as "chicken stew with tomatoes."

[0469] 4. The recipe suggestions are sent to the user's device, and the user can then purchase the food based on the suggestions.

[0470] An example of a prompt for a generative AI model is:

[0471] Generate a recipe using the following ingredients: chicken, tomatoes, carrots, cabbage, and onions.

[0472] This system allows users to instantly receive appropriate recipe suggestions based on the food they have in stores or at home, contributing to increased purchasing motivation and reduced food waste.

[0473] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0474] Step 1:

[0475] A user uses a smartphone or tablet to take a photo of the storage device or the shelves in the store. This photo becomes the input data. The user can also manually input ingredient information. The input data includes image data and manually entered ingredient information.

[0476] Step 2:

[0477] The terminal transmits the photos taken by the user and the food ingredient information entered by the user to the server. In this transmission process, image data and manually entered text data are sent to the server.

[0478] Step 3:

[0479] The server passes the received image data to an image analysis module, which uses algorithms such as OpenCV and YOLOv3. The image analysis module identifies each ingredient in the image. As a result of the analysis, a list of identified ingredients is generated.

[0480] Step 4:

[0481] If there is any manually entered ingredient information, the server adds it to the ingredient list as is. The final ingredient list is completed. The output at this stage is the identified ingredient list.

[0482] Step 5:

[0483] The server passes the identified ingredient list to a generative AI module, which uses a pre-trained generative AI model (e.g., GPT-2) to generate multiple recipe suggestions. In this process, the ingredient list is used as input, and the generative AI outputs a recipe based on it.

[0484] Step 6:

[0485] The server selects the most suitable recipe from multiple recipe suggestions generated based on the user's preferences and allergies. This selection process uses a filtering function to output a list of recipes that suit the user.

[0486] Step 7:

[0487] The server sends the optimal recipe suggestions to the user device, which then notifies the user and makes the information available for viewing. The final output is a recipe suggestion that is displayed on the user device.

[0488] Step 8:

[0489] Users can then take the suggestions provided, select the appropriate ingredients, and prepare their meal, which will increase purchasing motivation and encourage behavior that contributes to reducing food waste.

[0490] 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.

[0491] This invention is a system that acquires ingredient information entered by the user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user, in addition to a system that combines an emotion engine that recognizes the user's emotions. This system is designed to realize inventory management for restaurants, diversify cooking at home, and respond to user emotions.

[0492] Program processing

[0493] The program process in this system begins when the user takes a photo of the inside of the refrigerator and uploads the image and their emotional state to the system via their terminal. The user can also manually input ingredient information, and simultaneously use the emotion engine to obtain their current emotional state (e.g., joy, sadness, stress).

[0494] The specific program process is as follows:

[0495] Users can take pictures of the inside of their refrigerator using their smartphones, and the image data is saved on the device using the app. Users can also manually enter ingredient information and simultaneously input emotions by launching an emotion engine within the app.

[0496] The device uploads the saved images and manually entered data to the server, along with the emotion data.

[0497] The server launches an AI image analysis module to analyze the received image, which identifies the ingredients in the image and generates a list of ingredients such as "chicken," "carrots," and "cabbage."

[0498] The server receives the ingredient list as the analysis result and stores it in a database. It also records the received emotion data.

[0499] The server then launches a generative AI module, which receives the identified ingredient list and emotional data as input. The generative AI generates multiple recipes based on the ingredient list and emotional data. For example, if the user is recognized as "tired," a particularly easy and relaxing recipe is generated.

[0500] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in the selection of a recipe that is most appropriate for the user.

[0501] The server sends the selected recipe list to the user's terminal.

[0502] The device displays the received recipe list to the user, who can then select a recipe from the suggested recipes and begin cooking.

[0503] As a function for restaurants, the restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and indicates "stress," the AI ​​generator will suggest a recipe with a particularly relaxing effect and send it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[0504] Furthermore, it also enables the effective use of discarded food ingredients. When food data for food items to be discarded is sent to the server from restaurants and households, the server uses generative AI to generate recipes that can effectively use these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[0505] To prevent overbuying, the server periodically checks the food data in the user's refrigerator and generates and sends warning messages to the device about duplicate or unused food items. This function reduces food waste and allows for proper food management.

[0506] By incorporating user emotion recognition, this system goes beyond simply proposing recipes and can also suggest optimal ways to use ingredients and dishes based on the user's emotional state, thereby increasing the user's psychological satisfaction and supporting a healthier diet.

[0507] The processing flow will be explained below.

[0508] Step 1:

[0509] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to the device through the app. At the same time, the app activates an emotion engine and inputs the user's current emotional state (e.g., joy, stress, etc.).

[0510] Step 2:

[0511] The device uploads the saved images, emotion data, and manually entered ingredient information to the server, along with the user's emotion information.

[0512] Step 3:

[0513] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[0514] Step 4:

[0515] The server receives the analysis results from the AI ​​image analysis module and stores the identified ingredients (e.g., "chicken," "carrot," "cabbage") in a database. The received emotion data is also recorded at the same time.

[0516] Step 5:

[0517] The server launches a generative AI module, which receives the identified ingredients and the user's emotional data as input. The generative AI generates multiple recipes based on this data.

[0518] Step 6:

[0519] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in a recipe that is more suitable for the user.

[0520] Step 7:

[0521] The server transmits the selected recipe list to the terminal.

[0522] Step 8:

[0523] The device displays the received recipe list to the user, who then selects a recipe from the suggested recipes and begins cooking.

[0524] As a concrete example, if a user is recognized as being in a "stressed" state and there are "chicken," "carrots," and "cabbage" in the refrigerator, the generative AI will suggest recipes that are effective in reducing stress, such as "easy stewed chicken and carrots."

[0525] Step 9:

[0526] A restaurant's inventory management system periodically sends inventory data to a server and updates the database in real time.

[0527] Step 10:

[0528] A user inputs his / her preferences for ingredients and dishes and his / her emotional state through the mobile ordering service and sends an order request to the server.

[0529] Step 11:

[0530] The server uses generative AI to select the optimal recipe based on the order request and inventory data, and sends it to the restaurant's kitchen terminal.

[0531] Step 12:

[0532] The kitchen terminal in the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[0533] Step 13:

[0534] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[0535] Step 14:

[0536] The server uses AI to generate recipes that can be effectively used based on data on ingredients that are scheduled to be discarded, and notifies the system of affiliated bento shops of these recipes.

[0537] Step 15:

[0538] The server periodically checks the food ingredient data in the user's refrigerator, generates warning messages about duplicated or unused food ingredients, and sends them to the terminal.

[0539] Step 16:

[0540] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[0541] Example 2

[0542] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0543] In recent years, the effective use and management of ingredients has become increasingly important in homes and restaurants. However, conventional recipe suggestion systems have difficulty in proposing recipes that take into account the user's emotional state, and they are unable to handle ingredient inventory management and allergy information in an integrated manner. Therefore, there is a need for an efficient system that provides optimal recipes that reflect the user's emotional state and preference information, and also includes ingredient inventory management.

[0544] 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.

[0545] In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients and the user's emotional state, and means for providing the generated recipes to the user. This enables efficient ingredient management by integrating optimal recipe suggestions that take the user's emotional state into consideration and ingredient inventory management and allergy information.

[0546] "Ingredient information" is data about the food and ingredients present in the refrigerator, which is manually entered by the user or obtained through image analysis.

[0547] "Image analysis" is the process by which an AI module recognizes and identifies specific ingredients from images taken with a camera or smartphone.

[0548] "Generative AI" refers to artificial intelligence that generates new information (in this case, recipes) based on input data, typically using natural language processing techniques.

[0549] "Emotional state" is data that indicates the type of emotion the user is currently feeling (e.g., stress, fatigue, joy).

[0550] "Preference information" is information about the types of foods the user likes and foods they want to avoid.

[0551] "Allergy information" is information about the user's food allergies, specifically a list of ingredients that may cause allergies.

[0552] "Inventory control" is the process of monitoring and managing the quantity and type of food ingredients stored in refrigerators and within a restaurant.

[0553] A "recipe" is a list of instructions or ingredients for making a dish using specific ingredients.

[0554] A "prompt sentence" is an input sentence that provides specific information to the generative AI and produces a desired output.

[0555] "Terminal" means a hardware device (e.g., smartphone, tablet, or PC) used by a User to access the System.

[0556] The "database" is a system for efficiently storing and managing information such as ingredients, emotional state, preference information, allergy information, and inventory data.

[0557] The present invention is a system in which a user inputs information about ingredients in the refrigerator and their emotional state into the system, and a generation AI generates and provides multiple recipes based on that information. This system is designed to handle inventory management for restaurants, the diversification of home cooking, and the user's emotions. Below, we will explain in detail how to implement this system.

[0558] First, the user takes a photo of the contents of the refrigerator using a device such as a smartphone. This image data is then saved on the device using a dedicated app. The user can also manually enter information about ingredients, such as "two carrots and 300g of chicken." At the same time, the user can input their current emotional state (e.g., "stressed" or "tired") using the emotion engine built into the app.

[0559] The device then uploads the stored image data, manually entered ingredient information, and emotion data to a server using the HTTPS protocol, and the data may be compressed before transmission.

[0560] The server launches an AI image analysis module (e.g., Google Cloud Vision API) to analyze the received image data. This module identifies ingredients in the image and generates a list of ingredients, such as "chicken," "carrot," and "cabbage." The analysis results are returned to the server in JSON format.

[0561] The server then stores the ingredient list and emotion data resulting from this analysis in a database, which stores ingredient information, emotion data, user preference information, allergy information, and other information.

[0562] The server runs a generative AI (e.g., OpenAI GPT-4) that generates multiple recipes based on the identified ingredients and emotional data. Example prompts include:

[0563] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[0564] Based on this prompt, the AI ​​generates recipes such as "chicken and carrot soup" or "cabbage and chicken stir-fry." The server filters the generated recipes based on the user's preferences and allergies to select the most suitable recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded.

[0565] The selected recipe list is sent from the server to the device in JSON format, which the device parses and displays to the user. The user can then select a recipe from the displayed list and start cooking.

[0566] It also has functions for restaurants, and the inventory management system periodically sends inventory data to the server, allowing for real-time inventory management. The created recipes are also sent to devices used in the restaurant's kitchen, allowing for efficient food preparation.

[0567] In this way, the present invention is a system that provides optimal recipes by utilizing the user's emotional state and information about ingredients in the refrigerator, thereby improving the efficiency of ingredient management and diversifying cooking options. Furthermore, by selecting recipes that reflect food allergies and preferences, it is possible to increase user satisfaction.

[0568] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0569] Step 1:

[0570] User takes a photo of the inside of the refrigerator

[0571] The user takes a photo of the inside of the refrigerator using their smartphone. This image data is saved on the device using a dedicated app. The input is the photo of the inside of the refrigerator, and the output is the saved image data.

