System

Abstract

To provide a system for realizing efficient and economical food material management by automatically generating a daily menu.SOLUTION: A means for a user to photograph an image of a receipt, a means for a terminal to extract text data from the image using an optical character recognition technology, a means for the terminal to analyze food ingredient information from the extracted text data, a means for the terminal to send the analyzed food ingredient information to a server, and the server to record the food ingredient information in a database; A system includes a means for updating inventory information, a means for generating a menu suitable for a user on the basis of food material information by using a generation AI by a server, a means for transmitting the generated menu to terminals and presenting it to the user, and a means for collecting feedback from the user and reflecting it on learning of the generation AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The time and effort required to plan a daily menu is a burden for many families and individuals. It is especially difficult for single-person households and busy families to properly manage ingredients and plan menus based on that information. It is also difficult to plan and use ingredients in a way that avoids waste. A system that solves these problems and allows for efficient and economical meal preparation is needed. [Means for solving the problem]

[0005] The present invention provides a means for a user to take an image of a receipt, extract text data from the image using optical character recognition technology, and analyze ingredient information from that data. The terminal sends the analyzed ingredient information to a server, which records the ingredient information in a database and updates inventory information. The server also uses a generation AI to generate a menu suitable for the user based on the ingredient information, which is sent to the terminal and presented to the user. Furthermore, feedback from users is collected and reflected in the generation AI's learning, improving the accuracy of menu suggestions from the next time onwards. Using the above means, a system is provided that automatically generates daily menus and achieves efficient and economical ingredient management.

[0006] "User" refers to an individual or household who uses the system to manage food ingredient information and receive menu suggestions.

[0007] "Terminal" refers to a device such as a smartphone or tablet used by a user, which is used to take photos of receipts, analyze data, display menus, and perform other operations.

[0008] A "server" is an online entity that manages ingredient information, creates menus, accumulates and learns from user feedback, and processes data sent from user terminals.

[0009] "Receipt image" refers to image data of the product information purchased by the user.

[0010] Optical character recognition (OCR) refers to a technology that extracts text information from an image, and is used to obtain ingredient information from receipt images.

[0011] "Text data" refers to text information extracted from an image using OCR technology.

[0012] "Ingredient information" refers to information such as product name, quantity, date, etc. analyzed from the text data on the receipt.

[0013] "Analysis" refers to the process of identifying specific information from the extracted text data and extracting the necessary data.

[0014] "Database" refers to a recording system on a server that has the function of structurally storing and managing ingredient information and user information.

[0015] "Inventory information" refers to information such as the type and quantity of ingredients in the user's home, storage conditions, expiration dates, etc.

[0016] "Generative AI" refers to artificial intelligence that uses machine learning models and algorithms to generate menus for users based on ingredient information.

[0017] "Menu" refers to cooking recipes and meal suggestions generated based on ingredient information.

[0018] "Feedback" refers to the evaluations and comments that users make about the menus provided, and is information that includes their reactions to the system.

[0019] "Learning" refers to the process that the generative AI goes through to improve the accuracy of future menu suggestions based on collected feedback. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention relates to a system that automatically generates and proposes daily menus based on the ingredients available at home. The specific operation method and processing contents of the system are described below.

[0042] System configuration

[0043] This system consists of users, terminals, and a server. The terminals used by users are devices such as smartphones and tablets, through which they access the system. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[0044] Program processing

[0045] 1. Image recognition of receipts

[0046] When the user returns home from the supermarket, for example, they open the app and take a photo of the receipt.

[0047] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image. OCR technology extracts information such as product name, quantity, and date from the receipt image as text data.

[0048] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[0049] 2. Recording and managing food data

[0050] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares the information with existing ingredient information and updates inventory information.

[0051] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching, allowing the user to make effective use of ingredients without wasting them.

[0052] 3. Menu creation requests and suggestions

[0053] When a user requests "Today's Menu," the terminal sends this request to the server.

[0054] The server retrieves available ingredient information from the database and provides that information as input to the generation AI.

[0055] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[0056] The server sends the generated menu to the user's terminal, which displays the suggestions to the user.

[0057] 4. Feedback and learning

[0058] Users can provide feedback on the provided menus, such as "It was delicious" or "It was easy to make," by entering their ratings through the app.

[0059] The terminal sends the user's feedback to the server, which records the feedback in a database.

[0060] The server collects feedback and reflects it as learning data for the generating AI, improving the accuracy of menu suggestions from the next time onwards.

[0061] Specific examples

[0062] 1. The user finishes shopping at the supermarket and takes a photo of the receipt using the app.

[0063] 2. The device analyzes the image using OCR technology and extracts ingredient information such as "tomato, chicken, carrot."

[0064] 3. The device sends the analysis results to the server, which records the received information in a database.

[0065] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[0066] 5. The server uses a generation AI based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[0067] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[0068] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[0069] 8. The server collects feedback and updates the generative AI model to improve the accuracy of the next menu suggestion.

[0070] As described above, the present invention is a system that automates the entire process from ingredient management to menu proposals, significantly reducing the burden on users. This system allows users to enjoy everyday cooking simply and efficiently.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] The user logs in to the app and takes a photo of the receipt. The user uses the camera function in the app to take a photo of the receipt so that the entire receipt is visible.

[0074] Step 2:

[0075] The device captures the image of the receipt. The device stores the image data captured by the user in memory and enables optical character recognition (OCR) technology.

[0076] Step 3:

[0077] The device uses optical character recognition (OCR) technology to extract text data from the image. Specifically, it starts an OCR engine, analyzes the receipt image as input, and identifies text data such as product name, quantity, and date.

[0078] Step 4:

[0079] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[0080] Step 5:

[0081] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[0082] Step 6:

[0083] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[0084] Step 7:

[0085] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[0086] Step 8:

[0087] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[0088] Step 9:

[0089] The device sends the user's request to the server, which then sends the request, including the user's request parameters (such as meal times and preferred genres), to the server via the API.

[0090] Step 10:

[0091] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[0092] Step 11:

[0093] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[0094] Step 12:

[0095] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[0096] Step 13:

[0097] The server sends the generated menu to the user's terminal. The server formats the generated multiple recipe ideas, converts them into a format that is easy for the user to view, and sends them to the terminal.

[0098] Step 14:

[0099] The device displays the generated menu suggestions to the user, and displays the received recipe information on the app's UI so that the user can check it.

[0100] Step 15:

[0101] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[0102] Step 16:

[0103] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[0104] Step 17:

[0105] The server receives the feedback and reflects it as learning data for the generation AI. The server then stores the feedback information in a database and periodically uses it to update the generation AI model, thereby improving the accuracy of future menu suggestions.

[0106] Example 1

[0107] 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."

[0108] In today's busy daily lives, it is important to efficiently manage daily meals and reduce food waste. However, in many households, it is difficult to keep track of the ingredients in the refrigerator, which results in food waste. In addition, planning meals takes time and effort, and many people often find themselves unsure of what to cook. Furthermore, there is a need for automated assistance to make the most of available ingredients and provide healthy, balanced meals.

[0109] 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.

[0110] In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for using a generative AI model to generate a menu suitable for the user based on the ingredient information, and a means for providing the ingredient information as a prompt to the generative AI model to generate recipe candidates. This reduces ingredient waste, enables efficient and effective automatic generation of daily menus, and reduces the burden on the user.

[0111] "User" refers to an individual who uses the system to manage ingredients and receive menu suggestions.

[0112] A "terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[0113] "Server" refers to an online entity that manages ingredient information, generates menus using generative AI models, and accumulates and learns from user feedback.

[0114] "Optical character recognition technology" is a technology for extracting text data from images, and is also known as OCR (Optical Character Recognition).

[0115] "Ingredient information" refers to data such as the name, quantity, purchase date, and expiration date of the ingredients.

[0116] "Inventory information" refers to information such as the quantity and expiration date of ingredients recorded in the database.

[0117] A "generative AI model" refers to an artificial intelligence model that automatically generates menus based on ingredient information. Examples include GPT-3 and similar generative models.

[0118] A "prompt sentence" is a text sentence that is input into a generative AI model and contains specific instructions and conditions.

[0119] "Recipe candidates" refers to multiple dish suggestions generated by the generative AI model.

[0120] "Feedback" refers to the user's evaluation and impressions of the menu provided.

[0121] This invention relates to a system that efficiently manages ingredients in a household and automatically generates daily menus. This system is composed of three main components: a user, a terminal, and a server. The specific functions and processing contents of each component are explained below.

[0122] System configuration

[0123] 1. Users

[0124] Users use the system to manage information about ingredients in their households and receive daily menu suggestions. Users mainly access and operate the system using smartphones or tablet devices.

[0125] 2. Terminal

[0126] A terminal is a device through which a user accesses the system, such as a smartphone or tablet. Applications on the terminal have the following functions:

[0127] Capturing and acquiring receipt images

[0128] After shopping, the user takes a photo of the receipt.

[0129] Implementing Optical Character Recognition (OCR) technology

[0130] Use OCR technology (e.g., Google Vision API) to extract text information from receipt images.

[0131] Analysis and transmission of food ingredient information

[0132] The extracted text data is analyzed to format the ingredient information and sent to the server.

[0133] Display menu suggestions

[0134] The menu sent from the server is displayed to the user.

[0135] Collecting and sending feedback

[0136] Collect user feedback and send it to the server.

[0137] 3. Server

[0138] The server plays a central role in the entire system and has the following functions:

[0139] Food ingredient information database management

[0140] The food ingredient information sent from the terminal is recorded in a database (e.g., MySQL or PostgreSQL) and inventory information is updated.

[0141] Expiration notification settings

[0142] To automatically calculate the expiration date of ingredients and notify a user of ingredients whose expiration date is approaching.

[0143] Menu generation based on generative AI models

[0144] Based on the ingredient information, a menu is automatically generated using a generative AI model (e.g., GPT-3). A prompt is provided as input, and multiple recipe candidates are generated.

[0145] Learning Feedback

[0146] Feedback from users is collected and reflected as learning data for the generative AI model, improving the accuracy of future menu suggestions.

[0147] Specific examples

[0148] 1. After the user finishes shopping at the supermarket, they take a photo of the receipt using an app on their smartphone.

[0149] 2. The device analyzes the image using OCR technology (Google Vision API) and extracts ingredient information such as "tomato, chicken, carrot."

[0150] 3. The device sends the analysis results to the server, which records the received information in a database.

[0151] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[0152] 5. The server uses a generation AI (e.g., GPT-3) based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[0153] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[0154] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[0155] 8. The server collects feedback and uses it as training data to improve the accuracy of the generative AI model.

[0156] Prompt Sentence Examples

[0157] Here is an example of a prompt to input to a generative AI model:

[0158] Available ingredients: Tomato, chicken, carrot

[0159] Preferred type of food: Dinner

[0160] Other criteria: Easy to make, can be prepared in under 30 minutes

[0161] As described above, the present invention is a system that comprehensively automates everything from ingredient management to menu suggestions and learning from user feedback, greatly improving the efficiency of a user's eating habits.

[0162] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0163] Step 1:

[0164] A user comes home from the supermarket, opens the app on their smartphone or tablet, and takes a photo of the receipt.

[0165] Specific action: The user uses the app's camera to focus on the receipt and press the shutter button.

[0166] Input: Receipt image

[0167] Output: Receipt image data is saved to the device.

[0168] Step 2:

[0169] The device retrieves the stored receipt image and uses OCR technology to extract text data from the image.

[0170] Specific operation: The device app sends the captured image to an OCR API (e.g., Google Vision API) and analyzes the text information.

[0171] Input: Receipt image data

[0172] Output: Extracted text data (product name, quantity, date)

[0173] Step 3:

[0174] The device analyzes the text data obtained by OCR and formats the ingredient information.

[0175] Specific operation: The device parses the extracted character data, extracts the necessary items (ingredient name, quantity, purchase date) and generates ingredient information.

[0176] Input: Extracted character data

[0177] Output: Formatted ingredient information

[0178] Step 4:

[0179] The terminal transmits the formatted ingredient information to the server.

[0180] Specific operation: The device uses an HTTP request to send ingredient information to the server.

[0181] Input: Formatted ingredient information

[0182] Output: Ingredient information arrives at the server

[0183] Step 5:

[0184] The server records the received ingredient information in a database and updates inventory information.

[0185] Specific operation: The server inserts ingredient information into a database (e.g., MySQL, PostgreSQL) using SQL statements, matches it with existing data, and updates inventory information.

[0186] Input: Ingredient information

[0187] Output: Updated inventory information is recorded in the database.

[0188] Step 6:

[0189] The user requests, "Please suggest today's menu." This request is sent to the server by the terminal.

[0190] Specific operation: The user presses the menu request button on the app, and the device sends the request to the server.

[0191] Input: User request

[0192] Output: Request data arrives at the server

[0193] Step 7:

[0194] The server retrieves available ingredient information from the database and sends it to the generative AI model as a prompt.

[0195] Specific operation: The server retrieves the latest ingredient information from the database using an SQL query and sends the generated prompt text to the API of the generative AI model (e.g., GPT-3).

[0196] Input: Request data, ingredient information recorded in the database

[0197] Output: The prompt sent to the generative AI model

[0198] Step 8:

[0199] The generative AI model generates multiple recipe candidates based on the prompt sentence and sends them back to the server.

[0200] Specific operation: The generative AI model analyzes the prompt, generates multiple menu recipes based on the available ingredients, and sends them back to the server as an API response.

[0201] Input: prompt statement

[0202] Output: Multiple recipe candidates

[0203] Step 9:

[0204] The server transmits the generated recipe candidates to the user's terminal.

[0205] Specific operation: The server uses the HTTP response to send the generated recipe data to the device.

[0206] Input: Recipe candidate data

[0207] Output: Recipe candidate data arrives on the device

[0208] Step 10:

[0209] The terminal displays the received recipe candidates to the user.

[0210] Specific behavior: The device application displays recipe suggestions in the user interface for the user to review.

[0211] Input: Recipe candidate data

[0212] Output: A list of recipe suggestions that is displayed to the user

[0213] Step 11:

[0214] Users create a menu of their choice and then enter feedback within the app after eating.

[0215] What happens: The user uses the app's feedback function to enter their impressions, such as "It was delicious" or "It was easy to make," and presses the submit button.

[0216] Input: Feedback information

[0217] Output: Feedback data is saved to the device

[0218] Step 12:

[0219] The terminal sends the feedback to the server, which records the feedback in a database.

[0220] Specific operation: The terminal sends feedback data to the server via an HTTP request, and the server inserts and records the received feedback into a database.

[0221] Input: Feedback data

[0222] Output: Feedback is recorded in a database

[0223] Step 13:

[0224] The server trains the generative AI model based on the feedback collected, improving the accuracy of future menu suggestions.

[0225] How it works: The server adds the feedback data to the learning dataset of the AI ​​model and automatically retrains the model. The updated model is reflected in the next menu generation.

[0226] Input: Feedback data

[0227] Output: An improved generative AI model

[0228] (Application example 1)

[0229] 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."

[0230] In modern life, there is a demand for efficient use of food ingredients at home without waste. However, achieving this requires time-consuming inventory checks and planning appropriate menus, which is extremely cumbersome. Furthermore, if necessary ingredients are in short supply, additional effort is required to purchase them. There is a need for a system that simplifies this process while making effective use of ingredients.

[0231] 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.

[0232] In this invention, the server includes a means for generating a menu suitable for the user, a means for automatically ordering any missing ingredients from a food delivery service, and a means for presenting the menu to the user, thereby enabling the user to use ingredients at home without waste and easily replenish the necessary ingredients.

[0233] "Users" are individuals and households who use the system.

[0234] "Means for taking a picture of a receipt" refers to a function that allows a user to take a picture of a receipt after purchasing an item using a device such as a smartphone or tablet.

[0235] Optical character recognition (OCR) is a technology that extracts text data from images.

[0236] The "server" is an online entity that manages ingredient information, generates menus using AI, and accumulates and learns from user feedback.

[0237] "Ingredient information" refers to information such as the name, quantity, and expiration date of the item read from the receipt.

[0238] The "means for updating inventory information" is a function for updating existing inventory information using newly acquired ingredient information.

[0239] "Generative AI" is an artificial intelligence model that generates appropriate menus based on input ingredient information.

[0240] The "means of generating a menu" is a function in which the generation AI suggests dishes based on the input ingredient information.

[0241] The "means for presenting a menu to a user" is a function for displaying the generated dish suggestions on the user's terminal.

[0242] "Means for collecting feedback from users and reflecting it in the learning of the generative AI" refers to a function that collects evaluations of menus provided by users and updates the generative AI model based on that evaluation.

[0243] "Means for ordering from food delivery services" is a function that automatically orders missing ingredients and arranges for delivery.

[0244] MODE FOR CARRYING OUT THE INVENTION

[0245] The following system is conceivable as an embodiment of the present invention.

[0246] System configuration

[0247] This system consists of terminals, a server, and users. The terminals used by users are devices such as smartphones and tablets, and they access the system through these. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[0248] Program processing

[0249] 1. Image recognition of receipts

[0250] After a user brings home their purchases from a supermarket or other store, they use their device to take a photo of the receipt. Using optical character recognition (OCR), the device extracts food information such as product name, quantity, and expiration date from the receipt image as text data. The extracted text data is formatted and sent to the server.

[0251] 2. Recording and managing food data

[0252] The server records the received ingredient information in the database and updates the existing inventory information. Information such as the ingredient name, quantity, purchase date, and expiration date is recorded and reflected in the inventory.

[0253] 3. Menu creation requests and suggestions

[0254] When a user requests "Today's Menu," the device sends this request to the server. The server retrieves available ingredient information from the database and provides it as input to the generation AI. The generation AI generates multiple recipe candidates based on the ingredient information and returns the recipes to the server. The server sends the generated menu to the user's device and displays the suggestions to the user.

[0255] 4. Automatic ordering of missing ingredients

[0256] If the user selects a recipe from the suggested menu and any ingredients are missing, the server automatically orders the missing ingredients from a food delivery service, allowing the user to smoothly prepare all the ingredients needed for that day's menu.

[0257] 5. Feedback and learning

[0258] The user provides feedback on the provided menu. The feedback includes evaluations such as "It was delicious" and "It was easy to make." The device sends the feedback to the server, which records it in a database and uses it as learning data for the generation AI to improve the accuracy of future suggestions.

[0259] Hardware and software used

[0260] Devices: smartphones, tablets

[0261] Server: Cloud computing service

[0262] OCR technology: OCR Processor

[0263] Generation AI: MenuGeneratorAI

[0264] Delivery service API: FoodDeliveryService

[0265] Specific examples

[0266] After a user finishes shopping at the supermarket, they take a photo of the receipt with their device. The device analyzes the image using OCR technology and extracts ingredient information such as "tomatoes, chicken, and carrots." The extracted information is sent to the server and recorded in a database. When the user then requests "Please suggest today's dinner menu," the server uses the generative AI to generate multiple recipes, such as "tomato and chicken stew," based on the available ingredient information. The generated menu is sent to the device, and the user selects one of the suggested recipes. Any missing ingredients are automatically ordered from a food delivery service, ensuring that the ingredients needed for that day's dinner are available. In addition, after dinner, the user provides feedback on the provided menu, allowing the generative AI model to learn for the next suggestion.

[0267] Prompt Sentence Examples

[0268] Available ingredients: Tomato, chicken

[0269] Required recipe: Dinner

[0270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0271] Step 1:

[0272] After a user finishes shopping at a supermarket, they use a device to take a photo of the receipt. The receipt image taken by the user is input into the device. The device then analyzes the receipt image using optical character recognition (OCR) technology and extracts food information such as product name, quantity, and expiration date from the image as text data. The extracted text data is formatted and sent from the device to a server.

[0273] Step 2:

[0274] The server records the text data received from the terminal in a database and updates the existing inventory information. Text data (ingredient information) is provided as input. The server records information such as the ingredient name, quantity, purchase date, and expiration date in the database and updates the inventory information. As a result, the latest inventory status is reflected in the database.

[0275] Step 3:

[0276] The user uses a device to request "Today's Menu." The user's request is input from the device to the server. The server retrieves information about currently available ingredients from the database and provides that information as input to the generation AI. The generation AI receives the prompt and generates an appropriate menu. The generated multiple recipe candidates are output to the server.

