System

Abstract

A system is provided.SOLUTION: A system comprising: means for uploading an image of the contents of a refrigerator taken by a user; means for analyzing the received image and identifying ingredients in the image to generate an ingredient list; means for using a generative AI model to generate a cooking recipe based on the generated ingredient list; and means for presenting the generated cooking recipe 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] This invention aims to solve the problem of increasing food waste in households. Many foods used at home are discarded due to expiration dates or forgetting to be used. Many users also find planning their daily meals a hassle. Furthermore, when shopping on the go, they are unable to check the ingredients in the refrigerator, which can lead to duplicate purchases. This increases the amount of food waste, resulting in economic losses and a greater burden on the environment. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: A means for uploading images of the contents of a refrigerator taken by a user. A means for analyzing the received images, identifying ingredients in the images, and generating an ingredient list. A means for using a generative AI model to generate cooking recipes based on the generated ingredient list. This allows users to easily obtain recipes that make effective use of the ingredients they own. A system is provided that includes a means for presenting the generated cooking recipes to the user. Furthermore, by adding a means for the user to send a request to a server to check the contents of the refrigerator while away from home, appropriate purchasing behavior is supported even when away from home. A means for generating cooking recipes that takes into account the nutritional balance of ingredients and cooking time is provided, allowing users to cook healthily and efficiently.

[0006] "User" refers to an individual who operates the system, takes and uploads images of the inside of the refrigerator, and checks and uses suggested recipes.

[0007] "Terminal" refers to a digital device operated by a user, such as a smartphone, tablet, or PC.

[0008] "Server" refers to a computer system that receives data sent by a user, performs various processes in conjunction with an image recognition API and a generative AI model, and sends the results to the user's device.

[0009] "Image recognition API" refers to a program interface that analyzes received image data and identifies ingredients contained within the image.

[0010] "Ingredient list" refers to data that lists information about ingredients contained in an image analyzed by an image recognition API.

[0011] A "generative AI model" refers to an artificial intelligence algorithm that generates a cooking recipe based on a given list of ingredients.

[0012] A "cooking recipe" refers to a document created by a generative AI model that contains information such as cooking steps, required ingredients, cooking time, and nutritional balance.

[0013] A "request" refers to request data that a user sends to a server while away from home in order to check the contents of the refrigerator.

[0014] "The contents of the refrigerator" refers to the ingredients and food stored in the refrigerator.

[0015] "Nutritional balance" refers to the appropriate distribution of nutrients such as protein, fat, carbohydrates, vitamins, and minerals in a cooking recipe. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the inside of their refrigerator, automatically recognizes ingredients in the images, and suggests cooking recipes based on the generated ingredient list. The following describes how to specifically implement the present invention.

[0038] System configuration and operation

[0039] 1. Upload an image

[0040] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[0041] 2. Image analysis and ingredient list generation

[0042] The server identifies the ingredients contained in the image by sending the received image data to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition. The image recognition API analyzes the image and returns data including the names and quantities of the recognized ingredients.

[0043] The server receives the response from the image recognition API and generates an ingredient list based on it. The ingredient list includes the name and quantity of each ingredient in the refrigerator. This ingredient list is saved in a format that allows for easy data exchange, such as JSON.

[0044] 3. Recipe Generation

[0045] The server sends the generated ingredient list to a generative AI model, which can use a natural language processing model such as OpenAI's GPT-4. This model generates an optimal cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[0046] Dish name

[0047] Necessary ingredients

[0048] Cooking Instructions

[0049] Cooking time

[0050] Nutritional balance

[0051] 4. Presenting recipes to users

[0052] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[0053] Specific examples

[0054] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[0055] Tomatoes: 3

[0056] Eggs: 6 pieces

[0057] Milk: 500ml

[0058] Cheese: 200g

[0059] Lettuce: 1 head

[0060] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0061] 1. Dish name: Tomato and cheese omelette

[0062] 2. Ingredients needed: Tomato, egg, milk, cheese

[0063] 3. Cooking Instructions:

[0064] Slice the tomatoes.

[0065] Crack the eggs into a bowl, beat them and add the milk.

[0066] Preheat a frying pan and melt the butter.

[0067] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0068] Finish the omelette.

[0069] 4. Cooking time: 20 minutes

[0070] 5. Nutritional balance: high protein, low fat

[0071] This series of steps allows the user to easily create the right dish. Also, if the user wants to check the contents of the refrigerator while away from home, the server can send the latest ingredient list to the user's terminal, preventing duplicate food purchases.

[0072] As a result, the present invention provides a system that reduces food waste in the home and allows users to use ingredients in a healthy and efficient manner.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[0076] Step 2:

[0077] The device selects the stored image data and uploads it to the server via the application interface.

[0078] Step 3:

[0079] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[0080] Step 4:

[0081] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[0082] Step 5:

[0083] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format or similar.

[0084] Step 6:

[0085] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[0086] Step 7:

[0087] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0088] Step 8:

[0089] The server receives the generated recipe and sends it to the user's device. The recipe is sent in JSON format, for example.

[0090] Step 9:

[0091] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[0092] Step 10:

[0093] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[0094] Step 11:

[0095] When a user launches a smartphone app to check the contents of their refrigerator while away from home, the app sends a request to the server to retrieve the latest list of ingredients.

[0096] Step 12:

[0097] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[0098] Step 13:

[0099] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are away from home and prevent duplicate food purchases.

[0100] Example 1

[0101] 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."

[0102] This invention aims to automate and streamline the management of ingredients stored in home storage devices and the creation of recipe suggestions based on that information. In order for users to specifically understand the contents of the storage device and create appropriate dishes, it is necessary to utilize image recognition technology and generative AI models. However, existing systems have been criticized for their time-consuming manual input of information by users and the difficulty of checking information while away from home.

[0103] 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.

[0104] In this invention, the server includes means for uploading images of the contents of the storage device taken by the user, means for analyzing the received images and identifying items in the images to generate an item list, means for using a generative AI model to generate a cooking recipe based on the generated item list, means for presenting the generated cooking recipe to the user, means for the user to send a request to the server to check the contents of the storage device while away from home, and means for sending the latest item list to the user's terminal, thereby enabling the user to efficiently manage ingredients in the storage device and easily create optimal dishes.

[0105] A "user" is a person who uses the system and requests management of ingredients in the storage device and cooking suggestions.

[0106] "Storage equipment" refers to equipment such as refrigerators and freezers for preserving food.

[0107] The "means for uploading images" is a function for transmitting image data taken by the user to the server.

[0108] The "means for analyzing images" is a function for analyzing received image data using image recognition technology and identifying items in the image.

[0109] The "means for identifying items" is a function that identifies each item in an image through image analysis and extracts its name and quantity.

[0110] The "means for generating an item list" is a function for compiling information about identified items in list format and saving it as data.

[0111] A "generative AI model" is an artificial intelligence model that performs natural language processing based on input data and generates appropriate output (in this case, a cooking recipe).

[0112] The "means for generating cooking recipes" is a function that uses a generative AI model based on a list of items to generate recipes including the name of the dish, the necessary ingredients, cooking steps, etc.

[0113] The "means for presenting a cooking recipe" is a function for transmitting the generated recipe to the user's terminal and displaying it.

[0114] The "means for sending a request to a server" is a function that allows a user to send a specific request to a server in order to check the contents of a storage device while away from home.

[0115] The "means for transmitting the latest item list" is a function that enables the server to transmit the latest item list to the user's terminal.

[0116] "Terminal" refers to a portable electronic device used by a user, such as a smartphone or tablet.

[0117] This invention relates to a system that allows users to specifically grasp the contents of a storage device and create appropriate dishes based on that information. This system allows users to take and upload images of the contents of the storage device, automatically recognizes the items in the images, and suggests cooking recipes based on the generated list of items.

[0118] System configuration and operation

[0119] 1. Upload an image

[0120] Users take pictures of the contents of the storage device using a device such as a smartphone or tablet. The images are then uploaded to a server via a dedicated application. To do this, users open the app, select the option "Upload images from storage device," and take or select an image. Next, they press the "Upload" button to send the image to the server.

[0121] 2. Image analysis and item list generation

[0122] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition) to identify the items contained in the image. Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API performs analysis and returns the names and quantities of the recognized items as a response. The server receives this response and generates an item list. The item list stores the name and quantity of each item in the storage device in JSON format.

[0123] 3. Recipe Generation

[0124] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates an optimal cooking recipe. This recipe includes the name of the dish, the required ingredients, cooking steps, cooking time, and nutritional balance.

[0125] 4. Presenting recipes to users

[0126] The server sends the cooking recipes generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application, and then received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The user opens the application, selects the "Suggested Recipes" section, selects the desired recipe from the displayed recipes, and checks the detailed information. The detailed information includes the steps for each dish, the required ingredients, cooking time, and nutritional balance.

[0127] Specific examples

[0128] For example, a user may take an image of the inside of a storage device and the following items may be recognized:

[0129] Tomatoes: 3

[0130] Eggs: 6 pieces

[0131] Milk: 500ml

[0132] Cheese: 200g

[0133] Lettuce: 1 head

[0134] The server sends this list of items to a generative AI model, which generates a recipe like this:

[0135] 1. Dish name: Tomato and cheese omelette

[0136] 2. Ingredients needed: Tomato, egg, milk, cheese

[0137] 3. Cooking Instructions:

[0138] Slice the tomatoes.

[0139] Crack the eggs into a bowl, beat them and add the milk.

[0140] Preheat a frying pan and melt the butter.

[0141] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0142] Finish the omelette.

[0143] 4. Cooking time: 20 minutes

[0144] 5. Nutritional balance: high protein, low fat

[0145] The recipe is displayed on the user's device, allowing the user to easily follow the steps to create the dish. Furthermore, if the user wants to check the contents of the storage device while away from home, the server can send the latest item list to the device, preventing duplicate food purchases. This reduces food waste in the home and provides a system that allows users to use items in a healthy and efficient manner.

[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0147] Step 1:

[0148] Users use their smartphones or tablets to take pictures of the contents of the storage device. The images are then uploaded to the server via a dedicated application. Specifically, users open the app, select the option "Upload images from storage device," and take or select an image. Then, by pressing the "Upload" button, the captured image data is sent to the server. The input is the image taken by the user, and the output is the image data sent to the server.

[0149] Step 2:

[0150] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition). Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API analyzes the input image and identifies the objects contained in the image. The response returned by the API includes the names and quantities of the identified objects. The input is the image data received by the server, and the output is the response data (names and quantities of objects) from the image recognition API.

[0151] Step 3:

[0152] The server receives the response from the image recognition API and generates a list of items based on it. This list indicates the name and quantity of each item in the storage device and is saved in JSON format. The input is the response data from the image recognition API, and the output is the generated list of items. Specifically, the server analyzes the data in the response, extracts the name and quantity of each item, and compiles them into a list.

[0153] Step 4:

[0154] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates the optimal cooking recipe. The input is a list of items in JSON format, and the output is the generated cooking recipe.

[0155] Step 5:

[0156] The server sends the cooking recipe generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application and received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The input is the cooking recipe data sent from the server, and the output is the cooking recipe displayed on the device.

[0157] Step 6:

[0158] The user opens the application and selects the "Suggested Recipes" section. They select the recipe they want from the displayed list and view the detailed information, which includes the steps, ingredients needed, cooking time, and nutritional balance for each dish. The input is the recipe selected by the user, and the output is the detailed information displayed.

[0159] (Application example 1)

[0160] 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."

[0161] Conventional systems had limited functionality for identifying ingredients in the home and suggesting appropriate dishes, making it difficult for users to efficiently manage items in storage devices. Furthermore, even in brick-and-mortar stores, there were few mechanisms for customers to receive on-the-spot recipe suggestions based on the product list in the store, and suggestions for making effective use of ingredients were lacking. As a result, users and customers frequently wasted ingredients, creating a food waste problem.

[0162] 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.

[0163] In this invention, the server includes a means for uploading images of items in the storage device taken by the user, a means for analyzing the received images, identifying the items in the images, and generating an item list, and a means for using a generative AI model to generate recipes based on the generated item list. This allows users and customers to efficiently identify the items in the storage device and provide appropriate recipes. Specifically, when a user takes a photo of the contents of the storage device with their smartphone and uploads it, appropriate recipes are presented in real time using image analysis and the generative AI model, allowing ingredients to be used effectively without waste. The system can also be applied as a customer service in physical stores, providing a system that allows users to obtain recommended recipes from images of product shelves taken on the spot.

[0164] "Storage device"

[0165] is a general term for facilities and equipment used to preserve food and goods.

[0166] "Goods"

[0167] is a general term for all physical items that are subject to image analysis, such as food and merchandise stored in refrigerators and stores.

[0168] How to upload images

[0169] A camera is a device or system that has the function of transmitting image data captured by a user to a server via a network.

[0170] "Image analysis"

[0171] is a technique for processing received image data and identifying items contained within the image.

[0172] "List of Items"

[0173] This is data in the form of a list that includes the names and quantities of items identified through image analysis.

[0174] "Generative AI model"

[0175] is an algorithm or system that uses artificial intelligence to generate specific results or information based on input data.

[0176] "Cooking method"

[0177] is a general term for the steps and methods of cooking a dish using specific ingredients.

[0178] "Means of presenting to the user"

[0179] A recipe manager is a device or system that has the function of displaying the generated recipe to the user.

[0180] A way to send a request to the server

[0181] A storage device is a device or system that has the function of allowing a user to request information stored in a storage device from a server from a specified location.

[0182] "Terminal"

[0183] A device is an electronic device that is operated by a user, and includes smartphones, tablets, personal computers, etc.

[0184] "Nutritional balance"

[0185] This is a concept that refers to a healthy combination of ingredients, taking into account the type and amount of food ingredients in the cooking method.

[0186] "Cooking time"

[0187] is a general term for the time it takes to complete a dish according to a specific cooking method.

[0188] The present invention relates to a system that allows a user to efficiently manage items in a storage device and suggests appropriate recipes based on the managed items. Specific embodiments of this system will be described below.

[0189] System configuration and operation

[0190] 1. Upload an image

[0191] Users take photos of items in the storage device using a device such as a smartphone or tablet, and upload the images to the server via an application. The uploaded images are then processed on the cloud server.

[0192] 2. Image analysis and item list generation

[0193] The server sends the received image data to an image recognition API to identify the items contained in the image. This process uses common cloud services that provide image recognition technology (such as Google Cloud Vision API or Amazon Rekognition). The image recognition API analyzes the image and returns the names and quantities of the recognized items. The server generates an item list based on the response from the image recognition API. The item list contains the name and quantity of each item in the storage device, and this list is saved in JSON format or similar.

[0194] 3. Recipe generation

[0195] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model such as OpenAI's GPT series model. This model generates optimal recipes based on the ingredient list. The recipes include the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0196] 4. Presenting recipes to users

[0197] The generated recipes are sent from the server to the user's device and displayed to the user through the application. The user can select the recipe they want and check the detailed information.

[0198] Hardware and software used

[0199] Smartphones and tablets: Used by users to take pictures of items in the storage unit and upload the images.

[0200] Cloud server: Receives and analyzes image data, generates an ingredient list, and generates recipes using a generative AI model.

[0201] Image Recognition API: Use an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to automatically identify objects in images.

[0202] Generative AI models, such as OpenAI GPT-4, are used to generate appropriate recipes.

[0203] Specific examples

[0204] For example, a user may take a picture of the inside of a storage unit and recognize the following items:

[0205] Tomatoes: 3

[0206] Eggs: 6 pieces

[0207] Milk: 500ml

[0208] Cheese: 200g

[0209] Lettuce: 1 head

[0210] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0211] 1. Dish name: Tomato and cheese omelette

[0212] 2. Supplies needed: Tomatoes, eggs, milk, cheese

[0213] 3. Cooking Instructions:

[0214] Slice the tomatoes.

[0215] Crack the eggs into a bowl, beat them and add the milk.

[0216] Preheat a frying pan and melt the butter.

[0217] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0218] Finish the omelette.

[0219] 4. Cooking time: 20 minutes

[0220] 5. Nutritional balance: high protein, low fat

[0221] Prompt Sentence Examples

[0222] Suggest a recipe based on the following list of items:

[0223] Tomatoes: 3

[0224] Eggs: 6 pieces

[0225] Milk: 500ml

[0226] Cheese: 200g

[0227] Lettuce: 1 head

[0228] This series of steps allows users to easily select and prepare the appropriate recipe, which makes efficient use of stored items and reduces food waste.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1:

[0231] Users take photos of items in the storage device using a smartphone or tablet. The images are then uploaded to a cloud server via a dedicated application. The input is the captured image data, and the output is an image file uploaded to the cloud server.

[0232] Step 2:

[0233] The server sends the image to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to analyze the received image data. The input is the image data received by the server, and the output is the analysis results, including the names and quantities of items in the image.

[0234] Step 3:

[0235] The server generates an item list based on the analysis results obtained from the image recognition API. This item list includes the name and quantity of each item and is saved in JSON format or similar. The input is the analysis result data from the image recognition API, and the output is the item list.

[0236] Step 4:

[0237] The server sends the generated item list to a generative AI model, a natural language processing model, to generate a recipe. In this process, a prompt is used as input to the generative AI model, which then outputs the optimal recipe. The input is the item list and the prompt, and the output is the generated recipe.

[0238] Step 5:

[0239] The server sends the recipe generated by the generative AI model to the user's device, where the user can check the recipe using a dedicated application. The input is the generated recipe, and the output is the recipe displayed on the user's device.

[0240] Step 6:

[0241] The user selects the necessary ingredients based on the recipe provided and performs the cooking. The input is the recipe sent from the server, and the output is the cooking result performed by the user.

[0242] This series of processes enables the user to efficiently manage the items in the storage device and obtain appropriate recipes.

[0243] 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.

[0244] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized recipe suggestions become possible. The following describes how the present invention can be specifically implemented.

[0245] System configuration and operation

[0246] 1. Upload an image

[0247] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[0248] 2. Image analysis and ingredient list generation

[0249] The server sends the received image data to an image recognition API to identify the ingredients contained in the image. For example, it uses common image recognition technology to identify the names and quantities of ingredients. Based on the analysis results, it generates an ingredient list. This ingredient list is saved in JSON format or similar.