[0572] Step 2:

[0573] Input of ingredient information and emotion data

[0574] The user manually inputs ingredient information into the app, such as "2 carrots, 300g of chicken," and then uses the app's emotion engine to input their current emotional state (e.g., "stressed"). The input is the manually entered ingredient information and emotion data, and the output is the saved ingredient information and emotion data.

[0575] Step 3:

[0576] Uploading image data and input data

[0577] The device uploads the stored image data, manually entered ingredient information, and emotion data to the server. The upload uses the HTTPS protocol, and the data may be compressed. The input is the image data, ingredient information, and emotion data, and the output is the data sent to the server.

[0578] Step 4:

[0579] Identifying ingredients through image analysis

[0580] The server performs image analysis using the Google Cloud Vision API. Through this analysis, it recognizes ingredients in the image and generates a list of ingredients such as "chicken," "carrot," and "cabbage." The input is the uploaded image data, and the output is the list of ingredients.

[0581] Step 5:

[0582] Saving to a database

[0583] The server stores the ingredient list and emotional data as the analysis results in a database. The data includes ingredient information, emotional data, user preference information, allergy information, etc. The input is the generated ingredient list and emotional data, and the output is the data stored in the database.

[0584] Step 6:

[0585] Recipe Generation

[0586] The server runs a generative AI (e.g., OpenAI GPT-4) to generate multiple recipes using the identified ingredients list and emotion data. Example prompts include:

[0587] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[0588] The input is an ingredient list and emotion data, and the output is the generated recipe.

[0589] Step 7:

[0590] Recipe Selection

[0591] The server filters the generated recipes taking into account the user's preference and allergy information to select the optimal recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded. The input is the generated recipe and the user's preference and allergy information, and the output is the selected optimal recipe.

[0592] Step 8:

[0593] Recipe provided

[0594] The server sends the selected recipe list in JSON format to the terminal, which parses it and displays it to the user. The user can select a recipe from the displayed recipe and start cooking. The input is the selected recipe list, and the output is the recipe displayed on the terminal.

[0595] (Application example 2)

[0596] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0597] In conventional restaurants, it has been difficult to properly manage ingredients in the refrigerator and efficiently check inventory status. In addition, recipe suggestions based on emotions are rare, making it difficult to provide dishes that take into account the emotional state of the customer. This has led to a decline in customer satisfaction and the need for more efficient ingredient management.

[0598] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients, means for providing the generated recipes to the user, means for recognizing the user's emotions, and means for selecting an appropriate recipe based on the emotion data. This improves the efficiency of ingredient management in the refrigerator and enables optimal recipe suggestions based on the customer's emotions.

[0599] The "means for acquiring ingredient information entered by the user" is a function for collecting information about ingredients provided by the user manually or digitally.

[0600] "Means for identifying ingredients in a refrigerator through image analysis" refers to a technology for analyzing images of ingredients in a refrigerator and identifying the type of ingredients.

[0601] "Means for generating multiple recipes using generative AI based on identified ingredients" refers to a function that automatically generates multiple recipes using generative AI based on ingredient information identified through image analysis.

[0602] "Means for providing the generated recipe to the user" refers to means for providing the recipe generated by the generation AI in a form that the user can use.

[0603] The "means for recognizing user's emotions" is a function for recognizing and analyzing the user's current emotional state (e.g., joy, sadness, stress).

[0604] The "means for selecting an appropriate recipe based on emotional data" is a technology that takes into consideration the recognized emotional data of a user and selects a recipe that is appropriate for that emotional state.

[0605] "Means for selecting an optimal recipe taking into consideration user preference information and allergy information" refers to a technology that refers to information about a user's individual preferences and allergies and selects an optimal recipe.

[0606] "Means for managing food ingredient inventory and automatically linking inventory data" refers to a management system that monitors food ingredient inventory and automatically links the necessary information to a database, etc.

[0607] This invention is a system for efficiently managing ingredients and proposing recipes in restaurants and homes.

[0608] The user starts by taking a photo of the ingredients in the refrigerator using a device such as a smartphone. The device then uploads the captured image data and the ingredient information manually entered by the user to the server. The user also inputs their current emotional state (e.g., joy, sadness, stress) using the emotion engine.

[0609] The server then launches an AI image analysis module (such as OpenCV) on the received image data to identify the ingredients in the refrigerator. This generates an ingredient list, such as "chicken," "carrots," and "cabbage." The server then stores this ingredient list as a result of this analysis in a database, and simultaneously records the received emotion data.

[0610] Next, the server invokes a generative AI model (e.g., HuggingFace's Transformer library) and provides the identified ingredient list and emotion data as input. This generative AI generates prompts based on the given ingredient list and emotion data, and generates multiple recipes. For example, if the user is recognized as "stressed," a particularly easy and relaxing recipe is generated.

[0611] The generated recipes are compared with the user's preference and allergy information to select the most suitable recipe. The selected recipe list is sent to the user's device, and the user can choose from the suggested recipes and start cooking.

[0612] As a concrete example, the following prompt is input to the generator AI:

[0613] "Generate recipes using chicken, carrots, and cabbage when you're feeling stressed."

[0614] Another example of application for restaurants is that store employees can take photos of the inside of the refrigerator with their smartphones and upload them to an app, which can help streamline inventory management. If an employee feels tired, the generative AI can suggest a relaxing recipe, such as "Easy Chicken and Cabbage Consommé Soup," which can then be immediately made available on the menu.

[0615] In this way, by combining emotion recognition with ingredient information, it becomes possible to suggest recipes that meet the user's psychological and physical needs, thereby improving customer satisfaction and streamlining ingredient management.

[0616] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0617] Step 1:

[0618] The user takes a photo of the contents of the refrigerator using a smartphone and manually inputs the ingredients. This data is stored on the smartphone, and the user also inputs their current emotional state (e.g., stress, joy) through the device. The input data includes the photo data, manually input ingredients, and emotional data.

[0619] Step 2:

[0620] The device uploads the photo data, manually entered ingredient information, and emotion data entered by the user to the server, which then sends the data as a package to the server, where it is stored.

[0621] Step 3:

[0622] The server passes the received photo data to an AI image analysis module to identify the ingredients in the refrigerator. This analysis process uses an image processing library such as OpenCV to generate a list of ingredients such as "chicken," "carrots," and "cabbage." The input data is the photo data, and the output data is the list of identified ingredients.

[0623] Step 4:

[0624] The server stores the identified ingredient list in a database and simultaneously records the received emotion data. This recorded data is used for later recipe generation. The input data is the ingredient list and emotion data, and the output data is the result stored in the database.

[0625] Step 5:

[0626] The server inputs the saved ingredient list and emotion data into a generative AI model to generate an appropriate recipe. Using a generative AI model (e.g., HuggingFace's Transformer library), a prompt based on the ingredient list and emotion data is generated, and the recipe is generated by sending the prompt to the model. The input data is the ingredient list and emotion data, and the output data is the generated recipe list. Example: Prompt: "Please generate a recipe using chicken, carrots, and cabbage for when I'm feeling stressed."

[0627] Step 6:

[0628] The server compares the generated recipe list with the user's preference and allergy information to select the most suitable recipe. In this comparison process, the server compares the user information in the database with the generated recipes to select the most suitable candidates. The input data is the generated recipe list and the user's preference and allergy information, and the output data is the list of suitable recipes.

[0629] Step 7:

[0630] The server sends the optimal recipe list to the user's device. The user can view the received recipe list through the device, select a desired recipe, and start cooking. The input data is the optimal recipe list, and the output data is the recipe list displayed on the user's device.

[0631] In this way, a system is constructed that can suggest optimal recipes based on the user's emotional state and ingredient information.

[0632] 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.

[0633] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0634] 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.

[0635] [Third embodiment]

[0636] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0637] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0638] 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).

[0639] 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.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0648] The purpose of this invention is to realize a system that acquires ingredient information entered by a user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user. This system is designed to support inventory management in restaurants and diversify cooking at home.

[0649] The program and processing of this system can be explained as follows.

[0650] Program processing

[0651] Users can take a photo of the inside of their refrigerator and upload it to the system using their smartphone or tablet. At the same time, they can also manually enter ingredient information. The device then sends the captured image or manually entered ingredient information to the server.

[0652] The server launches an AI image analysis module to analyze the image sent. This module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the list as is.

[0653] Next, the server launches a generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list. This generation process also takes into account the user's preferences and allergy information. The server then sends the generated recipes to the terminal to be provided to the user.

[0654] Examples:

[0655] When a user takes a photo of the contents of their refrigerator with their smartphone and uploads it, the server analyzes the image and identifies chicken, carrots, and cabbage.The server then uses generative AI to generate recipes such as "Chicken and Carrot Stew" or "Cabbage and Chicken Stir-fry" from these ingredients and notifies the user of these recipes.The user then creates a dish based on the suggested recipes.

[0656] As a function for restaurants, the server can link with the restaurant's inventory management system and update the stock status of ingredients in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and requests a "grilled dish," the server generates an optimal recipe based on the generative AI and sends it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[0657] Furthermore, it also makes effective use of discarded food ingredients. When restaurants and households send data on food ingredients that are scheduled to be discarded to the server, the server uses generative AI to generate recipes based on these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[0658] To prevent overbuying, the server periodically checks the food data in the user's refrigerator, generates warning messages about duplicate or unused food items, and sends them to the device. This function reduces food waste and allows for proper food management.

[0659] As described above, this system offers a wide range of functions, is highly convenient for users, and enables effective ingredient management and recipe provision. It can also contribute to reducing food waste.

[0660] The processing flow will be explained below.

[0661] Step 1:

[0662] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to their device via the app.

[0663] Step 2:

[0664] The device uploads the saved image to the server. At this time, even if the user manually inputs ingredient information, the data is also sent to the server.

[0665] Step 3:

[0666] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[0667] Step 4:

[0668] The server receives the analysis results from the AI ​​image analysis module and stores the list of identified ingredients (e.g., "chicken," "carrots," and "cabbage") in a database.

[0669] Step 5:

[0670] The server launches the generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list.

[0671] Step 6:

[0672] The server compares the user's preference information and allergy information with the generated recipes and selects the most suitable recipe.

[0673] Step 7:

[0674] The server transmits the selected recipe list to the user's terminal.

[0675] Step 8:

[0676] The terminal displays the received recipe list to the user, and the user selects from the suggested recipes and starts cooking.

[0677] Step 9:

[0678] The restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time.

[0679] Step 10:

[0680] The server generates optimal recipes based on restaurant inventory data to accommodate mobile orders from users.

[0681] Step 11:

[0682] The kitchen terminal of the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[0683] Step 12:

[0684] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[0685] Step 13:

[0686] The server uses AI to generate recipes that can be effectively used based on ingredients that are scheduled to be discarded, and notifies affiliated bento shops.