[0277] Step 4:

[0278] The server sends the generated menu to the terminal and displays the suggestions to the user. Recipe candidates are input from the server to the terminal. The terminal displays multiple recipes to the user, allowing the user to select a suggested recipe.

[0279] Step 5:

[0280] The user selects a recipe from the suggested menu, and the terminal sends the selection information to the server. The server checks for missing ingredients based on the selected recipe. The selected recipe is provided as input. The server automatically orders the missing ingredients from a food delivery service and outputs the order information. This allows the missing ingredients to be delivered to the user.

[0281] Step 6:

[0282] After dinner, the user enters feedback on the menu provided on their device. The feedback information is then input from the device to the server. The server records this feedback information in a database and uses it as learning data for the generative AI. The server processes the feedback information and outputs it as data that will help improve the model. This improves the accuracy of menu suggestions from the next time onwards.

[0283] 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.

[0284] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a user, a terminal, a server, and an emotion engine, and its main operations are described in detail below.

[0285] System configuration

[0286] This system consists of a terminal used by the user, a server, and an emotion engine. The terminal is a device such as a smartphone or tablet, and provides an operation interface for users to take pictures of receipts, enter feedback, and send emotion data. The server manages ingredient information, generates menus using generative AI, accumulates user feedback, and analyzes learning and emotion data. The emotion engine has the function of recognizing emotions from the user's facial expressions and voice, and analyzing that information.

[0287] Program processing

[0288] 1. Image recognition of receipts

[0289] The user logs into the app and takes a photo of the receipt.

[0290] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image.

[0291] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[0292] 2. Recording and managing food data

[0293] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares it with existing inventory information and updates it.

[0294] The server will automatically calculate the expiration date of ingredients and notify the user when the expiration date is approaching, allowing ingredients to be used effectively without being wasted.

[0295] 3. Menu creation requests and suggestions

[0296] When a user requests "Today's Menu," the terminal sends the request to the server.

[0297] The server retrieves available ingredient information from the database and provides that information to the generation AI.

[0298] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[0299] 4. Emotion Recognition by Emotion Engine

[0300] Before and after the user receives the menu suggestion, the device uses an emotion engine to analyze the user's facial expressions and voice and collect emotional data.

[0301] The device sends emotion data to a server, which then analyzes the data.

[0302] The server adjusts menu suggestions based on the user's emotional data. For example, if it determines that the user is tired, it will prioritize easy-to-prepare meals.

[0303] 5. Feedback and learning

[0304] Users can provide feedback on the provided menus. Users can enter their ratings and comments using the in-app feedback form.

[0305] The device sends the feedback data to the server, which records it in a database. The server also records the user's emotional data obtained through the emotion engine and feeds it back to the generation AI.

[0306] The server updates the generative AI model based on the feedback and emotional data collected, improving the accuracy of the next menu suggestion.

[0307] Specific examples

[0308] 1. After a user finishes shopping at the supermarket, they open the app and take a photo of their receipt. The image is analyzed using OCR technology, and ingredient information such as "tomatoes, chicken, and carrots" is extracted.

[0309] 2. The terminal sends the ingredient information to the server, which records it in a database.

[0310] 3. The user sends a request saying, "Please suggest a menu for today's dinner," and the server sends the data to the generation AI, which generates multiple recipes.

[0311] 4. Before and after suggesting a menu, the device uses an emotion engine to analyze the user's facial expressions and voice, and sends the emotion data to the server.

[0312] 5. The server analyzes the emotional data and, for example, if it determines that the user is tired, it adjusts the menu to suggest easy-to-prepare meals.

[0313] 6. The terminal displays the generated menu to the user, and the user selects "Chicken and Tomato Stew" from the list.

[0314] 7. After dinner, the user sends feedback through the app saying "It was delicious," and the device sends this to the server.

[0315] 8. The server collects feedback and emotion data and updates the generative AI model to improve the accuracy of future menu suggestions.

[0316] As described above, the present invention is a food ingredient management and menu suggestion system that incorporates user emotion recognition, and significantly improves user convenience by making optimal suggestions based on the user's situation and emotions.

[0317] The processing flow will be explained below.

[0318] Step 1:

[0319] The user logs in to the app and takes a photo of the receipt. The user uses the app's camera function to take a photo of the receipt so that the entire receipt is visible.

[0320] Step 2:

[0321] The device captures the image of the receipt, stores the image data captured by the user in memory, and prepares it for the next OCR process.

[0322] Step 3:

[0323] The device uses optical character recognition (OCR) technology to extract text data from images. Specifically, the captured image is input into an OCR engine to identify text data such as product name, quantity, and date.

[0324] Step 4:

[0325] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[0326] Step 5:

[0327] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[0328] Step 6:

[0329] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[0330] Step 7:

[0331] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[0332] Step 8:

[0333] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[0334] Step 9:

[0335] The device sends the user's request to the server, which then sends the request parameters (such as meal timing and preferred genres) to the server via the API.

[0336] Step 10:

[0337] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[0338] Step 11:

[0339] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[0340] Step 12:

[0341] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[0342] Step 13:

[0343] The server sends the generated menu to the user's device. The server also formats the generated recipes, converts them into a format that is easy for the user to view, and sends them to the device.

[0344] Step 14:

[0345] The device displays the generated menu suggestions to the user, and the device displays the received recipe information on the app's UI so that the user can check it.

[0346] Step 15:

[0347] When a user receives a menu suggestion, the emotion engine analyzes the user's facial expressions and voice, and sends the emotion data to the server. The user expresses their feelings about the suggested menu, and the device processes them using the emotion engine.

[0348] Step 16:

[0349] The server analyzes the emotion data and adjusts the menu suggestions based on the emotion data. The server prioritizes easy-to-prepare menu suggestions depending on the user's emotional state (e.g., if they feel tired).

[0350] Step 17:

[0351] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[0352] Step 18:

[0353] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[0354] Step 19:

[0355] The server receives the feedback and reflects it as learning data for the generation AI. The server stores the feedback information in a database and periodically uses it to update the generation AI model, improving the accuracy of future menu suggestions.

[0356] Example 2

[0357] 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."

[0358] Conventional food ingredient management and menu suggestion systems have the problem of not providing sufficient user convenience because they do not make suggestions based on the user's emotions or circumstances. Another issue is that they are unable to effectively manage available ingredients, resulting in food waste.

[0359] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for generating a menu suitable for the user based on the ingredient information using a generation AI, and a means for adjusting the suggested content based on emotion data. This makes it possible to suggest an optimal menu according to the user's emotion and situation. It also promotes the effective use of ingredients and reduces food waste.

[0360] "User" refers to a person who uses the system to manage ingredients and receive menu suggestions.

[0361] "Terminal" refers to a device such as a smartphone or tablet operated by a user.

[0362] A "server" refers to a computer that manages and processes data at the center of a system.

[0363] "Means for taking images" refers to methods for obtaining images using the camera function of a smartphone, etc.

[0364] "Optical character recognition technology" refers to the technology that analyzes character information in an image and converts it into text data.

[0365] "Ingredient information" refers to information such as the name, quantity, purchase date, and expiration date of the food purchased by the user.

[0366] "Database" refers to data storage where ingredient information, feedback data, etc. are recorded and managed.

[0367] "Generative AI" refers to algorithms and functions that use artificial intelligence technology to automatically generate menus suitable for users.

[0368] "Emotion recognition technology" refers to technology that analyzes emotions from a user's facial expressions and voice data.

[0369] "Feedback" refers to the user's ratings and comments on the menu provided.

[0370] "Inventory information" refers to information such as the type, quantity, and expiration date of ingredients owned by the user.

[0371] "Request parameters" refer to the conditions and requests that a user specifies when requesting menu suggestions.

[0372] MODE FOR CARRYING OUT THE INVENTION

[0373] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a terminal used by the user, a server, and an emotion engine, and its operation is described in detail below.

[0374] Hardware and Software

[0375] This system uses the user's smartphone or tablet device, a general-purpose cloud server (e.g., Amazon Web Services or Google Cloud Platform), and an API for emotion recognition (e.g., Microsoft Azure's Emotion API). The program is implemented in Python and JavaScript, and uses Google Cloud Vision API and Amazon Textract for OCR technology. Furthermore, a generative AI model (e.g., OpenAI's GPT-4) is used to generate the menu.

[0376] Program processing

[0377] 1. Image recognition of receipts

[0378] The user launches the app on their smartphone, logs in, and takes a photo of the receipt. A prompt appears saying, "Press the receipt capture button."

[0379] The device captures the receipt image, performs OCR processing using the Google Cloud Vision API, and extracts ingredient information from the receipt.

[0380] The device formats the extracted ingredient information (e.g., tomato, chicken, carrot) and sends it to the server. A prompt saying "Sending ingredient information" is displayed.

[0381] 2. Recording and managing food data

[0382] The server records the received ingredient information in a database (e.g., AWS RDS).

[0383] The server stores information such as ingredient name, quantity, purchase date, expiration date, etc., and compares it with existing inventory information to update it. A prompt saying "Inventory updating" is displayed on the user's terminal.

[0384] The server automatically calculates the expiration date of ingredients, and if the expiration date is approaching, a notification is sent to the user saying, "The expiration date is tomorrow."

[0385] 3. Menu creation requests and suggestions

[0386] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[0387] The terminal sends a request to the server, and the server retrieves available ingredient information from a database.

[0388] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates (detailed cooking instructions, additional ingredients, cooking time, etc.).

[0389] The generation AI will display a list of the generated menus on the screen along with the prompt, "The following menus have been suggested."

[0390] 4. Emotion Recognition by Emotion Engine

[0391] The smartphone's camera and microphone are used to collect facial and voice data just before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[0392] The data collected by the device is sent to Microsoft Azure's Emotion API for emotional analysis.

[0393] The device sends emotional data to the server, which then analyzes it and adjusts the suggestions. For example, if the device determines that the user is tired, it will suggest the following simple meal plan.

[0394] 5. Feedback and learning

[0395] The user tries the provided menu and then enters feedback (ratings and comments) in the app. The app prompts the user to "Enter your rating for the dish."

[0396] The terminal sends the feedback data to the server, which records it in a database.

[0397] The server updates the generative AI model based on the collected feedback and sentiment data to improve the accuracy of the next menu suggestion. A prompt will appear saying, "We've updated the model based on your feedback."

[0398] The present invention makes it possible to propose an optimal menu that matches the user's situation and emotions, thereby significantly improving the effective use of ingredients and convenience of daily life.

[0399] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0400] Step 1: Take a photo of your receipt and send it

[0401] The user launches the app and logs in.

[0402] The user takes a photo of the receipt. The prompt "Press the receipt capture button" appears.

[0403] The device captures the image of the receipt and analyzes it using OCR technology.

[0404] Input: Receipt image

[0405] Output: Text data of ingredients (e.g., tomato, chicken, carrot)

[0406] The device sends the acquired text data to the server. A prompt saying "Sending ingredient information" is displayed.

[0407] Step 2: Record and manage food ingredient data

[0408] The server records the received ingredient information in a database.

[0409] The server stores information such as the ingredient name, quantity, purchase date, and expiration date.

[0410] Input: Text data of ingredients

[0411] Output: Ingredient information recorded in the database

[0412] The server will update the data against existing inventory information and display the prompt "Updating inventory."

[0413] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching. A notification saying "Tomorrow is the expiration date" is sent.

[0414] Step 3: Menu creation request and suggestions

[0415] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[0416] The device sends a request to the server.

[0417] The server obtains available ingredient information from the database.

[0418] Input: Request parameters

[0419] Output: Available ingredients information

[0420] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates.

[0421] The generative AI generates information such as detailed cooking steps, additional ingredients, and cooking time, and returns it to the server.

[0422] Input: Ingredient information

[0423] Output: Multiple recipe candidates

[0424] The server sends the generated recipe information to the terminal, and a prompt saying "The following menu has been suggested" is displayed.

[0425] Step 4: Emotion Recognition with the Emotion Engine

[0426] The smartphone's camera and microphone are used to collect facial and voice data immediately before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[0427] The data collected by the device is sent to an emotion engine, which analyzes emotions.

[0428] Input: facial expression data, voice data

[0429] Output: Emotion data

[0430] The device will send the analyzed emotion data to the server. A prompt will appear saying "Sending emotion data."

[0431] The server analyzes the user's emotional data and adjusts the suggestions accordingly. For example, if it determines that the user is tired, it will prioritize simpler menus.

[0432] Step 5: Gather feedback and learn

[0433] The user tries the provided meal and then provides feedback in the app, prompting them to "rate the dish."

[0434] The terminal transmits the feedback data to the server.

[0435] The server receives the feedback data and records it in a database.

[0436] Input: User feedback

[0437] Output: Updated database

[0438] The server updates the generative AI model based on the feedback and emotion data. A prompt appears saying, "We've updated the model based on your feedback."

[0439] (Application example 2)

[0440] 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."

[0441] Conventional food ingredient management and menu suggestion systems do not take into account the user's emotional state, making it difficult to suggest meals that are in line with the user's actual needs and circumstances. Furthermore, because menus cannot be adjusted based on emotions, it is difficult to improve user satisfaction. For example, if the user is tired or busy, easy-to-prepare meals may not be suggested, which can be a burden on the user's experience.

[0442] 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.

[0443] In this invention, the server is equipped with an emotion engine that recognizes the user's emotions, and includes means for transmitting emotion data to the server, means for the server to analyze the emotion data and adjust menu suggestions based on the user's emotions, and means for preferentially suggesting easy-to-prepare menus based on the emotion recognition data, thereby enabling optimal menu suggestions to be made according to the user's situation.

[0444] "User" refers to a person who uses a terminal to take an image of a receipt, manages ingredient information, and receives menu suggestions.

[0445] "Terminal" refers to a device such as a smartphone or tablet operated by a user, which has the functionality to take images of receipts and recognize emotions.

[0446] "Optical character recognition technology" refers to technology that detects text within an image and converts it into digital text data.

[0447] "Food information" refers to data such as the food name, quantity, purchase date, and expiration date extracted from the receipt.

[0448] "Server" refers to a computer system that manages food ingredient data, analyzes emotional data, and uses generative AI to suggest menus.

[0449] A "database" refers to a collection of data that allows information to be systematically managed and easily accessed.

[0450] "Generative AI" refers to algorithms and models that use generative artificial intelligence technology to generate appropriate menus based on ingredient information and emotional data.

[0451] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions and voice to recognize their emotional state.

[0452] "Emotion data" refers to information indicating the user's emotional state obtained by the emotion engine.

[0453] "Menu suggestion" refers to providing the user with specific recipes and cooking procedures for dishes that are generated based on ingredient information and emotion data.

[0454] "Feedback" refers to the evaluations and comments users make on menu suggestions, which are reflected in the learning of the generation AI.

[0455] A system embodying the present invention allows users to receive ingredient management and menu suggestions using emotion recognition technology. A detailed description of how to implement this system is provided below.

[0456] System Components

[0457] This system consists of the user's device (smartphone or tablet), server, emotion engine, etc. Specifically, it is as follows:

[0458] 1. Terminal

[0459] Using smart glasses or a smartphone, the user takes a picture of the receipt.

[0460] Extract text data from images using optical character recognition technology (Google Cloud Vision API).

[0461] An emotion engine is used to analyze the user's facial expressions and voice to obtain emotion data.

[0462] 2. Server

[0463] Corresponding ingredient information and emotion data are received and recorded and managed in a database (e.g., AWS RDS).

[0464] Using generative AI (OpenAI GPT model), appropriate menus are generated based on ingredient information and emotional data.

[0465] Using unsupervised learning, user feedback data is analyzed and the generative AI model is updated.

[0466] 3. Emotion Engine

[0467] Uses the Azure Emotion API to recognize emotions from the user's facial expressions and voice data.

[0468] The recognized emotion data is sent to the server and used to adjust menu suggestions.

[0469] System operation example

[0470] 1. Image recognition of receipts

[0471] The user takes a photo of the receipt with the smart glasses, and the device uses optical character recognition technology to extract text data from the image. The extracted ingredient information is sent to a server and recorded in a database.

[0472] 2. Emotion recognition

[0473] When a user requests a menu suggestion, the smart glasses analyze the user's facial expressions and voice using an emotion engine and send the resulting emotion data to the server.

[0474] 3. Menu suggestions

[0475] The server provides input to the AI ​​based on ingredient information and emotion data to generate an appropriate menu. The generated menu is then sent to the device and presented to the user.

[0476] 4. Emotion-Based Regulation

[0477] The server analyzes the emotional data and adjusts the menu suggestions, such as prioritizing easy-to-prepare dishes if the user is tired.

[0478] 5. Gather feedback and learn

[0479] When users send feedback on the menu, the data is stored on the server and reflected in the learning of the generation AI.

[0480] Specific examples

[0481] 1. After shopping at the supermarket, the user scans the receipt with the smart glasses. The system automatically extracts food data using OCR and manages the ingredient information.

[0482] 2. When food is nearing its expiration date, notifications are sent via smart glasses.

[0483] 3. When a user requests a menu suggestion, the smart glasses analyze their facial expressions and voice using an emotion engine and send the emotion data to the server.

[0484] 4. The server provides prompts to the generation AI based on ingredient information and emotion data, and generates an appropriate menu.

[0485] 5. The generated menu is displayed to the user, and user feedback is reflected in the next proposal.

[0486] Prompt Sentence Examples

[0487] Suggest an easy meal plan if the user has the following ingredients:

[0488] tomato

[0489] chicken meat

[0490] Carrots

[0491] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[0492] By combining these elements, it becomes possible to propose the most suitable menu according to the user's situation, thereby increasing user satisfaction.

[0493] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0494] Step 1:

[0495] The user takes a photo of the receipt using smart glasses or a smartphone. In this process, the image of the receipt is input and the image data captured by the user is output.

[0496] Step 2:

[0497] The device uses optical character recognition (OCR) technology to extract text data from the image of the receipt. The OCR software takes the image data as input, analyzes it, and outputs ingredient information, often in text form.

[0498] Step 3:

[0499] The device analyzes the extracted text data and formats the ingredient information. In this step, the OCR results (text data) are input, and organized ingredient information such as specific ingredient names, quantities, and purchase dates is output.

[0500] Step 4:

[0501] The terminal sends the analyzed ingredient information to the server. In this process, the organized ingredient information is the input, and the transmission action to the server is the output.

[0502] Step 5:

[0503] The server records the received ingredient information in the database and updates the inventory information. The ingredient information is input and the updated database is output.

[0504] Step 6:

[0505] The user requests a menu. The menu request is input and the request information is output.

[0506] Step 7:

[0507] The device uses an emotion engine to analyze the user's facial expressions and voice to obtain emotion data. New user actions (e.g., requests, questions, grins) are taken as input, and emotion data is output.

[0508] Step 8:

[0509] The emotion data is sent to the server, which then stores it. In this process, the emotion data is the input, and the sending and storing operations to the server are the output.

[0510] Step 9:

[0511] The server combines the ingredient information and emotion data and generates an appropriate menu using the generation AI. At this stage, the ingredient information and emotion data are input, and the generated menu (recipe information) is output. The generation AI uses the following prompt sentence:

[0512] Suggest an easy meal plan if the user has the following ingredients:

[0513] tomato

[0514] chicken meat

[0515] Carrots

[0516] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[0517] Step 10:

[0518] The server sends the generated menu to the terminal. The generated menu is the input, and the sending action to the terminal is the output.

[0519] Step 11:

[0520] The terminal displays the generated menu to the user. The terminal receives the menu (recipe information) received from the server as input and visually displays it to the user.

[0521] Step 12:

[0522] The user submits feedback on the menu. Here, the user's feedback information is input and feedback data is output.

[0523] Step 13:

[0524] The feedback data is received by the server and recorded in a database. The feedback information is the input and the updated database is the output.

[0525] Step 14:

[0526] The server uses the collected feedback and emotion data to train a generative AI model. At this stage, the feedback and emotion data are input, and an updated generative AI model is output.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] [Second embodiment]

[0531] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0532] 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.

[0533] 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).

[0534] 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.

[0535] 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.

[0536] 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).

[0537] 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.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] 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."

[0543] The present invention relates to a system that automatically generates and proposes daily menus based on the ingredients available at home. The specific operation method and processing contents of the system are described below.