[0250] 3. Recipe Generation

[0251] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model, for example, to generate a cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[0252] Dish name

[0253] Necessary ingredients

[0254] Cooking Instructions

[0255] Cooking time

[0256] Nutritional balance

[0257] 4. Utilizing the Emotion Engine

[0258] The server uses an emotion engine to recognize the user's emotions using images captured by the user and information acquired from the user interface. This emotion engine grasps the user's emotional state through, for example, voice recognition, image analysis, and touch interface.

[0259] The type of recipe and cooking method are customized based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect. The system also has an interface for providing notifications and suggestions that reflect the user's emotions.

[0260] 5. Presenting recipes to users

[0261] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[0262] Specific examples

[0263] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[0264] Tomatoes: 3

[0265] Eggs: 6 pieces

[0266] Milk: 500ml

[0267] Cheese: 200g

[0268] Lettuce: 1 head

[0269] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0270] 1. Dish name: Tomato and cheese omelette

[0271] 2. Ingredients needed: Tomato, egg, milk, cheese

[0272] 3. Cooking Instructions:

[0273] Slice the tomatoes.

[0274] Crack the eggs into a bowl, beat them and add the milk.

[0275] Preheat a frying pan and melt the butter.

[0276] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0277] Finish the omelette.

[0278] 4. Cooking time: 20 minutes

[0279] 5. Nutritional balance: high protein, low fat

[0280] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[0281] Check the contents of your refrigerator when you're out

[0282] When a user is out and about, they launch the app on their smartphone and send a request to the server. In response to this request, the server retrieves the latest ingredient list and sends it to the user's device. The device then analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and prevent duplicate food purchases.

[0283] This reduces food waste in the home and provides a system that allows users to use ingredients in a healthy and efficient manner. Furthermore, personalized recipe suggestions that take into account the user's emotional state can further increase user satisfaction.

[0284] The processing flow will be explained below.

[0285] Step 1:

[0286] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[0287] Step 2:

[0288] The device selects the stored image data and uploads it to the server via the application interface.

[0289] Step 3:

[0290] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[0291] Step 4:

[0292] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[0293] Step 5:

[0294] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format.

[0295] Step 6:

[0296] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[0297] Step 7:

[0298] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0299] Step 8:

[0300] The server receives the generated recipe and sends it to the user's device in JSON format.

[0301] Step 9:

[0302] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[0303] Step 10:

[0304] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[0305] Step 11:

[0306] The server analyzes the user interface, images, and audio data to understand the user's emotions, and determines the user's emotional state from the user's facial expressions and tone of voice.

[0307] Step 12:

[0308] The emotion engine analyzes the user's emotions and sends the emotion data, which can include stress, joy, excitement, etc., to the server.

[0309] Step 13:

[0310] The server receives data from the emotion engine and adjusts the recipe content based on the user's emotions. For example, if the user is under a lot of stress, it will select recipes that use ingredients that have a relaxing effect.

[0311] Step 14:

[0312] The server regenerates the adjusted recipe and sends it to the user's device, allowing the user to receive recipe suggestions tailored to their emotional state.

[0313] Step 15:

[0314] A user sends a request to the server via a smartphone app to check the contents of the refrigerator while away from home. The request is to obtain the latest list of ingredients.

[0315] Step 16:

[0316] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[0317] Step 17:

[0318] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and about, and avoid buying unnecessary food.

[0319] Example 2

[0320] 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."

[0321] In modern households, it is difficult to efficiently manage the contents of the refrigerator, resulting in inappropriate food purchases and food waste. Furthermore, it is cumbersome to consider appropriate dishes based on the contents of the refrigerator, making it difficult to provide personalized recipes that correspond to the user's emotional state. Furthermore, there are insufficient means to check the contents of the refrigerator while away from home, and a method to prevent duplicate or unnecessary food purchases is needed.

[0322] 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.

[0323] In this invention, the server includes a means for uploading images of the contents of the refrigerator taken by the user, a means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, a means for using a generative AI model to generate cooking recipes based on the generated ingredient list, a means for recognizing the user's emotional state and customizing recipes based on that state, and a means for presenting the generated cooking recipes to the user. This allows users to efficiently manage the contents of their refrigerator, reduce food waste, and easily obtain personalized cooking recipes that match their emotions. It also allows users to check the contents of their refrigerator while away from home and prevent duplicate food purchases.

[0324] "User" refers to a person who uses this system to manage the contents of their refrigerator and obtain cooking recipes.

[0325] The "server" refers to a computer system that receives and analyzes images taken by users and generates ingredient lists and cooking recipes.

[0326] "Image Recognition API" refers to an application programming interface for analyzing received images and identifying the ingredients contained within them.

[0327] "Ingredient list" refers to a list containing the names and quantities of ingredients identified by the image recognition API.

[0328] A "generative AI model" refers to an artificial intelligence model that generates cooking recipes based on an ingredient list.

[0329] An "emotion engine" refers to a system that recognizes a user's emotional state based on images taken by the user and information obtained from the interface.

[0330] A "cooking recipe" refers to information that includes specific cooking steps that users can use, the ingredients needed, cooking time, nutritional balance, and other information.

[0331] "Terminal" refers to a device (e.g., a smartphone or tablet) that a user uses to take pictures of the contents of the refrigerator or check ingredient lists and cooking recipes.

[0332] A "request from outside" refers to a request sent to the server by a user to check the contents of the refrigerator while the user is out.

[0333] "JSON format" refers to the JavaScript Object Notation data structure used to store the ingredient list.

[0334] This invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it enables more personalized recipe suggestions.

[0335] Hardware and software used

[0336] This system uses the following hardware and software:

[0337] 1. User device (e.g. smartphone, tablet)

[0338] Dedicated application: Application for taking and uploading images of the inside of the refrigerator

[0339] Internet connection: allows data transmission to the server

[0340] 2. Server

[0341] Image recognition API (e.g., Google Vision API): Used to identify ingredients in images

[0342] Generative AI models (e.g., GPT-3.5): Generate cooking recipes based on ingredient lists

[0343] Emotion Engine: Recognizes the user's emotional state and uses it to personalize recipes

[0344] Database: Stores ingredient lists and generated recipes

[0345] Specific operation of the system

[0346] 1. Taking and uploading images

[0347] The user uses the device to take pictures of the inside of the refrigerator, which are then uploaded to the server using a dedicated application.

[0348] 2. Image analysis and ingredient list generation

[0349] The server receives the image uploaded by the user. It then sends the image to an image recognition API to identify the ingredients in the image. The server generates an ingredient list based on the analysis results of the image recognition API and saves it in JSON format.

[0350] 3. Recipe Generation

[0351] The server sends the generated ingredient list to the generative AI model. The generative AI model generates a cooking recipe using a prompt. An example of a prompt is shown below.

[0352] You have the following ingredients in your refrigerator:

[0353] Tomatoes: 3

[0354] Eggs: 6 pieces

[0355] Milk: 500ml

[0356] Cheese: 200g

[0357] Lettuce: 1 head

[0358] Can you recommend some easy and delicious recipes using this ingredient?

[0359] 4. Utilizing the Emotion Engine

[0360] The server uses an emotion engine to recognize the user's emotions based on images taken by the user and information obtained from the user interface. Depending on the user's emotional state, the server adjusts the generated cooking recipes, generating personalized recipes, such as using ingredients with a relaxing effect for users who are feeling stressed.

[0361] 5. Presenting the recipe

[0362] The server sends the created recipe to the user's device, where the user can check the recipe and view details through a dedicated application on the device.

[0363] 6. Check the contents of your refrigerator while you're out

[0364] The user uses a dedicated application while on the go to send a request for the latest ingredient list to the server.

[0365] The server retrieves the latest ingredient list and sends it to the user's device, where the user can check the contents of the refrigerator.

[0366] Specific examples

[0367] For example, a user may take a picture of the inside of their refrigerator and the following ingredients may be recognized:

[0368] Tomatoes: 3

[0369] Eggs: 6 pieces

[0370] Milk: 500ml

[0371] Cheese: 200g

[0372] Lettuce: 1 head

[0373] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0374] 1. Dish name: Tomato and cheese omelette

[0375] 2. Ingredients needed: Tomato, egg, milk, cheese

[0376] 3. Cooking Instructions:

[0377] Slice the tomatoes.

[0378] Crack the eggs into a bowl, beat them and add the milk.

[0379] Preheat a frying pan and melt the butter.

[0380] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0381] Finish the omelette.

[0382] 4. Cooking time: 20 minutes

[0383] 5. Nutritional balance: high protein, low fat

[0384] If the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

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

[0386] Step 1:

[0387] Users use a smartphone or tablet to take pictures of the contents of the refrigerator using a dedicated application.

[0388] Input: Image of the contents of the refrigerator

[0389] Output: Image saved on the user's device

[0390] Step 2:

[0391] The device uploads the captured images to a server via a dedicated application, which requires an internet connection.

[0392] Input: Images stored on the user's device

[0393] Output: Image data uploaded to the server

[0394] Step 3:

[0395] The server receives the image data received from the user, then sends this image data to an image recognition API (e.g., Google Vision API) to identify the ingredients contained in the image.

[0396] Input: Image data uploaded to the server

[0397] Output: Ingredient information returned from the image recognition API

[0398] Step 4:

[0399] The server generates an ingredient list based on the image recognition results. This ingredient list includes the names and quantities of ingredients. The server saves this ingredient list in JSON format.

[0400] Input: Ingredient information returned from the image recognition API

[0401] Output: JSON formatted list of ingredients

[0402] Step 5:

[0403] The server sends the generated ingredient list to a generative AI model (e.g., GPT-3.5) using a prompt to instruct it to generate a cooking recipe based on the ingredient list.

[0404] Input: JSON format ingredients list, prompt

[0405] Output: Cooking recipes generated from the generative AI model

[0406] Step 6:

[0407] The server receives the cooking recipes returned by the generative AI model and, if necessary, uses an emotion engine to recognize the user's emotional state, generating a personalized recipe based on the user's emotions.

[0408] Input: Cooking recipes returned by the generative AI model, user emotional state

[0409] Output: personalized cooking recipes

[0410] Step 7:

[0411] The server finally sends the generated and customized cooking recipe to the user's device.

[0412] Input: Personalized cooking recipe

[0413] Output: Cooking recipe sent to the user's device

[0414] Step 8:

[0415] The device displays the received recipes in a dedicated application, allowing the user to select the recipe they want and check the details.

[0416] Input: A cooking recipe sent to the user's device

[0417] Output: Cooking recipe displayed on the device

[0418] Step 9:

[0419] To check the contents of the refrigerator while away from home, the user launches a dedicated application and sends a request to the server.

[0420] Input: Request to check the contents of the refrigerator

[0421] Output: Request data to the server

[0422] Step 10:

[0423] The server retrieves the latest ingredient list and sends it to the user's terminal.

[0424] Input: Request to check the contents of the refrigerator

[0425] Output: Latest ingredients list

[0426] Step 11:

[0427] The device displays the received ingredient list in a dedicated application and notifies the user, allowing the user to avoid purchasing duplicate food items.

[0428] Input: Latest ingredient list

[0429] Output: Ingredient list displayed on the device

[0430] (Application example 2)

[0431] 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."

[0432] Currently, there are systems that track the contents of a refrigerator and suggest appropriate dishes based on that information. However, these systems are unable to suggest recipes that take into account the user's emotions or personal preferences. Furthermore, there are no systems that can efficiently consume ingredients while delivering dishes that correspond to the user's emotional state. This makes it difficult for users to enjoy efficient, personalized cooking without hassle. Furthermore, even if there are systems that can track the contents of a refrigerator while on the go, they lack the functionality to instantly deliver dishes based on that information.

[0433] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0434] In this invention, the server includes means for uploading images of the contents of the refrigerator taken by the user, means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, means for using a generative AI model to generate a cooking recipe based on the generated ingredient list, means for using an emotion engine to recognize the emotional state of the user and customize the recipe based on that emotional state in generating the cooking recipe, and means for allowing the user to select from the generated cooking recipes and delivering food cooked based on the selected recipe.This allows the user not only to know the contents of the refrigerator, but also to receive personalized food suggestions based on that information and to check the contents of the refrigerator while on the go and have food delivered on the spot.

[0435] "User" refers to an individual who uses the system to understand the contents of their refrigerator and receive cooking recipe suggestions and delivery services.

[0436] "Means for uploading images" refers to a function that allows a user to send images of the contents of the refrigerator taken using a device such as a smartphone or tablet to a cloud server.

[0437] "Means for analyzing images" refers to the function for analyzing image data received by the server and recognizing and identifying the ingredients contained therein.

[0438] The means for generating an "ingredient list" refers to a function that compiles ingredient information obtained from analyzed image data into a list format.

[0439] A "generative AI model" refers to artificial intelligence technology that automatically generates cooking recipes based on a list of ingredients.

[0440] "Emotion engine" refers to technology that recognizes the user's emotional state and customizes the cooking recipes provided based on that emotional state.

[0441] "Delivery means" refers to a function for delivering food prepared based on a recipe selected by the user to a location designated by the user.

[0442] "Means for checking while away from home" refers to a function that allows users to check the contents of their refrigerator via their smartphone or tablet even when they are out.

[0443] The "means for transmitting the latest ingredient list" refers to a function that enables the server to transmit the latest ingredient information to the user's terminal.

[0444] "Nutritional balance" refers to the standard for providing healthy menus that take into consideration the nutritional balance of ingredients and dishes.

[0445] "Cooking time" refers to the time required to complete a dish based on a recipe.

[0446] The present invention is a system that allows a user to specifically grasp the contents of their refrigerator and provide appropriate meals based on that information. This system includes a function that proposes personalized recipes taking into account the user's emotional state and delivers meals prepared based on those recipes. Specific embodiments for carrying out the invention are described in detail below.

[0447] System configuration and operation

[0448] 1. Upload an image

[0449] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and then upload the images to a cloud server via a dedicated application.

[0450] 2. Image analysis and ingredient list generation

[0451] The server sends the image data received from cloud storage to an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition), which identifies the ingredients contained in the image and generates an ingredient list. This ingredient list is saved in JSON format or similar.

[0452] 3. Recipe Generation

[0453] The server uses a generative AI model (e.g., OpenAI GPT-3, GPT-4) to generate a cooking recipe based on the generated ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0454] 4. Utilizing the Emotion Engine

[0455] The server uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. It determines the user's emotional state based on information obtained from the user's voice input and touch interface. It customizes recipes based on the emotional state recognized by the emotion engine.

[0456] 5. Creating a delivery request

[0457] Based on the recipe selected by the user, order information is sent to the delivery system, which then prepares the specified dish and delivers it to the user.

[0458] 6. Present recipe to user and confirm order details

[0459] The server sends the created recipe to the user's device, where the user can check the recipe displayed in a dedicated application and confirm the order.

[0460] Specific examples

[0461] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[0462] Tomatoes: 3

[0463] Eggs: 6 pieces

[0464] Milk: 500ml

[0465] Cheese: 200g

[0466] Lettuce: 1 head

[0467] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0468] 1. Dish name: Tomato and cheese omelette

[0469] 2. Ingredients needed: Tomato, egg, milk, cheese

[0470] 3. Cooking Instructions:

[0471] Slice the tomatoes.

[0472] Crack the eggs into a bowl, beat them and add the milk.

[0473] Preheat a frying pan and melt the butter.

[0474] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0475] Finish the omelette.

[0476] 4. Cooking time: 20 minutes

[0477] 5. Nutritional balance: high protein, low fat

[0478] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[0479] Prompt Sentence Examples

[0480] text

[0481] Suggest an easy, healthy recipe using the following ingredient list. The user is stressed, so please consider cooking with ingredients that have a relaxing effect. Ingredient list: 3 tomatoes, 6 eggs, 500ml milk, 200g cheese, 1 lettuce

[0482] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0483] Step 1:

[0484] Image upload

[0485] Users can take a picture of the contents of their refrigerator using a camera app on their smartphone or tablet, and then upload the image to a cloud server via a dedicated application.

[0486] Input: Image file of the contents of the refrigerator

[0487] Output: Image data stored on a cloud server

[0488] Step 2:

[0489] Image analysis and ingredient list generation

[0490] The server retrieves the uploaded image data and analyzes it using an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition). As a result of the analysis, ingredients in the image are identified and an ingredient list is generated based on that information. This ingredient list is saved in JSON format.

[0491] Input: Image data stored on a cloud server

[0492] Output: JSON formatted list of ingredients

[0493] Data processing: Extracting image data as ingredient information and converting it into a list format

[0494] Step 3:

[0495] Recipe Generation

[0496] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a cooking recipe based on the generated ingredient list. The ingredient list is sent to the generative AI model as a prompt, and a recipe is generated that includes the name of the dish, the required ingredients, cooking steps, cooking time, nutritional balance, etc.

[0497] Input: JSON formatted list of ingredients

[0498] Output: Cooking recipe (text format)

[0499] Data computation: Input the list of ingredients as prompts into the AI ​​model to generate a recipe

[0500] Step 4:

[0501] Utilizing the Emotion Engine

[0502] The server analyzes information obtained from voice input and touch interface using an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. Based on the analysis results, the server customizes recipes according to the user's emotional state.

[0503] Input: Voice input data, touch interface data

[0504] Output: Customized cooking recipes

[0505] Data processing: Analyze the user's input data as an emotional state and reflect it in the recipe

[0506] Step 5:

[0507] Generating a delivery request

[0508] The user can check and select a recipe via the application. Then, by requesting delivery of a dish based on that recipe, the order information is sent to the delivery system. The delivery system then prepares and delivers the specified dish.

[0509] Input: Selected recipe

[0510] Output: Delivery order information

[0511] Data calculation: Sends order information to the delivery system based on the selected recipe

[0512] Step 6:

[0513] Present recipes to users and confirm order details

[0514] The server sends the created recipe to the user's device. The user can check the recipe displayed in a dedicated application and confirm the delivery order. Once the order details are confirmed, the final order information is sent to the delivery system.

[0515] Input: Generated cooking recipe

[0516] Output: Recipe displayed on the user's device, confirmed order information

[0517] Data calculation: Sending recipes, checking and confirming order details

[0518] 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.

[0519] 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.

[0520] 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.

[0521] [Second embodiment]

[0522] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0523] 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.

[0524] 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).

[0525] 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.

[0526] 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.

[0527] 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).

[0528] 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.

[0529] 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.

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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."

[0534] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the inside of their refrigerator, automatically recognizes ingredients in the images, and suggests cooking recipes based on the generated ingredient list. The following describes how to specifically implement the present invention.