[0687] Step 14:

[0688] The server periodically checks the food ingredient data in the user's refrigerator and generates a warning message about duplicate or unused food ingredients.

[0689] Step 15:

[0690] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[0691] Example 1

[0692] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0693] In modern society, food management has become increasingly complex in homes and restaurants, and efficient inventory management and recipe selection are required. In particular, it is a challenge to provide optimal cooking methods that take into account the user's preferences and allergies while minimizing food waste.

[0694] 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.

[0695] In this invention, the server includes a means for acquiring ingredient information entered by the user, a means for identifying ingredients in the storage device through image analysis, a means for generating multiple recipes using a generation AI based on the identified ingredients, and a means for providing the generated recipes to the user, thereby improving the efficiency of ingredient management and making it possible to provide optimal recipes that take into account the user's preferences and allergies.

[0696] "User" refers to any individual or entity that uses the System.

[0697] "Food information" refers to data such as the type, quantity, and expiration date of food stored in a refrigerator or storage device.

[0698] "Storage equipment" refers to equipment such as refrigerators, freezers, and pantries for storing food ingredients.

[0699] "Image analysis" refers to the technology of analyzing image data captured by a camera or smartphone and recognizing specific objects (e.g., food ingredients) contained within it.

[0700] "Generative AI" refers to artificial intelligence that generates new information or content (e.g., cooking methods) based on specified input data.

[0701] "Cooking instructions" refers to recipes that describe how to prepare a dish based on specific ingredients.

[0702] "Preference information" is data relating to the user's preferences, including preferences for seasonings and ingredients of specific dishes.

[0703] "Allergy Information" means data regarding specific ingredients to which a user is allergic.

[0704] "Stock status" refers to information such as the quantity and type of ingredients stored in the storage device.

[0705] "Inventory data" means data that records inventory status.

[0706] This system allows users to efficiently manage ingredient information stored in a storage device and provides optimal recipes using a generative AI model. This system aims to support ingredient inventory management and recipe selection, particularly in homes and restaurants.

[0707] System configuration

[0708] User actions

[0709] Users can use the camera on their smartphone or tablet to take photos of ingredients in their refrigerator or storage unit, then upload the images to the system via their device. Users can also manually enter ingredient information.

[0710] Terminal handling

[0711] The device sends the image acquired from the user or the manually entered ingredient information to the server. When uploading the image, a network communication method such as an HTTP POST request is used.

[0712] Server Processing

[0713] The server launches an AI image analysis module (e.g., TensorFlow, OpenCV) to analyze the received image data. This image analysis module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the ingredient list as is.

[0714] Next, the server launches a generative AI module (e.g., GPT-3, BERT) and provides it with the identified ingredient list and the user's preference and allergy information as input. The generative AI module generates multiple recipes based on the input data. The generated recipes are sent from the server to the device and provided to the user.

[0715] Hardware and software used

[0716] This system uses the following hardware and software:

[0717] Hardware: smartphones, tablets, servers

[0718] Software: TensorFlow for image analysis, OpenCV, GPT-3 for generative AI, BERT, network library for HTTP communication

[0719] Specific examples

[0720] 1. The user takes a photo of the inside of the refrigerator with their smartphone and uploads the image to the server via the application.

[0721] 2. The server uses TensorFlow to analyze the image and identify chicken, carrots, and cabbage.

[0722] 3. The server inputs the following prompt to GPT-3: "Could you come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy."

[0723] 4. Recipes generated by GPT-3, such as "Chicken and carrot stew" or "Cabbage and chicken stir-fry," are sent to the user's device.

[0724] 5. Users can create dishes based on these recipes.

[0725] This system, configured in this way, not only provides convenience to users but also contributes to effective ingredient management and the reduction of food waste. For restaurants, linking it to an inventory management system will enable real-time updates of inventory status, which is expected to lead to more efficient operations.

[0726] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0727] Step 1:

[0728] The user takes a photo of the inside of the refrigerator using the camera on their smartphone or tablet. The user then launches the camera app and takes a photo of the food from any position within the storage device. The captured image is saved to the device's photo library.

[0729] Input: Image taken with the camera app

[0730] Output: Image files saved in the device's photo library

[0731] Step 2:

[0732] The user opens the application on the device, selects the image they have taken, and presses the upload button. The user then clicks the "Upload Image" button in the application and selects the image file they have just taken from the file selection dialog. The selected image is then sent to the server via the Internet.

[0733] Input: An image file selected by the user.

[0734] Output: Image data sent to the server

[0735] Step 3:

[0736] The server launches an AI image analysis module to analyze the image data it receives. The server saves the image data received via the HTTP request in a specified directory, and launches an image analysis library such as TensorFlow or OpenCV with the path as an argument.

[0737] Input: Image data received via HTTP request

[0738] Output: Image analysis module is launched

[0739] Step 4:

[0740] The server uses an image analysis module to identify ingredients in the image. The module uses an object detection algorithm (e.g., YOLO, SSD) to identify the ingredients in the image and generate a list of items such as "chicken," "carrot," and "cabbage." The server outputs the location and label of each ingredient in the image as the analysis result.

[0741] Input: The path of the image file passed to the image analysis module

[0742] Output: List of identified ingredients (e.g. "chicken", "carrot", "cabbage")

[0743] Step 5:

[0744] The server starts the generation AI module and provides the identified ingredients list and the user's preference and allergy information as input. The server generates a prompt and calls the GPT-3 or BERT API to request recipe generation.

[0745] Input: List of identified ingredients, user preferences and allergy information

[0746] Output: The generative AI module is triggered

[0747] Step 6:

[0748] The generative AI module generates recipes. For example, it responds to a prompt such as, "Could you think of a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy." It then generates and returns multiple recipes in JSON format.

[0749] Input: Prompt text (e.g., "Could you please come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy.")

[0750] Output: The generated recipe (e.g. "Chicken and carrot stew", "Cabbage and chicken stir fry")

[0751] Step 7:

[0752] The server sends the generated recipe to the terminal. The generated recipe is sent to the terminal in JSON format, and the terminal receives it and displays it on the user interface.

[0753] Input: JSON data of the recipe returned by the generation AI module

[0754] Output: Sends JSON data to the terminal and displays it in the user interface.

[0755] Through each of the above steps, users can effectively manage ingredients and easily obtain multiple cooking methods using the generative AI model.

[0756] (Application example 1)

[0757] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0758] Conventional systems were able to suggest recipes based on food stored in a home storage device, but no system existed that could instantly analyze food combinations purchased in stores and suggest appropriate recipes to consumers. As a result, when consumers purchased food in stores, they sometimes did not know how to cook the food, which discouraged their desire to purchase it. In addition, there were insufficient methods for managing food inventory in stores and for effectively utilizing discarded food. A new system was needed to solve these problems.

[0759] 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.

[0760] In this invention, the server includes a means for acquiring ingredient information entered by a user, a means for identifying foods in the storage device through image analysis, a means for generating multiple recipe suggestions using AI based on the identified foods, a means for providing the generated recipe suggestions to the user, and a means for customers to acquire and analyze images of food on shelves in a store and provide recipe suggestions. This enables optimal recipe suggestions based on food at home and in stores. It also effectively manages food inventory in stores and reduces food waste.

[0761] The "means for acquiring ingredient information entered by the user" is a function that allows ingredient information manually entered by the user using a smartphone, tablet device, etc. to be sent to the server, and for that information to be received by the system.

[0762] "Means for identifying food in a storage device through image analysis" refers to a function that processes photographic data taken by a user in a storage device using an image analysis algorithm to automatically recognize and identify food in the photograph.

[0763] "Means for generating multiple dish suggestions using generative AI based on identified foods" refers to a function that automatically generates multiple dish suggestions using a generative AI model based on a food list obtained through image analysis or user input.

[0764] The "means for providing the generated recipe suggestions to the user" is a function that notifies the user's terminal of the recipe suggestions generated by the system, allowing the user to view the information.

[0765] "A means for customers to acquire, analyze, and suggest dishes from images of food on store shelves" refers to a function that allows customers to take photos of store shelves with their smartphones and upload those images to the system, which then identifies and analyzes the food on the shelves and generates and provides optimal dish suggestions based on the results.

[0766] The system that realizes this application example automatically recognizes and analyzes food items in refrigerators and on store shelves, and then makes recipe suggestions based on that information. The system consists of a user terminal, an image analysis module, a generative AI module, and a server.

[0767] First, users take a photo of the storage device or store shelves using their smartphone or tablet device, and then upload the photo to the server. Users can also manually enter ingredient information. The server uses an image analysis module to identify foods based on the provided photo. High-performance analysis algorithms such as OpenCV and YOLOv3 are used for image analysis.

[0768] After the food items are identified, the server passes this information to a generative AI module, which then makes recipe suggestions based on food information in supermarkets and home storage devices. For this purpose, a natural language generation model such as GPT-2 is used as the generative AI model. The generated recipe suggestions also take into account the user's preferences and allergies. The server then sends the generated recipe suggestions to the user's device, where they can be viewed by the user.

[0769] As a concrete example, consider the following case:

[0770] 1. A customer takes a photo of a supermarket shelf with their smartphone, opens the application and uploads the photo.

[0771] 2. The server analyzes the image and identifies tomatoes, chicken, cabbage, etc.

[0772] 3. The generative AI module generates dish suggestions based on these ingredients, such as "chicken stew with tomatoes."

[0773] 4. The recipe suggestions are sent to the user's device, and the user can then purchase the food based on the suggestions.

[0774] An example of a prompt for a generative AI model is:

[0775] Generate a recipe using the following ingredients: chicken, tomatoes, carrots, cabbage, and onions.

[0776] This system allows users to instantly receive appropriate recipe suggestions based on the food they have in stores or at home, contributing to increased purchasing motivation and reduced food waste.

[0777] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0778] Step 1:

[0779] A user uses a smartphone or tablet to take a photo of the storage device or the shelves in the store. This photo becomes the input data. The user can also manually input ingredient information. The input data includes image data and manually entered ingredient information.

[0780] Step 2:

[0781] The terminal transmits the photos taken by the user and the food ingredient information entered by the user to the server. In this transmission process, image data and manually entered text data are sent to the server.

[0782] Step 3:

[0783] The server passes the received image data to an image analysis module, which uses algorithms such as OpenCV and YOLOv3. The image analysis module identifies each ingredient in the image. As a result of the analysis, a list of identified ingredients is generated.

[0784] Step 4:

[0785] If there is any manually entered ingredient information, the server adds it to the ingredient list as is. The final ingredient list is completed. The output at this stage is the identified ingredient list.