[0544] System configuration

[0545] This system consists of users, terminals, and a server. The terminals used by users are devices such as smartphones and tablets, through which they access the system. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[0546] Program processing

[0547] 1. Image recognition of receipts

[0548] When the user returns home from the supermarket, for example, they open the app and take a photo of the receipt.

[0549] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image. OCR technology extracts information such as product name, quantity, and date from the receipt image as text data.

[0550] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[0551] 2. Recording and managing food data

[0552] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares the information with existing ingredient information and updates inventory information.

[0553] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching, allowing the user to make effective use of ingredients without wasting them.

[0554] 3. Menu creation requests and suggestions

[0555] When a user requests "Today's Menu," the terminal sends this request to the server.

[0556] The server retrieves available ingredient information from the database and provides that information as input to the generation AI.

[0557] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[0558] The server sends the generated menu to the user's terminal, which displays the suggestions to the user.

[0559] 4. Feedback and learning

[0560] Users can provide feedback on the provided menus, such as "It was delicious" or "It was easy to make," by entering their ratings through the app.

[0561] The terminal sends the user's feedback to the server, which records the feedback in a database.

[0562] The server collects feedback and reflects it as learning data for the generating AI, improving the accuracy of menu suggestions from the next time onwards.

[0563] Specific examples

[0564] 1. The user finishes shopping at the supermarket and takes a photo of the receipt using the app.

[0565] 2. The device analyzes the image using OCR technology and extracts ingredient information such as "tomato, chicken, carrot."

[0566] 3. The device sends the analysis results to the server, which records the received information in a database.

[0567] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[0568] 5. The server uses a generation AI based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[0569] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[0570] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[0571] 8. The server collects feedback and updates the generative AI model to improve the accuracy of the next menu suggestion.

[0572] As described above, the present invention is a system that automates the entire process from ingredient management to menu proposals, significantly reducing the burden on users. This system allows users to enjoy everyday cooking simply and efficiently.

[0573] The processing flow will be explained below.

[0574] Step 1:

[0575] The user logs in to the app and takes a photo of the receipt. The user uses the camera function in the app to take a photo of the receipt so that the entire receipt is visible.

[0576] Step 2:

[0577] The device captures the image of the receipt. The device stores the image data captured by the user in memory and enables optical character recognition (OCR) technology.

[0578] Step 3:

[0579] The device uses optical character recognition (OCR) technology to extract text data from the image. Specifically, it starts an OCR engine, analyzes the receipt image as input, and identifies text data such as product name, quantity, and date.

[0580] Step 4:

[0581] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[0582] Step 5:

[0583] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[0584] Step 6:

[0585] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[0586] Step 7:

[0587] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[0588] Step 8:

[0589] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[0590] Step 9:

[0591] The device sends the user's request to the server, which then sends the request, including the user's request parameters (such as meal times and preferred genres), to the server via the API.

[0592] Step 10:

[0593] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[0594] Step 11:

[0595] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[0596] Step 12:

[0597] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[0598] Step 13:

[0599] The server sends the generated menu to the user's terminal. The server formats the generated multiple recipe ideas, converts them into a format that is easy for the user to view, and sends them to the terminal.

[0600] Step 14:

[0601] The device displays the generated menu suggestions to the user, and displays the received recipe information on the app's UI so that the user can check it.

[0602] Step 15:

[0603] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[0604] Step 16:

[0605] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[0606] Step 17:

[0607] The server receives the feedback and reflects it as learning data for the generation AI. The server then stores the feedback information in a database and periodically uses it to update the generation AI model, thereby improving the accuracy of future menu suggestions.

[0608] Example 1

[0609] 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."

[0610] In today's busy daily lives, it is important to efficiently manage daily meals and reduce food waste. However, in many households, it is difficult to keep track of the ingredients in the refrigerator, which results in food waste. In addition, planning meals takes time and effort, and many people often find themselves unsure of what to cook. Furthermore, there is a need for automated assistance to make the most of available ingredients and provide healthy, balanced meals.

[0611] 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.

[0612] In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for using a generative AI model to generate a menu suitable for the user based on the ingredient information, and a means for providing the ingredient information as a prompt to the generative AI model to generate recipe candidates. This reduces ingredient waste, enables efficient and effective automatic generation of daily menus, and reduces the burden on the user.

[0613] "User" refers to an individual who uses the system to manage ingredients and receive menu suggestions.

[0614] A "terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[0615] "Server" refers to an online entity that manages ingredient information, generates menus using generative AI models, and accumulates and learns from user feedback.

[0616] "Optical character recognition technology" is a technology for extracting text data from images, and is also known as OCR (Optical Character Recognition).

[0617] "Ingredient information" refers to data such as the name, quantity, purchase date, and expiration date of the ingredients.

[0618] "Inventory information" refers to information such as the quantity and expiration date of ingredients recorded in the database.

[0619] A "generative AI model" refers to an artificial intelligence model that automatically generates menus based on ingredient information. Examples include GPT-3 and similar generative models.

[0620] A "prompt sentence" is a text sentence that is input into a generative AI model and contains specific instructions and conditions.

[0621] "Recipe candidates" refers to multiple dish suggestions generated by the generative AI model.

[0622] "Feedback" refers to the user's evaluation and impressions of the menu provided.

[0623] This invention relates to a system that efficiently manages ingredients in a household and automatically generates daily menus. This system is composed of three main components: a user, a terminal, and a server. The specific functions and processing contents of each component are explained below.

[0624] System configuration

[0625] 1. Users

[0626] Users use the system to manage information about ingredients in their households and receive daily menu suggestions. Users mainly access and operate the system using smartphones or tablet devices.

[0627] 2. Terminal

[0628] A terminal is a device through which a user accesses the system, such as a smartphone or tablet. Applications on the terminal have the following functions:

[0629] Capturing and acquiring receipt images

[0630] After shopping, the user takes a photo of the receipt.

[0631] Implementing Optical Character Recognition (OCR) technology

[0632] Use OCR technology (e.g., Google Vision API) to extract text information from receipt images.

[0633] Analysis and transmission of food ingredient information

[0634] The extracted text data is analyzed to format the ingredient information and sent to the server.

[0635] Display menu suggestions

[0636] The menu sent from the server is displayed to the user.

[0637] Collecting and sending feedback

[0638] Collect user feedback and send it to the server.

[0639] 3. Server

[0640] The server plays a central role in the entire system and has the following functions:

[0641] Food ingredient information database management

[0642] The food ingredient information sent from the terminal is recorded in a database (e.g., MySQL or PostgreSQL) and inventory information is updated.

[0643] Expiration notification settings

[0644] To automatically calculate the expiration date of ingredients and notify a user of ingredients whose expiration date is approaching.

[0645] Menu generation based on generative AI models

[0646] Based on the ingredient information, a menu is automatically generated using a generative AI model (e.g., GPT-3). A prompt is provided as input, and multiple recipe candidates are generated.

[0647] Learning Feedback

[0648] Feedback from users is collected and reflected as learning data for the generative AI model, improving the accuracy of future menu suggestions.

[0649] Specific examples

[0650] 1. After the user finishes shopping at the supermarket, they take a photo of the receipt using an app on their smartphone.

[0651] 2. The device analyzes the image using OCR technology (Google Vision API) and extracts ingredient information such as "tomato, chicken, carrot."

[0652] 3. The device sends the analysis results to the server, which records the received information in a database.

[0653] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[0654] 5. The server uses a generation AI (e.g., GPT-3) based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[0655] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[0656] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[0657] 8. The server collects feedback and uses it as training data to improve the accuracy of the generative AI model.

[0658] Prompt Sentence Examples

[0659] Here is an example of a prompt to input to a generative AI model:

[0660] Available ingredients: Tomato, chicken, carrot

[0661] Preferred type of food: Dinner

[0662] Other criteria: Easy to make, can be prepared in under 30 minutes

[0663] As described above, the present invention is a system that comprehensively automates everything from ingredient management to menu suggestions and learning from user feedback, greatly improving the efficiency of a user's eating habits.

[0664] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0665] Step 1:

[0666] A user comes home from the supermarket, opens the app on their smartphone or tablet, and takes a photo of the receipt.

[0667] Specific action: The user uses the app's camera to focus on the receipt and press the shutter button.

[0668] Input: Receipt image

[0669] Output: Receipt image data is saved to the device.

[0670] Step 2:

[0671] The device retrieves the stored receipt image and uses OCR technology to extract text data from the image.

[0672] Specific operation: The device app sends the captured image to an OCR API (e.g., Google Vision API) and analyzes the text information.

[0673] Input: Receipt image data

[0674] Output: Extracted text data (product name, quantity, date)

[0675] Step 3:

[0676] The device analyzes the text data obtained by OCR and formats the ingredient information.

[0677] Specific operation: The device parses the extracted character data, extracts the necessary items (ingredient name, quantity, purchase date) and generates ingredient information.

[0678] Input: Extracted character data

[0679] Output: Formatted ingredient information

[0680] Step 4:

[0681] The terminal transmits the formatted ingredient information to the server.

[0682] Specific operation: The device uses an HTTP request to send ingredient information to the server.

[0683] Input: Formatted ingredient information

[0684] Output: Ingredient information arrives at the server

[0685] Step 5:

[0686] The server records the received ingredient information in a database and updates inventory information.

[0687] Specific operation: The server inserts ingredient information into a database (e.g., MySQL, PostgreSQL) using SQL statements, matches it with existing data, and updates inventory information.

[0688] Input: Ingredient information

[0689] Output: Updated inventory information is recorded in the database.

[0690] Step 6:

[0691] The user requests, "Please suggest today's menu." This request is sent to the server by the terminal.

[0692] Specific operation: The user presses the menu request button on the app, and the device sends the request to the server.

[0693] Input: User request

[0694] Output: Request data arrives at the server

[0695] Step 7:

[0696] The server retrieves available ingredient information from the database and sends it to the generative AI model as a prompt.

[0697] Specific operation: The server retrieves the latest ingredient information from the database using an SQL query and sends the generated prompt text to the API of the generative AI model (e.g., GPT-3).

[0698] Input: Request data, ingredient information recorded in the database

[0699] Output: The prompt sent to the generative AI model

[0700] Step 8:

[0701] The generative AI model generates multiple recipe candidates based on the prompt sentence and sends them back to the server.

[0702] Specific operation: The generative AI model analyzes the prompt, generates multiple menu recipes based on the available ingredients, and sends them back to the server as an API response.

[0703] Input: prompt statement

[0704] Output: Multiple recipe candidates

[0705] Step 9:

[0706] The server transmits the generated recipe candidates to the user's terminal.

[0707] Specific operation: The server uses the HTTP response to send the generated recipe data to the device.

[0708] Input: Recipe candidate data

[0709] Output: Recipe candidate data arrives on the device

[0710] Step 10:

[0711] The terminal displays the received recipe candidates to the user.

[0712] Specific behavior: The device application displays recipe suggestions in the user interface for the user to review.

[0713] Input: Recipe candidate data

[0714] Output: A list of recipe suggestions that is displayed to the user

[0715] Step 11:

[0716] Users create a menu of their choice and then enter feedback within the app after eating.

[0717] What happens: The user uses the app's feedback function to enter their impressions, such as "It was delicious" or "It was easy to make," and presses the submit button.

[0718] Input: Feedback information

[0719] Output: Feedback data is saved to the device

[0720] Step 12:

[0721] The terminal sends the feedback to the server, which records the feedback in a database.

[0722] Specific operation: The terminal sends feedback data to the server via an HTTP request, and the server inserts and records the received feedback into a database.

[0723] Input: Feedback data

[0724] Output: Feedback is recorded in a database

[0725] Step 13:

[0726] The server trains the generative AI model based on the feedback collected, improving the accuracy of future menu suggestions.

[0727] How it works: The server adds the feedback data to the learning dataset of the AI ​​model and automatically retrains the model. The updated model is reflected in the next menu generation.

[0728] Input: Feedback data

[0729] Output: An improved generative AI model

[0730] (Application example 1)

[0731] 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."

[0732] In modern life, there is a demand for efficient use of food ingredients at home without waste. However, achieving this requires time-consuming inventory checks and planning appropriate menus, which is extremely cumbersome. Furthermore, if necessary ingredients are in short supply, additional effort is required to purchase them. There is a need for a system that simplifies this process while making effective use of ingredients.

[0733] 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.

[0734] In this invention, the server includes a means for generating a menu suitable for the user, a means for automatically ordering any missing ingredients from a food delivery service, and a means for presenting the menu to the user, thereby enabling the user to use ingredients at home without waste and easily replenish the necessary ingredients.

[0735] "Users" are individuals and households who use the system.

[0736] "Means for taking a picture of a receipt" refers to a function that allows a user to take a picture of a receipt after purchasing an item using a device such as a smartphone or tablet.

[0737] Optical character recognition (OCR) is a technology that extracts text data from images.

[0738] The "server" is an online entity that manages ingredient information, generates menus using AI, and accumulates and learns from user feedback.

[0739] "Ingredient information" refers to information such as the name, quantity, and expiration date of the item read from the receipt.

[0740] The "means for updating inventory information" is a function for updating existing inventory information using newly acquired ingredient information.

[0741] "Generative AI" is an artificial intelligence model that generates appropriate menus based on input ingredient information.

[0742] The "means of generating a menu" is a function in which the generation AI suggests dishes based on the input ingredient information.

[0743] The "means for presenting a menu to a user" is a function for displaying the generated dish suggestions on the user's terminal.

[0744] "Means for collecting feedback from users and reflecting it in the learning of the generative AI" refers to a function that collects evaluations of menus provided by users and updates the generative AI model based on that evaluation.

[0745] "Means for ordering from food delivery services" is a function that automatically orders missing ingredients and arranges for delivery.

[0746] MODE FOR CARRYING OUT THE INVENTION

[0747] The following system is conceivable as an embodiment of the present invention.

[0748] System configuration

[0749] This system consists of terminals, a server, and users. The terminals used by users are devices such as smartphones and tablets, and they access the system through these. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[0750] Program processing

[0751] 1. Image recognition of receipts

[0752] After a user brings home their purchases from a supermarket or other store, they use their device to take a photo of the receipt. Using optical character recognition (OCR), the device extracts food information such as product name, quantity, and expiration date from the receipt image as text data. The extracted text data is formatted and sent to the server.

[0753] 2. Recording and managing food data

[0754] The server records the received ingredient information in the database and updates the existing inventory information. Information such as the ingredient name, quantity, purchase date, and expiration date is recorded and reflected in the inventory.

[0755] 3. Menu creation requests and suggestions

[0756] When a user requests "Today's Menu," the device sends this request to the server. The server retrieves available ingredient information from the database and provides it as input to the generation AI. The generation AI generates multiple recipe candidates based on the ingredient information and returns the recipes to the server. The server sends the generated menu to the user's device and displays the suggestions to the user.

[0757] 4. Automatic ordering of missing ingredients

[0758] If the user selects a recipe from the suggested menu and any ingredients are missing, the server automatically orders the missing ingredients from a food delivery service, allowing the user to smoothly prepare all the ingredients needed for that day's menu.

[0759] 5. Feedback and learning

[0760] The user provides feedback on the provided menu. The feedback includes evaluations such as "It was delicious" and "It was easy to make." The device sends the feedback to the server, which records it in a database and uses it as learning data for the generation AI to improve the accuracy of future suggestions.

[0761] Hardware and software used

[0762] Devices: smartphones, tablets

[0763] Server: Cloud computing service

[0764] OCR technology: OCR Processor

[0765] Generation AI: MenuGeneratorAI

[0766] Delivery service API: FoodDeliveryService

[0767] Specific examples

[0768] After a user finishes shopping at the supermarket, they take a photo of the receipt with their device. The device analyzes the image using OCR technology and extracts ingredient information such as "tomatoes, chicken, and carrots." The extracted information is sent to the server and recorded in a database. When the user then requests "Please suggest today's dinner menu," the server uses the generative AI to generate multiple recipes, such as "tomato and chicken stew," based on the available ingredient information. The generated menu is sent to the device, and the user selects one of the suggested recipes. Any missing ingredients are automatically ordered from a food delivery service, ensuring that the ingredients needed for that day's dinner are available. In addition, after dinner, the user provides feedback on the provided menu, allowing the generative AI model to learn for the next suggestion.

[0769] Prompt Sentence Examples

[0770] Available ingredients: Tomato, chicken

[0771] Required recipe: Dinner

[0772] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0773] Step 1:

[0774] After a user finishes shopping at a supermarket, they use a device to take a photo of the receipt. The receipt image taken by the user is input into the device. The device then analyzes the receipt image using optical character recognition (OCR) technology and extracts food information such as product name, quantity, and expiration date from the image as text data. The extracted text data is formatted and sent from the device to a server.

[0775] Step 2:

[0776] The server records the text data received from the terminal in a database and updates the existing inventory information. Text data (ingredient information) is provided as input. The server records information such as the ingredient name, quantity, purchase date, and expiration date in the database and updates the inventory information. As a result, the latest inventory status is reflected in the database.

[0777] Step 3:

[0778] The user uses a device to request "Today's Menu." The user's request is input from the device to the server. The server retrieves information about currently available ingredients from the database and provides that information as input to the generation AI. The generation AI receives the prompt and generates an appropriate menu. The generated multiple recipe candidates are output to the server.

[0779] Step 4:

[0780] The server sends the generated menu to the terminal and displays the suggestions to the user. Recipe candidates are input from the server to the terminal. The terminal displays multiple recipes to the user, allowing the user to select a suggested recipe.

[0781] Step 5:

[0782] The user selects a recipe from the suggested menu, and the terminal sends the selection information to the server. The server checks for missing ingredients based on the selected recipe. The selected recipe is provided as input. The server automatically orders the missing ingredients from a food delivery service and outputs the order information. This allows the missing ingredients to be delivered to the user.

[0783] Step 6:

[0784] After dinner, the user enters feedback on the menu provided on their device. The feedback information is then input from the device to the server. The server records this feedback information in a database and uses it as learning data for the generative AI. The server processes the feedback information and outputs it as data that will help improve the model. This improves the accuracy of menu suggestions from the next time onwards.

[0785] 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.

[0786] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a user, a terminal, a server, and an emotion engine, and its main operations are described in detail below.

[0787] System configuration

[0788] This system consists of a terminal used by the user, a server, and an emotion engine. The terminal is a device such as a smartphone or tablet, and provides an operation interface for users to take pictures of receipts, enter feedback, and send emotion data. The server manages ingredient information, generates menus using generative AI, accumulates user feedback, and analyzes learning and emotion data. The emotion engine has the function of recognizing emotions from the user's facial expressions and voice, and analyzing that information.

[0789] Program processing

[0790] 1. Image recognition of receipts

[0791] The user logs into the app and takes a photo of the receipt.

[0792] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image.

[0793] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[0794] 2. Recording and managing food data

[0795] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares it with existing inventory information and updates it.

[0796] The server will automatically calculate the expiration date of ingredients and notify the user when the expiration date is approaching, allowing ingredients to be used effectively without being wasted.

[0797] 3. Menu creation requests and suggestions

[0798] When a user requests "Today's Menu," the terminal sends the request to the server.

[0799] The server retrieves available ingredient information from the database and provides that information to the generation AI.

[0800] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[0801] 4. Emotion Recognition by Emotion Engine

[0802] Before and after the user receives the menu suggestion, the device uses an emotion engine to analyze the user's facial expressions and voice and collect emotional data.

[0803] The device sends emotion data to a server, which then analyzes the data.

[0804] The server adjusts menu suggestions based on the user's emotional data. For example, if it determines that the user is tired, it will prioritize easy-to-prepare meals.

[0805] 5. Feedback and learning

[0806] Users can provide feedback on the provided menus. Users can enter their ratings and comments using the in-app feedback form.

[0807] The device sends the feedback data to the server, which records it in a database. The server also records the user's emotional data obtained through the emotion engine and feeds it back to the generation AI.

[0808] The server updates the generative AI model based on the feedback and emotional data collected, improving the accuracy of the next menu suggestion.

[0809] Specific examples

[0810] 1. After a user finishes shopping at the supermarket, they open the app and take a photo of their receipt. The image is analyzed using OCR technology, and ingredient information such as "tomatoes, chicken, and carrots" is extracted.

[0811] 2. The terminal sends the ingredient information to the server, which records it in a database.

[0812] 3. The user sends a request saying, "Please suggest a menu for today's dinner," and the server sends the data to the generation AI, which generates multiple recipes.

