System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving and analyzing a cooking video; means for instructing a user on a cooking procedure based on an analysis result; means for monitoring an action of the user and detecting an action different from the instructed procedure; means for aggregating action data and feedback from a plurality of users and generating an optimal recipe; and means for providing the generated recipe to other users.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When cooking using existing recipes, it is assumed that many people follow the same steps, and therefore support tailored to individual users' cooking experience and skill level is not adequately provided. Furthermore, even if there is room for improvement, conventional recipes are fixed, making it difficult to dynamically improve them based on user feedback or actual cooking data. As a result, people who are not good at cooking often fail due to difficult recipes, while skilled cooks tend to overlook efficient steps. The present invention aims to solve these problems and improve recipes and the quality of users' cooking experiences. [Means for solving the problem]

[0005] The present invention provides a means for receiving and analyzing cooking videos, a means for instructing users on cooking procedures based on the analysis results, and a means for monitoring user behavior and detecting deviations from the instructed procedures. Furthermore, the present invention proposes a system that includes a means for aggregating behavioral data and feedback from multiple users, generating optimal recipes, and providing them to other users. This allows users to cook using efficient recipes provided by the system while receiving support tailored to their individual cooking levels. Furthermore, recipes are dynamically improved based on user feedback, reducing the difficulty of cooking and increasing efficiency.

[0006] "Cooking videos" are video data that record the cooking process.

[0007] "Analysis" is the process of dividing the video into frames and analyzing the content to extract cooking steps and ingredient manipulations.

[0008] "Cooking procedure" refers to the specific work instructions and order in which to cook food.

[0009] "Instructions" means informing the user of the specific cooking tasks that should be performed.

[0010] "Monitoring" refers to observing and recording user behavior in real time.

[0011] "Behavioral data" is data that records the cooking operations and procedures that a user actually performs.

[0012] "Feedback" refers to ratings and opinions provided by users, including information that the system uses for future improvements.

[0013] The "optimal recipe" is a recipe generated based on the highest efficiency and taste ratings, based on the behavioral data and feedback of multiple users.

[0014] "Learning" means that the system acquires new information from past and new data and uses it to improve its behavior and decisions.

[0015] "Quick Tips" are short pieces of advice provided to help users perform specific cooking steps or ingredient selections more effectively. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention provides a system that loads cooking videos into AI and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a terminal, and a user. The details are explained below.

[0038] System Configuration

[0039] server

[0040] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses AI models to analyze various data and provide users with cooking instructions tailored to their needs.

[0041] Terminal

[0042] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the information to the server.

[0043] user

[0044] Users upload cooking videos, follow instructions on their devices to cook, and then provide feedback to the system after completing the dish.

[0045] Program processing

[0046] Video upload and analysis

[0047] 1. Users

[0048] Users film their cooking and upload it to a server through the application.

[0049] 2. Terminal

[0050] The device sends the video selected by the user to the server.

[0051] 3. Server

[0052] The server receives the video and passes it to the AI ​​model to begin analysis.

[0053] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[0054] Providing real-time support

[0055] 1. Server

[0056] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[0057] 2. Terminal

[0058] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[0059] 3. Users

[0060] The user follows the displayed instructions to proceed with cooking.

[0061] User behavior analysis

[0062] 1. Terminal

[0063] The device captures user actions using cameras and sensors and transmits them to the server in real time.

[0064] 2. Server

[0065] The server analyzes the user's behavioral data and compares it with the instructions.

[0066] If different behavior is detected, the data is passed to the AI ​​model and saved as learning data.

[0067] Feedback and Learning

[0068] 1. Users

[0069] Users rate the finished dish and enter their rating into the app.

[0070] 2. Terminal

[0071] The terminal transmits the user's evaluation data to the server.

[0072] 3. Server

[0073] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[0074] It also aggregates other users' rating data to generate optimal recipes.

[0075] Recipe Improvement and Serving

[0076] 1. Server

[0077] The server learns more efficient cooking procedures based on aggregated behavioral data and feedback.

[0078] Generate new optimized recipes and tips and share them with other users.

[0079] 2. Terminal

[0080] The device will display new recipes and tips to the user.

[0081] Specific examples

[0082] Example 1: Uploading and analyzing a video

[0083] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[0084] Example 2: Real-time support

[0085] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[0086] Example 3: Behavioral analysis and feedback

[0087] If user A actually stir-fries vegetables for only 3 minutes, the device will capture this behavior and send it to the server, which will then identify the different behavior and store it in the AI ​​model.

[0088] Example 4: Rating and improving recipes

[0089] User B also cooks the dish and sends a rating to the server saying it was "delicious." The server uses this rating data to provide a new recipe to the next user.

[0090] In this way, recipes are dynamically improved based on user behavior and feedback, helping everyone cook better.

[0091] The processing flow will be explained below.

[0092] Step 1:

[0093] user

[0094] Cooking videos are filmed and uploaded to the system through the application.

[0095] Step 2:

[0096] Terminal

[0097] Send the uploaded video to the server.

[0098] Step 3:

[0099] server

[0100] Receives video files and requests the AI ​​model to analyze them.

[0101] Step 4:

[0102] server

[0103] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[0104] Step 5:

[0105] server

[0106] Based on the analysis results, the next cooking procedure to be carried out is determined and sent to the terminal.

[0107] Step 6:

[0108] Terminal

[0109] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[0110] Step 7:

[0111] user

[0112] Follow the displayed instructions to continue cooking.

[0113] Step 8:

[0114] Terminal

[0115] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[0116] Step 9:

[0117] server

[0118] Analyze the received behavioral data and confirm that it matches the instructed procedures.