[0786] Step 5:

[0787] The server passes the identified ingredient list to a generative AI module, which uses a pre-trained generative AI model (e.g., GPT-2) to generate multiple recipe suggestions. In this process, the ingredient list is used as input, and the generative AI outputs a recipe based on it.

[0788] Step 6:

[0789] The server selects the most suitable recipe from multiple recipe suggestions generated based on the user's preferences and allergies. This selection process uses a filtering function to output a list of recipes that suit the user.

[0790] Step 7:

[0791] The server sends the optimal recipe suggestions to the user device, which then notifies the user and makes the information available for viewing. The final output is a recipe suggestion that is displayed on the user device.

[0792] Step 8:

[0793] Users can then take the suggestions provided, select the appropriate ingredients, and prepare their meal, which will increase purchasing motivation and encourage behavior that contributes to reducing food waste.

[0794] 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.

[0795] This invention is a system that acquires ingredient information entered by the user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user, in addition to a system that combines an emotion engine that recognizes the user's emotions. This system is designed to realize inventory management for restaurants, diversify cooking at home, and respond to user emotions.

[0796] Program processing

[0797] The program process in this system begins when the user takes a photo of the inside of the refrigerator and uploads the image and their emotional state to the system via their terminal. The user can also manually input ingredient information, and simultaneously use the emotion engine to obtain their current emotional state (e.g., joy, sadness, stress).

[0798] The specific program process is as follows:

[0799] Users can take pictures of the inside of their refrigerator using their smartphones, and the image data is saved on the device using the app. Users can also manually enter ingredient information and simultaneously input emotions by launching an emotion engine within the app.

[0800] The device uploads the saved images and manually entered data to the server, along with the emotion data.

[0801] The server launches an AI image analysis module to analyze the received image, which identifies the ingredients in the image and generates a list of ingredients such as "chicken," "carrots," and "cabbage."

[0802] The server receives the ingredient list as the analysis result and stores it in a database. It also records the received emotion data.

[0803] The server then launches a generative AI module, which receives the identified ingredient list and emotional data as input. The generative AI generates multiple recipes based on the ingredient list and emotional data. For example, if the user is recognized as "tired," a particularly easy and relaxing recipe is generated.

[0804] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in the selection of a recipe that is most appropriate for the user.

[0805] The server sends the selected recipe list to the user's terminal.

[0806] The device displays the received recipe list to the user, who can then select a recipe from the suggested recipes and begin cooking.

[0807] As a function for restaurants, the restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and indicates "stress," the AI ​​generator will suggest a recipe with a particularly relaxing effect and send it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[0808] Furthermore, it also enables the effective use of discarded food ingredients. When food data for food items to be discarded is sent to the server from restaurants and households, the server uses generative AI to generate recipes that can effectively use these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[0809] To prevent overbuying, the server periodically checks the food data in the user's refrigerator and generates and sends warning messages to the device about duplicate or unused food items. This function reduces food waste and allows for proper food management.

[0810] By incorporating user emotion recognition, this system goes beyond simply proposing recipes and can also suggest optimal ways to use ingredients and dishes based on the user's emotional state, thereby increasing the user's psychological satisfaction and supporting a healthier diet.

[0811] The processing flow will be explained below.

[0812] Step 1:

[0813] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to the device through the app. At the same time, the app activates an emotion engine and inputs the user's current emotional state (e.g., joy, stress, etc.).

[0814] Step 2:

[0815] The device uploads the saved images, emotion data, and manually entered ingredient information to the server, along with the user's emotion information.

[0816] Step 3:

[0817] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[0818] Step 4:

[0819] The server receives the analysis results from the AI ​​image analysis module and stores the identified ingredients (e.g., "chicken," "carrot," "cabbage") in a database. The received emotion data is also recorded at the same time.

[0820] Step 5:

[0821] The server launches a generative AI module, which receives the identified ingredients and the user's emotional data as input. The generative AI generates multiple recipes based on this data.

[0822] Step 6:

[0823] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in a recipe that is more suitable for the user.

[0824] Step 7:

[0825] The server transmits the selected recipe list to the terminal.

[0826] Step 8:

[0827] The device displays the received recipe list to the user, who then selects a recipe from the suggested recipes and begins cooking.

[0828] As a concrete example, if a user is recognized as being in a "stressed" state and there are "chicken," "carrots," and "cabbage" in the refrigerator, the generative AI will suggest recipes that are effective in reducing stress, such as "easy stewed chicken and carrots."

[0829] Step 9:

[0830] A restaurant's inventory management system periodically sends inventory data to a server and updates the database in real time.

[0831] Step 10:

[0832] A user inputs his / her preferences for ingredients and dishes and his / her emotional state through the mobile ordering service and sends an order request to the server.

[0833] Step 11:

[0834] The server uses generative AI to select the optimal recipe based on the order request and inventory data, and sends it to the restaurant's kitchen terminal.

[0835] Step 12:

[0836] The kitchen terminal in the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[0837] Step 13:

[0838] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[0839] Step 14:

[0840] The server uses AI to generate recipes that can be effectively used based on data on ingredients that are scheduled to be discarded, and notifies the system of affiliated bento shops of these recipes.

[0841] Step 15:

[0842] The server periodically checks the food ingredient data in the user's refrigerator, generates warning messages about duplicated or unused food ingredients, and sends them to the terminal.

[0843] Step 16:

[0844] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[0845] Example 2

[0846] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0847] In recent years, the effective use and management of ingredients has become increasingly important in homes and restaurants. However, conventional recipe suggestion systems have difficulty in proposing recipes that take into account the user's emotional state, and they are unable to handle ingredient inventory management and allergy information in an integrated manner. Therefore, there is a need for an efficient system that provides optimal recipes that reflect the user's emotional state and preference information, and also includes ingredient inventory management.

[0848] 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.

[0849] In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients and the user's emotional state, and means for providing the generated recipes to the user. This enables efficient ingredient management by integrating optimal recipe suggestions that take the user's emotional state into consideration and ingredient inventory management and allergy information.

[0850] "Ingredient information" is data about the food and ingredients present in the refrigerator, which is manually entered by the user or obtained through image analysis.

[0851] "Image analysis" is the process by which an AI module recognizes and identifies specific ingredients from images taken with a camera or smartphone.

[0852] "Generative AI" refers to artificial intelligence that generates new information (in this case, recipes) based on input data, typically using natural language processing techniques.

[0853] "Emotional state" is data that indicates the type of emotion the user is currently feeling (e.g., stress, fatigue, joy).

[0854] "Preference information" is information about the types of foods the user likes and foods they want to avoid.

[0855] "Allergy information" is information about the user's food allergies, specifically a list of ingredients that may cause allergies.

[0856] "Inventory control" is the process of monitoring and managing the quantity and type of food ingredients stored in refrigerators and within a restaurant.

[0857] A "recipe" is a list of instructions or ingredients for making a dish using specific ingredients.

[0858] A "prompt sentence" is an input sentence that provides specific information to the generative AI and produces a desired output.

[0859] "Terminal" means a hardware device (e.g., smartphone, tablet, or PC) used by a User to access the System.

[0860] The "database" is a system for efficiently storing and managing information such as ingredients, emotional state, preference information, allergy information, and inventory data.

[0861] The present invention is a system in which a user inputs information about ingredients in the refrigerator and their emotional state into the system, and a generation AI generates and provides multiple recipes based on that information. This system is designed to handle inventory management for restaurants, the diversification of home cooking, and the user's emotions. Below, we will explain in detail how to implement this system.

[0862] First, the user takes a photo of the contents of the refrigerator using a device such as a smartphone. This image data is then saved on the device using a dedicated app. The user can also manually enter information about ingredients, such as "two carrots and 300g of chicken." At the same time, the user can input their current emotional state (e.g., "stressed" or "tired") using the emotion engine built into the app.

[0863] The device then uploads the stored image data, manually entered ingredient information, and emotion data to a server using the HTTPS protocol, and the data may be compressed before transmission.

[0864] The server launches an AI image analysis module (e.g., Google Cloud Vision API) to analyze the received image data. This module identifies ingredients in the image and generates a list of ingredients, such as "chicken," "carrot," and "cabbage." The analysis results are returned to the server in JSON format.

[0865] The server then stores the ingredient list and emotion data resulting from this analysis in a database, which stores ingredient information, emotion data, user preference information, allergy information, and other information.

[0866] The server runs a generative AI (e.g., OpenAI GPT-4) that generates multiple recipes based on the identified ingredients and emotional data. Example prompts include:

[0867] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[0868] Based on this prompt, the AI ​​generates recipes such as "chicken and carrot soup" or "cabbage and chicken stir-fry." The server filters the generated recipes based on the user's preferences and allergies to select the most suitable recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded.

[0869] The selected recipe list is sent from the server to the device in JSON format, which the device parses and displays to the user. The user can then select a recipe from the displayed list and start cooking.

[0870] It also has functions for restaurants, and the inventory management system periodically sends inventory data to the server, allowing for real-time inventory management. The created recipes are also sent to devices used in the restaurant's kitchen, allowing for efficient food preparation.

[0871] In this way, the present invention is a system that provides optimal recipes by utilizing the user's emotional state and information about ingredients in the refrigerator, thereby improving the efficiency of ingredient management and diversifying cooking options. Furthermore, by selecting recipes that reflect food allergies and preferences, it is possible to increase user satisfaction.

[0872] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0873] Step 1:

[0874] User takes a photo of the inside of the refrigerator

[0875] The user takes a photo of the inside of the refrigerator using their smartphone. This image data is saved on the device using a dedicated app. The input is the photo of the inside of the refrigerator, and the output is the saved image data.

[0876] Step 2:

[0877] Input of ingredient information and emotion data

[0878] The user manually inputs ingredient information into the app, such as "2 carrots, 300g of chicken," and then uses the app's emotion engine to input their current emotional state (e.g., "stressed"). The input is the manually entered ingredient information and emotion data, and the output is the saved ingredient information and emotion data.

[0879] Step 3:

[0880] Uploading image data and input data

[0881] The device uploads the stored image data, manually entered ingredient information, and emotion data to the server. The upload uses the HTTPS protocol, and the data may be compressed. The input is the image data, ingredient information, and emotion data, and the output is the data sent to the server.

[0882] Step 4:

[0883] Identifying ingredients through image analysis

[0884] The server performs image analysis using the Google Cloud Vision API. Through this analysis, it recognizes ingredients in the image and generates a list of ingredients such as "chicken," "carrot," and "cabbage." The input is the uploaded image data, and the output is the list of ingredients.

[0885] Step 5:

[0886] Saving to a database

[0887] The server stores the ingredient list and emotional data as the analysis results in a database. The data includes ingredient information, emotional data, user preference information, allergy information, etc. The input is the generated ingredient list and emotional data, and the output is the data stored in the database.