[0535] System configuration and operation

[0536] 1. Upload an image

[0537] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[0538] 2. Image analysis and ingredient list generation

[0539] The server identifies the ingredients contained in the image by sending the received image data to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition. The image recognition API analyzes the image and returns data including the names and quantities of the recognized ingredients.

[0540] The server receives the response from the image recognition API and generates an ingredient list based on it. The ingredient list includes the name and quantity of each ingredient in the refrigerator. This ingredient list is saved in a format that allows for easy data exchange, such as JSON.

[0541] 3. Recipe Generation

[0542] The server sends the generated ingredient list to a generative AI model, which can use a natural language processing model such as OpenAI's GPT-4. This model generates an optimal cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[0543] Dish name

[0544] Necessary ingredients

[0545] Cooking Instructions

[0546] Cooking time

[0547] Nutritional balance

[0548] 4. Presenting recipes to users

[0549] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[0550] Specific examples

[0551] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[0552] Tomatoes: 3

[0553] Eggs: 6 pieces

[0554] Milk: 500ml

[0555] Cheese: 200g

[0556] Lettuce: 1 head

[0557] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0558] 1. Dish name: Tomato and cheese omelette

[0559] 2. Ingredients needed: Tomato, egg, milk, cheese

[0560] 3. Cooking Instructions:

[0561] Slice the tomatoes.

[0562] Crack the eggs into a bowl, beat them and add the milk.

[0563] Preheat a frying pan and melt the butter.

[0564] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0565] Finish the omelette.

[0566] 4. Cooking time: 20 minutes

[0567] 5. Nutritional balance: high protein, low fat

[0568] This series of steps allows the user to easily create the right dish. Also, if the user wants to check the contents of the refrigerator while away from home, the server can send the latest ingredient list to the user's terminal, preventing duplicate food purchases.

[0569] As a result, the present invention provides a system that reduces food waste in the home and allows users to use ingredients in a healthy and efficient manner.

[0570] The processing flow will be explained below.

[0571] Step 1:

[0572] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[0573] Step 2:

[0574] The device selects the stored image data and uploads it to the server via the application interface.

[0575] Step 3:

[0576] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[0577] Step 4:

[0578] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[0579] Step 5:

[0580] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format or similar.

[0581] Step 6:

[0582] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[0583] Step 7:

[0584] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0585] Step 8:

[0586] The server receives the generated recipe and sends it to the user's device. The recipe is sent in JSON format, for example.

[0587] Step 9:

[0588] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[0589] Step 10:

[0590] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[0591] Step 11:

[0592] When a user launches a smartphone app to check the contents of their refrigerator while away from home, the app sends a request to the server to retrieve the latest list of ingredients.

[0593] Step 12:

[0594] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[0595] Step 13:

[0596] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are away from home and prevent duplicate food purchases.

[0597] Example 1

[0598] 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."

[0599] This invention aims to automate and streamline the management of ingredients stored in home storage devices and the creation of recipe suggestions based on that information. In order for users to specifically understand the contents of the storage device and create appropriate dishes, it is necessary to utilize image recognition technology and generative AI models. However, existing systems have been criticized for their time-consuming manual input of information by users and the difficulty of checking information while away from home.

[0600] 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.

[0601] In this invention, the server includes means for uploading images of the contents of the storage device taken by the user, means for analyzing the received images and identifying items in the images to generate an item list, means for using a generative AI model to generate a cooking recipe based on the generated item list, means for presenting the generated cooking recipe to the user, means for the user to send a request to the server to check the contents of the storage device while away from home, and means for sending the latest item list to the user's terminal, thereby enabling the user to efficiently manage ingredients in the storage device and easily create optimal dishes.

[0602] A "user" is a person who uses the system and requests management of ingredients in the storage device and cooking suggestions.

[0603] "Storage equipment" refers to equipment such as refrigerators and freezers for preserving food.

[0604] The "means for uploading images" is a function for transmitting image data taken by the user to the server.

[0605] The "means for analyzing images" is a function for analyzing received image data using image recognition technology and identifying items in the image.

[0606] The "means for identifying items" is a function that identifies each item in an image through image analysis and extracts its name and quantity.

[0607] The "means for generating an item list" is a function for compiling information about identified items in list format and saving it as data.

[0608] A "generative AI model" is an artificial intelligence model that performs natural language processing based on input data and generates appropriate output (in this case, a cooking recipe).

[0609] The "means for generating cooking recipes" is a function that uses a generative AI model based on a list of items to generate recipes including the name of the dish, the necessary ingredients, cooking steps, etc.

[0610] The "means for presenting a cooking recipe" is a function for transmitting the generated recipe to the user's terminal and displaying it.

[0611] The "means for sending a request to a server" is a function that allows a user to send a specific request to a server in order to check the contents of a storage device while away from home.

[0612] The "means for transmitting the latest item list" is a function that enables the server to transmit the latest item list to the user's terminal.

[0613] "Terminal" refers to a portable electronic device used by a user, such as a smartphone or tablet.

[0614] This invention relates to a system that allows users to specifically grasp the contents of a storage device and create appropriate dishes based on that information. This system allows users to take and upload images of the contents of the storage device, automatically recognizes the items in the images, and suggests cooking recipes based on the generated list of items.

[0615] System configuration and operation

[0616] 1. Upload an image

[0617] Users take pictures of the contents of the storage device using a device such as a smartphone or tablet. The images are then uploaded to a server via a dedicated application. To do this, users open the app, select the option "Upload images from storage device," and take or select an image. Next, they press the "Upload" button to send the image to the server.

[0618] 2. Image analysis and item list generation

[0619] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition) to identify the items contained in the image. Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API performs analysis and returns the names and quantities of the recognized items as a response. The server receives this response and generates an item list. The item list stores the name and quantity of each item in the storage device in JSON format.

[0620] 3. Recipe Generation

[0621] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates an optimal cooking recipe. This recipe includes the name of the dish, the required ingredients, cooking steps, cooking time, and nutritional balance.

[0622] 4. Presenting recipes to users

[0623] The server sends the cooking recipes generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application, and then received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The user opens the application, selects the "Suggested Recipes" section, selects the desired recipe from the displayed recipes, and checks the detailed information. The detailed information includes the steps for each dish, the required ingredients, cooking time, and nutritional balance.

[0624] Specific examples

[0625] For example, a user may take an image of the inside of a storage device and the following items may be recognized:

[0626] Tomatoes: 3

[0627] Eggs: 6 pieces

[0628] Milk: 500ml

[0629] Cheese: 200g

[0630] Lettuce: 1 head

[0631] The server sends this list of items to a generative AI model, which generates a recipe like this:

[0632] 1. Dish name: Tomato and cheese omelette

[0633] 2. Ingredients needed: Tomato, egg, milk, cheese

[0634] 3. Cooking Instructions:

[0635] Slice the tomatoes.

[0636] Crack the eggs into a bowl, beat them and add the milk.

[0637] Preheat a frying pan and melt the butter.

[0638] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0639] Finish the omelette.

[0640] 4. Cooking time: 20 minutes

[0641] 5. Nutritional balance: high protein, low fat

[0642] The recipe is displayed on the user's device, allowing the user to easily follow the steps to create the dish. Furthermore, if the user wants to check the contents of the storage device while away from home, the server can send the latest item list to the device, preventing duplicate food purchases. This reduces food waste in the home and provides a system that allows users to use items in a healthy and efficient manner.

[0643] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0644] Step 1:

[0645] Users use their smartphones or tablets to take pictures of the contents of the storage device. The images are then uploaded to the server via a dedicated application. Specifically, users open the app, select the option "Upload images from storage device," and take or select an image. Then, by pressing the "Upload" button, the captured image data is sent to the server. The input is the image taken by the user, and the output is the image data sent to the server.

[0646] Step 2:

[0647] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition). Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API analyzes the input image and identifies the objects contained in the image. The response returned by the API includes the names and quantities of the identified objects. The input is the image data received by the server, and the output is the response data (names and quantities of objects) from the image recognition API.

[0648] Step 3:

[0649] The server receives the response from the image recognition API and generates a list of items based on it. This list indicates the name and quantity of each item in the storage device and is saved in JSON format. The input is the response data from the image recognition API, and the output is the generated list of items. Specifically, the server analyzes the data in the response, extracts the name and quantity of each item, and compiles them into a list.

[0650] Step 4:

[0651] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates the optimal cooking recipe. The input is a list of items in JSON format, and the output is the generated cooking recipe.

[0652] Step 5:

[0653] The server sends the cooking recipe generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application and received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The input is the cooking recipe data sent from the server, and the output is the cooking recipe displayed on the device.

[0654] Step 6:

[0655] The user opens the application and selects the "Suggested Recipes" section. They select the recipe they want from the displayed list and view the detailed information, which includes the steps, ingredients needed, cooking time, and nutritional balance for each dish. The input is the recipe selected by the user, and the output is the detailed information displayed.

[0656] (Application example 1)

[0657] 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."

[0658] Conventional systems had limited functionality for identifying ingredients in the home and suggesting appropriate dishes, making it difficult for users to efficiently manage items in storage devices. Furthermore, even in brick-and-mortar stores, there were few mechanisms for customers to receive on-the-spot recipe suggestions based on the product list in the store, and suggestions for making effective use of ingredients were lacking. As a result, users and customers frequently wasted ingredients, creating a food waste problem.

[0659] 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.

[0660] In this invention, the server includes a means for uploading images of items in the storage device taken by the user, a means for analyzing the received images, identifying the items in the images, and generating an item list, and a means for using a generative AI model to generate recipes based on the generated item list. This allows users and customers to efficiently identify the items in the storage device and provide appropriate recipes. Specifically, when a user takes a photo of the contents of the storage device with their smartphone and uploads it, appropriate recipes are presented in real time using image analysis and the generative AI model, allowing ingredients to be used effectively without waste. The system can also be applied as a customer service in physical stores, providing a system that allows users to obtain recommended recipes from images of product shelves taken on the spot.

[0661] "Storage device"

[0662] is a general term for facilities and equipment used to preserve food and goods.

[0663] "Goods"

[0664] is a general term for all physical items that are subject to image analysis, such as food and merchandise stored in refrigerators and stores.

[0665] How to upload images

[0666] A camera is a device or system that has the function of transmitting image data captured by a user to a server via a network.

[0667] "Image analysis"

[0668] is a technique for processing received image data and identifying items contained within the image.

[0669] "List of Items"

[0670] This is data in the form of a list that includes the names and quantities of items identified through image analysis.

[0671] "Generative AI model"

[0672] is an algorithm or system that uses artificial intelligence to generate specific results or information based on input data.

[0673] "Cooking method"

[0674] is a general term for the steps and methods of cooking a dish using specific ingredients.

[0675] "Means of presenting to the user"

[0676] A recipe manager is a device or system that has the function of displaying the generated recipe to the user.

[0677] A way to send a request to the server

[0678] A storage device is a device or system that has the function of allowing a user to request information stored in a storage device from a server from a specified location.

[0679] "Terminal"

[0680] A device is an electronic device that is operated by a user, and includes smartphones, tablets, personal computers, etc.

[0681] "Nutritional balance"

[0682] This is a concept that refers to a healthy combination of ingredients, taking into account the type and amount of food ingredients in the cooking method.

[0683] "Cooking time"

[0684] is a general term for the time it takes to complete a dish according to a specific cooking method.

[0685] The present invention relates to a system that allows a user to efficiently manage items in a storage device and suggests appropriate recipes based on the managed items. Specific embodiments of this system will be described below.

[0686] System configuration and operation

[0687] 1. Upload an image

[0688] Users take photos of items in the storage device using a device such as a smartphone or tablet, and upload the images to the server via an application. The uploaded images are then processed on the cloud server.

[0689] 2. Image analysis and item list generation

[0690] The server sends the received image data to an image recognition API to identify the items contained in the image. This process uses common cloud services that provide image recognition technology (such as Google Cloud Vision API or Amazon Rekognition). The image recognition API analyzes the image and returns the names and quantities of the recognized items. The server generates an item list based on the response from the image recognition API. The item list contains the name and quantity of each item in the storage device, and this list is saved in JSON format or similar.

[0691] 3. Recipe generation

[0692] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model such as OpenAI's GPT series model. This model generates optimal recipes based on the ingredient list. The recipes include the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0693] 4. Presenting recipes to users

[0694] The generated recipes are sent from the server to the user's device and displayed to the user through the application. The user can select the recipe they want and check the detailed information.

[0695] Hardware and software used

[0696] Smartphones and tablets: Used by users to take pictures of items in the storage unit and upload the images.

[0697] Cloud server: Receives and analyzes image data, generates an ingredient list, and generates recipes using a generative AI model.

[0698] Image Recognition API: Use an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to automatically identify objects in images.

[0699] Generative AI models, such as OpenAI GPT-4, are used to generate appropriate recipes.

[0700] Specific examples

[0701] For example, a user may take a picture of the inside of a storage unit and recognize the following items:

[0702] Tomatoes: 3

[0703] Eggs: 6 pieces

[0704] Milk: 500ml

[0705] Cheese: 200g

[0706] Lettuce: 1 head

[0707] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0708] 1. Dish name: Tomato and cheese omelette

[0709] 2. Supplies needed: Tomatoes, eggs, milk, cheese

[0710] 3. Cooking Instructions:

[0711] Slice the tomatoes.

[0712] Crack the eggs into a bowl, beat them and add the milk.

[0713] Preheat a frying pan and melt the butter.

[0714] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0715] Finish the omelette.

[0716] 4. Cooking time: 20 minutes

[0717] 5. Nutritional balance: high protein, low fat

[0718] Prompt Sentence Examples

[0719] Suggest a recipe based on the following list of items:

[0720] Tomatoes: 3

[0721] Eggs: 6 pieces

[0722] Milk: 500ml

[0723] Cheese: 200g

[0724] Lettuce: 1 head

[0725] This series of steps allows users to easily select and prepare the appropriate recipe, which makes efficient use of stored items and reduces food waste.

[0726] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0727] Step 1:

[0728] Users take photos of items in the storage device using a smartphone or tablet. The images are then uploaded to a cloud server via a dedicated application. The input is the captured image data, and the output is an image file uploaded to the cloud server.

[0729] Step 2:

[0730] The server sends the image to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to analyze the received image data. The input is the image data received by the server, and the output is the analysis results, including the names and quantities of items in the image.

[0731] Step 3:

[0732] The server generates an item list based on the analysis results obtained from the image recognition API. This item list includes the name and quantity of each item and is saved in JSON format or similar. The input is the analysis result data from the image recognition API, and the output is the item list.

[0733] Step 4:

[0734] The server sends the generated item list to a generative AI model, a natural language processing model, to generate a recipe. In this process, a prompt is used as input to the generative AI model, which then outputs the optimal recipe. The input is the item list and the prompt, and the output is the generated recipe.

[0735] Step 5:

[0736] The server sends the recipe generated by the generative AI model to the user's device, where the user can check the recipe using a dedicated application. The input is the generated recipe, and the output is the recipe displayed on the user's device.

[0737] Step 6:

[0738] The user selects the necessary ingredients based on the recipe provided and performs the cooking. The input is the recipe sent from the server, and the output is the cooking result performed by the user.

[0739] This series of processes enables the user to efficiently manage the items in the storage device and obtain appropriate recipes.

[0740] 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.

[0741] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized recipe suggestions become possible. The following describes how the present invention can be specifically implemented.

[0742] System configuration and operation

[0743] 1. Upload an image

[0744] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[0745] 2. Image analysis and ingredient list generation

[0746] The server sends the received image data to an image recognition API to identify the ingredients contained in the image. For example, it uses common image recognition technology to identify the names and quantities of ingredients. Based on the analysis results, it generates an ingredient list. This ingredient list is saved in JSON format or similar.

[0747] 3. Recipe Generation

[0748] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model, for example, to generate a cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[0749] Dish name

[0750] Necessary ingredients

[0751] Cooking Instructions

[0752] Cooking time

[0753] Nutritional balance

[0754] 4. Utilizing the Emotion Engine

[0755] The server uses an emotion engine to recognize the user's emotions using images captured by the user and information acquired from the user interface. This emotion engine grasps the user's emotional state through, for example, voice recognition, image analysis, and touch interface.

[0756] The type of recipe and cooking method are customized based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect. The system also has an interface for providing notifications and suggestions that reflect the user's emotions.

[0757] 5. Presenting recipes to users

[0758] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[0759] Specific examples

[0760] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[0761] Tomatoes: 3

[0762] Eggs: 6 pieces

[0763] Milk: 500ml

[0764] Cheese: 200g

[0765] Lettuce: 1 head

[0766] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0767] 1. Dish name: Tomato and cheese omelette

[0768] 2. Ingredients needed: Tomato, egg, milk, cheese

[0769] 3. Cooking Instructions:

[0770] Slice the tomatoes.

[0771] Crack the eggs into a bowl, beat them and add the milk.

[0772] Preheat a frying pan and melt the butter.

[0773] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0774] Finish the omelette.

[0775] 4. Cooking time: 20 minutes

[0776] 5. Nutritional balance: high protein, low fat

[0777] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[0778] Check the contents of your refrigerator when you're out

[0779] When a user is out and about, they launch the app on their smartphone and send a request to the server. In response to this request, the server retrieves the latest ingredient list and sends it to the user's device. The device then analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and prevent duplicate food purchases.

[0780] This reduces food waste in the home and provides a system that allows users to use ingredients in a healthy and efficient manner. Furthermore, personalized recipe suggestions that take into account the user's emotional state can further increase user satisfaction.

[0781] The processing flow will be explained below.

[0782] Step 1:

[0783] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[0784] Step 2:

[0785] The device selects the stored image data and uploads it to the server via the application interface.

[0786] Step 3:

[0787] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[0788] Step 4:

[0789] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[0790] Step 5:

[0791] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format.

[0792] Step 6:

[0793] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[0794] Step 7:

[0795] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0796] Step 8:

[0797] The server receives the generated recipe and sends it to the user's device in JSON format.

[0798] Step 9:

[0799] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[0800] Step 10:

[0801] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[0802] Step 11:

[0803] The server analyzes the user interface, images, and audio data to understand the user's emotions, and determines the user's emotional state from the user's facial expressions and tone of voice.

[0804] Step 12:

[0805] The emotion engine analyzes the user's emotions and sends the emotion data, which can include stress, joy, excitement, etc., to the server.

[0806] Step 13:

[0807] The server receives data from the emotion engine and adjusts the recipe content based on the user's emotions. For example, if the user is under a lot of stress, it will select recipes that use ingredients that have a relaxing effect.