[0813] 4. Before and after suggesting a menu, the device uses an emotion engine to analyze the user's facial expressions and voice, and sends the emotion data to the server.

[0814] 5. The server analyzes the emotional data and, for example, if it determines that the user is tired, it adjusts the menu to suggest easy-to-prepare meals.

[0815] 6. The terminal displays the generated menu to the user, and the user selects "Chicken and Tomato Stew" from the list.

[0816] 7. After dinner, the user sends feedback through the app saying "It was delicious," and the device sends this to the server.

[0817] 8. The server collects feedback and emotion data and updates the generative AI model to improve the accuracy of future menu suggestions.

[0818] As described above, the present invention is a food ingredient management and menu suggestion system that incorporates user emotion recognition, and significantly improves user convenience by making optimal suggestions based on the user's situation and emotions.

[0819] The processing flow will be explained below.

[0820] Step 1:

[0821] The user logs in to the app and takes a photo of the receipt. The user uses the app's camera function to take a photo of the receipt so that the entire receipt is visible.

[0822] Step 2:

[0823] The device captures the image of the receipt, stores the image data captured by the user in memory, and prepares it for the next OCR process.

[0824] Step 3:

[0825] The device uses optical character recognition (OCR) technology to extract text data from images. Specifically, the captured image is input into an OCR engine to identify text data such as product name, quantity, and date.

[0826] Step 4:

[0827] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[0828] Step 5:

[0829] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[0830] Step 6:

[0831] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[0832] Step 7:

[0833] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[0834] Step 8:

[0835] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[0836] Step 9:

[0837] The device sends the user's request to the server, which then sends the request parameters (such as meal timing and preferred genres) to the server via the API.

[0838] Step 10:

[0839] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[0840] Step 11:

[0841] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[0842] Step 12:

[0843] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[0844] Step 13:

[0845] The server sends the generated menu to the user's device. The server also formats the generated recipes, converts them into a format that is easy for the user to view, and sends them to the device.

[0846] Step 14:

[0847] The device displays the generated menu suggestions to the user, and the device displays the received recipe information on the app's UI so that the user can check it.

[0848] Step 15:

[0849] When a user receives a menu suggestion, the emotion engine analyzes the user's facial expressions and voice, and sends the emotion data to the server. The user expresses their feelings about the suggested menu, and the device processes them using the emotion engine.

[0850] Step 16:

[0851] The server analyzes the emotion data and adjusts the menu suggestions based on the emotion data. The server prioritizes easy-to-prepare menu suggestions depending on the user's emotional state (e.g., if they feel tired).

[0852] Step 17:

[0853] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[0854] Step 18:

[0855] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[0856] Step 19:

[0857] The server receives the feedback and reflects it as learning data for the generation AI. The server stores the feedback information in a database and periodically uses it to update the generation AI model, improving the accuracy of future menu suggestions.

[0858] Example 2

[0859] 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."

[0860] Conventional food ingredient management and menu suggestion systems have the problem of not providing sufficient user convenience because they do not make suggestions based on the user's emotions or circumstances. Another issue is that they are unable to effectively manage available ingredients, resulting in food waste.

[0861] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for generating a menu suitable for the user based on the ingredient information using a generation AI, and a means for adjusting the suggested content based on emotion data. This makes it possible to suggest an optimal menu according to the user's emotion and situation. It also promotes the effective use of ingredients and reduces food waste.

[0862] "User" refers to a person who uses the system to manage ingredients and receive menu suggestions.

[0863] "Terminal" refers to a device such as a smartphone or tablet operated by a user.

[0864] A "server" refers to a computer that manages and processes data at the center of a system.

[0865] "Means for taking images" refers to methods for obtaining images using the camera function of a smartphone, etc.

[0866] "Optical character recognition technology" refers to the technology that analyzes character information in an image and converts it into text data.

[0867] "Ingredient information" refers to information such as the name, quantity, purchase date, and expiration date of the food purchased by the user.

[0868] "Database" refers to data storage where ingredient information, feedback data, etc. are recorded and managed.

[0869] "Generative AI" refers to algorithms and functions that use artificial intelligence technology to automatically generate menus suitable for users.

[0870] "Emotion recognition technology" refers to technology that analyzes emotions from a user's facial expressions and voice data.

[0871] "Feedback" refers to the user's ratings and comments on the menu provided.

[0872] "Inventory information" refers to information such as the type, quantity, and expiration date of ingredients owned by the user.

[0873] "Request parameters" refer to the conditions and requests that a user specifies when requesting menu suggestions.

[0874] MODE FOR CARRYING OUT THE INVENTION

[0875] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a terminal used by the user, a server, and an emotion engine, and its operation is described in detail below.

[0876] Hardware and Software

[0877] This system uses the user's smartphone or tablet device, a general-purpose cloud server (e.g., Amazon Web Services or Google Cloud Platform), and an API for emotion recognition (e.g., Microsoft Azure's Emotion API). The program is implemented in Python and JavaScript, and uses Google Cloud Vision API and Amazon Textract for OCR technology. Furthermore, a generative AI model (e.g., OpenAI's GPT-4) is used to generate the menu.

[0878] Program processing

[0879] 1. Image recognition of receipts

[0880] The user launches the app on their smartphone, logs in, and takes a photo of the receipt. A prompt appears saying, "Press the receipt capture button."

[0881] The device captures the receipt image, performs OCR processing using the Google Cloud Vision API, and extracts ingredient information from the receipt.

[0882] The device formats the extracted ingredient information (e.g., tomato, chicken, carrot) and sends it to the server. A prompt saying "Sending ingredient information" is displayed.

[0883] 2. Recording and managing food data

[0884] The server records the received ingredient information in a database (e.g., AWS RDS).

[0885] The server stores information such as ingredient name, quantity, purchase date, expiration date, etc., and compares it with existing inventory information to update it. A prompt saying "Inventory updating" is displayed on the user's terminal.

[0886] The server automatically calculates the expiration date of ingredients, and if the expiration date is approaching, a notification is sent to the user saying, "The expiration date is tomorrow."

[0887] 3. Menu creation requests and suggestions

[0888] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[0889] The terminal sends a request to the server, and the server retrieves available ingredient information from a database.

[0890] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates (detailed cooking instructions, additional ingredients, cooking time, etc.).

[0891] The generation AI will display a list of the generated menus on the screen along with the prompt, "The following menus have been suggested."

[0892] 4. Emotion Recognition by Emotion Engine

[0893] The smartphone's camera and microphone are used to collect facial and voice data just before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[0894] The data collected by the device is sent to Microsoft Azure's Emotion API for emotional analysis.

[0895] The device sends emotional data to the server, which then analyzes it and adjusts the suggestions. For example, if the device determines that the user is tired, it will suggest the following simple meal plan.

[0896] 5. Feedback and learning

[0897] The user tries the provided menu and then enters feedback (ratings and comments) in the app. The app prompts the user to "Enter your rating for the dish."

[0898] The terminal sends the feedback data to the server, which records it in a database.

[0899] The server updates the generative AI model based on the collected feedback and sentiment data to improve the accuracy of the next menu suggestion. A prompt will appear saying, "We've updated the model based on your feedback."

[0900] The present invention makes it possible to propose an optimal menu that matches the user's situation and emotions, thereby significantly improving the effective use of ingredients and convenience of daily life.

[0901] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0902] Step 1: Take a photo of your receipt and send it

[0903] The user launches the app and logs in.

[0904] The user takes a photo of the receipt. The prompt "Press the receipt capture button" appears.

[0905] The device captures the image of the receipt and analyzes it using OCR technology.

[0906] Input: Receipt image

[0907] Output: Text data of ingredients (e.g., tomato, chicken, carrot)

[0908] The device sends the acquired text data to the server. A prompt saying "Sending ingredient information" is displayed.

[0909] Step 2: Record and manage food ingredient data

[0910] The server records the received ingredient information in a database.

[0911] The server stores information such as the ingredient name, quantity, purchase date, and expiration date.

[0912] Input: Text data of ingredients

[0913] Output: Ingredient information recorded in the database

[0914] The server will update the data against existing inventory information and display the prompt "Updating inventory."

[0915] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching. A notification saying "Tomorrow is the expiration date" is sent.

[0916] Step 3: Menu creation request and suggestions

[0917] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[0918] The device sends a request to the server.

[0919] The server obtains available ingredient information from the database.

[0920] Input: Request parameters

[0921] Output: Available ingredients information

[0922] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates.

[0923] The generative AI generates information such as detailed cooking steps, additional ingredients, and cooking time, and returns it to the server.

[0924] Input: Ingredient information

[0925] Output: Multiple recipe candidates

[0926] The server sends the generated recipe information to the terminal, and a prompt saying "The following menu has been suggested" is displayed.

[0927] Step 4: Emotion Recognition with the Emotion Engine

[0928] The smartphone's camera and microphone are used to collect facial and voice data immediately before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[0929] The data collected by the device is sent to an emotion engine, which analyzes emotions.

[0930] Input: facial expression data, voice data

[0931] Output: Emotion data

[0932] The device will send the analyzed emotion data to the server. A prompt will appear saying "Sending emotion data."

[0933] The server analyzes the user's emotional data and adjusts the suggestions accordingly. For example, if it determines that the user is tired, it will prioritize simpler menus.

[0934] Step 5: Gather feedback and learn

[0935] The user tries the provided meal and then provides feedback in the app, prompting them to "rate the dish."

[0936] The terminal transmits the feedback data to the server.

[0937] The server receives the feedback data and records it in a database.

[0938] Input: User feedback

[0939] Output: Updated database

[0940] The server updates the generative AI model based on the feedback and emotion data. A prompt appears saying, "We've updated the model based on your feedback."

[0941] (Application example 2)

[0942] 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."

[0943] Conventional food ingredient management and menu suggestion systems do not take into account the user's emotional state, making it difficult to suggest meals that are in line with the user's actual needs and circumstances. Furthermore, because menus cannot be adjusted based on emotions, it is difficult to improve user satisfaction. For example, if the user is tired or busy, easy-to-prepare meals may not be suggested, which can be a burden on the user's experience.

[0944] 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.

[0945] In this invention, the server is equipped with an emotion engine that recognizes the user's emotions, and includes means for transmitting emotion data to the server, means for the server to analyze the emotion data and adjust menu suggestions based on the user's emotions, and means for preferentially suggesting easy-to-prepare menus based on the emotion recognition data, thereby enabling optimal menu suggestions to be made according to the user's situation.

[0946] "User" refers to a person who uses a terminal to take an image of a receipt, manages ingredient information, and receives menu suggestions.

[0947] "Terminal" refers to a device such as a smartphone or tablet operated by a user, which has the functionality to take images of receipts and recognize emotions.

[0948] "Optical character recognition technology" refers to technology that detects text within an image and converts it into digital text data.

[0949] "Food information" refers to data such as the food name, quantity, purchase date, and expiration date extracted from the receipt.

[0950] "Server" refers to a computer system that manages food ingredient data, analyzes emotional data, and uses generative AI to suggest menus.

[0951] A "database" refers to a collection of data that allows information to be systematically managed and easily accessed.

[0952] "Generative AI" refers to algorithms and models that use generative artificial intelligence technology to generate appropriate menus based on ingredient information and emotional data.

[0953] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions and voice to recognize their emotional state.

[0954] "Emotion data" refers to information indicating the user's emotional state obtained by the emotion engine.

[0955] "Menu suggestion" refers to providing the user with specific recipes and cooking procedures for dishes that are generated based on ingredient information and emotion data.

[0956] "Feedback" refers to the evaluations and comments users make on menu suggestions, which are reflected in the learning of the generation AI.

[0957] A system embodying the present invention allows users to receive ingredient management and menu suggestions using emotion recognition technology. A detailed description of how to implement this system is provided below.

[0958] System Components

[0959] This system consists of the user's device (smartphone or tablet), server, emotion engine, etc. Specifically, it is as follows:

[0960] 1. Terminal

[0961] Using smart glasses or a smartphone, the user takes a picture of the receipt.

[0962] Extract text data from images using optical character recognition technology (Google Cloud Vision API).

[0963] An emotion engine is used to analyze the user's facial expressions and voice to obtain emotion data.

[0964] 2. Server

[0965] Corresponding ingredient information and emotion data are received and recorded and managed in a database (e.g., AWS RDS).

[0966] Using generative AI (OpenAI GPT model), appropriate menus are generated based on ingredient information and emotional data.

[0967] Using unsupervised learning, user feedback data is analyzed and the generative AI model is updated.

[0968] 3. Emotion Engine

[0969] Uses the Azure Emotion API to recognize emotions from the user's facial expressions and voice data.

[0970] The recognized emotion data is sent to the server and used to adjust menu suggestions.

[0971] System operation example

[0972] 1. Image recognition of receipts

[0973] The user takes a photo of the receipt with the smart glasses, and the device uses optical character recognition technology to extract text data from the image. The extracted ingredient information is sent to a server and recorded in a database.

[0974] 2. Emotion recognition

[0975] When a user requests a menu suggestion, the smart glasses analyze the user's facial expressions and voice using an emotion engine and send the resulting emotion data to the server.

[0976] 3. Menu suggestions

[0977] The server provides input to the AI ​​based on ingredient information and emotion data to generate an appropriate menu. The generated menu is then sent to the device and presented to the user.

[0978] 4. Emotion-Based Regulation

[0979] The server analyzes the emotional data and adjusts the menu suggestions, such as prioritizing easy-to-prepare dishes if the user is tired.

[0980] 5. Gather feedback and learn

[0981] When users send feedback on the menu, the data is stored on the server and reflected in the learning of the generation AI.

[0982] Specific examples

[0983] 1. After shopping at the supermarket, the user scans the receipt with the smart glasses. The system automatically extracts food data using OCR and manages the ingredient information.

[0984] 2. When food is nearing its expiration date, notifications are sent via smart glasses.

[0985] 3. When a user requests a menu suggestion, the smart glasses analyze their facial expressions and voice using an emotion engine and send the emotion data to the server.

[0986] 4. The server provides prompts to the generation AI based on ingredient information and emotion data, and generates an appropriate menu.

[0987] 5. The generated menu is displayed to the user, and user feedback is reflected in the next proposal.

[0988] Prompt Sentence Examples

[0989] Suggest an easy meal plan if the user has the following ingredients:

[0990] tomato

[0991] chicken meat

[0992] Carrots

[0993] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[0994] By combining these elements, it becomes possible to propose the most suitable menu according to the user's situation, thereby increasing user satisfaction.

[0995] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0996] Step 1:

[0997] The user takes a photo of the receipt using smart glasses or a smartphone. In this process, the image of the receipt is input and the image data captured by the user is output.

[0998] Step 2:

[0999] The device uses optical character recognition (OCR) technology to extract text data from the image of the receipt. The OCR software takes the image data as input, analyzes it, and outputs ingredient information, often in text form.

[1000] Step 3:

[1001] The device analyzes the extracted text data and formats the ingredient information. In this step, the OCR results (text data) are input, and organized ingredient information such as specific ingredient names, quantities, and purchase dates is output.

[1002] Step 4:

[1003] The terminal sends the analyzed ingredient information to the server. In this process, the organized ingredient information is the input, and the transmission action to the server is the output.

[1004] Step 5:

[1005] The server records the received ingredient information in the database and updates the inventory information. The ingredient information is input and the updated database is output.

[1006] Step 6:

[1007] The user requests a menu. The menu request is input and the request information is output.

[1008] Step 7:

[1009] The device uses an emotion engine to analyze the user's facial expressions and voice to obtain emotion data. New user actions (e.g., requests, questions, grins) are taken as input, and emotion data is output.

[1010] Step 8:

[1011] The emotion data is sent to the server, which then stores it. In this process, the emotion data is the input, and the sending and storing operations to the server are the output.

[1012] Step 9:

[1013] The server combines the ingredient information and emotion data and generates an appropriate menu using the generation AI. At this stage, the ingredient information and emotion data are input, and the generated menu (recipe information) is output. The generation AI uses the following prompt sentence:

[1014] Suggest an easy meal plan if the user has the following ingredients:

[1015] tomato

[1016] chicken meat

[1017] Carrots

[1018] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[1019] Step 10:

[1020] The server sends the generated menu to the terminal. The generated menu is the input, and the sending action to the terminal is the output.

[1021] Step 11:

[1022] The terminal displays the generated menu to the user. The terminal receives the menu (recipe information) received from the server as input and visually displays it to the user.

[1023] Step 12:

[1024] The user submits feedback on the menu. Here, the user's feedback information is input and feedback data is output.

[1025] Step 13:

[1026] The feedback data is received by the server and recorded in a database. The feedback information is the input and the updated database is the output.

[1027] Step 14:

[1028] The server uses the collected feedback and emotion data to train a generative AI model. At this stage, the feedback and emotion data are input, and an updated generative AI model is output.

[1029] 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.

[1030] 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.

[1031] 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.

[1032] [Third embodiment]

[1033] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1034] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1035] 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).

[1036] 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.

[1037] 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.

[1038] 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).

[1039] 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.

[1040] 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.

[1041] 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.

[1042] 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.

[1043] 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.

[1044] 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."

[1045] The present invention relates to a system that automatically generates and proposes daily menus based on the ingredients available at home. The specific operation method and processing contents of the system are described below.

[1046] System configuration

[1047] This system consists of users, terminals, and a server. The terminals used by users are devices such as smartphones and tablets, through which they access the system. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[1048] Program processing

[1049] 1. Image recognition of receipts

[1050] When the user returns home from the supermarket, for example, they open the app and take a photo of the receipt.

[1051] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image. OCR technology extracts information such as product name, quantity, and date from the receipt image as text data.

[1052] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[1053] 2. Recording and managing food data

[1054] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares the information with existing ingredient information and updates inventory information.

[1055] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching, allowing the user to make effective use of ingredients without wasting them.

[1056] 3. Menu creation requests and suggestions

[1057] When a user requests "Today's Menu," the terminal sends this request to the server.

[1058] The server retrieves available ingredient information from the database and provides that information as input to the generation AI.

[1059] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[1060] The server sends the generated menu to the user's terminal, which displays the suggestions to the user.

[1061] 4. Feedback and learning

[1062] Users can provide feedback on the provided menus, such as "It was delicious" or "It was easy to make," by entering their ratings through the app.

[1063] The terminal sends the user's feedback to the server, which records the feedback in a database.

[1064] The server collects feedback and reflects it as learning data for the generating AI, improving the accuracy of menu suggestions from the next time onwards.

[1065] Specific examples

[1066] 1. The user finishes shopping at the supermarket and takes a photo of the receipt using the app.

[1067] 2. The device analyzes the image using OCR technology and extracts ingredient information such as "tomato, chicken, carrot."

[1068] 3. The device sends the analysis results to the server, which records the received information in a database.

[1069] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[1070] 5. The server uses a generation AI based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[1071] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[1072] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[1073] 8. The server collects feedback and updates the generative AI model to improve the accuracy of the next menu suggestion.

[1074] As described above, the present invention is a system that automates the entire process from ingredient management to menu proposals, significantly reducing the burden on users. This system allows users to enjoy everyday cooking simply and efficiently.

[1075] The processing flow will be explained below.

[1076] Step 1:

[1077] The user logs in to the app and takes a photo of the receipt. The user uses the camera function in the app to take a photo of the receipt so that the entire receipt is visible.

[1078] Step 2:

[1079] The device captures the image of the receipt. The device stores the image data captured by the user in memory and enables optical character recognition (OCR) technology.

[1080] Step 3:

[1081] The device uses optical character recognition (OCR) technology to extract text data from the image. Specifically, it starts an OCR engine, analyzes the receipt image as input, and identifies text data such as product name, quantity, and date.

[1082] Step 4:

[1083] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[1084] Step 5:

[1085] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[1086] Step 6:

[1087] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[1088] Step 7:

[1089] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[1090] Step 8:

[1091] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[1092] Step 9:

[1093] The device sends the user's request to the server, which then sends the request, including the user's request parameters (such as meal times and preferred genres), to the server via the API.

[1094] Step 10:

[1095] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[1096] Step 11:

[1097] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[1098] Step 12:

[1099] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[1100] Step 13:

[1101] The server sends the generated menu to the user's terminal. The server formats the generated multiple recipe ideas, converts them into a format that is easy for the user to view, and sends them to the terminal.

[1102] Step 14:

[1103] The device displays the generated menu suggestions to the user, and displays the received recipe information on the app's UI so that the user can check it.