[0119] Step 10:

[0120] server

[0121] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[0122] Step 11:

[0123] user

[0124] Once cooking is complete, the food is tasted and evaluated.

[0125] Step 12:

[0126] Terminal

[0127] Send user rating data to the server.

[0128] Step 13:

[0129] server

[0130] Provide feedback to the AI ​​model based on the collected evaluation data.

[0131] Step 14:

[0132] server

[0133] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[0134] Step 15:

[0135] server

[0136] The generated new recipes and tips are sent to the device.

[0137] Step 16:

[0138] Terminal

[0139] The device will display new recipes and tips to the user.

[0140] Step 17:

[0141] user

[0142] Use new recipes and advice to prepare your next meal.

[0143] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[0144] Example 1

[0145] 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."

[0146] It is difficult for beginners and inexperienced users to cook accurately while following a recipe. It is also difficult to provide optimal support based on each individual's cooking skills and preferences. Furthermore, the inability to fully utilize user behavioral data and feedback limits improvements to the quality of recipes. This creates the challenge of making high-quality meals due to the lack of appropriate cooking support.

[0147] 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.

[0148] In this invention, the server includes means for receiving and analyzing cooking videos from users, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior with cameras and sensors and detecting behavior that deviates from the instructed procedures, means for aggregating behavioral data and feedback from multiple users to generate optimal recipes, and means for providing the generated recipes and cooking advice to other users. This makes it possible to provide optimal cooking support based on each user's skills and preferences and to improve the quality of recipes by utilizing accumulated data.

[0149] "User" refers to an individual who performs cooking operations, uploads videos, and rates them.

[0150] "Server" refers to a computing device that analyzes received cooking videos, generates cooking instructions, and aggregates user behavior data and feedback.

[0151] "Terminal" refers to a device such as a user's smartphone, tablet, or PC, which displays cooking instructions from the server and monitors the user's behavior.

[0152] "Means for receiving and analyzing videos" refers to the technology in which a server receives cooking videos uploaded by users and analyzes their content using a generative AI model.

[0153] "Means for instructing the user on cooking instructions" refers to a technology in which the analyzed cooking instructions are sent from the server to the terminal, and the terminal displays them to the user.

[0154] "Means of monitoring using cameras and sensors" refers to technology that uses cameras and sensors installed on the device to monitor the user's cooking operations in real time and transmits that data to a server.

[0155] "Means for aggregating behavioral data and feedback" refers to the technology by which a server collects user behavioral data and evaluation data and statistically analyzes it.

[0156] "Means for generating optimal recipes" refers to technology in which an AI model creates more efficient and appropriate cooking procedures and recipes based on aggregated data.

[0157] "Means for providing generated recipes and cooking advice" refers to technology for transmitting optimized recipes and cooking advice from a server to other users and displaying them on their terminals.

[0158] "Means for collecting evaluation data" refers to the technology that collects food evaluations from multiple users and stores them in a database.

[0159] "Means for training an AI model" refers to the technology of inputting collected behavioral data and evaluation data into an AI model and allowing the model to acquire new knowledge through its learning process.

[0160] This invention relates to a system that uses AI to load cooking videos and provide step-by-step support in real time. The main components of the system are a server, a terminal, and a user, all of which work together. The details of the system and how to use it are explained below.

[0161] System configuration

[0162] server

[0163] The server plays a central role in this system. It receives cooking videos, analyzes them, generates instructions, collects behavioral data, and generates optimal recipes. Specifically, the server analyzes various data using a generative AI model (e.g., OpenAI's GPT-4).

[0164] Terminal

[0165] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends it to the server. The terminal is also equipped with a camera and sensors that capture the user's cooking operations in real time.

[0166] User

[0167] Users film cooking videos and upload them to the server via the application. They then follow instructions on their device to cook, and once the dish is complete, they provide feedback to the system.

[0168] Program processing

[0169] Video upload and analysis

[0170] 1. A user shoots a cooking video on their smartphone. The user launches the application, selects the recorded video, and presses the upload button.

[0171] 2. The device sends the video uploaded by the user to the server.

[0172] 3. The server receives the video data and analyzes the video using the generative AI model, using the prompt "Please extract the cooking steps and ingredients from this video." Based on this prompt, the AI ​​model extracts the cooking steps and ingredients from the video in text format.

[0173] Providing real-time support

[0174] 1. The server receives the analysis results and determines the next cooking step, for example, "sauté the vegetables for 5 minutes."

[0175] 2. The device displays the cooking instructions sent from the server to the user, who then follows the instructions to proceed with the cooking.

[0176] User behavior analysis

[0177] 1. The device captures the user's cooking operations using cameras and sensors and transmits them to the server in real time, for example, monitoring frying time and temperature.

[0178] 2. The server analyzes the received behavioral data and compares the instructed steps with the actual behavior. If any discrepancies are detected, the data is passed to the generative AI model and saved as training data.

[0179] Feedback and Learning

[0180] 1. After the cooking is complete, the user enters their evaluation into the app, such as "It was delicious" or "I wish it was a little saltier."

[0181] 2. The terminal sends the evaluation data entered by the user to the server.

[0182] 3. The server aggregates the evaluation data and provides it as feedback to the generative AI model. It also aggregates evaluation data from other users to generate the optimal recipe.

[0183] Recipe Improvement and Serving

[0184] 1. The server learns more efficient cooking procedures based on aggregated behavioral and feedback data, and uses generative AI models to create new recipes and cooking advice.

[0185] 2. The device displays the newly generated recipes and advice to the user.