[0808] Step 14:

[0809] The server regenerates the adjusted recipe and sends it to the user's device, allowing the user to receive recipe suggestions tailored to their emotional state.

[0810] Step 15:

[0811] A user sends a request to the server via a smartphone app to check the contents of the refrigerator while away from home. The request is to obtain the latest list of ingredients.

[0812] Step 16:

[0813] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[0814] Step 17:

[0815] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and about, and avoid buying unnecessary food.

[0816] Example 2

[0817] 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."

[0818] In modern households, it is difficult to efficiently manage the contents of the refrigerator, resulting in inappropriate food purchases and food waste. Furthermore, it is cumbersome to consider appropriate dishes based on the contents of the refrigerator, making it difficult to provide personalized recipes that correspond to the user's emotional state. Furthermore, there are insufficient means to check the contents of the refrigerator while away from home, and a method to prevent duplicate or unnecessary food purchases is needed.

[0819] 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.

[0820] In this invention, the server includes a means for uploading images of the contents of the refrigerator taken by the user, a means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, a means for using a generative AI model to generate cooking recipes based on the generated ingredient list, a means for recognizing the user's emotional state and customizing recipes based on that state, and a means for presenting the generated cooking recipes to the user. This allows users to efficiently manage the contents of their refrigerator, reduce food waste, and easily obtain personalized cooking recipes that match their emotions. It also allows users to check the contents of their refrigerator while away from home and prevent duplicate food purchases.

[0821] "User" refers to a person who uses this system to manage the contents of their refrigerator and obtain cooking recipes.

[0822] The "server" refers to a computer system that receives and analyzes images taken by users and generates ingredient lists and cooking recipes.

[0823] "Image Recognition API" refers to an application programming interface for analyzing received images and identifying the ingredients contained within them.

[0824] "Ingredient list" refers to a list containing the names and quantities of ingredients identified by the image recognition API.

[0825] A "generative AI model" refers to an artificial intelligence model that generates cooking recipes based on an ingredient list.

[0826] An "emotion engine" refers to a system that recognizes a user's emotional state based on images taken by the user and information obtained from the interface.

[0827] A "cooking recipe" refers to information that includes specific cooking steps that users can use, the ingredients needed, cooking time, nutritional balance, and other information.

[0828] "Terminal" refers to a device (e.g., a smartphone or tablet) that a user uses to take pictures of the contents of the refrigerator or check ingredient lists and cooking recipes.

[0829] A "request from outside" refers to a request sent to the server by a user to check the contents of the refrigerator while the user is out.

[0830] "JSON format" refers to the JavaScript Object Notation data structure used to store the ingredient list.

[0831] This invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it enables more personalized recipe suggestions.

[0832] Hardware and software used

[0833] This system uses the following hardware and software:

[0834] 1. User device (e.g. smartphone, tablet)

[0835] Dedicated application: Application for taking and uploading images of the inside of the refrigerator

[0836] Internet connection: allows data transmission to the server

[0837] 2. Server

[0838] Image recognition API (e.g., Google Vision API): Used to identify ingredients in images

[0839] Generative AI models (e.g., GPT-3.5): Generate cooking recipes based on ingredient lists

[0840] Emotion Engine: Recognizes the user's emotional state and uses it to personalize recipes

[0841] Database: Stores ingredient lists and generated recipes

[0842] Specific operation of the system

[0843] 1. Taking and uploading images

[0844] The user uses the device to take pictures of the inside of the refrigerator, which are then uploaded to the server using a dedicated application.

[0845] 2. Image analysis and ingredient list generation

[0846] The server receives the image uploaded by the user. It then sends the image to an image recognition API to identify the ingredients in the image. The server generates an ingredient list based on the analysis results of the image recognition API and saves it in JSON format.

[0847] 3. Recipe Generation

[0848] The server sends the generated ingredient list to the generative AI model. The generative AI model generates a cooking recipe using a prompt. An example of a prompt is shown below.

[0849] You have the following ingredients in your refrigerator:

[0850] Tomatoes: 3

[0851] Eggs: 6 pieces

[0852] Milk: 500ml

[0853] Cheese: 200g

[0854] Lettuce: 1 head

[0855] Can you recommend some easy and delicious recipes using this ingredient?

[0856] 4. Utilizing the Emotion Engine

[0857] The server uses an emotion engine to recognize the user's emotions based on images taken by the user and information obtained from the user interface. Depending on the user's emotional state, the server adjusts the generated cooking recipes, generating personalized recipes, such as using ingredients with a relaxing effect for users who are feeling stressed.

[0858] 5. Presenting the recipe

[0859] The server sends the created recipe to the user's device, where the user can check the recipe and view details through a dedicated application on the device.

[0860] 6. Check the contents of your refrigerator while you're out

[0861] The user uses a dedicated application while on the go to send a request for the latest ingredient list to the server.

[0862] The server retrieves the latest ingredient list and sends it to the user's device, where the user can check the contents of the refrigerator.

[0863] Specific examples

[0864] For example, a user may take a picture of the inside of their refrigerator and the following ingredients may be recognized:

[0865] Tomatoes: 3

[0866] Eggs: 6 pieces

[0867] Milk: 500ml

[0868] Cheese: 200g

[0869] Lettuce: 1 head

[0870] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0871] 1. Dish name: Tomato and cheese omelette

[0872] 2. Ingredients needed: Tomato, egg, milk, cheese

[0873] 3. Cooking Instructions:

[0874] Slice the tomatoes.

[0875] Crack the eggs into a bowl, beat them and add the milk.

[0876] Preheat a frying pan and melt the butter.

[0877] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0878] Finish the omelette.

[0879] 4. Cooking time: 20 minutes

[0880] 5. Nutritional balance: high protein, low fat

[0881] If the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[0882] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0883] Step 1:

[0884] Users use a smartphone or tablet to take pictures of the contents of the refrigerator using a dedicated application.

[0885] Input: Image of the contents of the refrigerator

[0886] Output: Image saved on the user's device

[0887] Step 2:

[0888] The device uploads the captured images to a server via a dedicated application, which requires an internet connection.

[0889] Input: Images stored on the user's device

[0890] Output: Image data uploaded to the server

[0891] Step 3:

[0892] The server receives the image data received from the user, then sends this image data to an image recognition API (e.g., Google Vision API) to identify the ingredients contained in the image.

[0893] Input: Image data uploaded to the server

[0894] Output: Ingredient information returned from the image recognition API

[0895] Step 4:

[0896] The server generates an ingredient list based on the image recognition results. This ingredient list includes the names and quantities of ingredients. The server saves this ingredient list in JSON format.

[0897] Input: Ingredient information returned from the image recognition API

[0898] Output: JSON formatted list of ingredients

[0899] Step 5:

[0900] The server sends the generated ingredient list to a generative AI model (e.g., GPT-3.5) using a prompt to instruct it to generate a cooking recipe based on the ingredient list.

[0901] Input: JSON format ingredients list, prompt

[0902] Output: Cooking recipes generated from the generative AI model

[0903] Step 6:

[0904] The server receives the cooking recipes returned by the generative AI model and, if necessary, uses an emotion engine to recognize the user's emotional state, generating a personalized recipe based on the user's emotions.

[0905] Input: Cooking recipes returned by the generative AI model, user emotional state

[0906] Output: personalized cooking recipes

[0907] Step 7:

[0908] The server finally sends the generated and customized cooking recipe to the user's device.

[0909] Input: Personalized cooking recipe

[0910] Output: Cooking recipe sent to the user's device

[0911] Step 8:

[0912] The device displays the received recipes in a dedicated application, allowing the user to select the recipe they want and check the details.

[0913] Input: A cooking recipe sent to the user's device

[0914] Output: Cooking recipe displayed on the device

[0915] Step 9:

[0916] To check the contents of the refrigerator while away from home, the user launches a dedicated application and sends a request to the server.

[0917] Input: Request to check the contents of the refrigerator

[0918] Output: Request data to the server

[0919] Step 10:

[0920] The server retrieves the latest ingredient list and sends it to the user's terminal.

[0921] Input: Request to check the contents of the refrigerator

[0922] Output: Latest ingredients list

[0923] Step 11:

[0924] The device displays the received ingredient list in a dedicated application and notifies the user, allowing the user to avoid purchasing duplicate food items.

[0925] Input: Latest ingredient list

[0926] Output: Ingredient list displayed on the device

[0927] (Application example 2)

[0928] 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."

[0929] Currently, there are systems that track the contents of a refrigerator and suggest appropriate dishes based on that information. However, these systems are unable to suggest recipes that take into account the user's emotions or personal preferences. Furthermore, there are no systems that can efficiently consume ingredients while delivering dishes that correspond to the user's emotional state. This makes it difficult for users to enjoy efficient, personalized cooking without hassle. Furthermore, even if there are systems that can track the contents of a refrigerator while on the go, they lack the functionality to instantly deliver dishes based on that information.

[0930] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0931] In this invention, the server includes means for uploading images of the contents of the refrigerator taken by the user, means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, means for using a generative AI model to generate a cooking recipe based on the generated ingredient list, means for using an emotion engine to recognize the emotional state of the user and customize the recipe based on that emotional state in generating the cooking recipe, and means for allowing the user to select from the generated cooking recipes and delivering food cooked based on the selected recipe.This allows the user not only to know the contents of the refrigerator, but also to receive personalized food suggestions based on that information and to check the contents of the refrigerator while on the go and have food delivered on the spot.

[0932] "User" refers to an individual who uses the system to understand the contents of their refrigerator and receive cooking recipe suggestions and delivery services.

[0933] "Means for uploading images" refers to a function that allows a user to send images of the contents of the refrigerator taken using a device such as a smartphone or tablet to a cloud server.

[0934] "Means for analyzing images" refers to the function for analyzing image data received by the server and recognizing and identifying the ingredients contained therein.

[0935] The means for generating an "ingredient list" refers to a function that compiles ingredient information obtained from analyzed image data into a list format.

[0936] A "generative AI model" refers to artificial intelligence technology that automatically generates cooking recipes based on a list of ingredients.

[0937] "Emotion engine" refers to technology that recognizes the user's emotional state and customizes the cooking recipes provided based on that emotional state.

[0938] "Delivery means" refers to a function for delivering food prepared based on a recipe selected by the user to a location designated by the user.

[0939] "Means for checking while away from home" refers to a function that allows users to check the contents of their refrigerator via their smartphone or tablet even when they are out.

[0940] The "means for transmitting the latest ingredient list" refers to a function that enables the server to transmit the latest ingredient information to the user's terminal.

[0941] "Nutritional balance" refers to the standard for providing healthy menus that take into consideration the nutritional balance of ingredients and dishes.

[0942] "Cooking time" refers to the time required to complete a dish based on a recipe.

[0943] The present invention is a system that allows a user to specifically grasp the contents of their refrigerator and provide appropriate meals based on that information. This system includes a function that proposes personalized recipes taking into account the user's emotional state and delivers meals prepared based on those recipes. Specific embodiments for carrying out the invention are described in detail below.

[0944] System configuration and operation

[0945] 1. Upload an image

[0946] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and then upload the images to a cloud server via a dedicated application.

[0947] 2. Image analysis and ingredient list generation

[0948] The server sends the image data received from cloud storage to an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition), which identifies the ingredients contained in the image and generates an ingredient list. This ingredient list is saved in JSON format or similar.

[0949] 3. Recipe Generation

[0950] The server uses a generative AI model (e.g., OpenAI GPT-3, GPT-4) to generate a cooking recipe based on the generated ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[0951] 4. Utilizing the Emotion Engine

[0952] The server uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. It determines the user's emotional state based on information obtained from the user's voice input and touch interface. It customizes recipes based on the emotional state recognized by the emotion engine.

[0953] 5. Creating a delivery request

[0954] Based on the recipe selected by the user, order information is sent to the delivery system, which then prepares the specified dish and delivers it to the user.

[0955] 6. Present recipe to user and confirm order details

[0956] The server sends the created recipe to the user's device, where the user can check the recipe displayed in a dedicated application and confirm the order.

[0957] Specific examples

[0958] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[0959] Tomatoes: 3

[0960] Eggs: 6 pieces

[0961] Milk: 500ml

[0962] Cheese: 200g

[0963] Lettuce: 1 head

[0964] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[0965] 1. Dish name: Tomato and cheese omelette

[0966] 2. Ingredients needed: Tomato, egg, milk, cheese

[0967] 3. Cooking Instructions:

[0968] Slice the tomatoes.

[0969] Crack the eggs into a bowl, beat them and add the milk.

[0970] Preheat a frying pan and melt the butter.

[0971] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[0972] Finish the omelette.

[0973] 4. Cooking time: 20 minutes

[0974] 5. Nutritional balance: high protein, low fat

[0975] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[0976] Prompt Sentence Examples

[0977] text

[0978] Suggest an easy, healthy recipe using the following ingredient list. The user is stressed, so please consider cooking with ingredients that have a relaxing effect. Ingredient list: 3 tomatoes, 6 eggs, 500ml milk, 200g cheese, 1 lettuce

[0979] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0980] Step 1:

[0981] Image upload

[0982] Users can take a picture of the contents of their refrigerator using a camera app on their smartphone or tablet, and then upload the image to a cloud server via a dedicated application.

[0983] Input: Image file of the contents of the refrigerator

[0984] Output: Image data stored on a cloud server

[0985] Step 2:

[0986] Image analysis and ingredient list generation

[0987] The server retrieves the uploaded image data and analyzes it using an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition). As a result of the analysis, ingredients in the image are identified and an ingredient list is generated based on that information. This ingredient list is saved in JSON format.

[0988] Input: Image data stored on a cloud server

[0989] Output: JSON formatted list of ingredients

[0990] Data processing: Extracting image data as ingredient information and converting it into a list format

[0991] Step 3:

[0992] Recipe Generation

[0993] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a cooking recipe based on the generated ingredient list. The ingredient list is sent to the generative AI model as a prompt, and a recipe is generated that includes the name of the dish, the required ingredients, cooking steps, cooking time, nutritional balance, etc.

[0994] Input: JSON formatted list of ingredients

[0995] Output: Cooking recipe (text format)

[0996] Data computation: Input the list of ingredients as prompts into the AI ​​model to generate a recipe

[0997] Step 4:

[0998] Utilizing the Emotion Engine

[0999] The server analyzes information obtained from voice input and touch interface using an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. Based on the analysis results, the server customizes recipes according to the user's emotional state.

[1000] Input: Voice input data, touch interface data

[1001] Output: Customized cooking recipes

[1002] Data processing: Analyze the user's input data as an emotional state and reflect it in the recipe

[1003] Step 5:

[1004] Generating a delivery request

[1005] The user can check and select a recipe via the application. Then, by requesting delivery of a dish based on that recipe, the order information is sent to the delivery system. The delivery system then prepares and delivers the specified dish.

[1006] Input: Selected recipe

[1007] Output: Delivery order information

[1008] Data calculation: Sends order information to the delivery system based on the selected recipe

[1009] Step 6:

[1010] Present recipes to users and confirm order details

[1011] The server sends the created recipe to the user's device. The user can check the recipe displayed in a dedicated application and confirm the delivery order. Once the order details are confirmed, the final order information is sent to the delivery system.

[1012] Input: Generated cooking recipe

[1013] Output: Recipe displayed on the user's device, confirmed order information

[1014] Data calculation: Sending recipes, checking and confirming order details

[1015] 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.

[1016] 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.

[1017] 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.

[1018] [Third embodiment]

[1019] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1020] 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.

[1021] 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).

[1022] 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.

[1023] 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.

[1024] 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).

[1025] 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.

[1026] 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.

[1027] 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.

[1028] 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.

[1029] 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.

[1030] 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."

[1031] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the inside of their refrigerator, automatically recognizes ingredients in the images, and suggests cooking recipes based on the generated ingredient list. The following describes how to specifically implement the present invention.

[1032] System configuration and operation

[1033] 1. Upload an image

[1034] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[1035] 2. Image analysis and ingredient list generation

[1036] The server identifies the ingredients contained in the image by sending the received image data to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition. The image recognition API analyzes the image and returns data including the names and quantities of the recognized ingredients.

[1037] The server receives the response from the image recognition API and generates an ingredient list based on it. The ingredient list includes the name and quantity of each ingredient in the refrigerator. This ingredient list is saved in a format that allows for easy data exchange, such as JSON.

[1038] 3. Recipe Generation

[1039] The server sends the generated ingredient list to a generative AI model, which can use a natural language processing model such as OpenAI's GPT-4. This model generates an optimal cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[1040] Dish name

[1041] Necessary ingredients

[1042] Cooking Instructions

[1043] Cooking time

[1044] Nutritional balance

[1045] 4. Presenting recipes to users

[1046] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[1047] Specific examples

[1048] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[1049] Tomatoes: 3

[1050] Eggs: 6 pieces

[1051] Milk: 500ml

[1052] Cheese: 200g

[1053] Lettuce: 1 head

[1054] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1055] 1. Dish name: Tomato and cheese omelette

[1056] 2. Ingredients needed: Tomato, egg, milk, cheese

[1057] 3. Cooking Instructions:

[1058] Slice the tomatoes.

[1059] Crack the eggs into a bowl, beat them and add the milk.

[1060] Preheat a frying pan and melt the butter.

[1061] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1062] Finish the omelette.

[1063] 4. Cooking time: 20 minutes

[1064] 5. Nutritional balance: high protein, low fat

[1065] This series of steps allows the user to easily create the right dish. Also, if the user wants to check the contents of the refrigerator while away from home, the server can send the latest ingredient list to the user's terminal, preventing duplicate food purchases.

[1066] As a result, the present invention provides a system that reduces food waste in the home and allows users to use ingredients in a healthy and efficient manner.

[1067] The processing flow will be explained below.

[1068] Step 1:

[1069] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[1070] Step 2:

[1071] The device selects the stored image data and uploads it to the server via the application interface.

[1072] Step 3:

[1073] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[1074] Step 4:

[1075] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[1076] Step 5:

[1077] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format or similar.

[1078] Step 6:

[1079] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[1080] Step 7:

[1081] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1082] Step 8:

[1083] The server receives the generated recipe and sends it to the user's device. The recipe is sent in JSON format, for example.

[1084] Step 9:

[1085] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[1086] Step 10:

[1087] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[1088] Step 11:

[1089] When a user launches a smartphone app to check the contents of their refrigerator while away from home, the app sends a request to the server to retrieve the latest list of ingredients.