[1104] Step 15:

[1105] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[1106] Step 16:

[1107] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[1108] Step 17:

[1109] The server receives the feedback and reflects it as learning data for the generation AI. The server then stores the feedback information in a database and periodically uses it to update the generation AI model, thereby improving the accuracy of future menu suggestions.

[1110] Example 1

[1111] 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."

[1112] In today's busy daily lives, it is important to efficiently manage daily meals and reduce food waste. However, in many households, it is difficult to keep track of the ingredients in the refrigerator, which results in food waste. In addition, planning meals takes time and effort, and many people often find themselves unsure of what to cook. Furthermore, there is a need for automated assistance to make the most of available ingredients and provide healthy, balanced meals.

[1113] 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.

[1114] In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for using a generative AI model to generate a menu suitable for the user based on the ingredient information, and a means for providing the ingredient information as a prompt to the generative AI model to generate recipe candidates. This reduces ingredient waste, enables efficient and effective automatic generation of daily menus, and reduces the burden on the user.

[1115] "User" refers to an individual who uses the system to manage ingredients and receive menu suggestions.

[1116] A "terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[1117] "Server" refers to an online entity that manages ingredient information, generates menus using generative AI models, and accumulates and learns from user feedback.

[1118] "Optical character recognition technology" is a technology for extracting text data from images, and is also known as OCR (Optical Character Recognition).

[1119] "Ingredient information" refers to data such as the name, quantity, purchase date, and expiration date of the ingredients.

[1120] "Inventory information" refers to information such as the quantity and expiration date of ingredients recorded in the database.

[1121] A "generative AI model" refers to an artificial intelligence model that automatically generates menus based on ingredient information. Examples include GPT-3 and similar generative models.

[1122] A "prompt sentence" is a text sentence that is input into a generative AI model and contains specific instructions and conditions.

[1123] "Recipe candidates" refers to multiple dish suggestions generated by the generative AI model.

[1124] "Feedback" refers to the user's evaluation and impressions of the menu provided.

[1125] This invention relates to a system that efficiently manages ingredients in a household and automatically generates daily menus. This system is composed of three main components: a user, a terminal, and a server. The specific functions and processing contents of each component are explained below.

[1126] System configuration

[1127] 1. Users

[1128] Users use the system to manage information about ingredients in their households and receive daily menu suggestions. Users mainly access and operate the system using smartphones or tablet devices.

[1129] 2. Terminal

[1130] A terminal is a device through which a user accesses the system, such as a smartphone or tablet. Applications on the terminal have the following functions:

[1131] Capturing and acquiring receipt images

[1132] After shopping, the user takes a photo of the receipt.

[1133] Implementing Optical Character Recognition (OCR) technology

[1134] Use OCR technology (e.g., Google Vision API) to extract text information from receipt images.

[1135] Analysis and transmission of food ingredient information

[1136] The extracted text data is analyzed to format the ingredient information and sent to the server.

[1137] Display menu suggestions

[1138] The menu sent from the server is displayed to the user.

[1139] Collecting and sending feedback

[1140] Collect user feedback and send it to the server.

[1141] 3. Server

[1142] The server plays a central role in the entire system and has the following functions:

[1143] Food ingredient information database management

[1144] The food ingredient information sent from the terminal is recorded in a database (e.g., MySQL or PostgreSQL) and inventory information is updated.

[1145] Expiration notification settings

[1146] To automatically calculate the expiration date of ingredients and notify a user of ingredients whose expiration date is approaching.

[1147] Menu generation based on generative AI models

[1148] Based on the ingredient information, a menu is automatically generated using a generative AI model (e.g., GPT-3). A prompt is provided as input, and multiple recipe candidates are generated.

[1149] Learning Feedback

[1150] Feedback from users is collected and reflected as learning data for the generative AI model, improving the accuracy of future menu suggestions.

[1151] Specific examples

[1152] 1. After the user finishes shopping at the supermarket, they take a photo of the receipt using an app on their smartphone.

[1153] 2. The device analyzes the image using OCR technology (Google Vision API) and extracts ingredient information such as "tomato, chicken, carrot."

[1154] 3. The device sends the analysis results to the server, which records the received information in a database.

[1155] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[1156] 5. The server uses a generation AI (e.g., GPT-3) based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[1157] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[1158] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[1159] 8. The server collects feedback and uses it as training data to improve the accuracy of the generative AI model.

[1160] Prompt Sentence Examples

[1161] Here is an example of a prompt to input to a generative AI model:

[1162] Available ingredients: Tomato, chicken, carrot

[1163] Preferred type of food: Dinner

[1164] Other criteria: Easy to make, can be prepared in under 30 minutes

[1165] As described above, the present invention is a system that comprehensively automates everything from ingredient management to menu suggestions and learning from user feedback, greatly improving the efficiency of a user's eating habits.

[1166] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1167] Step 1:

[1168] A user comes home from the supermarket, opens the app on their smartphone or tablet, and takes a photo of the receipt.

[1169] Specific action: The user uses the app's camera to focus on the receipt and press the shutter button.

[1170] Input: Receipt image

[1171] Output: Receipt image data is saved to the device.

[1172] Step 2:

[1173] The device retrieves the stored receipt image and uses OCR technology to extract text data from the image.

[1174] Specific operation: The device app sends the captured image to an OCR API (e.g., Google Vision API) and analyzes the text information.

[1175] Input: Receipt image data

[1176] Output: Extracted text data (product name, quantity, date)

[1177] Step 3:

[1178] The device analyzes the text data obtained by OCR and formats the ingredient information.

[1179] Specific operation: The device parses the extracted character data, extracts the necessary items (ingredient name, quantity, purchase date) and generates ingredient information.

[1180] Input: Extracted character data

[1181] Output: Formatted ingredient information

[1182] Step 4:

[1183] The terminal transmits the formatted ingredient information to the server.

[1184] Specific operation: The device uses an HTTP request to send ingredient information to the server.

[1185] Input: Formatted ingredient information

[1186] Output: Ingredient information arrives at the server

[1187] Step 5:

[1188] The server records the received ingredient information in a database and updates inventory information.

[1189] Specific operation: The server inserts ingredient information into a database (e.g., MySQL, PostgreSQL) using SQL statements, matches it with existing data, and updates inventory information.

[1190] Input: Ingredient information

[1191] Output: Updated inventory information is recorded in the database.

[1192] Step 6:

[1193] The user requests, "Please suggest today's menu." This request is sent to the server by the terminal.

[1194] Specific operation: The user presses the menu request button on the app, and the device sends the request to the server.

[1195] Input: User request

[1196] Output: Request data arrives at the server

[1197] Step 7:

[1198] The server retrieves available ingredient information from the database and sends it to the generative AI model as a prompt.

[1199] Specific operation: The server retrieves the latest ingredient information from the database using an SQL query and sends the generated prompt text to the API of the generative AI model (e.g., GPT-3).

[1200] Input: Request data, ingredient information recorded in the database

[1201] Output: The prompt sent to the generative AI model

[1202] Step 8:

[1203] The generative AI model generates multiple recipe candidates based on the prompt sentence and sends them back to the server.

[1204] Specific operation: The generative AI model analyzes the prompt, generates multiple menu recipes based on the available ingredients, and sends them back to the server as an API response.

[1205] Input: prompt statement

[1206] Output: Multiple recipe candidates

[1207] Step 9:

[1208] The server transmits the generated recipe candidates to the user's terminal.

[1209] Specific operation: The server uses the HTTP response to send the generated recipe data to the device.

[1210] Input: Recipe candidate data

[1211] Output: Recipe candidate data arrives on the device

[1212] Step 10:

[1213] The terminal displays the received recipe candidates to the user.

[1214] Specific behavior: The device application displays recipe suggestions in the user interface for the user to review.

[1215] Input: Recipe candidate data

[1216] Output: A list of recipe suggestions that is displayed to the user

[1217] Step 11:

[1218] Users create a menu of their choice and then enter feedback within the app after eating.

[1219] What happens: The user uses the app's feedback function to enter their impressions, such as "It was delicious" or "It was easy to make," and presses the submit button.

[1220] Input: Feedback information

[1221] Output: Feedback data is saved to the device

[1222] Step 12:

[1223] The terminal sends the feedback to the server, which records the feedback in a database.

[1224] Specific operation: The terminal sends feedback data to the server via an HTTP request, and the server inserts and records the received feedback into a database.

[1225] Input: Feedback data

[1226] Output: Feedback is recorded in a database

[1227] Step 13:

[1228] The server trains the generative AI model based on the feedback collected, improving the accuracy of future menu suggestions.

[1229] How it works: The server adds the feedback data to the learning dataset of the AI ​​model and automatically retrains the model. The updated model is reflected in the next menu generation.

[1230] Input: Feedback data

[1231] Output: An improved generative AI model

[1232] (Application example 1)

[1233] 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."

[1234] In modern life, there is a demand for efficient use of food ingredients at home without waste. However, achieving this requires time-consuming inventory checks and planning appropriate menus, which is extremely cumbersome. Furthermore, if necessary ingredients are in short supply, additional effort is required to purchase them. There is a need for a system that simplifies this process while making effective use of ingredients.

[1235] 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.

[1236] In this invention, the server includes a means for generating a menu suitable for the user, a means for automatically ordering any missing ingredients from a food delivery service, and a means for presenting the menu to the user, thereby enabling the user to use ingredients at home without waste and easily replenish the necessary ingredients.

[1237] "Users" are individuals and households who use the system.

[1238] "Means for taking a picture of a receipt" refers to a function that allows a user to take a picture of a receipt after purchasing an item using a device such as a smartphone or tablet.

[1239] Optical character recognition (OCR) is a technology that extracts text data from images.

[1240] The "server" is an online entity that manages ingredient information, generates menus using AI, and accumulates and learns from user feedback.

[1241] "Ingredient information" refers to information such as the name, quantity, and expiration date of the item read from the receipt.

[1242] The "means for updating inventory information" is a function for updating existing inventory information using newly acquired ingredient information.

[1243] "Generative AI" is an artificial intelligence model that generates appropriate menus based on input ingredient information.

[1244] The "means of generating a menu" is a function in which the generation AI suggests dishes based on the input ingredient information.

[1245] The "means for presenting a menu to a user" is a function for displaying the generated dish suggestions on the user's terminal.

[1246] "Means for collecting feedback from users and reflecting it in the learning of the generative AI" refers to a function that collects evaluations of menus provided by users and updates the generative AI model based on that evaluation.

[1247] "Means for ordering from food delivery services" is a function that automatically orders missing ingredients and arranges for delivery.

[1248] MODE FOR CARRYING OUT THE INVENTION

[1249] The following system is conceivable as an embodiment of the present invention.

[1250] System configuration

[1251] This system consists of terminals, a server, and users. The terminals used by users are devices such as smartphones and tablets, and they access the system through these. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[1252] Program processing

[1253] 1. Image recognition of receipts

[1254] After a user brings home their purchases from a supermarket or other store, they use their device to take a photo of the receipt. Using optical character recognition (OCR), the device extracts food information such as product name, quantity, and expiration date from the receipt image as text data. The extracted text data is formatted and sent to the server.

[1255] 2. Recording and managing food data

[1256] The server records the received ingredient information in the database and updates the existing inventory information. Information such as the ingredient name, quantity, purchase date, and expiration date is recorded and reflected in the inventory.

[1257] 3. Menu creation requests and suggestions

[1258] When a user requests "Today's Menu," the device sends this request to the server. The server retrieves available ingredient information from the database and provides it as input to the generation AI. The generation AI generates multiple recipe candidates based on the ingredient information and returns the recipes to the server. The server sends the generated menu to the user's device and displays the suggestions to the user.

[1259] 4. Automatic ordering of missing ingredients

[1260] If the user selects a recipe from the suggested menu and any ingredients are missing, the server automatically orders the missing ingredients from a food delivery service, allowing the user to smoothly prepare all the ingredients needed for that day's menu.

[1261] 5. Feedback and learning

[1262] The user provides feedback on the provided menu. The feedback includes evaluations such as "It was delicious" and "It was easy to make." The device sends the feedback to the server, which records it in a database and uses it as learning data for the generation AI to improve the accuracy of future suggestions.

[1263] Hardware and software used

[1264] Devices: smartphones, tablets

[1265] Server: Cloud computing service

[1266] OCR technology: OCR Processor

[1267] Generation AI: MenuGeneratorAI

[1268] Delivery service API: FoodDeliveryService

[1269] Specific examples

[1270] After a user finishes shopping at the supermarket, they take a photo of the receipt with their device. The device analyzes the image using OCR technology and extracts ingredient information such as "tomatoes, chicken, and carrots." The extracted information is sent to the server and recorded in a database. When the user then requests "Please suggest today's dinner menu," the server uses the generative AI to generate multiple recipes, such as "tomato and chicken stew," based on the available ingredient information. The generated menu is sent to the device, and the user selects one of the suggested recipes. Any missing ingredients are automatically ordered from a food delivery service, ensuring that the ingredients needed for that day's dinner are available. In addition, after dinner, the user provides feedback on the provided menu, allowing the generative AI model to learn for the next suggestion.

[1271] Prompt Sentence Examples

[1272] Available ingredients: Tomato, chicken

[1273] Required recipe: Dinner

[1274] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1275] Step 1:

[1276] After a user finishes shopping at a supermarket, they use a device to take a photo of the receipt. The receipt image taken by the user is input into the device. The device then analyzes the receipt image using optical character recognition (OCR) technology and extracts food information such as product name, quantity, and expiration date from the image as text data. The extracted text data is formatted and sent from the device to a server.

[1277] Step 2:

[1278] The server records the text data received from the terminal in a database and updates the existing inventory information. Text data (ingredient information) is provided as input. The server records information such as the ingredient name, quantity, purchase date, and expiration date in the database and updates the inventory information. As a result, the latest inventory status is reflected in the database.

[1279] Step 3:

[1280] The user uses a device to request "Today's Menu." The user's request is input from the device to the server. The server retrieves information about currently available ingredients from the database and provides that information as input to the generation AI. The generation AI receives the prompt and generates an appropriate menu. The generated multiple recipe candidates are output to the server.

[1281] Step 4:

[1282] The server sends the generated menu to the terminal and displays the suggestions to the user. Recipe candidates are input from the server to the terminal. The terminal displays multiple recipes to the user, allowing the user to select a suggested recipe.

[1283] Step 5:

[1284] The user selects a recipe from the suggested menu, and the terminal sends the selection information to the server. The server checks for missing ingredients based on the selected recipe. The selected recipe is provided as input. The server automatically orders the missing ingredients from a food delivery service and outputs the order information. This allows the missing ingredients to be delivered to the user.

[1285] Step 6:

[1286] After dinner, the user enters feedback on the menu provided on their device. The feedback information is then input from the device to the server. The server records this feedback information in a database and uses it as learning data for the generative AI. The server processes the feedback information and outputs it as data that will help improve the model. This improves the accuracy of menu suggestions from the next time onwards.

[1287] 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.

[1288] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a user, a terminal, a server, and an emotion engine, and its main operations are described in detail below.

[1289] System configuration

[1290] This system consists of a terminal used by the user, a server, and an emotion engine. The terminal is a device such as a smartphone or tablet, and provides an operation interface for users to take pictures of receipts, enter feedback, and send emotion data. The server manages ingredient information, generates menus using generative AI, accumulates user feedback, and analyzes learning and emotion data. The emotion engine has the function of recognizing emotions from the user's facial expressions and voice, and analyzing that information.

[1291] Program processing

[1292] 1. Image recognition of receipts

[1293] The user logs into the app and takes a photo of the receipt.

[1294] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image.

[1295] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[1296] 2. Recording and managing food data

[1297] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares it with existing inventory information and updates it.

[1298] The server will automatically calculate the expiration date of ingredients and notify the user when the expiration date is approaching, allowing ingredients to be used effectively without being wasted.

[1299] 3. Menu creation requests and suggestions

[1300] When a user requests "Today's Menu," the terminal sends the request to the server.

[1301] The server retrieves available ingredient information from the database and provides that information to the generation AI.

[1302] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[1303] 4. Emotion Recognition by Emotion Engine

[1304] Before and after the user receives the menu suggestion, the device uses an emotion engine to analyze the user's facial expressions and voice and collect emotional data.

[1305] The device sends emotion data to a server, which then analyzes the data.

[1306] The server adjusts menu suggestions based on the user's emotional data. For example, if it determines that the user is tired, it will prioritize easy-to-prepare meals.

[1307] 5. Feedback and learning

[1308] Users can provide feedback on the provided menus. Users can enter their ratings and comments using the in-app feedback form.

[1309] The device sends the feedback data to the server, which records it in a database. The server also records the user's emotional data obtained through the emotion engine and feeds it back to the generation AI.

[1310] The server updates the generative AI model based on the feedback and emotional data collected, improving the accuracy of the next menu suggestion.

[1311] Specific examples

[1312] 1. After a user finishes shopping at the supermarket, they open the app and take a photo of their receipt. The image is analyzed using OCR technology, and ingredient information such as "tomatoes, chicken, and carrots" is extracted.

[1313] 2. The terminal sends the ingredient information to the server, which records it in a database.

[1314] 3. The user sends a request saying, "Please suggest a menu for today's dinner," and the server sends the data to the generation AI, which generates multiple recipes.

[1315] 4. Before and after suggesting a menu, the device uses an emotion engine to analyze the user's facial expressions and voice, and sends the emotion data to the server.

[1316] 5. The server analyzes the emotional data and, for example, if it determines that the user is tired, it adjusts the menu to suggest easy-to-prepare meals.

[1317] 6. The terminal displays the generated menu to the user, and the user selects "Chicken and Tomato Stew" from the list.

[1318] 7. After dinner, the user sends feedback through the app saying "It was delicious," and the device sends this to the server.

[1319] 8. The server collects feedback and emotion data and updates the generative AI model to improve the accuracy of future menu suggestions.

[1320] As described above, the present invention is a food ingredient management and menu suggestion system that incorporates user emotion recognition, and significantly improves user convenience by making optimal suggestions based on the user's situation and emotions.

[1321] The processing flow will be explained below.

[1322] Step 1:

[1323] The user logs in to the app and takes a photo of the receipt. The user uses the app's camera function to take a photo of the receipt so that the entire receipt is visible.

[1324] Step 2:

[1325] The device captures the image of the receipt, stores the image data captured by the user in memory, and prepares it for the next OCR process.

[1326] Step 3:

[1327] The device uses optical character recognition (OCR) technology to extract text data from images. Specifically, the captured image is input into an OCR engine to identify text data such as product name, quantity, and date.

[1328] Step 4:

[1329] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[1330] Step 5:

[1331] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[1332] Step 6:

[1333] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[1334] Step 7:

[1335] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[1336] Step 8:

[1337] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[1338] Step 9:

[1339] The device sends the user's request to the server, which then sends the request parameters (such as meal timing and preferred genres) to the server via the API.

[1340] Step 10:

[1341] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[1342] Step 11:

[1343] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[1344] Step 12:

[1345] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[1346] Step 13:

[1347] The server sends the generated menu to the user's device. The server also formats the generated recipes, converts them into a format that is easy for the user to view, and sends them to the device.

[1348] Step 14:

[1349] The device displays the generated menu suggestions to the user, and the device displays the received recipe information on the app's UI so that the user can check it.

[1350] Step 15:

[1351] When a user receives a menu suggestion, the emotion engine analyzes the user's facial expressions and voice, and sends the emotion data to the server. The user expresses their feelings about the suggested menu, and the device processes them using the emotion engine.

[1352] Step 16:

[1353] The server analyzes the emotion data and adjusts the menu suggestions based on the emotion data. The server prioritizes easy-to-prepare menu suggestions depending on the user's emotional state (e.g., if they feel tired).

[1354] Step 17:

[1355] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[1356] Step 18:

[1357] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[1358] Step 19:

[1359] The server receives the feedback and reflects it as learning data for the generation AI. The server stores the feedback information in a database and periodically uses it to update the generation AI model, improving the accuracy of future menu suggestions.

[1360] Example 2

[1361] 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."

[1362] Conventional food ingredient management and menu suggestion systems have the problem of not providing sufficient user convenience because they do not make suggestions based on the user's emotions or circumstances. Another issue is that they are unable to effectively manage available ingredients, resulting in food waste.