[0186] Specific examples

[0187] Example 1: Uploading and analyzing a video

[0188] User A films a cooking video on their smartphone and uploads it to a server via an application. The device sends the video to the server, which then analyzes it using a generative AI model (e.g., OpenAI's GPT-4) based on the prompt, "Please extract the cooking steps and ingredients from this video." The AI ​​model then generates the instruction, "Stir-fry the vegetables for 5 minutes."

[0189] Example 2: Real-time support

[0190] The server sends the generated instructions to the terminal, and the terminal displays the instruction "Stir-fry vegetables for 5 minutes" to User A. User A cooks according to the instructions.

[0191] Example 3: Behavioral analysis and feedback

[0192] If user A actually stir-fries the vegetables for only 3 minutes, the device captures this behavior and sends it to the server, which then identifies the different behavior and stores it in the generative AI model.

[0193] Example 4: Rating and improving recipes

[0194] User B also cooks the dish and sends a rating of "delicious" to the server. Based on this rating data, the server provides new recipes and advice to other users.

[0195] In this way, recipes are constantly improved based on user actions and feedback, helping everyone cook better.

[0196] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0197] Step 1:

[0198] The user shoots a cooking video on their smartphone, launches the application, selects the recorded video, and presses the upload button.

[0199] Input: Filmed cooking video

[0200] Output: Video file selected by user

[0201] Step 2:

[0202] The terminal receives a video upload request from the user and transmits the video file to the server.

[0203] Input: User's video upload request and video file

[0204] Output: Video file sent to the server

[0205] Step 3:

[0206] The server receives the video data and sends an analysis prompt to the generative AI model. The prompt is "Please extract the cooking steps and ingredients from this video." The AI ​​model analyzes the video and outputs the cooking steps and ingredients in text format.

[0207] Input: Video file sent to the server, analysis prompt

[0208] Output: Extracted text data of cooking instructions and ingredients

[0209] Step 4:

[0210] The server receives the analysis results and determines the next cooking steps, which are then used to provide specific instructions to the user.

[0211] Input: Extracted text data of cooking instructions and ingredients

[0212] Output: Cooking instructions text to the user

[0213] Step 5:

[0214] The device receives cooking instructions from the server and displays them to the user. For example, specific instructions such as "sauté vegetables for 5 minutes" are displayed. The user then follows the displayed instructions to cook.

[0215] Input: Cooking instruction text from the server

[0216] Output: Cooking instructions displayed to the user

[0217] Step 6:

[0218] The device captures the user's cooking operations in real time using cameras and sensors and sends the data, including frying time and temperature, to a server.

[0219] Input: User's real-time cooking operation data

[0220] Output: Cooking operation data sent to the server

[0221] Step 7:

[0222] The server analyzes the behavioral data and compares the instructions with the actual behavior. For example, it checks whether the user actually stir-fried vegetables for five minutes. If a different behavior is detected, the data is passed to the generative AI model for future feedback and learning.

[0223] Input: Cooking operation data sent

[0224] Output: Analyzed behavior data, detected abnormal behavior data

[0225] Step 8:

[0226] After the user has finished cooking, they can enter their evaluation of the dish through the application, for example, by entering comments such as "It was delicious" or "It wasn't spicy enough."

[0227] Input: User food rating data

[0228] Output: Rating data input to the app

[0229] Step 9:

[0230] The terminal transmits the user's evaluation data to the server.

[0231] Input: Food rating data from users

[0232] Output: Rating data sent to the server

[0233] Step 10:

[0234] The server aggregates the evaluation data and provides it as feedback to the generative AI model, which also aggregates evaluation data from other users to generate the optimal recipe.

[0235] Input: Aggregated rating data

[0236] Output: Feedback data for generative AI model, optimal recipe data

[0237] Step 11:

[0238] The server generates new recipes and cooking advice based on the collected behavioral data and feedback data, and provides the generated recipes and advice to other users.

[0239] Input: Behavioral data, feedback data

[0240] Output: New recipes, cooking advice

[0241] Step 12:

[0242] The device displays the newly generated recipes and advice to the user, who can then follow the new recipes and advice to create even better dishes.

[0243] Input: New recipes and cooking advice from the server

[0244] Output: New recipes and cooking advice displayed to the user

[0245] (Application example 1)

[0246] 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."

[0247] In recent years, the number of beginners and busy people has increased, and the need for easy and efficient cooking has grown. However, existing cooking support systems lack sufficient support for how to use individual ingredients and real-time cooking procedures, making it difficult for users to proceed with cooking at the appropriate time. It is also difficult to receive real-time feedback during the cooking process, resulting in an increased failure rate.

[0248] 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.

[0249] In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior and detecting behavior that differs from the instructed procedures, means for aggregating behavioral data and feedback from multiple users and generating optimal recipes, means for providing the generated recipes to other users, means for recognizing ingredients with a camera on a smart device and generating corresponding recipes, and means for displaying cooking procedures on a visual display in real time, thereby enabling users to efficiently select ingredients in the supermarket and receive real-time support when cooking.

[0250] "Cooking videos" refer to footage recorded by users during the cooking process, and cooking steps are extracted by analyzing this video data.

[0251] "Analysis" refers to the process of analyzing the received cooking video using AI models and image recognition technology, and extracting the cooking steps and ingredient manipulations in text format.

[0252] "Cooking procedure" refers to each step in the process of cooking ingredients, specifically including operations such as preparing ingredients, cutting, frying, and boiling.

[0253] "Users" refer to people who use this system to cook, upload videos, check cooking instructions, and provide feedback.