[1090] Step 12:

[1091] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[1092] Step 13:

[1093] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are away from home and prevent duplicate food purchases.

[1094] Example 1

[1095] 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."

[1096] This invention aims to automate and streamline the management of ingredients stored in home storage devices and the creation of recipe suggestions based on that information. In order for users to specifically understand the contents of the storage device and create appropriate dishes, it is necessary to utilize image recognition technology and generative AI models. However, existing systems have been criticized for their time-consuming manual input of information by users and the difficulty of checking information while away from home.

[1097] 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.

[1098] In this invention, the server includes means for uploading images of the contents of the storage device taken by the user, means for analyzing the received images and identifying items in the images to generate an item list, means for using a generative AI model to generate a cooking recipe based on the generated item list, means for presenting the generated cooking recipe to the user, means for the user to send a request to the server to check the contents of the storage device while away from home, and means for sending the latest item list to the user's terminal, thereby enabling the user to efficiently manage ingredients in the storage device and easily create optimal dishes.

[1099] A "user" is a person who uses the system and requests management of ingredients in the storage device and cooking suggestions.

[1100] "Storage equipment" refers to equipment such as refrigerators and freezers for preserving food.

[1101] The "means for uploading images" is a function for transmitting image data taken by the user to the server.

[1102] The "means for analyzing images" is a function for analyzing received image data using image recognition technology and identifying items in the image.

[1103] The "means for identifying items" is a function that identifies each item in an image through image analysis and extracts its name and quantity.

[1104] The "means for generating an item list" is a function for compiling information about identified items in list format and saving it as data.

[1105] A "generative AI model" is an artificial intelligence model that performs natural language processing based on input data and generates appropriate output (in this case, a cooking recipe).

[1106] The "means for generating cooking recipes" is a function that uses a generative AI model based on a list of items to generate recipes including the name of the dish, the necessary ingredients, cooking steps, etc.

[1107] The "means for presenting a cooking recipe" is a function for transmitting the generated recipe to the user's terminal and displaying it.

[1108] The "means for sending a request to a server" is a function that allows a user to send a specific request to a server in order to check the contents of a storage device while away from home.

[1109] The "means for transmitting the latest item list" is a function that enables the server to transmit the latest item list to the user's terminal.

[1110] "Terminal" refers to a portable electronic device used by a user, such as a smartphone or tablet.

[1111] This invention relates to a system that allows users to specifically grasp the contents of a storage device and create appropriate dishes based on that information. This system allows users to take and upload images of the contents of the storage device, automatically recognizes the items in the images, and suggests cooking recipes based on the generated list of items.

[1112] System configuration and operation

[1113] 1. Upload an image

[1114] Users take pictures of the contents of the storage device using a device such as a smartphone or tablet. The images are then uploaded to a server via a dedicated application. To do this, users open the app, select the option "Upload images from storage device," and take or select an image. Next, they press the "Upload" button to send the image to the server.

[1115] 2. Image analysis and item list generation

[1116] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition) to identify the items contained in the image. Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API performs analysis and returns the names and quantities of the recognized items as a response. The server receives this response and generates an item list. The item list stores the name and quantity of each item in the storage device in JSON format.

[1117] 3. Recipe Generation

[1118] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates an optimal cooking recipe. This recipe includes the name of the dish, the required ingredients, cooking steps, cooking time, and nutritional balance.

[1119] 4. Presenting recipes to users

[1120] The server sends the cooking recipes generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application, and then received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The user opens the application, selects the "Suggested Recipes" section, selects the desired recipe from the displayed recipes, and checks the detailed information. The detailed information includes the steps for each dish, the required ingredients, cooking time, and nutritional balance.

[1121] Specific examples

[1122] For example, a user may take an image of the inside of a storage device and the following items may be recognized:

[1123] Tomatoes: 3

[1124] Eggs: 6 pieces

[1125] Milk: 500ml

[1126] Cheese: 200g

[1127] Lettuce: 1 head

[1128] The server sends this list of items to a generative AI model, which generates a recipe like this:

[1129] 1. Dish name: Tomato and cheese omelette

[1130] 2. Ingredients needed: Tomato, egg, milk, cheese

[1131] 3. Cooking Instructions:

[1132] Slice the tomatoes.

[1133] Crack the eggs into a bowl, beat them and add the milk.

[1134] Preheat a frying pan and melt the butter.

[1135] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1136] Finish the omelette.

[1137] 4. Cooking time: 20 minutes

[1138] 5. Nutritional balance: high protein, low fat

[1139] The recipe is displayed on the user's device, allowing the user to easily follow the steps to create the dish. Furthermore, if the user wants to check the contents of the storage device while away from home, the server can send the latest item list to the device, preventing duplicate food purchases. This reduces food waste in the home and provides a system that allows users to use items in a healthy and efficient manner.

[1140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1141] Step 1:

[1142] Users use their smartphones or tablets to take pictures of the contents of the storage device. The images are then uploaded to the server via a dedicated application. Specifically, users open the app, select the option "Upload images from storage device," and take or select an image. Then, by pressing the "Upload" button, the captured image data is sent to the server. The input is the image taken by the user, and the output is the image data sent to the server.

[1143] Step 2:

[1144] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition). Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API analyzes the input image and identifies the objects contained in the image. The response returned by the API includes the names and quantities of the identified objects. The input is the image data received by the server, and the output is the response data (names and quantities of objects) from the image recognition API.

[1145] Step 3:

[1146] The server receives the response from the image recognition API and generates a list of items based on it. This list indicates the name and quantity of each item in the storage device and is saved in JSON format. The input is the response data from the image recognition API, and the output is the generated list of items. Specifically, the server analyzes the data in the response, extracts the name and quantity of each item, and compiles them into a list.

[1147] Step 4:

[1148] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates the optimal cooking recipe. The input is a list of items in JSON format, and the output is the generated cooking recipe.

[1149] Step 5:

[1150] The server sends the cooking recipe generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application and received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The input is the cooking recipe data sent from the server, and the output is the cooking recipe displayed on the device.

[1151] Step 6:

[1152] The user opens the application and selects the "Suggested Recipes" section. They select the recipe they want from the displayed list and view the detailed information, which includes the steps, ingredients needed, cooking time, and nutritional balance for each dish. The input is the recipe selected by the user, and the output is the detailed information displayed.

[1153] (Application example 1)

[1154] 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."

[1155] Conventional systems had limited functionality for identifying ingredients in the home and suggesting appropriate dishes, making it difficult for users to efficiently manage items in storage devices. Furthermore, even in brick-and-mortar stores, there were few mechanisms for customers to receive on-the-spot recipe suggestions based on the product list in the store, and suggestions for making effective use of ingredients were lacking. As a result, users and customers frequently wasted ingredients, creating a food waste problem.

[1156] 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.

[1157] In this invention, the server includes a means for uploading images of items in the storage device taken by the user, a means for analyzing the received images, identifying the items in the images, and generating an item list, and a means for using a generative AI model to generate recipes based on the generated item list. This allows users and customers to efficiently identify the items in the storage device and provide appropriate recipes. Specifically, when a user takes a photo of the contents of the storage device with their smartphone and uploads it, appropriate recipes are presented in real time using image analysis and the generative AI model, allowing ingredients to be used effectively without waste. The system can also be applied as a customer service in physical stores, providing a system that allows users to obtain recommended recipes from images of product shelves taken on the spot.

[1158] "Storage device"

[1159] is a general term for facilities and equipment used to preserve food and goods.

[1160] "Goods"

[1161] is a general term for all physical items that are subject to image analysis, such as food and merchandise stored in refrigerators and stores.

[1162] How to upload images

[1163] A camera is a device or system that has the function of transmitting image data captured by a user to a server via a network.

[1164] "Image analysis"

[1165] is a technique for processing received image data and identifying items contained within the image.

[1166] "List of Items"

[1167] This is data in the form of a list that includes the names and quantities of items identified through image analysis.

[1168] "Generative AI model"

[1169] is an algorithm or system that uses artificial intelligence to generate specific results or information based on input data.

[1170] "Cooking method"

[1171] is a general term for the steps and methods of cooking a dish using specific ingredients.

[1172] "Means of presenting to the user"

[1173] A recipe manager is a device or system that has the function of displaying the generated recipe to the user.

[1174] A way to send a request to the server

[1175] A storage device is a device or system that has the function of allowing a user to request information stored in a storage device from a server from a specified location.

[1176] "Terminal"

[1177] A device is an electronic device that is operated by a user, and includes smartphones, tablets, personal computers, etc.

[1178] "Nutritional balance"

[1179] This is a concept that refers to a healthy combination of ingredients, taking into account the type and amount of food ingredients in the cooking method.

[1180] "Cooking time"

[1181] is a general term for the time it takes to complete a dish according to a specific cooking method.

[1182] The present invention relates to a system that allows a user to efficiently manage items in a storage device and suggests appropriate recipes based on the managed items. Specific embodiments of this system will be described below.

[1183] System configuration and operation

[1184] 1. Upload an image

[1185] Users take photos of items in the storage device using a device such as a smartphone or tablet, and upload the images to the server via an application. The uploaded images are then processed on the cloud server.

[1186] 2. Image analysis and item list generation

[1187] The server sends the received image data to an image recognition API to identify the items contained in the image. This process uses common cloud services that provide image recognition technology (such as Google Cloud Vision API or Amazon Rekognition). The image recognition API analyzes the image and returns the names and quantities of the recognized items. The server generates an item list based on the response from the image recognition API. The item list contains the name and quantity of each item in the storage device, and this list is saved in JSON format or similar.

[1188] 3. Recipe generation

[1189] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model such as OpenAI's GPT series model. This model generates optimal recipes based on the ingredient list. The recipes include the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1190] 4. Presenting recipes to users

[1191] The generated recipes are sent from the server to the user's device and displayed to the user through the application. The user can select the recipe they want and check the detailed information.

[1192] Hardware and software used

[1193] Smartphones and tablets: Used by users to take pictures of items in the storage unit and upload the images.

[1194] Cloud server: Receives and analyzes image data, generates an ingredient list, and generates recipes using a generative AI model.

[1195] Image Recognition API: Use an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to automatically identify objects in images.

[1196] Generative AI models, such as OpenAI GPT-4, are used to generate appropriate recipes.

[1197] Specific examples

[1198] For example, a user may take a picture of the inside of a storage unit and recognize the following items:

[1199] Tomatoes: 3

[1200] Eggs: 6 pieces

[1201] Milk: 500ml

[1202] Cheese: 200g

[1203] Lettuce: 1 head

[1204] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1205] 1. Dish name: Tomato and cheese omelette

[1206] 2. Supplies needed: Tomatoes, eggs, milk, cheese

[1207] 3. Cooking Instructions:

[1208] Slice the tomatoes.

[1209] Crack the eggs into a bowl, beat them and add the milk.

[1210] Preheat a frying pan and melt the butter.

[1211] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1212] Finish the omelette.

[1213] 4. Cooking time: 20 minutes

[1214] 5. Nutritional balance: high protein, low fat

[1215] Prompt Sentence Examples

[1216] Suggest a recipe based on the following list of items:

[1217] Tomatoes: 3

[1218] Eggs: 6 pieces

[1219] Milk: 500ml

[1220] Cheese: 200g

[1221] Lettuce: 1 head

[1222] This series of steps allows users to easily select and prepare the appropriate recipe, which makes efficient use of stored items and reduces food waste.

[1223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1224] Step 1:

[1225] Users take photos of items in the storage device using a smartphone or tablet. The images are then uploaded to a cloud server via a dedicated application. The input is the captured image data, and the output is an image file uploaded to the cloud server.

[1226] Step 2:

[1227] The server sends the image to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to analyze the received image data. The input is the image data received by the server, and the output is the analysis results, including the names and quantities of items in the image.

[1228] Step 3:

[1229] The server generates an item list based on the analysis results obtained from the image recognition API. This item list includes the name and quantity of each item and is saved in JSON format or similar. The input is the analysis result data from the image recognition API, and the output is the item list.

[1230] Step 4:

[1231] The server sends the generated item list to a generative AI model, a natural language processing model, to generate a recipe. In this process, a prompt is used as input to the generative AI model, which then outputs the optimal recipe. The input is the item list and the prompt, and the output is the generated recipe.

[1232] Step 5:

[1233] The server sends the recipe generated by the generative AI model to the user's device, where the user can check the recipe using a dedicated application. The input is the generated recipe, and the output is the recipe displayed on the user's device.

[1234] Step 6:

[1235] The user selects the necessary ingredients based on the recipe provided and performs the cooking. The input is the recipe sent from the server, and the output is the cooking result performed by the user.

[1236] This series of processes enables the user to efficiently manage the items in the storage device and obtain appropriate recipes.

[1237] 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.

[1238] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized recipe suggestions become possible. The following describes how the present invention can be specifically implemented.

[1239] System configuration and operation

[1240] 1. Upload an image

[1241] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[1242] 2. Image analysis and ingredient list generation

[1243] The server sends the received image data to an image recognition API to identify the ingredients contained in the image. For example, it uses common image recognition technology to identify the names and quantities of ingredients. Based on the analysis results, it generates an ingredient list. This ingredient list is saved in JSON format or similar.

[1244] 3. Recipe Generation

[1245] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model, for example, to generate a cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[1246] Dish name

[1247] Necessary ingredients

[1248] Cooking Instructions

[1249] Cooking time

[1250] Nutritional balance

[1251] 4. Utilizing the Emotion Engine

[1252] The server uses an emotion engine to recognize the user's emotions using images captured by the user and information acquired from the user interface. This emotion engine grasps the user's emotional state through, for example, voice recognition, image analysis, and touch interface.

[1253] The type of recipe and cooking method are customized based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect. The system also has an interface for providing notifications and suggestions that reflect the user's emotions.

[1254] 5. Presenting recipes to users

[1255] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[1256] Specific examples

[1257] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[1258] Tomatoes: 3

[1259] Eggs: 6 pieces

[1260] Milk: 500ml

[1261] Cheese: 200g

[1262] Lettuce: 1 head

[1263] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1264] 1. Dish name: Tomato and cheese omelette

[1265] 2. Ingredients needed: Tomato, egg, milk, cheese

[1266] 3. Cooking Instructions:

[1267] Slice the tomatoes.

[1268] Crack the eggs into a bowl, beat them and add the milk.

[1269] Preheat a frying pan and melt the butter.

[1270] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1271] Finish the omelette.

[1272] 4. Cooking time: 20 minutes

[1273] 5. Nutritional balance: high protein, low fat

[1274] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[1275] Check the contents of your refrigerator when you're out

[1276] When a user is out and about, they launch the app on their smartphone and send a request to the server. In response to this request, the server retrieves the latest ingredient list and sends it to the user's device. The device then analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and prevent duplicate food purchases.

[1277] This reduces food waste in the home and provides a system that allows users to use ingredients in a healthy and efficient manner. Furthermore, personalized recipe suggestions that take into account the user's emotional state can further increase user satisfaction.

[1278] The processing flow will be explained below.

[1279] Step 1:

[1280] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[1281] Step 2:

[1282] The device selects the stored image data and uploads it to the server via the application interface.

[1283] Step 3:

[1284] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[1285] Step 4:

[1286] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[1287] Step 5:

[1288] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format.

[1289] Step 6:

[1290] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[1291] Step 7:

[1292] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1293] Step 8:

[1294] The server receives the generated recipe and sends it to the user's device in JSON format.

[1295] Step 9:

[1296] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[1297] Step 10:

[1298] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[1299] Step 11:

[1300] The server analyzes the user interface, images, and audio data to understand the user's emotions, and determines the user's emotional state from the user's facial expressions and tone of voice.

[1301] Step 12:

[1302] The emotion engine analyzes the user's emotions and sends the emotion data, which can include stress, joy, excitement, etc., to the server.

[1303] Step 13:

[1304] The server receives data from the emotion engine and adjusts the recipe content based on the user's emotions. For example, if the user is under a lot of stress, it will select recipes that use ingredients that have a relaxing effect.

[1305] Step 14:

[1306] The server regenerates the adjusted recipe and sends it to the user's device, allowing the user to receive recipe suggestions tailored to their emotional state.

[1307] Step 15:

[1308] A user sends a request to the server via a smartphone app to check the contents of the refrigerator while away from home. The request is to obtain the latest list of ingredients.

[1309] Step 16:

[1310] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[1311] Step 17:

[1312] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and about, and avoid buying unnecessary food.

[1313] Example 2

[1314] 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."

[1315] In modern households, it is difficult to efficiently manage the contents of the refrigerator, resulting in inappropriate food purchases and food waste. Furthermore, it is cumbersome to consider appropriate dishes based on the contents of the refrigerator, making it difficult to provide personalized recipes that correspond to the user's emotional state. Furthermore, there are insufficient means to check the contents of the refrigerator while away from home, and a method to prevent duplicate or unnecessary food purchases is needed.

[1316] 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.

[1317] In this invention, the server includes a means for uploading images of the contents of the refrigerator taken by the user, a means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, a means for using a generative AI model to generate cooking recipes based on the generated ingredient list, a means for recognizing the user's emotional state and customizing recipes based on that state, and a means for presenting the generated cooking recipes to the user. This allows users to efficiently manage the contents of their refrigerator, reduce food waste, and easily obtain personalized cooking recipes that match their emotions. It also allows users to check the contents of their refrigerator while away from home and prevent duplicate food purchases.

[1318] "User" refers to a person who uses this system to manage the contents of their refrigerator and obtain cooking recipes.

[1319] The "server" refers to a computer system that receives and analyzes images taken by users and generates ingredient lists and cooking recipes.

[1320] "Image Recognition API" refers to an application programming interface for analyzing received images and identifying the ingredients contained within them.

[1321] "Ingredient list" refers to a list containing the names and quantities of ingredients identified by the image recognition API.

[1322] A "generative AI model" refers to an artificial intelligence model that generates cooking recipes based on an ingredient list.

[1323] An "emotion engine" refers to a system that recognizes a user's emotional state based on images taken by the user and information obtained from the interface.

[1324] A "cooking recipe" refers to information that includes specific cooking steps that users can use, the ingredients needed, cooking time, nutritional balance, and other information.

[1325] "Terminal" refers to a device (e.g., a smartphone or tablet) that a user uses to take pictures of the contents of the refrigerator or check ingredient lists and cooking recipes.

[1326] A "request from outside" refers to a request sent to the server by a user to check the contents of the refrigerator while the user is out.