[0888] Step 6:

[0889] Recipe Generation

[0890] The server runs a generative AI (e.g., OpenAI GPT-4) to generate multiple recipes using the identified ingredients list and emotion data. Example prompts include:

[0891] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[0892] The input is an ingredient list and emotion data, and the output is the generated recipe.

[0893] Step 7:

[0894] Recipe Selection

[0895] The server filters the generated recipes taking into account the user's preference and allergy information to select the optimal recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded. The input is the generated recipe and the user's preference and allergy information, and the output is the selected optimal recipe.

[0896] Step 8:

[0897] Recipe provided

[0898] The server sends the selected recipe list in JSON format to the terminal, which parses it and displays it to the user. The user can select a recipe from the displayed recipe and start cooking. The input is the selected recipe list, and the output is the recipe displayed on the terminal.

[0899] (Application example 2)

[0900] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0901] In conventional restaurants, it has been difficult to properly manage ingredients in the refrigerator and efficiently check inventory status. In addition, recipe suggestions based on emotions are rare, making it difficult to provide dishes that take into account the emotional state of the customer. This has led to a decline in customer satisfaction and the need for more efficient ingredient management.

[0902] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients, means for providing the generated recipes to the user, means for recognizing the user's emotions, and means for selecting an appropriate recipe based on the emotion data. This improves the efficiency of ingredient management in the refrigerator and enables optimal recipe suggestions based on the customer's emotions.

[0903] The "means for acquiring ingredient information entered by the user" is a function for collecting information about ingredients provided by the user manually or digitally.

[0904] "Means for identifying ingredients in a refrigerator through image analysis" refers to a technology for analyzing images of ingredients in a refrigerator and identifying the type of ingredients.

[0905] "Means for generating multiple recipes using generative AI based on identified ingredients" refers to a function that automatically generates multiple recipes using generative AI based on ingredient information identified through image analysis.

[0906] "Means for providing the generated recipe to the user" refers to means for providing the recipe generated by the generation AI in a form that the user can use.

[0907] The "means for recognizing user's emotions" is a function for recognizing and analyzing the user's current emotional state (e.g., joy, sadness, stress).

[0908] The "means for selecting an appropriate recipe based on emotional data" is a technology that takes into consideration the recognized emotional data of a user and selects a recipe that is appropriate for that emotional state.

[0909] "Means for selecting an optimal recipe taking into consideration user preference information and allergy information" refers to a technology that refers to information about a user's individual preferences and allergies and selects an optimal recipe.

[0910] "Means for managing food ingredient inventory and automatically linking inventory data" refers to a management system that monitors food ingredient inventory and automatically links the necessary information to a database, etc.

[0911] This invention is a system for efficiently managing ingredients and proposing recipes in restaurants and homes.

[0912] The user starts by taking a photo of the ingredients in the refrigerator using a device such as a smartphone. The device then uploads the captured image data and the ingredient information manually entered by the user to the server. The user also inputs their current emotional state (e.g., joy, sadness, stress) using the emotion engine.

[0913] The server then launches an AI image analysis module (such as OpenCV) on the received image data to identify the ingredients in the refrigerator. This generates an ingredient list, such as "chicken," "carrots," and "cabbage." The server then stores this ingredient list as a result of this analysis in a database, and simultaneously records the received emotion data.

[0914] Next, the server invokes a generative AI model (e.g., HuggingFace's Transformer library) and provides the identified ingredient list and emotion data as input. This generative AI generates prompts based on the given ingredient list and emotion data, and generates multiple recipes. For example, if the user is recognized as "stressed," a particularly easy and relaxing recipe is generated.

[0915] The generated recipes are compared with the user's preference and allergy information to select the most suitable recipe. The selected recipe list is sent to the user's device, and the user can choose from the suggested recipes and start cooking.

[0916] As a concrete example, the following prompt is input to the generator AI:

[0917] "Generate recipes using chicken, carrots, and cabbage when you're feeling stressed."

[0918] Another example of application for restaurants is that store employees can take photos of the inside of the refrigerator with their smartphones and upload them to an app, which can help streamline inventory management. If an employee feels tired, the generative AI can suggest a relaxing recipe, such as "Easy Chicken and Cabbage Consommé Soup," which can then be immediately made available on the menu.

[0919] In this way, by combining emotion recognition with ingredient information, it becomes possible to suggest recipes that meet the user's psychological and physical needs, thereby improving customer satisfaction and streamlining ingredient management.

[0920] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0921] Step 1:

[0922] The user takes a photo of the contents of the refrigerator using a smartphone and manually inputs the ingredients. This data is stored on the smartphone, and the user also inputs their current emotional state (e.g., stress, joy) through the device. The input data includes the photo data, manually input ingredients, and emotional data.

[0923] Step 2:

[0924] The device uploads the photo data, manually entered ingredient information, and emotion data entered by the user to the server, which then sends the data as a package to the server, where it is stored.

[0925] Step 3:

[0926] The server passes the received photo data to an AI image analysis module to identify the ingredients in the refrigerator. This analysis process uses an image processing library such as OpenCV to generate a list of ingredients such as "chicken," "carrots," and "cabbage." The input data is the photo data, and the output data is the list of identified ingredients.

[0927] Step 4:

[0928] The server stores the identified ingredient list in a database and simultaneously records the received emotion data. This recorded data is used for later recipe generation. The input data is the ingredient list and emotion data, and the output data is the result stored in the database.

[0929] Step 5:

[0930] The server inputs the saved ingredient list and emotion data into a generative AI model to generate an appropriate recipe. Using a generative AI model (e.g., HuggingFace's Transformer library), a prompt based on the ingredient list and emotion data is generated, and the recipe is generated by sending the prompt to the model. The input data is the ingredient list and emotion data, and the output data is the generated recipe list. Example: Prompt: "Please generate a recipe using chicken, carrots, and cabbage for when I'm feeling stressed."

[0931] Step 6:

[0932] The server compares the generated recipe list with the user's preference and allergy information to select the most suitable recipe. In this comparison process, the server compares the user information in the database with the generated recipes to select the most suitable candidates. The input data is the generated recipe list and the user's preference and allergy information, and the output data is the list of suitable recipes.

[0933] Step 7:

[0934] The server sends the optimal recipe list to the user's device. The user can view the received recipe list through the device, select a desired recipe, and start cooking. The input data is the optimal recipe list, and the output data is the recipe list displayed on the user's device.

[0935] In this way, a system is constructed that can suggest optimal recipes based on the user's emotional state and ingredient information.

[0936] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0937] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0938] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0939] [Fourth embodiment]

[0940] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0941] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0942] 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).

[0943] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0944] 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.

[0945] 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).

[0946] 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.

[0947] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0948] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0949] 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.

[0950] 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.

[0951] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0952] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0953] The purpose of this invention is to realize a system that acquires ingredient information entered by a user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user. This system is designed to support inventory management in restaurants and diversify cooking at home.

[0954] The program and processing of this system can be explained as follows.

[0955] Program processing

[0956] Users can take a photo of the inside of their refrigerator and upload it to the system using their smartphone or tablet. At the same time, they can also manually enter ingredient information. The device then sends the captured image or manually entered ingredient information to the server.

[0957] The server launches an AI image analysis module to analyze the image sent. This module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the list as is.

[0958] Next, the server launches a generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list. This generation process also takes into account the user's preferences and allergy information. The server then sends the generated recipes to the terminal to be provided to the user.

[0959] Examples:

[0960] When a user takes a photo of the contents of their refrigerator with their smartphone and uploads it, the server analyzes the image and identifies chicken, carrots, and cabbage.The server then uses generative AI to generate recipes such as "Chicken and Carrot Stew" or "Cabbage and Chicken Stir-fry" from these ingredients and notifies the user of these recipes.The user then creates a dish based on the suggested recipes.

[0961] As a function for restaurants, the server can link with the restaurant's inventory management system and update the stock status of ingredients in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and requests a "grilled dish," the server generates an optimal recipe based on the generative AI and sends it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[0962] Furthermore, it also makes effective use of discarded food ingredients. When restaurants and households send data on food ingredients that are scheduled to be discarded to the server, the server uses generative AI to generate recipes based on these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[0963] To prevent overbuying, the server periodically checks the food data in the user's refrigerator, generates warning messages about duplicate or unused food items, and sends them to the device. This function reduces food waste and allows for proper food management.

[0964] As described above, this system offers a wide range of functions, is highly convenient for users, and enables effective ingredient management and recipe provision. It can also contribute to reducing food waste.

[0965] The processing flow will be explained below.

[0966] Step 1:

[0967] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to their device via the app.

[0968] Step 2:

[0969] The device uploads the saved image to the server. At this time, even if the user manually inputs ingredient information, the data is also sent to the server.

[0970] Step 3:

[0971] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[0972] Step 4:

[0973] The server receives the analysis results from the AI ​​image analysis module and stores the list of identified ingredients (e.g., "chicken," "carrots," and "cabbage") in a database.

[0974] Step 5:

[0975] The server launches the generation AI module and provides the identified ingredient list as input. The generation AI generates multiple recipes based on the ingredient list.

[0976] Step 6:

[0977] The server compares the user's preference information and allergy information with the generated recipes and selects the most suitable recipe.

[0978] Step 7:

[0979] The server transmits the selected recipe list to the user's terminal.

[0980] Step 8:

[0981] The terminal displays the received recipe list to the user, and the user selects from the suggested recipes and starts cooking.

[0982] Step 9:

[0983] The restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time.

[0984] Step 10:

[0985] The server generates optimal recipes based on restaurant inventory data to accommodate mobile orders from users.

[0986] Step 11:

[0987] The kitchen terminal of the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[0988] Step 12:

[0989] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[0990] Step 13:

[0991] The server uses AI to generate recipes that can be effectively used based on ingredients that are scheduled to be discarded, and notifies affiliated bento shops.

[0992] Step 14:

[0993] The server periodically checks the food ingredient data in the user's refrigerator and generates a warning message about duplicate or unused food ingredients.

[0994] Step 15:

[0995] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[0996] Example 1

[0997] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0998] In modern society, food management has become increasingly complex in homes and restaurants, and efficient inventory management and recipe selection are required. In particular, it is a challenge to provide optimal cooking methods that take into account the user's preferences and allergies while minimizing food waste.

[0999] 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.

[1000] In this invention, the server includes a means for acquiring ingredient information entered by the user, a means for identifying ingredients in the storage device through image analysis, a means for generating multiple recipes using a generation AI based on the identified ingredients, and a means for providing the generated recipes to the user, thereby improving the efficiency of ingredient management and making it possible to provide optimal recipes that take into account the user's preferences and allergies.

[1001] "User" refers to any individual or entity that uses the System.

[1002] "Food information" refers to data such as the type, quantity, and expiration date of food stored in a refrigerator or storage device.