[1363] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for generating a menu suitable for the user based on the ingredient information using a generation AI, and a means for adjusting the suggested content based on emotion data. This makes it possible to suggest an optimal menu according to the user's emotion and situation. It also promotes the effective use of ingredients and reduces food waste.

[1364] "User" refers to a person who uses the system to manage ingredients and receive menu suggestions.

[1365] "Terminal" refers to a device such as a smartphone or tablet operated by a user.

[1366] A "server" refers to a computer that manages and processes data at the center of a system.

[1367] "Means for taking images" refers to methods for obtaining images using the camera function of a smartphone, etc.

[1368] "Optical character recognition technology" refers to the technology that analyzes character information in an image and converts it into text data.

[1369] "Ingredient information" refers to information such as the name, quantity, purchase date, and expiration date of the food purchased by the user.

[1370] "Database" refers to data storage where ingredient information, feedback data, etc. are recorded and managed.

[1371] "Generative AI" refers to algorithms and functions that use artificial intelligence technology to automatically generate menus suitable for users.

[1372] "Emotion recognition technology" refers to technology that analyzes emotions from a user's facial expressions and voice data.

[1373] "Feedback" refers to the user's ratings and comments on the menu provided.

[1374] "Inventory information" refers to information such as the type, quantity, and expiration date of ingredients owned by the user.

[1375] "Request parameters" refer to the conditions and requests that a user specifies when requesting menu suggestions.

[1376] MODE FOR CARRYING OUT THE INVENTION

[1377] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a terminal used by the user, a server, and an emotion engine, and its operation is described in detail below.

[1378] Hardware and Software

[1379] This system uses the user's smartphone or tablet device, a general-purpose cloud server (e.g., Amazon Web Services or Google Cloud Platform), and an API for emotion recognition (e.g., Microsoft Azure's Emotion API). The program is implemented in Python and JavaScript, and uses Google Cloud Vision API and Amazon Textract for OCR technology. Furthermore, a generative AI model (e.g., OpenAI's GPT-4) is used to generate the menu.

[1380] Program processing

[1381] 1. Image recognition of receipts

[1382] The user launches the app on their smartphone, logs in, and takes a photo of the receipt. A prompt appears saying, "Press the receipt capture button."

[1383] The device captures the receipt image, performs OCR processing using the Google Cloud Vision API, and extracts ingredient information from the receipt.

[1384] The device formats the extracted ingredient information (e.g., tomato, chicken, carrot) and sends it to the server. A prompt saying "Sending ingredient information" is displayed.

[1385] 2. Recording and managing food data

[1386] The server records the received ingredient information in a database (e.g., AWS RDS).

[1387] The server stores information such as ingredient name, quantity, purchase date, expiration date, etc., and compares it with existing inventory information to update it. A prompt saying "Inventory updating" is displayed on the user's terminal.

[1388] The server automatically calculates the expiration date of ingredients, and if the expiration date is approaching, a notification is sent to the user saying, "The expiration date is tomorrow."

[1389] 3. Menu creation requests and suggestions

[1390] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[1391] The terminal sends a request to the server, and the server retrieves available ingredient information from a database.

[1392] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates (detailed cooking instructions, additional ingredients, cooking time, etc.).

[1393] The generation AI will display a list of the generated menus on the screen along with the prompt, "The following menus have been suggested."

[1394] 4. Emotion Recognition by Emotion Engine

[1395] The smartphone's camera and microphone are used to collect facial and voice data just before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[1396] The data collected by the device is sent to Microsoft Azure's Emotion API for emotional analysis.

[1397] The device sends emotional data to the server, which then analyzes it and adjusts the suggestions. For example, if the device determines that the user is tired, it will suggest the following simple meal plan.

[1398] 5. Feedback and learning

[1399] The user tries the provided menu and then enters feedback (ratings and comments) in the app. The app prompts the user to "Enter your rating for the dish."

[1400] The terminal sends the feedback data to the server, which records it in a database.

[1401] The server updates the generative AI model based on the collected feedback and sentiment data to improve the accuracy of the next menu suggestion. A prompt will appear saying, "We've updated the model based on your feedback."

[1402] The present invention makes it possible to propose an optimal menu that matches the user's situation and emotions, thereby significantly improving the effective use of ingredients and convenience of daily life.

[1403] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1404] Step 1: Take a photo of your receipt and send it

[1405] The user launches the app and logs in.

[1406] The user takes a photo of the receipt. The prompt "Press the receipt capture button" appears.

[1407] The device captures the image of the receipt and analyzes it using OCR technology.

[1408] Input: Receipt image

[1409] Output: Text data of ingredients (e.g., tomato, chicken, carrot)

[1410] The device sends the acquired text data to the server. A prompt saying "Sending ingredient information" is displayed.

[1411] Step 2: Record and manage food ingredient data

[1412] The server records the received ingredient information in a database.

[1413] The server stores information such as the ingredient name, quantity, purchase date, and expiration date.

[1414] Input: Text data of ingredients

[1415] Output: Ingredient information recorded in the database

[1416] The server will update the data against existing inventory information and display the prompt "Updating inventory."

[1417] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching. A notification saying "Tomorrow is the expiration date" is sent.

[1418] Step 3: Menu creation request and suggestions

[1419] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[1420] The device sends a request to the server.

[1421] The server obtains available ingredient information from the database.

[1422] Input: Request parameters

[1423] Output: Available ingredients information

[1424] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates.

[1425] The generative AI generates information such as detailed cooking steps, additional ingredients, and cooking time, and returns it to the server.

[1426] Input: Ingredient information

[1427] Output: Multiple recipe candidates

[1428] The server sends the generated recipe information to the terminal, and a prompt saying "The following menu has been suggested" is displayed.

[1429] Step 4: Emotion Recognition with the Emotion Engine

[1430] The smartphone's camera and microphone are used to collect facial and voice data immediately before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[1431] The data collected by the device is sent to an emotion engine, which analyzes emotions.

[1432] Input: facial expression data, voice data

[1433] Output: Emotion data

[1434] The device will send the analyzed emotion data to the server. A prompt will appear saying "Sending emotion data."

[1435] The server analyzes the user's emotional data and adjusts the suggestions accordingly. For example, if it determines that the user is tired, it will prioritize simpler menus.

[1436] Step 5: Gather feedback and learn

[1437] The user tries the provided meal and then provides feedback in the app, prompting them to "rate the dish."

[1438] The terminal transmits the feedback data to the server.

[1439] The server receives the feedback data and records it in a database.

[1440] Input: User feedback

[1441] Output: Updated database

[1442] The server updates the generative AI model based on the feedback and emotion data. A prompt appears saying, "We've updated the model based on your feedback."

[1443] (Application example 2)

[1444] 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."

[1445] Conventional food ingredient management and menu suggestion systems do not take into account the user's emotional state, making it difficult to suggest meals that are in line with the user's actual needs and circumstances. Furthermore, because menus cannot be adjusted based on emotions, it is difficult to improve user satisfaction. For example, if the user is tired or busy, easy-to-prepare meals may not be suggested, which can be a burden on the user's experience.

[1446] 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.

[1447] In this invention, the server is equipped with an emotion engine that recognizes the user's emotions, and includes means for transmitting emotion data to the server, means for the server to analyze the emotion data and adjust menu suggestions based on the user's emotions, and means for preferentially suggesting easy-to-prepare menus based on the emotion recognition data, thereby enabling optimal menu suggestions to be made according to the user's situation.

[1448] "User" refers to a person who uses a terminal to take an image of a receipt, manages ingredient information, and receives menu suggestions.

[1449] "Terminal" refers to a device such as a smartphone or tablet operated by a user, which has the functionality to take images of receipts and recognize emotions.

[1450] "Optical character recognition technology" refers to technology that detects text within an image and converts it into digital text data.

[1451] "Food information" refers to data such as the food name, quantity, purchase date, and expiration date extracted from the receipt.

[1452] "Server" refers to a computer system that manages food ingredient data, analyzes emotional data, and uses generative AI to suggest menus.

[1453] A "database" refers to a collection of data that allows information to be systematically managed and easily accessed.

[1454] "Generative AI" refers to algorithms and models that use generative artificial intelligence technology to generate appropriate menus based on ingredient information and emotional data.

[1455] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions and voice to recognize their emotional state.

[1456] "Emotion data" refers to information indicating the user's emotional state obtained by the emotion engine.

[1457] "Menu suggestion" refers to providing the user with specific recipes and cooking procedures for dishes that are generated based on ingredient information and emotion data.

[1458] "Feedback" refers to the evaluations and comments users make on menu suggestions, which are reflected in the learning of the generation AI.

[1459] A system embodying the present invention allows users to receive ingredient management and menu suggestions using emotion recognition technology. A detailed description of how to implement this system is provided below.

[1460] System Components

[1461] This system consists of the user's device (smartphone or tablet), server, emotion engine, etc. Specifically, it is as follows:

[1462] 1. Terminal

[1463] Using smart glasses or a smartphone, the user takes a picture of the receipt.

[1464] Extract text data from images using optical character recognition technology (Google Cloud Vision API).

[1465] An emotion engine is used to analyze the user's facial expressions and voice to obtain emotion data.

[1466] 2. Server

[1467] Corresponding ingredient information and emotion data are received and recorded and managed in a database (e.g., AWS RDS).

[1468] Using generative AI (OpenAI GPT model), appropriate menus are generated based on ingredient information and emotional data.

[1469] Using unsupervised learning, user feedback data is analyzed and the generative AI model is updated.

[1470] 3. Emotion Engine

[1471] Uses the Azure Emotion API to recognize emotions from the user's facial expressions and voice data.

[1472] The recognized emotion data is sent to the server and used to adjust menu suggestions.

[1473] System operation example

[1474] 1. Image recognition of receipts

[1475] The user takes a photo of the receipt with the smart glasses, and the device uses optical character recognition technology to extract text data from the image. The extracted ingredient information is sent to a server and recorded in a database.

[1476] 2. Emotion recognition

[1477] When a user requests a menu suggestion, the smart glasses analyze the user's facial expressions and voice using an emotion engine and send the resulting emotion data to the server.

[1478] 3. Menu suggestions

[1479] The server provides input to the AI ​​based on ingredient information and emotion data to generate an appropriate menu. The generated menu is then sent to the device and presented to the user.

[1480] 4. Emotion-Based Regulation

[1481] The server analyzes the emotional data and adjusts the menu suggestions, such as prioritizing easy-to-prepare dishes if the user is tired.

[1482] 5. Gather feedback and learn

[1483] When users send feedback on the menu, the data is stored on the server and reflected in the learning of the generation AI.

[1484] Specific examples

[1485] 1. After shopping at the supermarket, the user scans the receipt with the smart glasses. The system automatically extracts food data using OCR and manages the ingredient information.

[1486] 2. When food is nearing its expiration date, notifications are sent via smart glasses.

[1487] 3. When a user requests a menu suggestion, the smart glasses analyze their facial expressions and voice using an emotion engine and send the emotion data to the server.

[1488] 4. The server provides prompts to the generation AI based on ingredient information and emotion data, and generates an appropriate menu.

[1489] 5. The generated menu is displayed to the user, and user feedback is reflected in the next proposal.

[1490] Prompt Sentence Examples

[1491] Suggest an easy meal plan if the user has the following ingredients:

[1492] tomato

[1493] chicken meat

[1494] Carrots

[1495] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[1496] By combining these elements, it becomes possible to propose the most suitable menu according to the user's situation, thereby increasing user satisfaction.

[1497] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1498] Step 1:

[1499] The user takes a photo of the receipt using smart glasses or a smartphone. In this process, the image of the receipt is input and the image data captured by the user is output.

[1500] Step 2:

[1501] The device uses optical character recognition (OCR) technology to extract text data from the image of the receipt. The OCR software takes the image data as input, analyzes it, and outputs ingredient information, often in text form.

[1502] Step 3:

[1503] The device analyzes the extracted text data and formats the ingredient information. In this step, the OCR results (text data) are input, and organized ingredient information such as specific ingredient names, quantities, and purchase dates is output.

[1504] Step 4:

[1505] The terminal sends the analyzed ingredient information to the server. In this process, the organized ingredient information is the input, and the transmission action to the server is the output.

[1506] Step 5:

[1507] The server records the received ingredient information in the database and updates the inventory information. The ingredient information is input and the updated database is output.

[1508] Step 6:

[1509] The user requests a menu. The menu request is input and the request information is output.

[1510] Step 7:

[1511] The device uses an emotion engine to analyze the user's facial expressions and voice to obtain emotion data. New user actions (e.g., requests, questions, grins) are taken as input, and emotion data is output.

[1512] Step 8:

[1513] The emotion data is sent to the server, which then stores it. In this process, the emotion data is the input, and the sending and storing operations to the server are the output.

[1514] Step 9:

[1515] The server combines the ingredient information and emotion data and generates an appropriate menu using the generation AI. At this stage, the ingredient information and emotion data are input, and the generated menu (recipe information) is output. The generation AI uses the following prompt sentence:

[1516] Suggest an easy meal plan if the user has the following ingredients:

[1517] tomato

[1518] chicken meat

[1519] Carrots

[1520] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[1521] Step 10:

[1522] The server sends the generated menu to the terminal. The generated menu is the input, and the sending action to the terminal is the output.

[1523] Step 11:

[1524] The terminal displays the generated menu to the user. The terminal receives the menu (recipe information) received from the server as input and visually displays it to the user.

[1525] Step 12:

[1526] The user submits feedback on the menu. Here, the user's feedback information is input and feedback data is output.

[1527] Step 13:

[1528] The feedback data is received by the server and recorded in a database. The feedback information is the input and the updated database is the output.

[1529] Step 14:

[1530] The server uses the collected feedback and emotion data to train a generative AI model. At this stage, the feedback and emotion data are input, and an updated generative AI model is output.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] [Fourth embodiment]

[1535] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1536] 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.

[1537] 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).

[1538] 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.

[1539] 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.

[1540] 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).

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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.

[1545] 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.

[1546] 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.

[1547] 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."

[1548] The present invention relates to a system that automatically generates and proposes daily menus based on the ingredients available at home. The specific operation method and processing contents of the system are described below.

[1549] System configuration

[1550] This system consists of users, terminals, and a server. The terminals used by users are devices such as smartphones and tablets, through which they access the system. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[1551] Program processing

[1552] 1. Image recognition of receipts

[1553] When the user returns home from the supermarket, for example, they open the app and take a photo of the receipt.

[1554] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image. OCR technology extracts information such as product name, quantity, and date from the receipt image as text data.

[1555] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[1556] 2. Recording and managing food data

[1557] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares the information with existing ingredient information and updates inventory information.

[1558] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching, allowing the user to make effective use of ingredients without wasting them.

[1559] 3. Menu creation requests and suggestions

[1560] When a user requests "Today's Menu," the terminal sends this request to the server.

[1561] The server retrieves available ingredient information from the database and provides that information as input to the generation AI.

[1562] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[1563] The server sends the generated menu to the user's terminal, which displays the suggestions to the user.

[1564] 4. Feedback and learning

[1565] Users can provide feedback on the provided menus, such as "It was delicious" or "It was easy to make," by entering their ratings through the app.

[1566] The terminal sends the user's feedback to the server, which records the feedback in a database.

[1567] The server collects feedback and reflects it as learning data for the generating AI, improving the accuracy of menu suggestions from the next time onwards.

[1568] Specific examples

[1569] 1. The user finishes shopping at the supermarket and takes a photo of the receipt using the app.

[1570] 2. The device analyzes the image using OCR technology and extracts ingredient information such as "tomato, chicken, carrot."

[1571] 3. The device sends the analysis results to the server, which records the received information in a database.

[1572] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[1573] 5. The server uses a generation AI based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[1574] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[1575] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[1576] 8. The server collects feedback and updates the generative AI model to improve the accuracy of the next menu suggestion.

[1577] As described above, the present invention is a system that automates the entire process from ingredient management to menu proposals, significantly reducing the burden on users. This system allows users to enjoy everyday cooking simply and efficiently.

[1578] The processing flow will be explained below.

[1579] Step 1:

[1580] The user logs in to the app and takes a photo of the receipt. The user uses the camera function in the app to take a photo of the receipt so that the entire receipt is visible.

[1581] Step 2:

[1582] The device captures the image of the receipt. The device stores the image data captured by the user in memory and enables optical character recognition (OCR) technology.

[1583] Step 3:

[1584] The device uses optical character recognition (OCR) technology to extract text data from the image. Specifically, it starts an OCR engine, analyzes the receipt image as input, and identifies text data such as product name, quantity, and date.

[1585] Step 4:

[1586] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[1587] Step 5:

[1588] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[1589] Step 6:

[1590] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[1591] Step 7:

[1592] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[1593] Step 8:

[1594] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[1595] Step 9:

[1596] The device sends the user's request to the server, which then sends the request, including the user's request parameters (such as meal times and preferred genres), to the server via the API.

[1597] Step 10:

[1598] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[1599] Step 11:

[1600] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[1601] Step 12:

[1602] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[1603] Step 13:

[1604] The server sends the generated menu to the user's terminal. The server formats the generated multiple recipe ideas, converts them into a format that is easy for the user to view, and sends them to the terminal.

[1605] Step 14:

[1606] The device displays the generated menu suggestions to the user, and displays the received recipe information on the app's UI so that the user can check it.

[1607] Step 15:

[1608] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[1609] Step 16:

[1610] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[1611] Step 17:

[1612] The server receives the feedback and reflects it as learning data for the generation AI. The server then stores the feedback information in a database and periodically uses it to update the generation AI model, thereby improving the accuracy of future menu suggestions.

[1613] Example 1

[1614] 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."

[1615] In today's busy daily lives, it is important to efficiently manage daily meals and reduce food waste. However, in many households, it is difficult to keep track of the ingredients in the refrigerator, which results in food waste. In addition, planning meals takes time and effort, and many people often find themselves unsure of what to cook. Furthermore, there is a need for automated assistance to make the most of available ingredients and provide healthy, balanced meals.

[1616] 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.

[1617] In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for using a generative AI model to generate a menu suitable for the user based on the ingredient information, and a means for providing the ingredient information as a prompt to the generative AI model to generate recipe candidates. This reduces ingredient waste, enables efficient and effective automatic generation of daily menus, and reduces the burden on the user.

[1618] "User" refers to an individual who uses the system to manage ingredients and receive menu suggestions.

[1619] A "terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[1620] "Server" refers to an online entity that manages ingredient information, generates menus using generative AI models, and accumulates and learns from user feedback.

[1621] "Optical character recognition technology" is a technology for extracting text data from images, and is also known as OCR (Optical Character Recognition).

[1622] "Ingredient information" refers to data such as the name, quantity, purchase date, and expiration date of the ingredients.

[1623] "Inventory information" refers to information such as the quantity and expiration date of ingredients recorded in the database.

[1624] A "generative AI model" refers to an artificial intelligence model that automatically generates menus based on ingredient information. Examples include GPT-3 and similar generative models.

[1625] A "prompt sentence" is a text sentence that is input into a generative AI model and contains specific instructions and conditions.

[1626] "Recipe candidates" refers to multiple dish suggestions generated by the generative AI model.

[1627] "Feedback" refers to the user's evaluation and impressions of the menu provided.

[1628] This invention relates to a system that efficiently manages ingredients in a household and automatically generates daily menus. This system is composed of three main components: a user, a terminal, and a server. The specific functions and processing contents of each component are explained below.

[1629] System configuration

[1630] 1. Users

[1631] Users use the system to manage information about ingredients in their households and receive daily menu suggestions. Users mainly access and operate the system using smartphones or tablet devices.

[1632] 2. Terminal

[1633] A terminal is a device through which a user accesses the system, such as a smartphone or tablet. Applications on the terminal have the following functions:

[1634] Capturing and acquiring receipt images

[1635] After shopping, the user takes a photo of the receipt.

[1636] Implementing Optical Character Recognition (OCR) technology

[1637] Use OCR technology (e.g., Google Vision API) to extract text information from receipt images.

[1638] Analysis and transmission of food ingredient information

[1639] The extracted text data is analyzed to format the ingredient information and sent to the server.

[1640] Display menu suggestions

[1641] The menu sent from the server is displayed to the user.

[1642] Collecting and sending feedback

[1643] Collect user feedback and send it to the server.