[1327] "JSON format" refers to the JavaScript Object Notation data structure used to store the ingredient list.

[1328] This invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it enables more personalized recipe suggestions.

[1329] Hardware and software used

[1330] This system uses the following hardware and software:

[1331] 1. User device (e.g. smartphone, tablet)

[1332] Dedicated application: Application for taking and uploading images of the inside of the refrigerator

[1333] Internet connection: allows data transmission to the server

[1334] 2. Server

[1335] Image recognition API (e.g., Google Vision API): Used to identify ingredients in images

[1336] Generative AI models (e.g., GPT-3.5): Generate cooking recipes based on ingredient lists

[1337] Emotion Engine: Recognizes the user's emotional state and uses it to personalize recipes

[1338] Database: Stores ingredient lists and generated recipes

[1339] Specific operation of the system

[1340] 1. Taking and uploading images

[1341] The user uses the device to take pictures of the inside of the refrigerator, which are then uploaded to the server using a dedicated application.

[1342] 2. Image analysis and ingredient list generation

[1343] The server receives the image uploaded by the user. It then sends the image to an image recognition API to identify the ingredients in the image. The server generates an ingredient list based on the analysis results of the image recognition API and saves it in JSON format.

[1344] 3. Recipe Generation

[1345] The server sends the generated ingredient list to the generative AI model. The generative AI model generates a cooking recipe using a prompt. An example of a prompt is shown below.

[1346] You have the following ingredients in your refrigerator:

[1347] Tomatoes: 3

[1348] Eggs: 6 pieces

[1349] Milk: 500ml

[1350] Cheese: 200g

[1351] Lettuce: 1 head

[1352] Can you recommend some easy and delicious recipes using this ingredient?

[1353] 4. Utilizing the Emotion Engine

[1354] The server uses an emotion engine to recognize the user's emotions based on images taken by the user and information obtained from the user interface. Depending on the user's emotional state, the server adjusts the generated cooking recipes, generating personalized recipes, such as using ingredients with a relaxing effect for users who are feeling stressed.

[1355] 5. Presenting the recipe

[1356] The server sends the created recipe to the user's device, where the user can check the recipe and view details through a dedicated application on the device.

[1357] 6. Check the contents of your refrigerator while you're out

[1358] The user uses a dedicated application while on the go to send a request for the latest ingredient list to the server.

[1359] The server retrieves the latest ingredient list and sends it to the user's device, where the user can check the contents of the refrigerator.

[1360] Specific examples

[1361] For example, a user may take a picture of the inside of their refrigerator and the following ingredients may be recognized:

[1362] Tomatoes: 3

[1363] Eggs: 6 pieces

[1364] Milk: 500ml

[1365] Cheese: 200g

[1366] Lettuce: 1 head

[1367] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1368] 1. Dish name: Tomato and cheese omelette

[1369] 2. Ingredients needed: Tomato, egg, milk, cheese

[1370] 3. Cooking Instructions:

[1371] Slice the tomatoes.

[1372] Crack the eggs into a bowl, beat them and add the milk.

[1373] Preheat a frying pan and melt the butter.

[1374] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1375] Finish the omelette.

[1376] 4. Cooking time: 20 minutes

[1377] 5. Nutritional balance: high protein, low fat

[1378] If the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[1379] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1380] Step 1:

[1381] Users use a smartphone or tablet to take pictures of the contents of the refrigerator using a dedicated application.

[1382] Input: Image of the contents of the refrigerator

[1383] Output: Image saved on the user's device

[1384] Step 2:

[1385] The device uploads the captured images to a server via a dedicated application, which requires an internet connection.

[1386] Input: Images stored on the user's device

[1387] Output: Image data uploaded to the server

[1388] Step 3:

[1389] The server receives the image data received from the user, then sends this image data to an image recognition API (e.g., Google Vision API) to identify the ingredients contained in the image.

[1390] Input: Image data uploaded to the server

[1391] Output: Ingredient information returned from the image recognition API

[1392] Step 4:

[1393] The server generates an ingredient list based on the image recognition results. This ingredient list includes the names and quantities of ingredients. The server saves this ingredient list in JSON format.

[1394] Input: Ingredient information returned from the image recognition API

[1395] Output: JSON formatted list of ingredients

[1396] Step 5:

[1397] The server sends the generated ingredient list to a generative AI model (e.g., GPT-3.5) using a prompt to instruct it to generate a cooking recipe based on the ingredient list.

[1398] Input: JSON format ingredients list, prompt

[1399] Output: Cooking recipes generated from the generative AI model

[1400] Step 6:

[1401] The server receives the cooking recipes returned by the generative AI model and, if necessary, uses an emotion engine to recognize the user's emotional state, generating a personalized recipe based on the user's emotions.

[1402] Input: Cooking recipes returned by the generative AI model, user emotional state

[1403] Output: personalized cooking recipes

[1404] Step 7:

[1405] The server finally sends the generated and customized cooking recipe to the user's device.

[1406] Input: Personalized cooking recipe

[1407] Output: Cooking recipe sent to the user's device

[1408] Step 8:

[1409] The device displays the received recipes in a dedicated application, allowing the user to select the recipe they want and check the details.

[1410] Input: A cooking recipe sent to the user's device

[1411] Output: Cooking recipe displayed on the device

[1412] Step 9:

[1413] To check the contents of the refrigerator while away from home, the user launches a dedicated application and sends a request to the server.

[1414] Input: Request to check the contents of the refrigerator

[1415] Output: Request data to the server

[1416] Step 10:

[1417] The server retrieves the latest ingredient list and sends it to the user's terminal.

[1418] Input: Request to check the contents of the refrigerator

[1419] Output: Latest ingredients list

[1420] Step 11:

[1421] The device displays the received ingredient list in a dedicated application and notifies the user, allowing the user to avoid purchasing duplicate food items.

[1422] Input: Latest ingredient list

[1423] Output: Ingredient list displayed on the device

[1424] (Application example 2)

[1425] 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."

[1426] Currently, there are systems that track the contents of a refrigerator and suggest appropriate dishes based on that information. However, these systems are unable to suggest recipes that take into account the user's emotions or personal preferences. Furthermore, there are no systems that can efficiently consume ingredients while delivering dishes that correspond to the user's emotional state. This makes it difficult for users to enjoy efficient, personalized cooking without hassle. Furthermore, even if there are systems that can track the contents of a refrigerator while on the go, they lack the functionality to instantly deliver dishes based on that information.

[1427] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1428] In this invention, the server includes means for uploading images of the contents of the refrigerator taken by the user, means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, means for using a generative AI model to generate a cooking recipe based on the generated ingredient list, means for using an emotion engine to recognize the emotional state of the user and customize the recipe based on that emotional state in generating the cooking recipe, and means for allowing the user to select from the generated cooking recipes and delivering food cooked based on the selected recipe.This allows the user not only to know the contents of the refrigerator, but also to receive personalized food suggestions based on that information and to check the contents of the refrigerator while on the go and have food delivered on the spot.

[1429] "User" refers to an individual who uses the system to understand the contents of their refrigerator and receive cooking recipe suggestions and delivery services.

[1430] "Means for uploading images" refers to a function that allows a user to send images of the contents of the refrigerator taken using a device such as a smartphone or tablet to a cloud server.

[1431] "Means for analyzing images" refers to the function for analyzing image data received by the server and recognizing and identifying the ingredients contained therein.

[1432] The means for generating an "ingredient list" refers to a function that compiles ingredient information obtained from analyzed image data into a list format.

[1433] A "generative AI model" refers to artificial intelligence technology that automatically generates cooking recipes based on a list of ingredients.

[1434] "Emotion engine" refers to technology that recognizes the user's emotional state and customizes the cooking recipes provided based on that emotional state.

[1435] "Delivery means" refers to a function for delivering food prepared based on a recipe selected by the user to a location designated by the user.

[1436] "Means for checking while away from home" refers to a function that allows users to check the contents of their refrigerator via their smartphone or tablet even when they are out.

[1437] The "means for transmitting the latest ingredient list" refers to a function that enables the server to transmit the latest ingredient information to the user's terminal.

[1438] "Nutritional balance" refers to the standard for providing healthy menus that take into consideration the nutritional balance of ingredients and dishes.

[1439] "Cooking time" refers to the time required to complete a dish based on a recipe.

[1440] The present invention is a system that allows a user to specifically grasp the contents of their refrigerator and provide appropriate meals based on that information. This system includes a function that proposes personalized recipes taking into account the user's emotional state and delivers meals prepared based on those recipes. Specific embodiments for carrying out the invention are described in detail below.

[1441] System configuration and operation

[1442] 1. Upload an image

[1443] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and then upload the images to a cloud server via a dedicated application.

[1444] 2. Image analysis and ingredient list generation

[1445] The server sends the image data received from cloud storage to an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition), which identifies the ingredients contained in the image and generates an ingredient list. This ingredient list is saved in JSON format or similar.

[1446] 3. Recipe Generation

[1447] The server uses a generative AI model (e.g., OpenAI GPT-3, GPT-4) to generate a cooking recipe based on the generated ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1448] 4. Utilizing the Emotion Engine

[1449] The server uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. It determines the user's emotional state based on information obtained from the user's voice input and touch interface. It customizes recipes based on the emotional state recognized by the emotion engine.

[1450] 5. Creating a delivery request

[1451] Based on the recipe selected by the user, order information is sent to the delivery system, which then prepares the specified dish and delivers it to the user.

[1452] 6. Present recipe to user and confirm order details

[1453] The server sends the created recipe to the user's device, where the user can check the recipe displayed in a dedicated application and confirm the order.

[1454] Specific examples

[1455] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[1456] Tomatoes: 3

[1457] Eggs: 6 pieces

[1458] Milk: 500ml

[1459] Cheese: 200g

[1460] Lettuce: 1 head

[1461] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1462] 1. Dish name: Tomato and cheese omelette

[1463] 2. Ingredients needed: Tomato, egg, milk, cheese

[1464] 3. Cooking Instructions:

[1465] Slice the tomatoes.

[1466] Crack the eggs into a bowl, beat them and add the milk.

[1467] Preheat a frying pan and melt the butter.

[1468] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1469] Finish the omelette.

[1470] 4. Cooking time: 20 minutes

[1471] 5. Nutritional balance: high protein, low fat

[1472] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[1473] Prompt Sentence Examples

[1474] text

[1475] Suggest an easy, healthy recipe using the following ingredient list. The user is stressed, so please consider cooking with ingredients that have a relaxing effect. Ingredient list: 3 tomatoes, 6 eggs, 500ml milk, 200g cheese, 1 lettuce

[1476] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1477] Step 1:

[1478] Image upload

[1479] Users can take a picture of the contents of their refrigerator using a camera app on their smartphone or tablet, and then upload the image to a cloud server via a dedicated application.

[1480] Input: Image file of the contents of the refrigerator

[1481] Output: Image data stored on a cloud server

[1482] Step 2:

[1483] Image analysis and ingredient list generation

[1484] The server retrieves the uploaded image data and analyzes it using an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition). As a result of the analysis, ingredients in the image are identified and an ingredient list is generated based on that information. This ingredient list is saved in JSON format.

[1485] Input: Image data stored on a cloud server

[1486] Output: JSON formatted list of ingredients

[1487] Data processing: Extracting image data as ingredient information and converting it into a list format

[1488] Step 3:

[1489] Recipe Generation

[1490] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a cooking recipe based on the generated ingredient list. The ingredient list is sent to the generative AI model as a prompt, and a recipe is generated that includes the name of the dish, the required ingredients, cooking steps, cooking time, nutritional balance, etc.

[1491] Input: JSON formatted list of ingredients

[1492] Output: Cooking recipe (text format)

[1493] Data computation: Input the list of ingredients as prompts into the AI ​​model to generate a recipe

[1494] Step 4:

[1495] Utilizing the Emotion Engine

[1496] The server analyzes information obtained from voice input and touch interface using an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. Based on the analysis results, the server customizes recipes according to the user's emotional state.

[1497] Input: Voice input data, touch interface data

[1498] Output: Customized cooking recipes

[1499] Data processing: Analyze the user's input data as an emotional state and reflect it in the recipe

[1500] Step 5:

[1501] Generating a delivery request

[1502] The user can check and select a recipe via the application. Then, by requesting delivery of a dish based on that recipe, the order information is sent to the delivery system. The delivery system then prepares and delivers the specified dish.

[1503] Input: Selected recipe

[1504] Output: Delivery order information

[1505] Data calculation: Sends order information to the delivery system based on the selected recipe

[1506] Step 6:

[1507] Present recipes to users and confirm order details

[1508] The server sends the created recipe to the user's device. The user can check the recipe displayed in a dedicated application and confirm the delivery order. Once the order details are confirmed, the final order information is sent to the delivery system.

[1509] Input: Generated cooking recipe

[1510] Output: Recipe displayed on the user's device, confirmed order information

[1511] Data calculation: Sending recipes, checking and confirming order details

[1512] 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.

[1513] 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.

[1514] 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.

[1515] [Fourth embodiment]

[1516] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1517] 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.

[1518] 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).

[1519] 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.

[1520] 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.

[1521] 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).

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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."

[1529] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the inside of their refrigerator, automatically recognizes ingredients in the images, and suggests cooking recipes based on the generated ingredient list. The following describes how to specifically implement the present invention.

[1530] System configuration and operation

[1531] 1. Upload an image

[1532] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[1533] 2. Image analysis and ingredient list generation

[1534] The server identifies the ingredients contained in the image by sending the received image data to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition. The image recognition API analyzes the image and returns data including the names and quantities of the recognized ingredients.

[1535] The server receives the response from the image recognition API and generates an ingredient list based on it. The ingredient list includes the name and quantity of each ingredient in the refrigerator. This ingredient list is saved in a format that allows for easy data exchange, such as JSON.

[1536] 3. Recipe Generation

[1537] The server sends the generated ingredient list to a generative AI model, which can use a natural language processing model such as OpenAI's GPT-4. This model generates an optimal cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[1538] Dish name

[1539] Necessary ingredients

[1540] Cooking Instructions

[1541] Cooking time

[1542] Nutritional balance

[1543] 4. Presenting recipes to users

[1544] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[1545] Specific examples

[1546] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[1547] Tomatoes: 3

[1548] Eggs: 6 pieces

[1549] Milk: 500ml

[1550] Cheese: 200g

[1551] Lettuce: 1 head

[1552] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1553] 1. Dish name: Tomato and cheese omelette

[1554] 2. Ingredients needed: Tomato, egg, milk, cheese

[1555] 3. Cooking Instructions:

[1556] Slice the tomatoes.

[1557] Crack the eggs into a bowl, beat them and add the milk.

[1558] Preheat a frying pan and melt the butter.

[1559] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1560] Finish the omelette.

[1561] 4. Cooking time: 20 minutes

[1562] 5. Nutritional balance: high protein, low fat

[1563] This series of steps allows the user to easily create the right dish. Also, if the user wants to check the contents of the refrigerator while away from home, the server can send the latest ingredient list to the user's terminal, preventing duplicate food purchases.

[1564] As a result, the present invention provides a system that reduces food waste in the home and allows users to use ingredients in a healthy and efficient manner.

[1565] The processing flow will be explained below.

[1566] Step 1:

[1567] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[1568] Step 2:

[1569] The device selects the stored image data and uploads it to the server via the application interface.

[1570] Step 3:

[1571] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[1572] Step 4:

[1573] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[1574] Step 5:

[1575] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format or similar.

[1576] Step 6:

[1577] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[1578] Step 7:

[1579] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1580] Step 8:

[1581] The server receives the generated recipe and sends it to the user's device. The recipe is sent in JSON format, for example.

[1582] Step 9:

[1583] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[1584] Step 10:

[1585] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[1586] Step 11:

[1587] When a user launches a smartphone app to check the contents of their refrigerator while away from home, the app sends a request to the server to retrieve the latest list of ingredients.

[1588] Step 12:

[1589] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[1590] Step 13:

[1591] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are away from home and prevent duplicate food purchases.

[1592] Example 1

[1593] 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."

[1594] This invention aims to automate and streamline the management of ingredients stored in home storage devices and the creation of recipe suggestions based on that information. In order for users to specifically understand the contents of the storage device and create appropriate dishes, it is necessary to utilize image recognition technology and generative AI models. However, existing systems have been criticized for their time-consuming manual input of information by users and the difficulty of checking information while away from home.

[1595] 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.

[1596] In this invention, the server includes means for uploading images of the contents of the storage device taken by the user, means for analyzing the received images and identifying items in the images to generate an item list, means for using a generative AI model to generate a cooking recipe based on the generated item list, means for presenting the generated cooking recipe to the user, means for the user to send a request to the server to check the contents of the storage device while away from home, and means for sending the latest item list to the user's terminal, thereby enabling the user to efficiently manage ingredients in the storage device and easily create optimal dishes.

[1597] A "user" is a person who uses the system and requests management of ingredients in the storage device and cooking suggestions.

[1598] "Storage equipment" refers to equipment such as refrigerators and freezers for preserving food.

[1599] The "means for uploading images" is a function for transmitting image data taken by the user to the server.

[1600] The "means for analyzing images" is a function for analyzing received image data using image recognition technology and identifying items in the image.

[1601] The "means for identifying items" is a function that identifies each item in an image through image analysis and extracts its name and quantity.

[1602] The "means for generating an item list" is a function for compiling information about identified items in list format and saving it as data.

[1603] A "generative AI model" is an artificial intelligence model that performs natural language processing based on input data and generates appropriate output (in this case, a cooking recipe).

[1604] The "means for generating cooking recipes" is a function that uses a generative AI model based on a list of items to generate recipes including the name of the dish, the necessary ingredients, cooking steps, etc.

[1605] The "means for presenting a cooking recipe" is a function for transmitting the generated recipe to the user's terminal and displaying it.

[1606] The "means for sending a request to a server" is a function that allows a user to send a specific request to a server in order to check the contents of a storage device while away from home.

[1607] The "means for transmitting the latest item list" is a function that enables the server to transmit the latest item list to the user's terminal.

[1608] "Terminal" refers to a portable electronic device used by a user, such as a smartphone or tablet.

[1609] This invention relates to a system that allows users to specifically grasp the contents of a storage device and create appropriate dishes based on that information. This system allows users to take and upload images of the contents of the storage device, automatically recognizes the items in the images, and suggests cooking recipes based on the generated list of items.