[1003] "Storage equipment" refers to equipment such as refrigerators, freezers, and pantries for storing food ingredients.

[1004] "Image analysis" refers to the technology of analyzing image data captured by a camera or smartphone and recognizing specific objects (e.g., food ingredients) contained within it.

[1005] "Generative AI" refers to artificial intelligence that generates new information or content (e.g., cooking methods) based on specified input data.

[1006] "Cooking instructions" refers to recipes that describe how to prepare a dish based on specific ingredients.

[1007] "Preference information" is data relating to the user's preferences, including preferences for seasonings and ingredients of specific dishes.

[1008] "Allergy Information" means data regarding specific ingredients to which a user is allergic.

[1009] "Stock status" refers to information such as the quantity and type of ingredients stored in the storage device.

[1010] "Inventory data" means data that records inventory status.

[1011] This system allows users to efficiently manage ingredient information stored in a storage device and provides optimal recipes using a generative AI model. This system aims to support ingredient inventory management and recipe selection, particularly in homes and restaurants.

[1012] System configuration

[1013] User actions

[1014] Users can use the camera on their smartphone or tablet to take photos of ingredients in their refrigerator or storage unit, then upload the images to the system via their device. Users can also manually enter ingredient information.

[1015] Terminal handling

[1016] The device sends the image acquired from the user or the manually entered ingredient information to the server. When uploading the image, a network communication method such as an HTTP POST request is used.

[1017] Server Processing

[1018] The server launches an AI image analysis module (e.g., TensorFlow, OpenCV) to analyze the received image data. This image analysis module identifies the ingredients in the image and generates an ingredient list, such as "chicken," "carrot," and "cabbage." If the ingredient list is entered manually, the server receives the ingredient list as is.

[1019] Next, the server launches a generative AI module (e.g., GPT-3, BERT) and provides it with the identified ingredient list and the user's preference and allergy information as input. The generative AI module generates multiple recipes based on the input data. The generated recipes are sent from the server to the device and provided to the user.

[1020] Hardware and software used

[1021] This system uses the following hardware and software:

[1022] Hardware: smartphones, tablets, servers

[1023] Software: TensorFlow for image analysis, OpenCV, GPT-3 for generative AI, BERT, network library for HTTP communication

[1024] Specific examples

[1025] 1. The user takes a photo of the inside of the refrigerator with their smartphone and uploads the image to the server via the application.

[1026] 2. The server uses TensorFlow to analyze the image and identify chicken, carrots, and cabbage.

[1027] 3. The server inputs the following prompt to GPT-3: "Could you come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy."

[1028] 4. Recipes generated by GPT-3, such as "Chicken and carrot stew" or "Cabbage and chicken stir-fry," are sent to the user's device.

[1029] 5. Users can create dishes based on these recipes.

[1030] This system, configured in this way, not only provides convenience to users but also contributes to effective ingredient management and the reduction of food waste. For restaurants, linking it to an inventory management system will enable real-time updates of inventory status, which is expected to lead to more efficient operations.

[1031] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1032] Step 1:

[1033] The user takes a photo of the inside of the refrigerator using the camera on their smartphone or tablet. The user then launches the camera app and takes a photo of the food from any position within the storage device. The captured image is saved to the device's photo library.

[1034] Input: Image taken with the camera app

[1035] Output: Image files saved in the device's photo library

[1036] Step 2:

[1037] The user opens the application on the device, selects the image they have taken, and presses the upload button. The user then clicks the "Upload Image" button in the application and selects the image file they have just taken from the file selection dialog. The selected image is then sent to the server via the Internet.

[1038] Input: An image file selected by the user.

[1039] Output: Image data sent to the server

[1040] Step 3:

[1041] The server launches an AI image analysis module to analyze the image data it receives. The server saves the image data received via the HTTP request in a specified directory, and launches an image analysis library such as TensorFlow or OpenCV with the path as an argument.

[1042] Input: Image data received via HTTP request

[1043] Output: Image analysis module is launched

[1044] Step 4:

[1045] The server uses an image analysis module to identify ingredients in the image. The module uses an object detection algorithm (e.g., YOLO, SSD) to identify the ingredients in the image and generate a list of items such as "chicken," "carrot," and "cabbage." The server outputs the location and label of each ingredient in the image as the analysis result.

[1046] Input: The path of the image file passed to the image analysis module

[1047] Output: List of identified ingredients (e.g. "chicken", "carrot", "cabbage")

[1048] Step 5:

[1049] The server starts the generation AI module and provides the identified ingredients list and the user's preference and allergy information as input. The server generates a prompt and calls the GPT-3 or BERT API to request recipe generation.

[1050] Input: List of identified ingredients, user preferences and allergy information

[1051] Output: The generative AI module is triggered

[1052] Step 6:

[1053] The generative AI module generates recipes. For example, it responds to a prompt such as, "Could you think of a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy." It then generates and returns multiple recipes in JSON format.

[1054] Input: Prompt text (e.g., "Could you please come up with a recipe using the following ingredients: chicken, carrots, and cabbage? The user likes spicy food and has a nut allergy.")

[1055] Output: The generated recipe (e.g. "Chicken and carrot stew", "Cabbage and chicken stir fry")

[1056] Step 7:

[1057] The server sends the generated recipe to the terminal. The generated recipe is sent to the terminal in JSON format, and the terminal receives it and displays it on the user interface.

[1058] Input: JSON data of the recipe returned by the generation AI module

[1059] Output: Sends JSON data to the terminal and displays it in the user interface.

[1060] Through each of the above steps, users can effectively manage ingredients and easily obtain multiple cooking methods using the generative AI model.

[1061] (Application example 1)

[1062] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1063] Conventional systems were able to suggest recipes based on food stored in a home storage device, but no system existed that could instantly analyze food combinations purchased in stores and suggest appropriate recipes to consumers. As a result, when consumers purchased food in stores, they sometimes did not know how to cook the food, which discouraged their desire to purchase it. In addition, there were insufficient methods for managing food inventory in stores and for effectively utilizing discarded food. A new system was needed to solve these problems.

[1064] 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.

[1065] In this invention, the server includes a means for acquiring ingredient information entered by a user, a means for identifying foods in the storage device through image analysis, a means for generating multiple recipe suggestions using AI based on the identified foods, a means for providing the generated recipe suggestions to the user, and a means for customers to acquire and analyze images of food on shelves in a store and provide recipe suggestions. This enables optimal recipe suggestions based on food at home and in stores. It also effectively manages food inventory in stores and reduces food waste.

[1066] The "means for acquiring ingredient information entered by the user" is a function that allows ingredient information manually entered by the user using a smartphone, tablet device, etc. to be sent to the server, and for that information to be received by the system.

[1067] "Means for identifying food in a storage device through image analysis" refers to a function that processes photographic data taken by a user in a storage device using an image analysis algorithm to automatically recognize and identify food in the photograph.

[1068] "Means for generating multiple dish suggestions using generative AI based on identified foods" refers to a function that automatically generates multiple dish suggestions using a generative AI model based on a food list obtained through image analysis or user input.

[1069] The "means for providing the generated recipe suggestions to the user" is a function that notifies the user's terminal of the recipe suggestions generated by the system, allowing the user to view the information.

[1070] "A means for customers to acquire, analyze, and suggest dishes from images of food on store shelves" refers to a function that allows customers to take photos of store shelves with their smartphones and upload those images to the system, which then identifies and analyzes the food on the shelves and generates and provides optimal dish suggestions based on the results.

[1071] The system that realizes this application example automatically recognizes and analyzes food items in refrigerators and on store shelves, and then makes recipe suggestions based on that information. The system consists of a user terminal, an image analysis module, a generative AI module, and a server.

[1072] First, users take a photo of the storage device or store shelves using their smartphone or tablet device, and then upload the photo to the server. Users can also manually enter ingredient information. The server uses an image analysis module to identify foods based on the provided photo. High-performance analysis algorithms such as OpenCV and YOLOv3 are used for image analysis.

[1073] After the food items are identified, the server passes this information to a generative AI module, which then makes recipe suggestions based on food information in supermarkets and home storage devices. For this purpose, a natural language generation model such as GPT-2 is used as the generative AI model. The generated recipe suggestions also take into account the user's preferences and allergies. The server then sends the generated recipe suggestions to the user's device, where they can be viewed by the user.

[1074] As a concrete example, consider the following case:

[1075] 1. A customer takes a photo of a supermarket shelf with their smartphone, opens the application and uploads the photo.

[1076] 2. The server analyzes the image and identifies tomatoes, chicken, cabbage, etc.

[1077] 3. The generative AI module generates dish suggestions based on these ingredients, such as "chicken stew with tomatoes."

[1078] 4. The recipe suggestions are sent to the user's device, and the user can then purchase the food based on the suggestions.

[1079] An example of a prompt for a generative AI model is:

[1080] Generate a recipe using the following ingredients: chicken, tomatoes, carrots, cabbage, and onions.

[1081] This system allows users to instantly receive appropriate recipe suggestions based on the food they have in stores or at home, contributing to increased purchasing motivation and reduced food waste.

[1082] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1083] Step 1:

[1084] A user uses a smartphone or tablet to take a photo of the storage device or the shelves in the store. This photo becomes the input data. The user can also manually input ingredient information. The input data includes image data and manually entered ingredient information.

[1085] Step 2:

[1086] The terminal transmits the photos taken by the user and the food ingredient information entered by the user to the server. In this transmission process, image data and manually entered text data are sent to the server.

[1087] Step 3:

[1088] The server passes the received image data to an image analysis module, which uses algorithms such as OpenCV and YOLOv3. The image analysis module identifies each ingredient in the image. As a result of the analysis, a list of identified ingredients is generated.

[1089] Step 4:

[1090] If there is any manually entered ingredient information, the server adds it to the ingredient list as is. The final ingredient list is completed. The output at this stage is the identified ingredient list.

[1091] Step 5:

[1092] The server passes the identified ingredient list to a generative AI module, which uses a pre-trained generative AI model (e.g., GPT-2) to generate multiple recipe suggestions. In this process, the ingredient list is used as input, and the generative AI outputs a recipe based on it.

[1093] Step 6:

[1094] The server selects the most suitable recipe from multiple recipe suggestions generated based on the user's preferences and allergies. This selection process uses a filtering function to output a list of recipes that suit the user.

[1095] Step 7:

[1096] The server sends the optimal recipe suggestions to the user device, which then notifies the user and makes the information available for viewing. The final output is a recipe suggestion that is displayed on the user device.

[1097] Step 8:

[1098] Users can then take the suggestions provided, select the appropriate ingredients, and prepare their meal, which will increase purchasing motivation and encourage behavior that contributes to reducing food waste.

[1099] 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.