[1644] 3. Server

[1645] The server plays a central role in the entire system and has the following functions:

[1646] Food ingredient information database management

[1647] The food ingredient information sent from the terminal is recorded in a database (e.g., MySQL or PostgreSQL) and inventory information is updated.

[1648] Expiration notification settings

[1649] To automatically calculate the expiration date of ingredients and notify a user of ingredients whose expiration date is approaching.

[1650] Menu generation based on generative AI models

[1651] Based on the ingredient information, a menu is automatically generated using a generative AI model (e.g., GPT-3). A prompt is provided as input, and multiple recipe candidates are generated.

[1652] Learning Feedback

[1653] Feedback from users is collected and reflected as learning data for the generative AI model, improving the accuracy of future menu suggestions.

[1654] Specific examples

[1655] 1. After the user finishes shopping at the supermarket, they take a photo of the receipt using an app on their smartphone.

[1656] 2. The device analyzes the image using OCR technology (Google Vision API) and extracts ingredient information such as "tomato, chicken, carrot."

[1657] 3. The device sends the analysis results to the server, which records the received information in a database.

[1658] 4. When the user sends a request saying, "Please suggest a menu for today's dinner," the device sends the request to the server.

[1659] 5. The server uses a generation AI (e.g., GPT-3) based on the available ingredient information to generate multiple recipes, including "Tomato and Chicken Stew," and sends them to the device.

[1660] 6. The device displays suggested recipes to the user, and the user selects "Chicken and Tomato Stew."

[1661] 7. After dinner, the user sends feedback saying "It was delicious," and the device sends that feedback to the server.

[1662] 8. The server collects feedback and uses it as training data to improve the accuracy of the generative AI model.

[1663] Prompt Sentence Examples

[1664] Here is an example of a prompt to input to a generative AI model:

[1665] Available ingredients: Tomato, chicken, carrot

[1666] Preferred type of food: Dinner

[1667] Other criteria: Easy to make, can be prepared in under 30 minutes

[1668] As described above, the present invention is a system that comprehensively automates everything from ingredient management to menu suggestions and learning from user feedback, greatly improving the efficiency of a user's eating habits.

[1669] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1670] Step 1:

[1671] A user comes home from the supermarket, opens the app on their smartphone or tablet, and takes a photo of the receipt.

[1672] Specific action: The user uses the app's camera to focus on the receipt and press the shutter button.

[1673] Input: Receipt image

[1674] Output: Receipt image data is saved to the device.

[1675] Step 2:

[1676] The device retrieves the stored receipt image and uses OCR technology to extract text data from the image.

[1677] Specific operation: The device app sends the captured image to an OCR API (e.g., Google Vision API) and analyzes the text information.

[1678] Input: Receipt image data

[1679] Output: Extracted text data (product name, quantity, date)

[1680] Step 3:

[1681] The device analyzes the text data obtained by OCR and formats the ingredient information.

[1682] Specific operation: The device parses the extracted character data, extracts the necessary items (ingredient name, quantity, purchase date) and generates ingredient information.

[1683] Input: Extracted character data

[1684] Output: Formatted ingredient information

[1685] Step 4:

[1686] The terminal transmits the formatted ingredient information to the server.

[1687] Specific operation: The device uses an HTTP request to send ingredient information to the server.

[1688] Input: Formatted ingredient information

[1689] Output: Ingredient information arrives at the server

[1690] Step 5:

[1691] The server records the received ingredient information in a database and updates inventory information.

[1692] Specific operation: The server inserts ingredient information into a database (e.g., MySQL, PostgreSQL) using SQL statements, matches it with existing data, and updates inventory information.

[1693] Input: Ingredient information

[1694] Output: Updated inventory information is recorded in the database.

[1695] Step 6:

[1696] The user requests, "Please suggest today's menu." This request is sent to the server by the terminal.

[1697] Specific operation: The user presses the menu request button on the app, and the device sends the request to the server.

[1698] Input: User request

[1699] Output: Request data arrives at the server

[1700] Step 7:

[1701] The server retrieves available ingredient information from the database and sends it to the generative AI model as a prompt.

[1702] Specific operation: The server retrieves the latest ingredient information from the database using an SQL query and sends the generated prompt text to the API of the generative AI model (e.g., GPT-3).

[1703] Input: Request data, ingredient information recorded in the database

[1704] Output: The prompt sent to the generative AI model

[1705] Step 8:

[1706] The generative AI model generates multiple recipe candidates based on the prompt sentence and sends them back to the server.

[1707] Specific operation: The generative AI model analyzes the prompt, generates multiple menu recipes based on the available ingredients, and sends them back to the server as an API response.

[1708] Input: prompt statement

[1709] Output: Multiple recipe candidates

[1710] Step 9:

[1711] The server transmits the generated recipe candidates to the user's terminal.

[1712] Specific operation: The server uses the HTTP response to send the generated recipe data to the device.

[1713] Input: Recipe candidate data

[1714] Output: Recipe candidate data arrives on the device

[1715] Step 10:

[1716] The terminal displays the received recipe candidates to the user.

[1717] Specific behavior: The device application displays recipe suggestions in the user interface for the user to review.

[1718] Input: Recipe candidate data

[1719] Output: A list of recipe suggestions that is displayed to the user

[1720] Step 11:

[1721] Users create a menu of their choice and then enter feedback within the app after eating.

[1722] What happens: The user uses the app's feedback function to enter their impressions, such as "It was delicious" or "It was easy to make," and presses the submit button.

[1723] Input: Feedback information

[1724] Output: Feedback data is saved to the device

[1725] Step 12:

[1726] The terminal sends the feedback to the server, which records the feedback in a database.

[1727] Specific operation: The terminal sends feedback data to the server via an HTTP request, and the server inserts and records the received feedback into a database.

[1728] Input: Feedback data

[1729] Output: Feedback is recorded in a database

[1730] Step 13:

[1731] The server trains the generative AI model based on the feedback collected, improving the accuracy of future menu suggestions.

[1732] How it works: The server adds the feedback data to the learning dataset of the AI ​​model and automatically retrains the model. The updated model is reflected in the next menu generation.

[1733] Input: Feedback data

[1734] Output: An improved generative AI model

[1735] (Application example 1)

[1736] 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."

[1737] In modern life, there is a demand for efficient use of food ingredients at home without waste. However, achieving this requires time-consuming inventory checks and planning appropriate menus, which is extremely cumbersome. Furthermore, if necessary ingredients are in short supply, additional effort is required to purchase them. There is a need for a system that simplifies this process while making effective use of ingredients.

[1738] 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.

[1739] In this invention, the server includes a means for generating a menu suitable for the user, a means for automatically ordering any missing ingredients from a food delivery service, and a means for presenting the menu to the user, thereby enabling the user to use ingredients at home without waste and easily replenish the necessary ingredients.

[1740] "Users" are individuals and households who use the system.

[1741] "Means for taking a picture of a receipt" refers to a function that allows a user to take a picture of a receipt after purchasing an item using a device such as a smartphone or tablet.

[1742] Optical character recognition (OCR) is a technology that extracts text data from images.

[1743] The "server" is an online entity that manages ingredient information, generates menus using AI, and accumulates and learns from user feedback.

[1744] "Ingredient information" refers to information such as the name, quantity, and expiration date of the item read from the receipt.

[1745] The "means for updating inventory information" is a function for updating existing inventory information using newly acquired ingredient information.

[1746] "Generative AI" is an artificial intelligence model that generates appropriate menus based on input ingredient information.

[1747] The "means of generating a menu" is a function in which the generation AI suggests dishes based on the input ingredient information.

[1748] The "means for presenting a menu to a user" is a function for displaying the generated dish suggestions on the user's terminal.

[1749] "Means for collecting feedback from users and reflecting it in the learning of the generative AI" refers to a function that collects evaluations of menus provided by users and updates the generative AI model based on that evaluation.

[1750] "Means for ordering from food delivery services" is a function that automatically orders missing ingredients and arranges for delivery.

[1751] MODE FOR CARRYING OUT THE INVENTION

[1752] The following system is conceivable as an embodiment of the present invention.

[1753] System configuration

[1754] This system consists of terminals, a server, and users. The terminals used by users are devices such as smartphones and tablets, and they access the system through these. The server is the online entity that manages ingredient information, generates menus using generative AI, and accumulates and learns from user feedback.

[1755] Program processing

[1756] 1. Image recognition of receipts

[1757] After a user brings home their purchases from a supermarket or other store, they use their device to take a photo of the receipt. Using optical character recognition (OCR), the device extracts food information such as product name, quantity, and expiration date from the receipt image as text data. The extracted text data is formatted and sent to the server.

[1758] 2. Recording and managing food data

[1759] The server records the received ingredient information in the database and updates the existing inventory information. Information such as the ingredient name, quantity, purchase date, and expiration date is recorded and reflected in the inventory.

[1760] 3. Menu creation requests and suggestions

[1761] When a user requests "Today's Menu," the device sends this request to the server. The server retrieves available ingredient information from the database and provides it as input to the generation AI. The generation AI generates multiple recipe candidates based on the ingredient information and returns the recipes to the server. The server sends the generated menu to the user's device and displays the suggestions to the user.

[1762] 4. Automatic ordering of missing ingredients

[1763] If the user selects a recipe from the suggested menu and any ingredients are missing, the server automatically orders the missing ingredients from a food delivery service, allowing the user to smoothly prepare all the ingredients needed for that day's menu.

[1764] 5. Feedback and learning

[1765] The user provides feedback on the provided menu. The feedback includes evaluations such as "It was delicious" and "It was easy to make." The device sends the feedback to the server, which records it in a database and uses it as learning data for the generation AI to improve the accuracy of future suggestions.

[1766] Hardware and software used

[1767] Devices: smartphones, tablets

[1768] Server: Cloud computing service

[1769] OCR technology: OCR Processor

[1770] Generation AI: MenuGeneratorAI

[1771] Delivery service API: FoodDeliveryService

[1772] Specific examples

[1773] After a user finishes shopping at the supermarket, they take a photo of the receipt with their device. The device analyzes the image using OCR technology and extracts ingredient information such as "tomatoes, chicken, and carrots." The extracted information is sent to the server and recorded in a database. When the user then requests "Please suggest today's dinner menu," the server uses the generative AI to generate multiple recipes, such as "tomato and chicken stew," based on the available ingredient information. The generated menu is sent to the device, and the user selects one of the suggested recipes. Any missing ingredients are automatically ordered from a food delivery service, ensuring that the ingredients needed for that day's dinner are available. In addition, after dinner, the user provides feedback on the provided menu, allowing the generative AI model to learn for the next suggestion.

[1774] Prompt Sentence Examples

[1775] Available ingredients: Tomato, chicken

[1776] Required recipe: Dinner

[1777] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1778] Step 1:

[1779] After a user finishes shopping at a supermarket, they use a device to take a photo of the receipt. The receipt image taken by the user is input into the device. The device then analyzes the receipt image using optical character recognition (OCR) technology and extracts food information such as product name, quantity, and expiration date from the image as text data. The extracted text data is formatted and sent from the device to a server.

[1780] Step 2:

[1781] The server records the text data received from the terminal in a database and updates the existing inventory information. Text data (ingredient information) is provided as input. The server records information such as the ingredient name, quantity, purchase date, and expiration date in the database and updates the inventory information. As a result, the latest inventory status is reflected in the database.

[1782] Step 3:

[1783] The user uses a device to request "Today's Menu." The user's request is input from the device to the server. The server retrieves information about currently available ingredients from the database and provides that information as input to the generation AI. The generation AI receives the prompt and generates an appropriate menu. The generated multiple recipe candidates are output to the server.

[1784] Step 4:

[1785] The server sends the generated menu to the terminal and displays the suggestions to the user. Recipe candidates are input from the server to the terminal. The terminal displays multiple recipes to the user, allowing the user to select a suggested recipe.

[1786] Step 5:

[1787] The user selects a recipe from the suggested menu, and the terminal sends the selection information to the server. The server checks for missing ingredients based on the selected recipe. The selected recipe is provided as input. The server automatically orders the missing ingredients from a food delivery service and outputs the order information. This allows the missing ingredients to be delivered to the user.

[1788] Step 6:

[1789] After dinner, the user enters feedback on the menu provided on their device. The feedback information is then input from the device to the server. The server records this feedback information in a database and uses it as learning data for the generative AI. The server processes the feedback information and outputs it as data that will help improve the model. This improves the accuracy of menu suggestions from the next time onwards.

[1790] 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.

[1791] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a user, a terminal, a server, and an emotion engine, and its main operations are described in detail below.

[1792] System configuration

[1793] This system consists of a terminal used by the user, a server, and an emotion engine. The terminal is a device such as a smartphone or tablet, and provides an operation interface for users to take pictures of receipts, enter feedback, and send emotion data. The server manages ingredient information, generates menus using generative AI, accumulates user feedback, and analyzes learning and emotion data. The emotion engine has the function of recognizing emotions from the user's facial expressions and voice, and analyzing that information.

[1794] Program processing

[1795] 1. Image recognition of receipts

[1796] The user logs into the app and takes a photo of the receipt.

[1797] The device captures an image of the receipt and uses optical character recognition (OCR) technology to extract text data from the image.

[1798] The terminal analyzes the extracted text data, formats the ingredient information, and transmits it to the server.

[1799] 2. Recording and managing food data

[1800] The server records the received ingredient information in a database. The recorded information includes the ingredient name, quantity, purchase date, expiration date, etc. It also compares it with existing inventory information and updates it.

[1801] The server will automatically calculate the expiration date of ingredients and notify the user when the expiration date is approaching, allowing ingredients to be used effectively without being wasted.

[1802] 3. Menu creation requests and suggestions

[1803] When a user requests "Today's Menu," the terminal sends the request to the server.

[1804] The server retrieves available ingredient information from the database and provides that information to the generation AI.

[1805] The AI ​​then generates a menu based on the ingredient information and returns multiple recipe candidates to the server, including detailed cooking instructions, any additional ingredients needed, and estimated cooking times.

[1806] 4. Emotion Recognition by Emotion Engine

[1807] Before and after the user receives the menu suggestion, the device uses an emotion engine to analyze the user's facial expressions and voice and collect emotional data.

[1808] The device sends emotion data to a server, which then analyzes the data.

[1809] The server adjusts menu suggestions based on the user's emotional data. For example, if it determines that the user is tired, it will prioritize easy-to-prepare meals.

[1810] 5. Feedback and learning

[1811] Users can provide feedback on the provided menus. Users can enter their ratings and comments using the in-app feedback form.

[1812] The device sends the feedback data to the server, which records it in a database. The server also records the user's emotional data obtained through the emotion engine and feeds it back to the generation AI.

[1813] The server updates the generative AI model based on the feedback and emotional data collected, improving the accuracy of the next menu suggestion.

[1814] Specific examples

[1815] 1. After a user finishes shopping at the supermarket, they open the app and take a photo of their receipt. The image is analyzed using OCR technology, and ingredient information such as "tomatoes, chicken, and carrots" is extracted.

[1816] 2. The terminal sends the ingredient information to the server, which records it in a database.

[1817] 3. The user sends a request saying, "Please suggest a menu for today's dinner," and the server sends the data to the generation AI, which generates multiple recipes.

[1818] 4. Before and after suggesting a menu, the device uses an emotion engine to analyze the user's facial expressions and voice, and sends the emotion data to the server.

[1819] 5. The server analyzes the emotional data and, for example, if it determines that the user is tired, it adjusts the menu to suggest easy-to-prepare meals.

[1820] 6. The terminal displays the generated menu to the user, and the user selects "Chicken and Tomato Stew" from the list.

[1821] 7. After dinner, the user sends feedback through the app saying "It was delicious," and the device sends this to the server.

[1822] 8. The server collects feedback and emotion data and updates the generative AI model to improve the accuracy of future menu suggestions.

[1823] As described above, the present invention is a food ingredient management and menu suggestion system that incorporates user emotion recognition, and significantly improves user convenience by making optimal suggestions based on the user's situation and emotions.

[1824] The processing flow will be explained below.

[1825] Step 1:

[1826] The user logs in to the app and takes a photo of the receipt. The user uses the app's camera function to take a photo of the receipt so that the entire receipt is visible.

[1827] Step 2:

[1828] The device captures the image of the receipt, stores the image data captured by the user in memory, and prepares it for the next OCR process.

[1829] Step 3:

[1830] The device uses optical character recognition (OCR) technology to extract text data from images. Specifically, the captured image is input into an OCR engine to identify text data such as product name, quantity, and date.

[1831] Step 4:

[1832] The device analyzes the extracted text data and formats the ingredient information. The device applies regular expressions and pre-trained machine learning models to select the necessary information from the extracted text data and structure it as ingredient information.

[1833] Step 5:

[1834] The device sends the analyzed ingredient information to the server, which then converts the structured ingredient information into JSON format and sends it to the server via the API.

[1835] Step 6:

[1836] The server records the received ingredient information in the database. The server adds the received ingredient information to the database and updates it in a way that maintains consistency with existing inventory information.

[1837] Step 7:

[1838] The server automatically calculates the expiration date of ingredients and sets up a notification when the expiration date is approaching. Specifically, it calculates the purchase date and expiration date of ingredients, and based on that, sets up a notification to be sent to the user when the expiration date is approaching.

[1839] Step 8:

[1840] The user requests "Today's Menu" from the app. The user presses a dedicated button in the app to request a menu suggestion for the day.

[1841] Step 9:

[1842] The device sends the user's request to the server, which then sends the request parameters (such as meal timing and preferred genres) to the server via the API.

[1843] Step 10:

[1844] The server retrieves available ingredient information from the database, searches the user's inventory information using SQL queries, etc., and extracts a list of available ingredients.

[1845] Step 11:

[1846] The server provides the generation AI with ingredient information as input and instructs it to generate an appropriate recipe. Specifically, the server inputs the ingredient information in JSON format into the generation AI's API and requests it to generate a menu.

[1847] Step 12:

[1848] The generation AI generates multiple menus based on the input ingredient information and returns them to the server. The generation AI then refers to the ingredient information and past user feedback to generate and return the most appropriate recipe suggestions.

[1849] Step 13:

[1850] The server sends the generated menu to the user's device. The server also formats the generated recipes, converts them into a format that is easy for the user to view, and sends them to the device.

[1851] Step 14:

[1852] The device displays the generated menu suggestions to the user, and the device displays the received recipe information on the app's UI so that the user can check it.

[1853] Step 15:

[1854] When a user receives a menu suggestion, the emotion engine analyzes the user's facial expressions and voice, and sends the emotion data to the server. The user expresses their feelings about the suggested menu, and the device processes them using the emotion engine.

[1855] Step 16:

[1856] The server analyzes the emotion data and adjusts the menu suggestions based on the emotion data. The server prioritizes easy-to-prepare menu suggestions depending on the user's emotional state (e.g., if they feel tired).

[1857] Step 17:

[1858] Users can enter feedback on the menu. Users can enter their ratings and comments on the menu provided through the feedback form within the app.

[1859] Step 18:

[1860] The device sends the feedback to the server. The device converts the user's feedback information into JSON format and sends it to the server via the API.

[1861] Step 19:

[1862] The server receives the feedback and reflects it as learning data for the generation AI. The server stores the feedback information in a database and periodically uses it to update the generation AI model, improving the accuracy of future menu suggestions.

[1863] Example 2

[1864] 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."

[1865] Conventional food ingredient management and menu suggestion systems have the problem of not providing sufficient user convenience because they do not make suggestions based on the user's emotions or circumstances. Another issue is that they are unable to effectively manage available ingredients, resulting in food waste.

[1866] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for recording ingredient information in a database and updating inventory information, a means for generating a menu suitable for the user based on the ingredient information using a generation AI, and a means for adjusting the suggested content based on emotion data. This makes it possible to suggest an optimal menu according to the user's emotion and situation. It also promotes the effective use of ingredients and reduces food waste.

[1867] "User" refers to a person who uses the system to manage ingredients and receive menu suggestions.

[1868] "Terminal" refers to a device such as a smartphone or tablet operated by a user.

[1869] A "server" refers to a computer that manages and processes data at the center of a system.

[1870] "Means for taking images" refers to methods for obtaining images using the camera function of a smartphone, etc.

[1871] "Optical character recognition technology" refers to the technology that analyzes character information in an image and converts it into text data.

[1872] "Ingredient information" refers to information such as the name, quantity, purchase date, and expiration date of the food purchased by the user.