[0254] "Monitoring" refers to the process of monitoring the user's cooking behavior using cameras and sensors and sending the data to a server in real time.

[0255] "Behavioral data" refers to data on the cooking actions actually performed by the user, and includes specific action data obtained from video and sensors.

[0256] "Feedback" refers to the user inputting their evaluation and impressions of the completed dish and sending it to the system, which the system uses as learning data.

[0257] The "optimal recipe" is a recipe generated based on behavioral data and feedback from multiple users, and improves taste and cooking efficiency.

[0258] "Smart device" refers to an electronic device with a camera and display function, and specifically includes smart glasses and smartphones.

[0259] "Ingredient recognition" refers to capturing an image of an ingredient using a smart device's camera and analyzing that image to identify a specific ingredient.

[0260] "Visual display" refers to the screen or display of a smart device, in this case intended to show cooking instructions or recipes to the user in real time.

[0261] This invention provides a system that uses AI to read cooking videos and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a device, and a user. The details are described below.

[0262] System Configuration

[0263] server

[0264] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses a generative AI model to analyze various data and provide users with cooking instructions tailored to their needs. It also optimizes recipes based on user feedback. Specifically, it uses TensorFlow or PyTorch to operate a deep learning model.

[0265] Terminal

[0266] The user's device (smart glasses, smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the results to the server. In addition, the terminal recognizes ingredients in real time using the user's camera, and displays the results analyzed by the server on the display. The terminal usually uses an image recognition library such as OpenCV.

[0267] user

[0268] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system, including evaluations of cooking efficiency and taste. User behavior data is captured by cameras and sensors and sent to the server in real time.

[0269] Explanation of program processing

[0270] Video upload and analysis

[0271] 1. The user takes a video of the cooking using a smartphone or other device and uploads it to the server via the application.

[0272] 2. The device sends the video selected by the user to the server.

[0273] 3. The server receives the video and passes it to the AI ​​model to begin analysis. The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[0274] Providing real-time support

[0275] 1. The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[0276] 2. The device displays the cooking instructions to the user, for example, "Sauté the vegetables for 5 minutes."

[0277] 3. The user follows the displayed instructions to proceed with cooking.

[0278] Food ingredient recognition using smart devices

[0279] 1. The device sends the ingredients identified by the smart glasses camera to the server.

[0280] 2. The server analyzes the ingredients, generates a corresponding recipe, and sends it to the device.

[0281] 3. The device will display the recipe and cooking instructions on the screen, for example, "Here's how to make a salad using these carrots."

[0282] Specific examples

[0283] Imagine a user is in a supermarket, putting on smart glasses and pointing a carrot at the camera.

[0284] The device recognizes the carrot and sends the data to the server.

[0285] The server generates a recipe based on carrots and sends the recipe and cooking instructions for "Healthy Salad with Carrots" to the terminal.

[0286] The device displays this information on its screen and guides the user through the cooking process in real time.

[0287] Example prompts to input to the generative AI model

[0288] The user will take a photo of the ingredients and send it to us, and we will generate a recommended recipe using those ingredients. We will also output cooking instructions in real time.

[0289] In this way, users can efficiently select ingredients and receive real-time cooking instructions while shopping in a physical store.

[0290] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0291] Step 1:

[0292] The user takes a picture of the food with the camera on the smart glasses. The camera captures the food image data and stores it on the device. The input is the food image taken by the camera, and the output is the image data stored on the device.

[0293] Step 2:

[0294] The device sends the image of the food taken by the user to the server. The image data is sent via the HTTPS protocol. The input is the image data stored on the device, and the output is the image data sent to the server.

[0295] Step 3:

[0296] The server passes the received image data to the generative AI model for analysis. This analysis uses image recognition technology (e.g., OpenCV) to recognize ingredients and inputs that information into the AI ​​model. The input is the image data sent to the server, and the output is the recognized ingredient information.

[0297] Step 4:

[0298] The server generates an appropriate recipe based on the recognized ingredient information. At this time, the generative AI model uses past data and feedback to propose optimal cooking procedures. The input is the recognized ingredient information and past feedback data, and the output is the generated recipe and cooking procedures.

[0299] Step 5:

[0300] The server sends the generated recipe and cooking instructions to the terminal. Again, the HTTPS protocol is used. The input is the generated recipe and cooking instructions, and the output is the recipe and cooking instructions sent to the terminal.

[0301] Step 6:

[0302] The terminal displays the received recipe and cooking instructions on a visual display, allowing the user to see the next action in real time. The input is the recipe and cooking instructions sent to the terminal, and the output is the cooking instructions shown on the display.

[0303] Step 7:

[0304] The user follows the visual display to proceed with the cooking. For example, if the instruction is "sauté carrots for 5 minutes," the user follows the instructions to cook. The output is the cooking action performed by the user.

[0305] Step 8:

[0306] The device monitors the user's cooking behavior using cameras and sensors and sends the data to a server. The input is the user's cooking behavior data, and the output is the behavior data sent to the server.

[0307] Step 9:

[0308] The server analyzes the received behavioral data and detects any behavior that deviates from the instructed procedure. Furthermore, this behavioral data is provided as feedback to the AI ​​model and saved as training data for the model. The input is the behavioral data sent to the server, and the output is the training data provided to the AI ​​model.

[0309] Step 10:

[0310] The user rates the cooked dish and inputs the rating into the terminal. The terminal sends the rating data to the server. The input is the rating data entered by the user, and the output is the rating data sent to the server.