[1100] This invention is a system that acquires ingredient information entered by the user, identifies ingredients in the refrigerator through image analysis, generates multiple recipes based on the identified ingredients using a generation AI, and provides the generated recipes to the user, in addition to a system that combines an emotion engine that recognizes the user's emotions. This system is designed to realize inventory management for restaurants, diversify cooking at home, and respond to user emotions.

[1101] Program processing

[1102] The program process in this system begins when the user takes a photo of the inside of the refrigerator and uploads the image and their emotional state to the system via their terminal. The user can also manually input ingredient information, and simultaneously use the emotion engine to obtain their current emotional state (e.g., joy, sadness, stress).

[1103] The specific program process is as follows:

[1104] Users can take pictures of the inside of their refrigerator using their smartphones, and the image data is saved on the device using the app. Users can also manually enter ingredient information and simultaneously input emotions by launching an emotion engine within the app.

[1105] The device uploads the saved images and manually entered data to the server, along with the emotion data.

[1106] The server launches an AI image analysis module to analyze the received image, which identifies the ingredients in the image and generates a list of ingredients such as "chicken," "carrots," and "cabbage."

[1107] The server receives the ingredient list as the analysis result and stores it in a database. It also records the received emotion data.

[1108] The server then launches a generative AI module, which receives the identified ingredient list and emotional data as input. The generative AI generates multiple recipes based on the ingredient list and emotional data. For example, if the user is recognized as "tired," a particularly easy and relaxing recipe is generated.

[1109] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in the selection of a recipe that is most appropriate for the user.

[1110] The server sends the selected recipe list to the user's terminal.

[1111] The device displays the received recipe list to the user, who can then select a recipe from the suggested recipes and begin cooking.

[1112] As a function for restaurants, the restaurant's inventory management system periodically sends inventory data to the server, updating the server's database in real time. Users can input their desired ingredients and dishes through the mobile ordering service. For example, if a user selects "chicken," "carrots," and "cabbage" and indicates "stress," the AI ​​generator will suggest a recipe with a particularly relaxing effect and send it to the restaurant's kitchen terminal. As a result, the restaurant can serve food based on the generated recipe.

[1113] Furthermore, it also enables the effective use of discarded food ingredients. When food data for food items to be discarded is sent to the server from restaurants and households, the server uses generative AI to generate recipes that can effectively use these ingredients, and partner bento shops can use these recipes to create and sell eco-friendly bento boxes.

[1114] To prevent overbuying, the server periodically checks the food data in the user's refrigerator and generates and sends warning messages to the device about duplicate or unused food items. This function reduces food waste and allows for proper food management.

[1115] By incorporating user emotion recognition, this system goes beyond simply proposing recipes and can also suggest optimal ways to use ingredients and dishes based on the user's emotional state, thereby increasing the user's psychological satisfaction and supporting a healthier diet.

[1116] The processing flow will be explained below.

[1117] Step 1:

[1118] The user takes a photo of the inside of the refrigerator with their smartphone and saves the image to the device through the app. At the same time, the app activates an emotion engine and inputs the user's current emotional state (e.g., joy, stress, etc.).

[1119] Step 2:

[1120] The device uploads the saved images, emotion data, and manually entered ingredient information to the server, along with the user's emotion information.

[1121] Step 3:

[1122] The server launches an AI image analysis module to analyze the received images, which recognizes objects in the images and identifies ingredients in the refrigerator.

[1123] Step 4:

[1124] The server receives the analysis results from the AI ​​image analysis module and stores the identified ingredients (e.g., "chicken," "carrot," "cabbage") in a database. The received emotion data is also recorded at the same time.

[1125] Step 5:

[1126] The server launches a generative AI module, which receives the identified ingredients and the user's emotional data as input. The generative AI generates multiple recipes based on this data.

[1127] Step 6:

[1128] The server compares the generated recipes with the user's preferences and allergies to select the most suitable recipe. The server also takes into account the user's emotional state, resulting in a recipe that is more suitable for the user.

[1129] Step 7:

[1130] The server transmits the selected recipe list to the terminal.

[1131] Step 8:

[1132] The device displays the received recipe list to the user, who then selects a recipe from the suggested recipes and begins cooking.

[1133] As a concrete example, if a user is recognized as being in a "stressed" state and there are "chicken," "carrots," and "cabbage" in the refrigerator, the generative AI will suggest recipes that are effective in reducing stress, such as "easy stewed chicken and carrots."

[1134] Step 9:

[1135] A restaurant's inventory management system periodically sends inventory data to a server and updates the database in real time.

[1136] Step 10:

[1137] A user inputs his / her preferences for ingredients and dishes and his / her emotional state through the mobile ordering service and sends an order request to the server.

[1138] Step 11:

[1139] The server uses generative AI to select the optimal recipe based on the order request and inventory data, and sends it to the restaurant's kitchen terminal.

[1140] Step 12:

[1141] The kitchen terminal in the restaurant receives instructions from the server, cooks the dish selected by the user, and serves it.

[1142] Step 13:

[1143] Food ingredient data to be discarded is sent from restaurants and homes to a server.

[1144] Step 14:

[1145] The server uses AI to generate recipes that can be effectively used based on data on ingredients that are scheduled to be discarded, and notifies the system of affiliated bento shops of these recipes.

[1146] Step 15:

[1147] The server periodically checks the food ingredient data in the user's refrigerator, generates warning messages about duplicated or unused food ingredients, and sends them to the terminal.

[1148] Step 16:

[1149] The terminal notifies the user of a warning message and encourages consumption of ingredients.

[1150] Example 2

[1151] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1152] In recent years, the effective use and management of ingredients has become increasingly important in homes and restaurants. However, conventional recipe suggestion systems have difficulty in proposing recipes that take into account the user's emotional state, and they are unable to handle ingredient inventory management and allergy information in an integrated manner. Therefore, there is a need for an efficient system that provides optimal recipes that reflect the user's emotional state and preference information, and also includes ingredient inventory management.

[1153] 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.

[1154] In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients and the user's emotional state, and means for providing the generated recipes to the user. This enables efficient ingredient management by integrating optimal recipe suggestions that take the user's emotional state into consideration and ingredient inventory management and allergy information.

[1155] "Ingredient information" is data about the food and ingredients present in the refrigerator, which is manually entered by the user or obtained through image analysis.

[1156] "Image analysis" is the process by which an AI module recognizes and identifies specific ingredients from images taken with a camera or smartphone.

[1157] "Generative AI" refers to artificial intelligence that generates new information (in this case, recipes) based on input data, typically using natural language processing techniques.

[1158] "Emotional state" is data that indicates the type of emotion the user is currently feeling (e.g., stress, fatigue, joy).

[1159] "Preference information" is information about the types of foods the user likes and foods they want to avoid.

[1160] "Allergy information" is information about the user's food allergies, specifically a list of ingredients that may cause allergies.

[1161] "Inventory control" is the process of monitoring and managing the quantity and type of food ingredients stored in refrigerators and within a restaurant.

[1162] A "recipe" is a list of instructions or ingredients for making a dish using specific ingredients.

[1163] A "prompt sentence" is an input sentence that provides specific information to the generative AI and produces a desired output.

[1164] "Terminal" means a hardware device (e.g., smartphone, tablet, or PC) used by a User to access the System.

[1165] The "database" is a system for efficiently storing and managing information such as ingredients, emotional state, preference information, allergy information, and inventory data.

[1166] The present invention is a system in which a user inputs information about ingredients in the refrigerator and their emotional state into the system, and a generation AI generates and provides multiple recipes based on that information. This system is designed to handle inventory management for restaurants, the diversification of home cooking, and the user's emotions. Below, we will explain in detail how to implement this system.

[1167] First, the user takes a photo of the contents of the refrigerator using a device such as a smartphone. This image data is then saved on the device using a dedicated app. The user can also manually enter information about ingredients, such as "two carrots and 300g of chicken." At the same time, the user can input their current emotional state (e.g., "stressed" or "tired") using the emotion engine built into the app.

[1168] The device then uploads the stored image data, manually entered ingredient information, and emotion data to a server using the HTTPS protocol, and the data may be compressed before transmission.

[1169] The server launches an AI image analysis module (e.g., Google Cloud Vision API) to analyze the received image data. This module identifies ingredients in the image and generates a list of ingredients, such as "chicken," "carrot," and "cabbage." The analysis results are returned to the server in JSON format.

[1170] The server then stores the ingredient list and emotion data resulting from this analysis in a database, which stores ingredient information, emotion data, user preference information, allergy information, and other information.

[1171] The server runs a generative AI (e.g., OpenAI GPT-4) that generates multiple recipes based on the identified ingredients and emotional data. Example prompts include:

[1172] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[1173] Based on this prompt, the AI ​​generates recipes such as "chicken and carrot soup" or "cabbage and chicken stir-fry." The server filters the generated recipes based on the user's preferences and allergies to select the most suitable recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded.

[1174] The selected recipe list is sent from the server to the device in JSON format, which the device parses and displays to the user. The user can then select a recipe from the displayed list and start cooking.

[1175] It also has functions for restaurants, and the inventory management system periodically sends inventory data to the server, allowing for real-time inventory management. The created recipes are also sent to devices used in the restaurant's kitchen, allowing for efficient food preparation.

[1176] In this way, the present invention is a system that provides optimal recipes by utilizing the user's emotional state and information about ingredients in the refrigerator, thereby improving the efficiency of ingredient management and diversifying cooking options. Furthermore, by selecting recipes that reflect food allergies and preferences, it is possible to increase user satisfaction.

[1177] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1178] Step 1:

[1179] User takes a photo of the inside of the refrigerator

[1180] The user takes a photo of the inside of the refrigerator using their smartphone. This image data is saved on the device using a dedicated app. The input is the photo of the inside of the refrigerator, and the output is the saved image data.

[1181] Step 2:

[1182] Input of ingredient information and emotion data

[1183] The user manually inputs ingredient information into the app, such as "2 carrots, 300g of chicken," and then uses the app's emotion engine to input their current emotional state (e.g., "stressed"). The input is the manually entered ingredient information and emotion data, and the output is the saved ingredient information and emotion data.

[1184] Step 3:

[1185] Uploading image data and input data

[1186] The device uploads the stored image data, manually entered ingredient information, and emotion data to the server. The upload uses the HTTPS protocol, and the data may be compressed. The input is the image data, ingredient information, and emotion data, and the output is the data sent to the server.

[1187] Step 4:

[1188] Identifying ingredients through image analysis

[1189] The server performs image analysis using the Google Cloud Vision API. Through this analysis, it recognizes ingredients in the image and generates a list of ingredients such as "chicken," "carrot," and "cabbage." The input is the uploaded image data, and the output is the list of ingredients.

[1190] Step 5:

[1191] Saving to a database

[1192] The server stores the ingredient list and emotional data as the analysis results in a database. The data includes ingredient information, emotional data, user preference information, allergy information, etc. The input is the generated ingredient list and emotional data, and the output is the data stored in the database.