[1610] System configuration and operation

[1611] 1. Upload an image

[1612] Users take pictures of the contents of the storage device using a device such as a smartphone or tablet. The images are then uploaded to a server via a dedicated application. To do this, users open the app, select the option "Upload images from storage device," and take or select an image. Next, they press the "Upload" button to send the image to the server.

[1613] 2. Image analysis and item list generation

[1614] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition) to identify the items contained in the image. Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API performs analysis and returns the names and quantities of the recognized items as a response. The server receives this response and generates an item list. The item list stores the name and quantity of each item in the storage device in JSON format.

[1615] 3. Recipe Generation

[1616] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates an optimal cooking recipe. This recipe includes the name of the dish, the required ingredients, cooking steps, cooking time, and nutritional balance.

[1617] 4. Presenting recipes to users

[1618] The server sends the cooking recipes generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application, and then received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The user opens the application, selects the "Suggested Recipes" section, selects the desired recipe from the displayed recipes, and checks the detailed information. The detailed information includes the steps for each dish, the required ingredients, cooking time, and nutritional balance.

[1619] Specific examples

[1620] For example, a user may take an image of the inside of a storage device and the following items may be recognized:

[1621] Tomatoes: 3

[1622] Eggs: 6 pieces

[1623] Milk: 500ml

[1624] Cheese: 200g

[1625] Lettuce: 1 head

[1626] The server sends this list of items to a generative AI model, which generates a recipe like this:

[1627] 1. Dish name: Tomato and cheese omelette

[1628] 2. Ingredients needed: Tomato, egg, milk, cheese

[1629] 3. Cooking Instructions:

[1630] Slice the tomatoes.

[1631] Crack the eggs into a bowl, beat them and add the milk.

[1632] Preheat a frying pan and melt the butter.

[1633] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1634] Finish the omelette.

[1635] 4. Cooking time: 20 minutes

[1636] 5. Nutritional balance: high protein, low fat

[1637] The recipe is displayed on the user's device, allowing the user to easily follow the steps to create the dish. Furthermore, if the user wants to check the contents of the storage device while away from home, the server can send the latest item list to the device, preventing duplicate food purchases. This reduces food waste in the home and provides a system that allows users to use items in a healthy and efficient manner.

[1638] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1639] Step 1:

[1640] Users use their smartphones or tablets to take pictures of the contents of the storage device. The images are then uploaded to the server via a dedicated application. Specifically, users open the app, select the option "Upload images from storage device," and take or select an image. Then, by pressing the "Upload" button, the captured image data is sent to the server. The input is the image taken by the user, and the output is the image data sent to the server.

[1641] Step 2:

[1642] The server sends the received image data to an image recognition API (for example, Google Cloud Vision API or Amazon Rekognition). Specifically, the server sends the image data to the API endpoint as a POST request. The image recognition API analyzes the input image and identifies the objects contained in the image. The response returned by the API includes the names and quantities of the identified objects. The input is the image data received by the server, and the output is the response data (names and quantities of objects) from the image recognition API.

[1643] Step 3:

[1644] The server receives the response from the image recognition API and generates a list of items based on it. This list indicates the name and quantity of each item in the storage device and is saved in JSON format. The input is the response data from the image recognition API, and the output is the generated list of items. Specifically, the server analyzes the data in the response, extracts the name and quantity of each item, and compiles them into a list.

[1645] Step 4:

[1646] The server sends the generated list of items to a generative AI model (for example, OpenAI's GPT-4). Specifically, the list of items is sent as a prompt to the generative AI model's endpoint. The prompt uses the following format: "Based on this list of items, please suggest an appropriate cooking recipe: tomatoes (3), eggs (6), milk (500ml), cheese (200g)." The generative AI model receives this prompt, analyzes it, and generates the optimal cooking recipe. The input is a list of items in JSON format, and the output is the generated cooking recipe.

[1647] Step 5:

[1648] The server sends the cooking recipe generated by the generative AI model to the user's device. Specifically, the recipe data is sent to the API endpoint of the dedicated application and received by the user's device. The device analyzes the received recipe data and displays it to the user within the dedicated application. The input is the cooking recipe data sent from the server, and the output is the cooking recipe displayed on the device.

[1649] Step 6:

[1650] The user opens the application and selects the "Suggested Recipes" section. They select the recipe they want from the displayed list and view the detailed information, which includes the steps, ingredients needed, cooking time, and nutritional balance for each dish. The input is the recipe selected by the user, and the output is the detailed information displayed.

[1651] (Application example 1)

[1652] 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."

[1653] Conventional systems had limited functionality for identifying ingredients in the home and suggesting appropriate dishes, making it difficult for users to efficiently manage items in storage devices. Furthermore, even in brick-and-mortar stores, there were few mechanisms for customers to receive on-the-spot recipe suggestions based on the product list in the store, and suggestions for making effective use of ingredients were lacking. As a result, users and customers frequently wasted ingredients, creating a food waste problem.

[1654] 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.

[1655] In this invention, the server includes a means for uploading images of items in the storage device taken by the user, a means for analyzing the received images, identifying the items in the images, and generating an item list, and a means for using a generative AI model to generate recipes based on the generated item list. This allows users and customers to efficiently identify the items in the storage device and provide appropriate recipes. Specifically, when a user takes a photo of the contents of the storage device with their smartphone and uploads it, appropriate recipes are presented in real time using image analysis and the generative AI model, allowing ingredients to be used effectively without waste. The system can also be applied as a customer service in physical stores, providing a system that allows users to obtain recommended recipes from images of product shelves taken on the spot.

[1656] "Storage device"

[1657] is a general term for facilities and equipment used to preserve food and goods.

[1658] "Goods"

[1659] is a general term for all physical items that are subject to image analysis, such as food and merchandise stored in refrigerators and stores.

[1660] How to upload images

[1661] A camera is a device or system that has the function of transmitting image data captured by a user to a server via a network.

[1662] "Image analysis"

[1663] is a technique for processing received image data and identifying items contained within the image.

[1664] "List of Items"

[1665] This is data in the form of a list that includes the names and quantities of items identified through image analysis.

[1666] "Generative AI model"

[1667] is an algorithm or system that uses artificial intelligence to generate specific results or information based on input data.

[1668] "Cooking method"

[1669] is a general term for the steps and methods of cooking a dish using specific ingredients.

[1670] "Means of presenting to the user"

[1671] A recipe manager is a device or system that has the function of displaying the generated recipe to the user.

[1672] A way to send a request to the server

[1673] A storage device is a device or system that has the function of allowing a user to request information stored in a storage device from a server from a specified location.

[1674] "Terminal"

[1675] A device is an electronic device that is operated by a user, and includes smartphones, tablets, personal computers, etc.

[1676] "Nutritional balance"

[1677] This is a concept that refers to a healthy combination of ingredients, taking into account the type and amount of food ingredients in the cooking method.

[1678] "Cooking time"

[1679] is a general term for the time it takes to complete a dish according to a specific cooking method.

[1680] The present invention relates to a system that allows a user to efficiently manage items in a storage device and suggests appropriate recipes based on the managed items. Specific embodiments of this system will be described below.

[1681] System configuration and operation

[1682] 1. Upload an image

[1683] Users take photos of items in the storage device using a device such as a smartphone or tablet, and upload the images to the server via an application. The uploaded images are then processed on the cloud server.

[1684] 2. Image analysis and item list generation

[1685] The server sends the received image data to an image recognition API to identify the items contained in the image. This process uses common cloud services that provide image recognition technology (such as Google Cloud Vision API or Amazon Rekognition). The image recognition API analyzes the image and returns the names and quantities of the recognized items. The server generates an item list based on the response from the image recognition API. The item list contains the name and quantity of each item in the storage device, and this list is saved in JSON format or similar.

[1686] 3. Recipe generation

[1687] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model such as OpenAI's GPT series model. This model generates optimal recipes based on the ingredient list. The recipes include the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1688] 4. Presenting recipes to users

[1689] The generated recipes are sent from the server to the user's device and displayed to the user through the application. The user can select the recipe they want and check the detailed information.

[1690] Hardware and software used

[1691] Smartphones and tablets: Used by users to take pictures of items in the storage unit and upload the images.

[1692] Cloud server: Receives and analyzes image data, generates an ingredient list, and generates recipes using a generative AI model.

[1693] Image Recognition API: Use an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to automatically identify objects in images.

[1694] Generative AI models, such as OpenAI GPT-4, are used to generate appropriate recipes.

[1695] Specific examples

[1696] For example, a user may take a picture of the inside of a storage unit and recognize the following items:

[1697] Tomatoes: 3

[1698] Eggs: 6 pieces

[1699] Milk: 500ml

[1700] Cheese: 200g

[1701] Lettuce: 1 head

[1702] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1703] 1. Dish name: Tomato and cheese omelette

[1704] 2. Supplies needed: Tomatoes, eggs, milk, cheese

[1705] 3. Cooking Instructions:

[1706] Slice the tomatoes.

[1707] Crack the eggs into a bowl, beat them and add the milk.

[1708] Preheat a frying pan and melt the butter.

[1709] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1710] Finish the omelette.

[1711] 4. Cooking time: 20 minutes

[1712] 5. Nutritional balance: high protein, low fat

[1713] Prompt Sentence Examples

[1714] Suggest a recipe based on the following list of items:

[1715] Tomatoes: 3

[1716] Eggs: 6 pieces

[1717] Milk: 500ml

[1718] Cheese: 200g

[1719] Lettuce: 1 head

[1720] This series of steps allows users to easily select and prepare the appropriate recipe, which makes efficient use of stored items and reduces food waste.

[1721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1722] Step 1:

[1723] Users take photos of items in the storage device using a smartphone or tablet. The images are then uploaded to a cloud server via a dedicated application. The input is the captured image data, and the output is an image file uploaded to the cloud server.

[1724] Step 2:

[1725] The server sends the image to an image recognition API, such as Google Cloud Vision API or Amazon Rekognition, to analyze the received image data. The input is the image data received by the server, and the output is the analysis results, including the names and quantities of items in the image.

[1726] Step 3:

[1727] The server generates an item list based on the analysis results obtained from the image recognition API. This item list includes the name and quantity of each item and is saved in JSON format or similar. The input is the analysis result data from the image recognition API, and the output is the item list.

[1728] Step 4:

[1729] The server sends the generated item list to a generative AI model, a natural language processing model, to generate a recipe. In this process, a prompt is used as input to the generative AI model, which then outputs the optimal recipe. The input is the item list and the prompt, and the output is the generated recipe.

[1730] Step 5:

[1731] The server sends the recipe generated by the generative AI model to the user's device, where the user can check the recipe using a dedicated application. The input is the generated recipe, and the output is the recipe displayed on the user's device.

[1732] Step 6:

[1733] The user selects the necessary ingredients based on the recipe provided and performs the cooking. The input is the recipe sent from the server, and the output is the cooking result performed by the user.

[1734] This series of processes enables the user to efficiently manage the items in the storage device and obtain appropriate recipes.

[1735] 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.

[1736] The present invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, more personalized recipe suggestions become possible. The following describes how the present invention can be specifically implemented.

[1737] System configuration and operation

[1738] 1. Upload an image

[1739] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are uploaded to a server via a dedicated application on the device.

[1740] 2. Image analysis and ingredient list generation

[1741] The server sends the received image data to an image recognition API to identify the ingredients contained in the image. For example, it uses common image recognition technology to identify the names and quantities of ingredients. Based on the analysis results, it generates an ingredient list. This ingredient list is saved in JSON format or similar.

[1742] 3. Recipe Generation

[1743] The server sends the generated ingredient list to a generative AI model, which uses a natural language processing model, for example, to generate a cooking recipe based on the ingredient list. This cooking recipe includes the following elements:

[1744] Dish name

[1745] Necessary ingredients

[1746] Cooking Instructions

[1747] Cooking time

[1748] Nutritional balance

[1749] 4. Utilizing the Emotion Engine

[1750] The server uses an emotion engine to recognize the user's emotions using images captured by the user and information acquired from the user interface. This emotion engine grasps the user's emotional state through, for example, voice recognition, image analysis, and touch interface.

[1751] The type of recipe and cooking method are customized based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the system will suggest recipes using ingredients that have a relaxing effect. The system also has an interface for providing notifications and suggestions that reflect the user's emotions.

[1752] 5. Presenting recipes to users

[1753] The server sends the cooking recipes generated by the generative AI model to the user's device, which receives them and displays them to the user in a dedicated application. The user can then select the recipe they want and check the details.

[1754] Specific examples

[1755] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[1756] Tomatoes: 3

[1757] Eggs: 6 pieces

[1758] Milk: 500ml

[1759] Cheese: 200g

[1760] Lettuce: 1 head

[1761] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1762] 1. Dish name: Tomato and cheese omelette

[1763] 2. Ingredients needed: Tomato, egg, milk, cheese

[1764] 3. Cooking Instructions:

[1765] Slice the tomatoes.

[1766] Crack the eggs into a bowl, beat them and add the milk.

[1767] Preheat a frying pan and melt the butter.

[1768] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1769] Finish the omelette.

[1770] 4. Cooking time: 20 minutes

[1771] 5. Nutritional balance: high protein, low fat

[1772] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[1773] Check the contents of your refrigerator when you're out

[1774] When a user is out and about, they launch the app on their smartphone and send a request to the server. In response to this request, the server retrieves the latest ingredient list and sends it to the user's device. The device then analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and prevent duplicate food purchases.

[1775] This reduces food waste in the home and provides a system that allows users to use ingredients in a healthy and efficient manner. Furthermore, personalized recipe suggestions that take into account the user's emotional state can further increase user satisfaction.

[1776] The processing flow will be explained below.

[1777] Step 1:

[1778] Users take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and the images are saved in a dedicated application on the device.

[1779] Step 2:

[1780] The device selects the stored image data and uploads it to the server via the application interface.

[1781] Step 3:

[1782] The server checks the received image data and sends a request to the image recognition API. The request contains the image data.

[1783] Step 4:

[1784] The image recognition API analyzes the image and identifies the ingredients contained within it. The identification results, including the names and quantities of the ingredients, are returned to the server.

[1785] Step 5:

[1786] The server receives the response from the image recognition API and generates an ingredient list, which is saved in JSON format.

[1787] Step 6:

[1788] The server sends the generated ingredient list to the generative AI model. The ingredient list is included in the request.

[1789] Step 7:

[1790] The generative AI model generates a cooking recipe based on the submitted ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1791] Step 8:

[1792] The server receives the generated recipe and sends it to the user's device in JSON format.

[1793] Step 9:

[1794] The device analyzes the cooking recipe received from the server and displays it to the user. The application displays an overview of the dish, including the name of the dish, cooking time, and nutritional balance.

[1795] Step 10:

[1796] Users can select the recipe they want from the suggested recipes and check the detailed information, which includes cooking instructions and details of the ingredients needed.

[1797] Step 11:

[1798] The server analyzes the user interface, images, and audio data to understand the user's emotions, and determines the user's emotional state from the user's facial expressions and tone of voice.

[1799] Step 12:

[1800] The emotion engine analyzes the user's emotions and sends the emotion data, which can include stress, joy, excitement, etc., to the server.

[1801] Step 13:

[1802] The server receives data from the emotion engine and adjusts the recipe content based on the user's emotions. For example, if the user is under a lot of stress, it will select recipes that use ingredients that have a relaxing effect.

[1803] Step 14:

[1804] The server regenerates the adjusted recipe and sends it to the user's device, allowing the user to receive recipe suggestions tailored to their emotional state.

[1805] Step 15:

[1806] A user sends a request to the server via a smartphone app to check the contents of the refrigerator while away from home. The request is to obtain the latest list of ingredients.

[1807] Step 16:

[1808] The server retrieves the latest ingredient list and sends it to the user's device in JSON format.

[1809] Step 17:

[1810] The device analyzes the received ingredient list and displays it to the user, allowing the user to check the contents of their refrigerator even when they are out and about, and avoid buying unnecessary food.

[1811] Example 2

[1812] 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."

[1813] In modern households, it is difficult to efficiently manage the contents of the refrigerator, resulting in inappropriate food purchases and food waste. Furthermore, it is cumbersome to consider appropriate dishes based on the contents of the refrigerator, making it difficult to provide personalized recipes that correspond to the user's emotional state. Furthermore, there are insufficient means to check the contents of the refrigerator while away from home, and a method to prevent duplicate or unnecessary food purchases is needed.

[1814] 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.

[1815] In this invention, the server includes a means for uploading images of the contents of the refrigerator taken by the user, a means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, a means for using a generative AI model to generate cooking recipes based on the generated ingredient list, a means for recognizing the user's emotional state and customizing recipes based on that state, and a means for presenting the generated cooking recipes to the user. This allows users to efficiently manage the contents of their refrigerator, reduce food waste, and easily obtain personalized cooking recipes that match their emotions. It also allows users to check the contents of their refrigerator while away from home and prevent duplicate food purchases.

[1816] "User" refers to a person who uses this system to manage the contents of their refrigerator and obtain cooking recipes.

[1817] The "server" refers to a computer system that receives and analyzes images taken by users and generates ingredient lists and cooking recipes.

[1818] "Image Recognition API" refers to an application programming interface for analyzing received images and identifying the ingredients contained within them.

[1819] "Ingredient list" refers to a list containing the names and quantities of ingredients identified by the image recognition API.

[1820] A "generative AI model" refers to an artificial intelligence model that generates cooking recipes based on an ingredient list.

[1821] An "emotion engine" refers to a system that recognizes a user's emotional state based on images taken by the user and information obtained from the interface.

[1822] A "cooking recipe" refers to information that includes specific cooking steps that users can use, the ingredients needed, cooking time, nutritional balance, and other information.

[1823] "Terminal" refers to a device (e.g., a smartphone or tablet) that a user uses to take pictures of the contents of the refrigerator or check ingredient lists and cooking recipes.

[1824] A "request from outside" refers to a request sent to the server by a user to check the contents of the refrigerator while the user is out.

[1825] "JSON format" refers to the JavaScript Object Notation data structure used to store the ingredient list.

[1826] This invention relates to a system that allows users to grasp the specific contents of their refrigerator and create appropriate dishes based on that information. This system allows users to take and upload images of the refrigerator's contents, automatically recognizes ingredients in the images, and suggests recipes based on the generated ingredient list. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, it enables more personalized recipe suggestions.