[0311] Step 11:

[0312] The server provides optimal recipes to other users based on the received rating data. It also improves the recipes using the aggregated rating data and behavioral data. The input is the rating data and behavioral data sent to the server, and the output is an improved recipe and helpful advice.

[0313] 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.

[0314] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[0315] System Configuration

[0316] server

[0317] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotion data from the emotion engine and adjusts cooking procedures and timings.

[0318] Terminal

[0319] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server.

[0320] Emotion Engine

[0321] The emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice.

[0322] user

[0323] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[0324] Program processing

[0325] Video upload and analysis

[0326] 1. Users

[0327] Users film their cooking and upload it to a server through the application.

[0328] 2. Terminal

[0329] The device sends the video selected by the user to the server.

[0330] 3. Server

[0331] The server receives the video and asks the AI ​​model to analyze it.

[0332] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[0333] Providing real-time support

[0334] 1. Server

[0335] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[0336] 2. Terminal

[0337] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[0338] 3. Users

[0339] The user follows the displayed instructions to proceed with cooking.

[0340] User behavior analysis and emotion recognition

[0341] 1. Terminal

[0342] The device captures user actions in real time using cameras and sensors and sends them to the emotion engine.

[0343] 2. Emotion Engine

[0344] The emotion engine analyzes facial expressions and voice to recognize the user's emotional state.

[0345] The recognized emotion data is sent to the server.

[0346] 3. Server

[0347] The server analyzes the user's behavioral and emotional data and checks whether it matches the instructed steps.

[0348] If different behaviors or emotional changes are detected, the data is passed to the AI ​​model and saved as learning data.

[0349] Feedback and Learning

[0350] 1. Users

[0351] Users rate the finished dish and enter their rating into the app.

[0352] 2. Terminal

[0353] The terminal transmits the user's evaluation data to the server.

[0354] 3. Server

[0355] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[0356] It also aggregates other users' rating data to generate optimal recipes.

[0357] Recipe Improvement and Serving

[0358] 1. Server

[0359] The server learns more efficient cooking procedures based on aggregated behavioral data, emotional data, and feedback.

[0360] Generate new optimized recipes and tips and share them with other users.

[0361] 2. Terminal

[0362] The device will display new recipes and tips to the user.

[0363] Specific examples

[0364] Example 1: Uploading and analyzing a video

[0365] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[0366] Example 2: Real-time support

[0367] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[0368] Example 3: Behavioral analysis and emotion recognition

[0369] If User A actually stir-fries vegetables for only 3 minutes, the device will capture User A's actions and facial expressions with the camera and send them to the server. The emotion engine will recognize User A's emotional state and report it to the server. The server will review the different behavioral and emotional data and store it in the AI ​​model.

[0370] Example 4: Rating and improving recipes

[0371] User B also cooks the dish and sends a rating of "delicious" to the server. The server uses this rating data and emotion data to provide new recipes and advice to the next user.

[0372] In this way, recipes are dynamically improved based on user behavior, sentiment, and feedback, helping everyone cook better.

[0373] The processing flow will be explained below.

[0374] Step 1:

[0375] user

[0376] Cooking videos are filmed and uploaded to the system through the application.

[0377] Step 2:

[0378] Terminal

[0379] Send the uploaded video to the server.

[0380] Step 3:

[0381] server

[0382] Receives video files and requests the AI ​​model to analyze them.

[0383] Step 4:

[0384] server

[0385] The AI ​​model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format.

[0386] Step 5:

[0387] server

[0388] Based on the analysis results, the next cooking procedure is determined and the instructions are sent to the terminal.

[0389] Step 6:

[0390] Terminal

[0391] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[0392] Step 7:

[0393] user

[0394] Follow the displayed instructions to continue cooking.

[0395] Step 8:

[0396] Terminal

[0397] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[0398] Step 9:

[0399] Emotion Engine

[0400] It analyzes the user's facial expressions and voice to recognize their emotional state, and sends the acquired emotional data to the server.

[0401] Step 10:

[0402] server

[0403] The received behavioral and emotional data is analyzed and compared with the instructed procedures.

[0404] Step 11:

[0405] server

[0406] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[0407] Step 12:

[0408] server

[0409] Based on the recognized emotional data, the cooking instructions and timing of advice are adjusted.

[0410] Step 13:

[0411] user

[0412] Once cooking is complete, the food is tasted and evaluated.

[0413] Step 14:

[0414] Terminal

[0415] Send user rating data to the server.

[0416] Step 15:

[0417] server

[0418] Provide feedback to the AI ​​model based on the collected evaluation data.

[0419] Step 16:

[0420] server

[0421] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[0422] Step 17:

[0423] server

[0424] The generated new recipes and tips are sent to the device.

[0425] Step 18:

[0426] Terminal

[0427] The device will display new recipes and tips to the user.

[0428] Step 19:

[0429] user

[0430] Use new recipes and advice to prepare your next meal.

[0431] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[0432] Example 2

[0433] 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."

[0434] Conventional cooking assistance systems can only monitor user behavior and lack support that reflects user emotions. Furthermore, methods that improve recipes based solely on user feedback may not provide effective real-time cooking assistance. As a result, follow-up during cooking is insufficient, resulting in a lack of improvement in the user's cooking experience.

[0435] 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 means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and emotions and detecting behavioral and emotional changes that differ from the instructed procedures, means for aggregating behavioral data, emotional data, and feedback from multiple users and generating optimal cooking procedures, and means for providing the generated cooking procedures and advice to other users. This enables real-time cooking assistance that reflects both the user's behavior and emotions.

[0436] "Cooking videos" are digital data that record cooking steps and how to prepare ingredients.