[1193] Step 6:

[1194] Recipe Generation

[1195] The server runs a generative AI (e.g., OpenAI GPT-4) to generate multiple recipes using the identified ingredients list and emotion data. Example prompts include:

[1196] "Given the ingredients 'chicken', 'carrot', and 'cabbage', and the user's emotional state being 'stressed', provide several simple and relaxing recipes."

[1197] The input is an ingredient list and emotion data, and the output is the generated recipe.

[1198] Step 7:

[1199] Recipe Selection

[1200] The server filters the generated recipes taking into account the user's preference and allergy information to select the optimal recipe. For example, if the user has a "nut allergy," recipes that use nuts will be excluded. The input is the generated recipe and the user's preference and allergy information, and the output is the selected optimal recipe.

[1201] Step 8:

[1202] Recipe provided

[1203] The server sends the selected recipe list in JSON format to the terminal, which parses it and displays it to the user. The user can select a recipe from the displayed recipe and start cooking. The input is the selected recipe list, and the output is the recipe displayed on the terminal.

[1204] (Application example 2)

[1205] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1206] In conventional restaurants, it has been difficult to properly manage ingredients in the refrigerator and efficiently check inventory status. In addition, recipe suggestions based on emotions are rare, making it difficult to provide dishes that take into account the emotional state of the customer. This has led to a decline in customer satisfaction and the need for more efficient ingredient management.

[1207] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring ingredient information entered by the user, means for identifying ingredients in the refrigerator through image analysis, means for generating multiple recipes using a generation AI based on the identified ingredients, means for providing the generated recipes to the user, means for recognizing the user's emotions, and means for selecting an appropriate recipe based on the emotion data. This improves the efficiency of ingredient management in the refrigerator and enables optimal recipe suggestions based on the customer's emotions.

[1208] The "means for acquiring ingredient information entered by the user" is a function for collecting information about ingredients provided by the user manually or digitally.

[1209] "Means for identifying ingredients in a refrigerator through image analysis" refers to a technology for analyzing images of ingredients in a refrigerator and identifying the type of ingredients.

[1210] "Means for generating multiple recipes using generative AI based on identified ingredients" refers to a function that automatically generates multiple recipes using generative AI based on ingredient information identified through image analysis.

[1211] "Means for providing the generated recipe to the user" refers to means for providing the recipe generated by the generation AI in a form that the user can use.

[1212] The "means for recognizing user's emotions" is a function for recognizing and analyzing the user's current emotional state (e.g., joy, sadness, stress).

[1213] The "means for selecting an appropriate recipe based on emotional data" is a technology that takes into consideration the recognized emotional data of a user and selects a recipe that is appropriate for that emotional state.

[1214] "Means for selecting an optimal recipe taking into consideration user preference information and allergy information" refers to a technology that refers to information about a user's individual preferences and allergies and selects an optimal recipe.

[1215] "Means for managing food ingredient inventory and automatically linking inventory data" refers to a management system that monitors food ingredient inventory and automatically links the necessary information to a database, etc.

[1216] This invention is a system for efficiently managing ingredients and proposing recipes in restaurants and homes.

[1217] The user starts by taking a photo of the ingredients in the refrigerator using a device such as a smartphone. The device then uploads the captured image data and the ingredient information manually entered by the user to the server. The user also inputs their current emotional state (e.g., joy, sadness, stress) using the emotion engine.

[1218] The server then launches an AI image analysis module (such as OpenCV) on the received image data to identify the ingredients in the refrigerator. This generates an ingredient list, such as "chicken," "carrots," and "cabbage." The server then stores this ingredient list as a result of this analysis in a database, and simultaneously records the received emotion data.

[1219] Next, the server invokes a generative AI model (e.g., HuggingFace's Transformer library) and provides the identified ingredient list and emotion data as input. This generative AI generates prompts based on the given ingredient list and emotion data, and generates multiple recipes. For example, if the user is recognized as "stressed," a particularly easy and relaxing recipe is generated.

[1220] The generated recipes are compared with the user's preference and allergy information to select the most suitable recipe. The selected recipe list is sent to the user's device, and the user can choose from the suggested recipes and start cooking.

[1221] As a concrete example, the following prompt is input to the generator AI:

[1222] "Generate recipes using chicken, carrots, and cabbage when you're feeling stressed."

[1223] Another example of application for restaurants is that store employees can take photos of the inside of the refrigerator with their smartphones and upload them to an app, which can help streamline inventory management. If an employee feels tired, the generative AI can suggest a relaxing recipe, such as "Easy Chicken and Cabbage Consommé Soup," which can then be immediately made available on the menu.

[1224] In this way, by combining emotion recognition with ingredient information, it becomes possible to suggest recipes that meet the user's psychological and physical needs, thereby improving customer satisfaction and streamlining ingredient management.

[1225] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1226] Step 1:

[1227] The user takes a photo of the contents of the refrigerator using a smartphone and manually inputs the ingredients. This data is stored on the smartphone, and the user also inputs their current emotional state (e.g., stress, joy) through the device. The input data includes the photo data, manually input ingredients, and emotional data.

[1228] Step 2:

[1229] The device uploads the photo data, manually entered ingredient information, and emotion data entered by the user to the server, which then sends the data as a package to the server, where it is stored.

[1230] Step 3:

[1231] The server passes the received photo data to an AI image analysis module to identify the ingredients in the refrigerator. This analysis process uses an image processing library such as OpenCV to generate a list of ingredients such as "chicken," "carrots," and "cabbage." The input data is the photo data, and the output data is the list of identified ingredients.

[1232] Step 4:

[1233] The server stores the identified ingredient list in a database and simultaneously records the received emotion data. This recorded data is used for later recipe generation. The input data is the ingredient list and emotion data, and the output data is the result stored in the database.

[1234] Step 5:

[1235] The server inputs the saved ingredient list and emotion data into a generative AI model to generate an appropriate recipe. Using a generative AI model (e.g., HuggingFace's Transformer library), a prompt based on the ingredient list and emotion data is generated, and the recipe is generated by sending the prompt to the model. The input data is the ingredient list and emotion data, and the output data is the generated recipe list. Example: Prompt: "Please generate a recipe using chicken, carrots, and cabbage for when I'm feeling stressed."

[1236] Step 6:

[1237] The server compares the generated recipe list with the user's preference and allergy information to select the most suitable recipe. In this comparison process, the server compares the user information in the database with the generated recipes to select the most suitable candidates. The input data is the generated recipe list and the user's preference and allergy information, and the output data is the list of suitable recipes.

[1238] Step 7:

[1239] The server sends the optimal recipe list to the user's device. The user can view the received recipe list through the device, select a desired recipe, and start cooking. The input data is the optimal recipe list, and the output data is the recipe list displayed on the user's device.

[1240] In this way, a system is constructed that can suggest optimal recipes based on the user's emotional state and ingredient information.

[1241] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1242] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1243] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1244] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1245] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1246] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1247] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1248] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1249] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1250] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1251] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1252] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1253] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1254] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1255] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1256] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1257] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1258] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1259] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1260] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1261] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1262] The following is further disclosed regarding the above embodiment.

[1263] (Claim 1)

[1264] A means for acquiring ingredient information input by a user;

[1265] A means for identifying ingredients in a refrigerator through image analysis;

[1266] A means for generating multiple recipes using generative AI based on identified ingredients;

[1267] a means for providing the generated recipe to a user;

[1268] A system including:

[1269] (Claim 2)

[1270] 10. The system according to claim 1, further comprising means for selecting an optimal recipe taking into consideration user preference information.

[1271] (Claim 3)

[1272] The system of claim 1, further comprising means for managing ingredient inventory status and automatically linking inventory data.

[1273] "Example 1"

[1274] (Claim 1)

[1275] A means for acquiring ingredient information input by a user;

[1276] means for identifying ingredients in the storage device by image analysis;

[1277] A means for generating multiple recipes using AI based on identified ingredients;

[1278] means for providing the generated recipe to a user;

[1279] A system including:

[1280] (Claim 2)

[1281] 10. The system according to claim 1, further comprising means for selecting an optimum recipe in consideration of the user's preference information and allergy information.

[1282] (Claim 3)

[1283] The system of claim 1, further comprising means for managing ingredient inventory status and automatically linking inventory data.

[1284] "Application Example 1"

[1285] (Claim 1)

[1286] A means for acquiring ingredient information input by a user;

[1287] means for identifying food in the storage device by image analysis;

[1288] A means for generating multiple recipe suggestions using generative AI based on the identified foods;

[1289] means for providing the generated recipe suggestions to a user;

[1290] A means for customers to acquire and analyze images of food on shelves in a store and make cooking suggestions;

[1291] A system including:

[1292] (Claim 2)

[1293] 10. The system of claim 1, further comprising means for selecting optimal recipe suggestions taking into account user preference information.

[1294] (Claim 3)

[1295] 10. The system of claim 1, further comprising means for managing food inventory and automatically linking inventory data.

[1296] "Example 2: Combining Emotion Engines"

[1297] (Claim 1)

[1298] A means for acquiring ingredient information input by a user;

[1299] A means for identifying ingredients in a refrigerator through image analysis;

[1300] A means for generating multiple recipes using a generative AI based on the identified ingredients and the user's emotional state;

[1301] a means for providing the generated recipe to a user;

[1302] A system including:

[1303] (Claim 2)

[1304] 10. The system according to claim 1, further comprising means for selecting an optimal recipe taking into consideration user preference information and allergy information.

[1305] (Claim 3)

[1306] The system of claim 1, further comprising means for managing ingredient inventory status and automatically linking inventory data.

[1307] "Application example 2 when combining emotion engines"

[1308] (Claim 1)

[1309] A means for acquiring ingredient information input by a user;

[1310] A means for identifying ingredients in a refrigerator through image analysis;

[1311] A means for generating multiple recipes using generative AI based on identified ingredients;

[1312] a means for providing the generated recipe to a user;

[1313] means for recognizing a user's emotion;

[1314] A means for selecting suitable recipes based on emotion data;

[1315] A system including:

[1316] (Claim 2)

[1317] 10. The system according to claim 1, further comprising means for selecting an optimal recipe taking into consideration user preference information and allergy information.

[1318] (Claim 3)

[1319] The system according to claim 1, further comprising means for managing the inventory status of ingredients and automatically linking inventory data. [Explanation of symbols]

[1320] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring ingredient information input by a user; A means for identifying ingredients in a refrigerator through image analysis; A means for generating multiple recipes using generative AI based on identified ingredients; a means for providing the generated recipe to a user; A system including:

2. The system according to claim 1 , further comprising means for selecting an optimum recipe in consideration of user preference information.

3. The system according to claim 1 , further comprising means for managing the inventory status of ingredients and automatically linking inventory data.

Images