[1873] "Database" refers to data storage where ingredient information, feedback data, etc. are recorded and managed.

[1874] "Generative AI" refers to algorithms and functions that use artificial intelligence technology to automatically generate menus suitable for users.

[1875] "Emotion recognition technology" refers to technology that analyzes emotions from a user's facial expressions and voice data.

[1876] "Feedback" refers to the user's ratings and comments on the menu provided.

[1877] "Inventory information" refers to information such as the type, quantity, and expiration date of ingredients owned by the user.

[1878] "Request parameters" refer to the conditions and requests that a user specifies when requesting menu suggestions.

[1879] MODE FOR CARRYING OUT THE INVENTION

[1880] The present invention relates to an ingredient management and menu suggestion system that includes user emotion recognition. The system is composed of a terminal used by the user, a server, and an emotion engine, and its operation is described in detail below.

[1881] Hardware and Software

[1882] This system uses the user's smartphone or tablet device, a general-purpose cloud server (e.g., Amazon Web Services or Google Cloud Platform), and an API for emotion recognition (e.g., Microsoft Azure's Emotion API). The program is implemented in Python and JavaScript, and uses Google Cloud Vision API and Amazon Textract for OCR technology. Furthermore, a generative AI model (e.g., OpenAI's GPT-4) is used to generate the menu.

[1883] Program processing

[1884] 1. Image recognition of receipts

[1885] The user launches the app on their smartphone, logs in, and takes a photo of the receipt. A prompt appears saying, "Press the receipt capture button."

[1886] The device captures the receipt image, performs OCR processing using the Google Cloud Vision API, and extracts ingredient information from the receipt.

[1887] The device formats the extracted ingredient information (e.g., tomato, chicken, carrot) and sends it to the server. A prompt saying "Sending ingredient information" is displayed.

[1888] 2. Recording and managing food data

[1889] The server records the received ingredient information in a database (e.g., AWS RDS).

[1890] The server stores information such as ingredient name, quantity, purchase date, expiration date, etc., and compares it with existing inventory information to update it. A prompt saying "Inventory updating" is displayed on the user's terminal.

[1891] The server automatically calculates the expiration date of ingredients, and if the expiration date is approaching, a notification is sent to the user saying, "The expiration date is tomorrow."

[1892] 3. Menu creation requests and suggestions

[1893] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[1894] The terminal sends a request to the server, and the server retrieves available ingredient information from a database.

[1895] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates (detailed cooking instructions, additional ingredients, cooking time, etc.).

[1896] The generation AI will display a list of the generated menus on the screen along with the prompt, "The following menus have been suggested."

[1897] 4. Emotion Recognition by Emotion Engine

[1898] The smartphone's camera and microphone are used to collect facial and voice data just before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[1899] The data collected by the device is sent to Microsoft Azure's Emotion API for emotional analysis.

[1900] The device sends emotional data to the server, which then analyzes it and adjusts the suggestions. For example, if the device determines that the user is tired, it will suggest the following simple meal plan.

[1901] 5. Feedback and learning

[1902] The user tries the provided menu and then enters feedback (ratings and comments) in the app. The app prompts the user to "Enter your rating for the dish."

[1903] The terminal sends the feedback data to the server, which records it in a database.

[1904] The server updates the generative AI model based on the collected feedback and sentiment data to improve the accuracy of the next menu suggestion. A prompt will appear saying, "We've updated the model based on your feedback."

[1905] The present invention makes it possible to propose an optimal menu that matches the user's situation and emotions, thereby significantly improving the effective use of ingredients and convenience of daily life.

[1906] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1907] Step 1: Take a photo of your receipt and send it

[1908] The user launches the app and logs in.

[1909] The user takes a photo of the receipt. The prompt "Press the receipt capture button" appears.

[1910] The device captures the image of the receipt and analyzes it using OCR technology.

[1911] Input: Receipt image

[1912] Output: Text data of ingredients (e.g., tomato, chicken, carrot)

[1913] The device sends the acquired text data to the server. A prompt saying "Sending ingredient information" is displayed.

[1914] Step 2: Record and manage food ingredient data

[1915] The server records the received ingredient information in a database.

[1916] The server stores information such as the ingredient name, quantity, purchase date, and expiration date.

[1917] Input: Text data of ingredients

[1918] Output: Ingredient information recorded in the database

[1919] The server will update the data against existing inventory information and display the prompt "Updating inventory."

[1920] The server automatically calculates the expiration date of ingredients and notifies the user when the expiration date is approaching. A notification saying "Tomorrow is the expiration date" is sent.

[1921] Step 3: Menu creation request and suggestions

[1922] The user sends a request to the app saying, "I want today's menu suggestions." The app prompts the user, "Would you like today's menu suggestions?"

[1923] The device sends a request to the server.

[1924] The server obtains available ingredient information from the database.

[1925] Input: Request parameters

[1926] Output: Available ingredients information

[1927] The server inputs ingredient information into the generated AI model and generates multiple recipe candidates.

[1928] The generative AI generates information such as detailed cooking steps, additional ingredients, and cooking time, and returns it to the server.

[1929] Input: Ingredient information

[1930] Output: Multiple recipe candidates

[1931] The server sends the generated recipe information to the terminal, and a prompt saying "The following menu has been suggested" is displayed.

[1932] Step 4: Emotion Recognition with the Emotion Engine

[1933] The smartphone's camera and microphone are used to collect facial and voice data immediately before and after the user receives the menu suggestion. A prompt appears saying, "We're going to capture your facial expression."

[1934] The data collected by the device is sent to an emotion engine, which analyzes emotions.

[1935] Input: facial expression data, voice data

[1936] Output: Emotion data

[1937] The device will send the analyzed emotion data to the server. A prompt will appear saying "Sending emotion data."

[1938] The server analyzes the user's emotional data and adjusts the suggestions accordingly. For example, if it determines that the user is tired, it will prioritize simpler menus.

[1939] Step 5: Gather feedback and learn

[1940] The user tries the provided meal and then provides feedback in the app, prompting them to "rate the dish."

[1941] The terminal transmits the feedback data to the server.

[1942] The server receives the feedback data and records it in a database.

[1943] Input: User feedback

[1944] Output: Updated database

[1945] The server updates the generative AI model based on the feedback and emotion data. A prompt appears saying, "We've updated the model based on your feedback."

[1946] (Application example 2)

[1947] 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."

[1948] Conventional food ingredient management and menu suggestion systems do not take into account the user's emotional state, making it difficult to suggest meals that are in line with the user's actual needs and circumstances. Furthermore, because menus cannot be adjusted based on emotions, it is difficult to improve user satisfaction. For example, if the user is tired or busy, easy-to-prepare meals may not be suggested, which can be a burden on the user's experience.

[1949] 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.

[1950] In this invention, the server is equipped with an emotion engine that recognizes the user's emotions, and includes means for transmitting emotion data to the server, means for the server to analyze the emotion data and adjust menu suggestions based on the user's emotions, and means for preferentially suggesting easy-to-prepare menus based on the emotion recognition data, thereby enabling optimal menu suggestions to be made according to the user's situation.

[1951] "User" refers to a person who uses a terminal to take an image of a receipt, manages ingredient information, and receives menu suggestions.

[1952] "Terminal" refers to a device such as a smartphone or tablet operated by a user, which has the functionality to take images of receipts and recognize emotions.

[1953] "Optical character recognition technology" refers to technology that detects text within an image and converts it into digital text data.

[1954] "Food information" refers to data such as the food name, quantity, purchase date, and expiration date extracted from the receipt.

[1955] "Server" refers to a computer system that manages food ingredient data, analyzes emotional data, and uses generative AI to suggest menus.

[1956] A "database" refers to a collection of data that allows information to be systematically managed and easily accessed.

[1957] "Generative AI" refers to algorithms and models that use generative artificial intelligence technology to generate appropriate menus based on ingredient information and emotional data.

[1958] An "emotion engine" refers to software or hardware that analyzes a user's facial expressions and voice to recognize their emotional state.

[1959] "Emotion data" refers to information indicating the user's emotional state obtained by the emotion engine.

[1960] "Menu suggestion" refers to providing the user with specific recipes and cooking procedures for dishes that are generated based on ingredient information and emotion data.

[1961] "Feedback" refers to the evaluations and comments users make on menu suggestions, which are reflected in the learning of the generation AI.

[1962] A system embodying the present invention allows users to receive ingredient management and menu suggestions using emotion recognition technology. A detailed description of how to implement this system is provided below.

[1963] System Components

[1964] This system consists of the user's device (smartphone or tablet), server, emotion engine, etc. Specifically, it is as follows:

[1965] 1. Terminal

[1966] Using smart glasses or a smartphone, the user takes a picture of the receipt.

[1967] Extract text data from images using optical character recognition technology (Google Cloud Vision API).

[1968] An emotion engine is used to analyze the user's facial expressions and voice to obtain emotion data.

[1969] 2. Server

[1970] Corresponding ingredient information and emotion data are received and recorded and managed in a database (e.g., AWS RDS).

[1971] Using generative AI (OpenAI GPT model), appropriate menus are generated based on ingredient information and emotional data.

[1972] Using unsupervised learning, user feedback data is analyzed and the generative AI model is updated.

[1973] 3. Emotion Engine

[1974] Uses the Azure Emotion API to recognize emotions from the user's facial expressions and voice data.

[1975] The recognized emotion data is sent to the server and used to adjust menu suggestions.

[1976] System operation example

[1977] 1. Image recognition of receipts

[1978] The user takes a photo of the receipt with the smart glasses, and the device uses optical character recognition technology to extract text data from the image. The extracted ingredient information is sent to a server and recorded in a database.

[1979] 2. Emotion recognition

[1980] When a user requests a menu suggestion, the smart glasses analyze the user's facial expressions and voice using an emotion engine and send the resulting emotion data to the server.

[1981] 3. Menu suggestions

[1982] The server provides input to the AI ​​based on ingredient information and emotion data to generate an appropriate menu. The generated menu is then sent to the device and presented to the user.

[1983] 4. Emotion-Based Regulation

[1984] The server analyzes the emotional data and adjusts the menu suggestions, such as prioritizing easy-to-prepare dishes if the user is tired.

[1985] 5. Gather feedback and learn

[1986] When users send feedback on the menu, the data is stored on the server and reflected in the learning of the generation AI.

[1987] Specific examples

[1988] 1. After shopping at the supermarket, the user scans the receipt with the smart glasses. The system automatically extracts food data using OCR and manages the ingredient information.

[1989] 2. When food is nearing its expiration date, notifications are sent via smart glasses.

[1990] 3. When a user requests a menu suggestion, the smart glasses analyze their facial expressions and voice using an emotion engine and send the emotion data to the server.

[1991] 4. The server provides prompts to the generation AI based on ingredient information and emotion data, and generates an appropriate menu.

[1992] 5. The generated menu is displayed to the user, and user feedback is reflected in the next proposal.

[1993] Prompt Sentence Examples

[1994] Suggest an easy meal plan if the user has the following ingredients:

[1995] tomato

[1996] chicken meat

[1997] Carrots

[1998] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[1999] By combining these elements, it becomes possible to propose the most suitable menu according to the user's situation, thereby increasing user satisfaction.

[2000] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2001] Step 1:

[2002] The user takes a photo of the receipt using smart glasses or a smartphone. In this process, the image of the receipt is input and the image data captured by the user is output.

[2003] Step 2:

[2004] The device uses optical character recognition (OCR) technology to extract text data from the image of the receipt. The OCR software takes the image data as input, analyzes it, and outputs ingredient information, often in text form.

[2005] Step 3:

[2006] The device analyzes the extracted text data and formats the ingredient information. In this step, the OCR results (text data) are input, and organized ingredient information such as specific ingredient names, quantities, and purchase dates is output.

[2007] Step 4:

[2008] The terminal sends the analyzed ingredient information to the server. In this process, the organized ingredient information is the input, and the transmission action to the server is the output.

[2009] Step 5:

[2010] The server records the received ingredient information in the database and updates the inventory information. The ingredient information is input and the updated database is output.

[2011] Step 6:

[2012] The user requests a menu. The menu request is input and the request information is output.

[2013] Step 7:

[2014] The device uses an emotion engine to analyze the user's facial expressions and voice to obtain emotion data. New user actions (e.g., requests, questions, grins) are taken as input, and emotion data is output.

[2015] Step 8:

[2016] The emotion data is sent to the server, which then stores it. In this process, the emotion data is the input, and the sending and storing operations to the server are the output.

[2017] Step 9:

[2018] The server combines the ingredient information and emotion data and generates an appropriate menu using the generation AI. At this stage, the ingredient information and emotion data are input, and the generated menu (recipe information) is output. The generation AI uses the following prompt sentence:

[2019] Suggest an easy meal plan if the user has the following ingredients:

[2020] tomato

[2021] chicken meat

[2022] Carrots

[2023] Users are likely to be tired, so prioritize recipes that can be prepared quickly.

[2024] Step 10:

[2025] The server sends the generated menu to the terminal. The generated menu is the input, and the sending action to the terminal is the output.

[2026] Step 11:

[2027] The terminal displays the generated menu to the user. The terminal receives the menu (recipe information) received from the server as input and visually displays it to the user.

[2028] Step 12:

[2029] The user submits feedback on the menu. Here, the user's feedback information is input and feedback data is output.

[2030] Step 13:

[2031] The feedback data is received by the server and recorded in a database. The feedback information is the input and the updated database is the output.

[2032] Step 14:

[2033] The server uses the collected feedback and emotion data to train a generative AI model. At this stage, the feedback and emotion data are input, and an updated generative AI model is output.

[2034] 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.

[2035] 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.

[2036] 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.

[2037] 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.

[2038] 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.

[2039] 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.

[2040] 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).

[2041] 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.

[2042] 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."

[2043] 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.

[2044] 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).

[2045] 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.

[2046] 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.

[2047] 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.

[2048] 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.

[2049] 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.

[2050] 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.

[2051] 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.

[2052] 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.

[2053] 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.

[2054] 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.

[2055] The following is further disclosed regarding the above embodiment.

[2056] (Claim 1)

[2057] A means for a user to take an image of a receipt;

[2058] means for extracting text data from the image by the terminal using optical character recognition technology;

[2059] A device for analyzing ingredient information from the extracted text data;

[2060] A means for transmitting the analyzed ingredient information to a server by the terminal;

[2061] A means for the server to record ingredient information in a database and update inventory information;

[2062] A means for the server to generate a menu suitable for the user based on the ingredient information using a generation AI;

[2063] means for transmitting the generated menu to a terminal and presenting it to a user;

[2064] A means of collecting user feedback and reflecting it in the learning of the generative AI,

[2065] A system including:

[2066] (Claim 2)

[2067] 10. The system of claim 1, further comprising means for the terminal to automatically calculate expiration dates of ingredients and set notifications for ingredients approaching their expiration date.

[2068] (Claim 3)

[2069] 10. The system of claim 1, wherein the server includes means for providing input to the generation AI based on user request parameters to generate an appropriate menu.

[2070] "Example 1"

[2071] (Claim 1)

[2072] A means for a user to take an image of a receipt;

[2073] means for extracting text data from the image by the terminal using optical character recognition technology;

[2074] A device for analyzing ingredient information from the extracted text data;

[2075] A means for transmitting the analyzed ingredient information to a server by the terminal;

[2076] A means for the server to record ingredient information in a database and update inventory information;

[2077] A means for the server to generate a menu suitable for the user based on the ingredient information using a generation AI model;

[2078] A means for the server to provide ingredient information as prompt sentences to the generation AI model and generate recipe candidates;

[2079] means for transmitting the generated menu to a terminal and presenting it to a user;

[2080] A means of collecting user feedback and incorporating it into the training of generative AI models;

[2081] A system including:

[2082] (Claim 2)

[2083] 10. The system of claim 1, further comprising means for the terminal to automatically calculate expiration dates of ingredients and set notifications for ingredients approaching their expiration date.

[2084] (Claim 3)

[2085] 10. The system of claim 1, wherein the server includes means for providing input to the generative AI model based on user request parameters to generate an appropriate menu.

[2086] "Application Example 1"

[2087] (Claim 1)

[2088] A means for a user to take an image of a receipt;

[2089] means for extracting text data from the image by the terminal using optical character recognition technology;

[2090] A device for analyzing ingredient information from the extracted text data;

[2091] A means for transmitting the analyzed ingredient information to a server by the terminal;

[2092] A means for the server to record ingredient information in a database and update inventory information;

[2093] A means for the server to generate a menu suitable for the user based on the ingredient information using a generation AI;

[2094] means for transmitting the generated menu to a terminal and presenting it to a user;

[2095] A means of collecting user feedback and reflecting it in the learning of the generative AI,

[2096] A means for the server to automatically order from a food delivery service any missing portion of the menu proposed to the user;

[2097] A system including:

[2098] (Claim 2)

[2099] 10. The system of claim 1, further comprising means for the terminal to automatically calculate expiration dates of ingredients and set notifications for ingredients approaching their expiration date.

[2100] (Claim 3)

[2101] 10. The system of claim 1, wherein the server includes means for providing input to the generation AI based on user request parameters to generate an appropriate menu.

[2102] "Example 2: Combining Emotion Engines"

[2103] (Claim 1)

[2104] a means for a user to capture an image;

[2105] means for extracting text data from the image by the terminal using optical character recognition technology;

[2106] A device for analyzing ingredient information from the extracted text data;

[2107] A means for transmitting the analyzed ingredient information to a server by the terminal;

[2108] A means for the server to record ingredient information in a database and update inventory information;

[2109] A means for the server to generate a menu suitable for the user based on the ingredient information using a generation AI;

[2110] means for transmitting the generated menu to a terminal and presenting it to a user;

[2111] A device that uses emotion recognition technology to analyze emotions from facial expressions and voice data of a user;

[2112] a means for adjusting the suggestions based on the emotion data;

[2113] A means of collecting user feedback and reflecting it in the learning of the generative AI,

[2114] A system including:

[2115] (Claim 2)

[2116] 10. The system of claim 1, further comprising means for the terminal to automatically calculate expiration dates of ingredients and set notifications for ingredients approaching their expiration date.

[2117] (Claim 3)

[2118] 10. The system of claim 1, wherein the server includes means for providing input to the generation AI based on user request parameters to generate an appropriate menu.

[2119] "Application example 2 when combining emotion engines"

[2120] (Claim 1)

[2121] A means for a user to take an image of a receipt;

[2122] means for extracting text data from the image by the terminal using optical character recognition technology;

[2123] A device for analyzing ingredient information from the extracted text data;

[2124] A means for transmitting the analyzed ingredient information to a server by the terminal;

[2125] A means for the server to record ingredient information in a database and update inventory information;

[2126] A means for the server to generate a menu suitable for the user based on the ingredient information using a generation AI;

[2127] means for transmitting the generated menu to a terminal and presenting it to a user;

[2128] a means for transmitting emotion data to a server, the emotion engine being provided for recognizing the emotion of a user;

[2129] means for the server to analyze the emotion data and adjust menu suggestions based on the user's emotion;

[2130] A method to prioritize easy-to-prepare menu suggestions based on emotion recognition data,

[2131] A means of collecting user feedback and reflecting it in the learning of the generative AI,

[2132] A system including:

[2133] (Claim 2)

[2134] 10. The system of claim 1, further comprising means for the terminal to automatically calculate expiration dates of ingredients and set notifications for ingredients approaching their expiration date.

[2135] (Claim 3)

[2136] The system of claim 1, wherein the server includes means for providing input to the generation AI based on the user's request parameters and emotion data to generate an appropriate menu. [Explanation of symbols]

[2137] 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 take an image of a receipt; means for extracting text data from the image by the terminal using optical character recognition technology; A device for analyzing ingredient information from the extracted text data; A means for transmitting the analyzed ingredient information to a server by the terminal; A means for the server to record ingredient information in a database and update inventory information; A means for the server to generate a menu suitable for the user based on the ingredient information using a generation AI; means for transmitting the generated menu to a terminal and presenting it to a user; A means of collecting user feedback and reflecting it in the learning of the generative AI, A system including:

2. The system of claim 1 further comprising means for the terminal to automatically calculate expiration dates of ingredients and set notifications regarding ingredients approaching their expiration date.

3. 2. The system of claim 1, wherein the server includes means for providing input to the generation AI to generate an appropriate menu based on user request parameters.

Images