[0437] "Analysis" refers to the process of analyzing cooking videos based on an AI model and extracting cooking steps and ingredient manipulations in text format.

[0438] A "cooking procedure" is each step required to complete a dish, and includes specific actions, time, and conditions.

[0439] "User" refers to an individual user of the cooking assistance system.

[0440] "Monitoring" is the means of observing and recording a user's behavior and emotional state in real time.

[0441] "Emotional changes" refers to changes in emotions recognized by analyzing changes in the user's facial expressions and voice.

[0442] "Feedback" refers to data on the evaluations and impressions users provide about the completed dishes.

[0443] The "optimal cooking procedure" is a method generated as the most effective and efficient cooking procedure based on the user's behavioral data, emotional data, and feedback.

[0444] "Advice" is information containing additional instructions or suggestions that will be helpful during cooking or for your next cooking session.

[0445] A "server" is a computer system that performs central processing such as analysis, data collection, and instruction generation.

[0446] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[0447] System Configuration

[0448] server

[0449] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotional data from the emotion engine and adjusts cooking steps and timing. Specifically, the server receives the video and requests analysis from the AI ​​model. The AI ​​model analyzes the video and extracts cooking steps and ingredient manipulations for each frame in text format.

[0450] Terminal

[0451] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server. The terminal can capture the user's actions and facial expressions in real time using cameras and sensors.

[0452] Emotion Engine

[0453] The emotion engine analyzes the user's facial expressions and voice to provide a function for recognizing their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice. The emotion engine analyzes the captured facial and voice data to detect emotions such as "happy" or "troubled."

[0454] user

[0455] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[0456] Specific examples

[0457] User A takes a video of "how to make spaghetti" on their smartphone and uploads it to the server using the app. The device sends the video to the server, which then analyzes it with an AI model. The AI ​​model analyzes the cooking steps and generates specific instructions, such as "boil the spaghetti for 8 to 10 minutes."

[0458] The server sends the instruction "Boil the spaghetti for 8 to 10 minutes" to the device. The device displays this instruction to User A and provides a voice message saying "Boil the spaghetti for 8 to 10 minutes." User A then follows the displayed instructions to continue cooking.

[0459] If User A shows a confused expression while cooking, the device's camera captures that expression and sends it to the emotion engine. The emotion engine recognizes User A's confusion and sends that information to the server. The server uses this data to generate additional instructions, such as "Please check the detailed instructions for making the sauce again."

[0460] After the dish is complete, User A enters a rating into the app, saying "The sauce is a little sour," and sends that rating to the server. The server compiles the ratings and provides the next user with advice, such as "Try adding a little sugar to the sauce." User B then receives that advice the next time they cook and can try it out.

[0461] Example prompts to input to the generative AI model

[0462] Here are some examples of prompts to input to a generative AI model:

[0463] "We are building a system that allows users to upload cooking videos and provides cooking instructions. The text returned from analyzing the video should be in the following format: "Instructions: Do △△". Also, please provide instructions on how to recognize user emotions and reflect them in real-time instructions."

[0464] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0465] Step 1:

[0466] Users film cooking videos and upload them to the server through the application. The input is the cooking video filmed by the user, and the output is the video being sent to the server.

[0467] Step 2:

[0468] The device sends the video file selected by the user to the server and confirms that the transmission is complete. The input is the video uploaded by the user, and the output is the video data sent to the server.

[0469] Step 3:

[0470] The server receives the video data and requests the AI ​​model to analyze it. The AI ​​model extracts cooking instructions and ingredient handling information from each frame of the video. The input is the received video data, and the output is the analyzed cooking instructions and ingredient handling information in text format.

[0471] Step 4:

[0472] The server determines the next cooking steps based on the analysis results obtained from the AI ​​model. Specifically, it organizes the cooking steps for each frame based on the analysis results and generates specific instructions such as "mince the onion." The input is the analysis results from the AI ​​model, and the output is the organized cooking steps.

[0473] Step 5:

[0474] The server sends the generated recipe to the terminal. The input is the organized recipe instructions, and the output is the recipe data sent to the terminal.

[0475] Step 6:

[0476] The device displays the cooking instructions received from the server to the user. When displaying the instructions, the voice assistant function is used to allow voice instructions. The input is the cooking instructions data received from the server, and the output is the cooking instructions information displayed to the user. Voice instructions are also provided as a specific action.

[0477] Step 7:

[0478] The user follows the instructions displayed on the device to cook. For example, the user actually stir-fries vegetables in a frying pan based on the instruction "Stir-fry vegetables for 5 minutes." The input is the cooking instructions displayed on the device, and the output is the cooking behavior according to those instructions.

[0479] Step 8:

[0480] The device uses cameras and sensors to capture the user's operations and facial expressions in real time and send them to the emotion engine. The input is the user's real-time operations and facial expression data, and the output is the captured data sent to the emotion engine.

[0481] Step 9:

[0482] The emotion engine analyzes the captured data and recognizes the user's emotional state. For example, it detects emotions such as "happy" or "troubled." The input is the captured operation and facial expression data, and the output is the analyzed emotional state data.

[0483] Step 10:

[0484] The emotion engine sends the recognized emotion data to the server. The input is the analyzed emotional state data, and the output is the emotion data sent to the server.

[0485] Step 11:

[0486] The server analyzes the user's behavioral and emotional data to confirm that it matches the current cooking instructions. For example, if the user appears anxious, it generates instructions to explain the cooking instructions again more slowly. The input is the user's behavioral and emotional data, and the output is instruction data for additional cooking steps.