[1827] Hardware and software used

[1828] This system uses the following hardware and software:

[1829] 1. User device (e.g. smartphone, tablet)

[1830] Dedicated application: Application for taking and uploading images of the inside of the refrigerator

[1831] Internet connection: allows data transmission to the server

[1832] 2. Server

[1833] Image recognition API (e.g., Google Vision API): Used to identify ingredients in images

[1834] Generative AI models (e.g., GPT-3.5): Generate cooking recipes based on ingredient lists

[1835] Emotion Engine: Recognizes the user's emotional state and uses it to personalize recipes

[1836] Database: Stores ingredient lists and generated recipes

[1837] Specific operation of the system

[1838] 1. Taking and uploading images

[1839] The user uses the device to take pictures of the inside of the refrigerator, which are then uploaded to the server using a dedicated application.

[1840] 2. Image analysis and ingredient list generation

[1841] The server receives the image uploaded by the user. It then sends the image to an image recognition API to identify the ingredients in the image. The server generates an ingredient list based on the analysis results of the image recognition API and saves it in JSON format.

[1842] 3. Recipe Generation

[1843] The server sends the generated ingredient list to the generative AI model. The generative AI model generates a cooking recipe using a prompt. An example of a prompt is shown below.

[1844] You have the following ingredients in your refrigerator:

[1845] Tomatoes: 3

[1846] Eggs: 6 pieces

[1847] Milk: 500ml

[1848] Cheese: 200g

[1849] Lettuce: 1 head

[1850] Can you recommend some easy and delicious recipes using this ingredient?

[1851] 4. Utilizing the Emotion Engine

[1852] The server uses an emotion engine to recognize the user's emotions based on images taken by the user and information obtained from the user interface. Depending on the user's emotional state, the server adjusts the generated cooking recipes, generating personalized recipes, such as using ingredients with a relaxing effect for users who are feeling stressed.

[1853] 5. Presenting the recipe

[1854] The server sends the created recipe to the user's device, where the user can check the recipe and view details through a dedicated application on the device.

[1855] 6. Check the contents of your refrigerator while you're out

[1856] The user uses a dedicated application while on the go to send a request for the latest ingredient list to the server.

[1857] The server retrieves the latest ingredient list and sends it to the user's device, where the user can check the contents of the refrigerator.

[1858] Specific examples

[1859] For example, a user may take a picture of the inside of their refrigerator and the following ingredients may be recognized:

[1860] Tomatoes: 3

[1861] Eggs: 6 pieces

[1862] Milk: 500ml

[1863] Cheese: 200g

[1864] Lettuce: 1 head

[1865] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1866] 1. Dish name: Tomato and cheese omelette

[1867] 2. Ingredients needed: Tomato, egg, milk, cheese

[1868] 3. Cooking Instructions:

[1869] Slice the tomatoes.

[1870] Crack the eggs into a bowl, beat them and add the milk.

[1871] Preheat a frying pan and melt the butter.

[1872] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1873] Finish the omelette.

[1874] 4. Cooking time: 20 minutes

[1875] 5. Nutritional balance: high protein, low fat

[1876] If the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[1877] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1878] Step 1:

[1879] Users use a smartphone or tablet to take pictures of the contents of the refrigerator using a dedicated application.

[1880] Input: Image of the contents of the refrigerator

[1881] Output: Image saved on the user's device

[1882] Step 2:

[1883] The device uploads the captured images to a server via a dedicated application, which requires an internet connection.

[1884] Input: Images stored on the user's device

[1885] Output: Image data uploaded to the server

[1886] Step 3:

[1887] The server receives the image data received from the user, then sends this image data to an image recognition API (e.g., Google Vision API) to identify the ingredients contained in the image.

[1888] Input: Image data uploaded to the server

[1889] Output: Ingredient information returned from the image recognition API

[1890] Step 4:

[1891] The server generates an ingredient list based on the image recognition results. This ingredient list includes the names and quantities of ingredients. The server saves this ingredient list in JSON format.

[1892] Input: Ingredient information returned from the image recognition API

[1893] Output: JSON formatted list of ingredients

[1894] Step 5:

[1895] The server sends the generated ingredient list to a generative AI model (e.g., GPT-3.5) using a prompt to instruct it to generate a cooking recipe based on the ingredient list.

[1896] Input: JSON format ingredients list, prompt

[1897] Output: Cooking recipes generated from the generative AI model

[1898] Step 6:

[1899] The server receives the cooking recipes returned by the generative AI model and, if necessary, uses an emotion engine to recognize the user's emotional state, generating a personalized recipe based on the user's emotions.

[1900] Input: Cooking recipes returned by the generative AI model, user emotional state

[1901] Output: personalized cooking recipes

[1902] Step 7:

[1903] The server finally sends the generated and customized cooking recipe to the user's device.

[1904] Input: Personalized cooking recipe

[1905] Output: Cooking recipe sent to the user's device

[1906] Step 8:

[1907] The device displays the received recipes in a dedicated application, allowing the user to select the recipe they want and check the details.

[1908] Input: A cooking recipe sent to the user's device

[1909] Output: Cooking recipe displayed on the device

[1910] Step 9:

[1911] To check the contents of the refrigerator while away from home, the user launches a dedicated application and sends a request to the server.

[1912] Input: Request to check the contents of the refrigerator

[1913] Output: Request data to the server

[1914] Step 10:

[1915] The server retrieves the latest ingredient list and sends it to the user's terminal.

[1916] Input: Request to check the contents of the refrigerator

[1917] Output: Latest ingredients list

[1918] Step 11:

[1919] The device displays the received ingredient list in a dedicated application and notifies the user, allowing the user to avoid purchasing duplicate food items.

[1920] Input: Latest ingredient list

[1921] Output: Ingredient list displayed on the device

[1922] (Application example 2)

[1923] 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."

[1924] Currently, there are systems that track the contents of a refrigerator and suggest appropriate dishes based on that information. However, these systems are unable to suggest recipes that take into account the user's emotions or personal preferences. Furthermore, there are no systems that can efficiently consume ingredients while delivering dishes that correspond to the user's emotional state. This makes it difficult for users to enjoy efficient, personalized cooking without hassle. Furthermore, even if there are systems that can track the contents of a refrigerator while on the go, they lack the functionality to instantly deliver dishes based on that information.

[1925] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1926] In this invention, the server includes means for uploading images of the contents of the refrigerator taken by the user, means for analyzing the received images and identifying ingredients in the images to generate an ingredient list, means for using a generative AI model to generate a cooking recipe based on the generated ingredient list, means for using an emotion engine to recognize the emotional state of the user and customize the recipe based on that emotional state in generating the cooking recipe, and means for allowing the user to select from the generated cooking recipes and delivering food cooked based on the selected recipe.This allows the user not only to know the contents of the refrigerator, but also to receive personalized food suggestions based on that information and to check the contents of the refrigerator while on the go and have food delivered on the spot.

[1927] "User" refers to an individual who uses the system to understand the contents of their refrigerator and receive cooking recipe suggestions and delivery services.

[1928] "Means for uploading images" refers to a function that allows a user to send images of the contents of the refrigerator taken using a device such as a smartphone or tablet to a cloud server.

[1929] "Means for analyzing images" refers to the function for analyzing image data received by the server and recognizing and identifying the ingredients contained therein.

[1930] The means for generating an "ingredient list" refers to a function that compiles ingredient information obtained from analyzed image data into a list format.

[1931] A "generative AI model" refers to artificial intelligence technology that automatically generates cooking recipes based on a list of ingredients.

[1932] "Emotion engine" refers to technology that recognizes the user's emotional state and customizes the cooking recipes provided based on that emotional state.

[1933] "Delivery means" refers to a function for delivering food prepared based on a recipe selected by the user to a location designated by the user.

[1934] "Means for checking while away from home" refers to a function that allows users to check the contents of their refrigerator via their smartphone or tablet even when they are out.

[1935] The "means for transmitting the latest ingredient list" refers to a function that enables the server to transmit the latest ingredient information to the user's terminal.

[1936] "Nutritional balance" refers to the standard for providing healthy menus that take into consideration the nutritional balance of ingredients and dishes.

[1937] "Cooking time" refers to the time required to complete a dish based on a recipe.

[1938] The present invention is a system that allows a user to specifically grasp the contents of their refrigerator and provide appropriate meals based on that information. This system includes a function that proposes personalized recipes taking into account the user's emotional state and delivers meals prepared based on those recipes. Specific embodiments for carrying out the invention are described in detail below.

[1939] System configuration and operation

[1940] 1. Upload an image

[1941] Users can take pictures of the contents of their refrigerator using a device such as a smartphone or tablet, and then upload the images to a cloud server via a dedicated application.

[1942] 2. Image analysis and ingredient list generation

[1943] The server sends the image data received from cloud storage to an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition), which identifies the ingredients contained in the image and generates an ingredient list. This ingredient list is saved in JSON format or similar.

[1944] 3. Recipe Generation

[1945] The server uses a generative AI model (e.g., OpenAI GPT-3, GPT-4) to generate a cooking recipe based on the generated ingredient list, including the name of the dish, the ingredients needed, cooking steps, cooking time, and nutritional balance.

[1946] 4. Utilizing the Emotion Engine

[1947] The server uses an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. It determines the user's emotional state based on information obtained from the user's voice input and touch interface. It customizes recipes based on the emotional state recognized by the emotion engine.

[1948] 5. Creating a delivery request

[1949] Based on the recipe selected by the user, order information is sent to the delivery system, which then prepares the specified dish and delivers it to the user.

[1950] 6. Present recipe to user and confirm order details

[1951] The server sends the created recipe to the user's device, where the user can check the recipe displayed in a dedicated application and confirm the order.

[1952] Specific examples

[1953] For example, let's say a user takes a picture of the inside of their refrigerator and the following ingredients are recognized:

[1954] Tomatoes: 3

[1955] Eggs: 6 pieces

[1956] Milk: 500ml

[1957] Cheese: 200g

[1958] Lettuce: 1 head

[1959] The server sends this list of ingredients to a generative AI model, which generates a recipe like this:

[1960] 1. Dish name: Tomato and cheese omelette

[1961] 2. Ingredients needed: Tomato, egg, milk, cheese

[1962] 3. Cooking Instructions:

[1963] Slice the tomatoes.

[1964] Crack the eggs into a bowl, beat them and add the milk.

[1965] Preheat a frying pan and melt the butter.

[1966] Pour the egg mixture into the frying pan and add the tomatoes and cheese.

[1967] Finish the omelette.

[1968] 4. Cooking time: 20 minutes

[1969] 5. Nutritional balance: high protein, low fat

[1970] Furthermore, if the emotion engine determines that the user is feeling stressed, the system can suggest recipes using relaxing herbs or calming ingredients such as chocolate.

[1971] Prompt Sentence Examples

[1972] text

[1973] Suggest an easy, healthy recipe using the following ingredient list. The user is stressed, so please consider cooking with ingredients that have a relaxing effect. Ingredient list: 3 tomatoes, 6 eggs, 500ml milk, 200g cheese, 1 lettuce

[1974] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1975] Step 1:

[1976] Image upload

[1977] Users can take a picture of the contents of their refrigerator using a camera app on their smartphone or tablet, and then upload the image to a cloud server via a dedicated application.

[1978] Input: Image file of the contents of the refrigerator

[1979] Output: Image data stored on a cloud server

[1980] Step 2:

[1981] Image analysis and ingredient list generation

[1982] The server retrieves the uploaded image data and analyzes it using an image recognition API (e.g., Google Cloud Vision API, Amazon Rekognition). As a result of the analysis, ingredients in the image are identified and an ingredient list is generated based on that information. This ingredient list is saved in JSON format.

[1983] Input: Image data stored on a cloud server

[1984] Output: JSON formatted list of ingredients

[1985] Data processing: Extracting image data as ingredient information and converting it into a list format

[1986] Step 3:

[1987] Recipe Generation

[1988] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate a cooking recipe based on the generated ingredient list. The ingredient list is sent to the generative AI model as a prompt, and a recipe is generated that includes the name of the dish, the required ingredients, cooking steps, cooking time, nutritional balance, etc.

[1989] Input: JSON formatted list of ingredients

[1990] Output: Cooking recipe (text format)

[1991] Data computation: Input the list of ingredients as prompts into the AI ​​model to generate a recipe

[1992] Step 4:

[1993] Utilizing the Emotion Engine

[1994] The server analyzes information obtained from voice input and touch interface using an emotion engine (e.g., Microsoft Azure Emotion API) to recognize the user's emotional state. Based on the analysis results, the server customizes recipes according to the user's emotional state.

[1995] Input: Voice input data, touch interface data

[1996] Output: Customized cooking recipes

[1997] Data processing: Analyze the user's input data as an emotional state and reflect it in the recipe

[1998] Step 5:

[1999] Generating a delivery request

[2000] The user can check and select a recipe via the application. Then, by requesting delivery of a dish based on that recipe, the order information is sent to the delivery system. The delivery system then prepares and delivers the specified dish.

[2001] Input: Selected recipe

[2002] Output: Delivery order information

[2003] Data calculation: Sends order information to the delivery system based on the selected recipe

[2004] Step 6:

[2005] Present recipes to users and confirm order details

[2006] The server sends the created recipe to the user's device. The user can check the recipe displayed in a dedicated application and confirm the delivery order. Once the order details are confirmed, the final order information is sent to the delivery system.

[2007] Input: Generated cooking recipe

[2008] Output: Recipe displayed on the user's device, confirmed order information

[2009] Data calculation: Sending recipes, checking and confirming order details

[2010] 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.

[2011] 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.

[2012] 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.

[2013] 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.

[2014] 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.

[2015] 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.

[2016] 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).

[2017] 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.

[2018] 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."

[2019] 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.

[2020] 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).

[2021] 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.

[2022] 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.

[2023] 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.

[2024] 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.

[2025] 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.

[2026] 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.

[2027] 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.

[2028] 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.

[2029] 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.

[2030] 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.

[2031] The following is further disclosed regarding the above embodiment.

[2032] (Claim 1)

[2033] a means for a user to upload an image of the contents of the refrigerator;

[2034] means for analyzing the received image and identifying ingredients in the image to generate an ingredient list;

[2035] using a generative AI model to generate a cooking recipe based on the generated ingredient list; and

[2036] A means for presenting the generated cooking recipe to a user;

[2037] A system including:

[2038] (Claim 2)

[2039] A means for a user to send a request to a server to check the contents of a refrigerator while away from home;

[2040] means for transmitting the updated ingredient list to a user's terminal;

[2041] The system of claim 1 further comprising:

[2042] (Claim 3)

[2043] 2. The system according to claim 1, further comprising means for generating a cooking recipe taking into consideration the nutritional balance of ingredients and cooking time.

[2044] "Example 1"

[2045] (Claim 1)

[2046] means for uploading images taken by a user of the contents of the storage device;

[2047] means for analyzing the received images and identifying items in the images to generate an item list;

[2048] a means for using a generative AI model to generate a cooking recipe based on the generated list of items;

[2049] A means for presenting the generated cooking recipe to a user;

[2050] A means for transmitting a request to a server for a user to check the contents of the storage device while away from home;

[2051] means for transmitting the latest item list to a user terminal;

[2052] A system including:

[2053] (Claim 2)

[2054] The system of claim 1 uses a generative AI model that generates cooking recipes taking into account nutritional balance and cooking time.

[2055] (Claim 3)

[2056] 10. The system of claim 1, wherein the item list is stored in JSON format.

[2057] "Application Example 1"

[2058] (Claim 1)

[2059] means for uploading images of items in the storage device taken by a user;

[2060] means for analyzing the received images and identifying items in the images to generate an item list;

[2061] a means for using a generative AI model to generate a recipe based on the generated ingredient list;

[2062] means for presenting the generated recipe to a user;

[2063] A system including:

[2064] (Claim 2)

[2065] A means for a user to send a request to a server from a specified location to check the contents of the storage device;

[2066] means for transmitting the latest item list to a user terminal;

[2067] The system of claim 1 further comprising:

[2068] (Claim 3)

[2069] 2. The system according to claim 1, further comprising means for generating a recipe taking into consideration the nutritional balance and cooking time of the item in generating the recipe.

[2070] "Example 2: Combining Emotion Engines"

[2071] (Claim 1)

[2072] a means for a user to upload an image of the contents of the refrigerator;

[2073] means for analyzing the received image and identifying ingredients in the image to generate an ingredient list;

[2074] using a generative AI model to generate a cooking recipe based on the generated ingredient list; and

[2075] A means for presenting the generated cooking recipe to a user;

[2076] a means for recognizing a user's emotional state and customizing recipes based thereon;

[2077] A system including:

[2078] (Claim 2)

[2079] A means for a user to send a request to a server to check the contents of a refrigerator while away from home;

[2080] means for transmitting the updated ingredient list to a user's terminal;

[2081] 10. The system of claim 1, comprising:

[2082] (Claim 3)

[2083] A means for generating a cooking recipe taking into consideration the nutritional balance of ingredients and cooking time;

[2084] 10. The system of claim 1, comprising:

[2085] "Application example 2 when combining emotion engines"

[2086] (Claim 1)

[2087] a means for a user to upload an image of the contents of the refrigerator;

[2088] means for analyzing the received image and identifying ingredients in the image to generate an ingredient list;

[2089] using a generative AI model to generate a cooking recipe based on the generated ingredient list; and

[2090] In generating cooking recipes, a means for using an emotion engine that recognizes an emotional state of a user and customizes the recipe based on the emotional state;

[2091] A means for allowing a user to select one of the generated recipes and delivering a dish prepared based on the selected recipe;

[2092] A system including:

[2093] (Claim 2)

[2094] A means for a user to send a request to a server to check the contents of a refrigerator while away from home;

[2095] means for transmitting the updated ingredient list to a user's terminal;

[2096] The system of claim 1 further comprising:

[2097] (Claim 3)

[2098] 2. The system according to claim 1, further comprising means for generating a cooking recipe taking into consideration the nutritional balance of ingredients and cooking time. [Explanation of symbols]

[2099] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to upload an image of the contents of the refrigerator; means for analyzing the received image and identifying ingredients in the image to generate an ingredient list; using a generative AI model to generate a cooking recipe based on the generated ingredient list; and A means for presenting the generated cooking recipe to a user; A system including:

2. A means for a user to send a request to a server to check the contents of a refrigerator while away from home; means for transmitting the updated ingredient list to a user's terminal; The system of claim 1 further comprising:

3. The system according to claim 1, further comprising means for generating a cooking recipe taking into consideration the nutritional balance of ingredients and cooking time.

Images