[0487] Step 12:

[0488] The server generates additional instructions and sends them to the terminal. The input is the instruction data for the additional cooking steps, and the output is the instruction data sent to the terminal.

[0489] Step 13:

[0490] The terminal displays additional instructions to the user and provides voice guidance such as, "Please check the detailed instructions for making the sauce again." The input is the additional instruction data received from the server, and the output is the additional cooking procedure information displayed to the user and the voice guidance.

[0491] Step 14:

[0492] The user rates the completed dish and inputs the rating into the application. The input is the user's rating, and the output is the rating data sent to the server.

[0493] Step 15:

[0494] The terminal transmits the user's rating data to the server. The input is the user's rating data, and the output is the rating data transmitted to the server.

[0495] Step 16:

[0496] The server aggregates the collected evaluation data and provides it as feedback to the AI ​​model. The input is the collected evaluation data, and the output is the feedback data provided to the AI ​​model.

[0497] Step 17:

[0498] The server also aggregates behavioral and emotional data from other users to learn more efficient cooking procedures. The input is behavioral and emotional data from other users, and the output is optimized new cooking procedures and advice.

[0499] Step 18:

[0500] The server generates new optimized cooking recipes and tips and sends them to the device. The input is the optimized cooking recipes and tips, and the output is the cooking recipes and tips sent to the device.

[0501] Step 19:

[0502] The device notifies the user of the newly generated recipe or advice and displays it on the screen, for example, "Next time, add one teaspoon of salt." The input is the optimized cooking instructions or advice received from the server, and the output is the recipe or advice notified to the user.

[0503] (Application example 2)

[0504] 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."

[0505] Conventional cooking support systems only provide instructions for cooking procedures and lack appropriate feedback or support for the user's emotional state. As a result, users can feel stressed while cooking and have difficulty following instructions. Furthermore, there are insufficient means to effectively utilize feedback data from multiple users and optimize recipes. This makes it difficult to improve the cooking experience and recipes.

[0506] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and detecting behavior that differs from the instructed procedures, means for analyzing the user's emotional state and reflecting this in cooking procedures and feedback, means for aggregating behavioral data and feedback from multiple users and generating an optimal recipe, and means for providing the generated recipe to other users. This enables real-time feedback according to the user's emotional state, improving the quality of the cooking experience and enabling recipe optimization by effectively utilizing data from multiple users.

[0507] A "cooking video" is a video that records the cooking process.

[0508] The "analysis results" are information about cooking procedures and ingredient manipulations extracted from cooking videos.

[0509] "Cooking steps" are the steps required to complete a dish.

[0510] "User behavior" refers to the steps and operations performed by the user while cooking.

[0511] "Emotional state" refers to the psychological state that can be read from the user's facial expression, tone of voice, etc.

[0512] "Feedback" refers to evaluations and advice on users' actions.

[0513] A "recipe" is a collection of information about ingredients and steps for making a dish.

[0514] The "server" is a central computer system that receives cooking videos, analyzes them, generates cooking instructions, and compiles data.

[0515] "Monitoring" is a means of observing a user's behavior and emotional state and obtaining the data.

[0516] An "optimized recipe" is a combination of cooking steps and ingredients that has been refined to maximize effectiveness based on feedback and behavioral data from multiple users.

[0517] "Means" are technical components or methods used to achieve a specific function or purpose.

[0518] The "described system" is a collection of a series of devices and programs having specific functions and purposes proposed by the present invention.

[0519] To put this invention into practice, a system is required in which a server, a user's terminal, and an emotion engine work in cooperation with each other. The specific configuration and operation of this system will be described below.

[0520] The server is a central computer system that receives and analyzes cooking videos, generates cooking instructions, collects behavioral data, and processes emotional data. Specifically, when a user uploads a cooking video, the server receives the video and requests an AI model to analyze it. This AI model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format. The server then generates cooking instructions based on the extracted results and sends the instructions to the user's device.

[0521] The user's device (smartphone, tablet, etc.) receives the cooking instructions sent from the server and displays them to the user. The device also monitors the user's cooking operations in real time using cameras and sensors and sends the data to the emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state and sends the data to the server. Based on this, the server generates feedback according to the user's emotional state and sends it to the device.

[0522] Below is an example of how the system works:

[0523] Example 1: Uploading and analyzing a video

[0524] Users film cooking videos on their smartphones and upload them to a server via the app. The videos are then sent to the server and analyzed by an AI model, which then generates specific cooking instructions, such as "stir-fry vegetables for five minutes."

[0525] Example 2: Real-time support

[0526] The server sends the cooking instructions to the user's device, which displays them to the user, who then follows the instructions to proceed with the cooking.

[0527] Example 3: Behavioral analysis and emotion recognition

[0528] If the user does not stir-fry the vegetables for five minutes as instructed (for example, if they only stir-fry for three minutes), the device captures the user's behavior through the camera and sends it to the emotion engine. The emotion engine analyzes the user's emotional state from facial expressions and voice and sends it to the server. The server then adjusts the feedback content based on this data and sends appropriate advice to the user.

[0529] Example 4: Rating and improving recipes

[0530] After a user completes a dish, they rate it within the app. The rating data is sent to the server, which aggregates it and feeds it back into the AI ​​model. The server then analyzes the data from other users to generate an optimized recipe and serve it to the next user.

[0531] This allows users to cook while receiving emotional support in real time, and recipes can be optimized by effectively utilizing data from multiple users.

[0532] For example, a prompt such as "What is the next cooking step?" can be answered with "Stir-fry the vegetables for 5 minutes." This allows the system to provide appropriate answers to the user's questions and doubts.

[0533] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0534] Step 1: Upload your video

[0535] A user shoots a cooking video on their smartphone and uploads it to a server via an application. The input is the cooking video shot by the user, and the output is the video data sent to the server. Specifically, the application selects the user's video file and performs communication processing to upload it to the server.

[0536] Step 2: Analyze the video

[0537] The server requests the AI ​​model to analyze the received video. The input is the video data uploaded in step 1, and the output is text data on the analyzed cooking steps and ingredient manipulations. Specifically, the server analyzes the video frame by frame, and the AI ​​model extracts cooking steps from each frame.

[0538] Step 3: Generate and provide cooking instructions

[0539] The server generates appropriate cooking instructions based on the analysis results and sends them to the user's device. The input is the text-format cooking instruction data obtained in step 2, and the output is the cooking instructions sent to the user's device. Specifically, the server organizes the analysis results, generates cooking instructions in a format that is easy for the user to understand, and sends them to the device.

[0540] Step 4: Display cooking instructions

[0541] The user's device displays the cooking instructions received from the server to the user. The input is the cooking instructions sent from the server in step 3, and the output is the cooking instructions displayed on the device screen. Specifically, the device renders the received data appropriately on the display screen.

[0542] Step 5: Monitor behavior and capture emotions

[0543] The device monitors the user's actions and emotions in real time using cameras and sensors and sends them to the emotion engine. The input is the user's actual actions, facial expressions, and voice data, and the output is the data sent to the emotion engine. Specifically, the device uses a camera and microphone to capture the user's actions and voice, and sends the data to the emotion engine for analysis.

[0544] Step 6: Sentiment analysis and feedback generation

[0545] The emotion engine analyzes the user's emotional state and sends the data to the server. The input is the facial expression and voice data sent from the device in step 5, and the output is the analyzed emotional data and its feedback. Specifically, the emotion engine performs analysis using an emotion analysis algorithm and sends the results to the server.

[0546] Step 7: Provide feedback

[0547] The server generates feedback based on the emotional data and sends it to the user's device. The input is the emotional data and cooking instructions obtained in step 6, and the output is a feedback message sent to the user's device. Specifically, the server generates a feedback message taking into account the user's emotional state and sends it to the device.

[0548] Step 8: Evaluation and data aggregation

[0549] The user rates the completed dish and sends the data to the server through the application. The input is the user's rating data, and the output is the rating data compiled by the server. Specifically, the user fills out a rating form within the application and sends it to the server.

[0550] Step 9: Optimize the recipe

[0551] The server aggregates behavioral data, emotional data, and evaluation data from multiple users and feeds it back to the AI ​​model. The input is the data aggregated in step 8, and the output is a new optimized recipe. Specifically, the server analyzes the data collected by the server using the AI ​​model to generate a new recipe.

[0552] Step 10: Serving an optimized recipe

[0553] The server generates an optimized recipe and provides it to other users. The input is the optimized recipe generated in step 9, and the output is the new recipe displayed on the user's device. Specifically, the server sends the new recipe data to the other user's device, and the application displays it.

[0554] Through these steps, users can receive real-time support for cooking procedures and receive appropriate feedback based on their emotions, improving their cooking experience. By utilizing data from multiple users, recipes are optimized daily, enabling better cooking suggestions.

[0555] 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.

[0556] 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.

[0557] 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.

[0558] [Second embodiment]

[0559] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0560] 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.

[0561] 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).

[0562] 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.

[0563] 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.

[0564] 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).

[0565] 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.

[0566] 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.

[0567] 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.

[0568] 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.

[0569] In the smart glasses 214, 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.

[0570] 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."

[0571] This invention provides a system that loads cooking videos into AI and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a terminal, and a user. The details are explained below.

[0572] System Configuration

[0573] server

[0574] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses AI models to analyze various data and provide users with cooking instructions tailored to their needs.

[0575] Terminal

[0576] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the information to the server.

[0577] user

[0578] Users upload cooking videos, follow instructions on their devices to cook, and then provide feedback to the system after completing the dish.

[0579] Program processing

[0580] Video upload and analysis

[0581] 1. Users

[0582] Users film their cooking and upload it to a server through the application.

[0583] 2. Terminal

[0584] The device sends the video selected by the user to the server.

[0585] 3. Server

[0586] The server receives the video and passes it to the AI ​​model to begin analysis.

[0587] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[0588] Providing real-time support

[0589] 1. Server

[0590] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[0591] 2. Terminal

[0592] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[0593] 3. Users

[0594] The user follows the displayed instructions to proceed with cooking.

[0595] User behavior analysis

[0596] 1. Terminal

[0597] The device captures user actions using cameras and sensors and transmits them to the server in real time.

[0598] 2. Server

[0599] The server analyzes the user's behavioral data and compares it with the instructions.

[0600] If different behavior is detected, the data is passed to the AI ​​model and saved as learning data.

[0601] Feedback and Learning

[0602] 1. Users

[0603] Users rate the finished dish and enter their rating into the app.

[0604] 2. Terminal

[0605] The terminal transmits the user's evaluation data to the server.

[0606] 3. Server

[0607] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[0608] It also aggregates other users' rating data to generate optimal recipes.

[0609] Recipe Improvement and Serving

[0610] 1. Server

[0611] The server learns more efficient cooking procedures based on aggregated behavioral data and feedback.

[0612] Generate new optimized recipes and tips and share them with other users.

[0613] 2. Terminal

[0614] The device will display new recipes and tips to the user.

[0615] Specific examples

[0616] Example 1: Uploading and analyzing a video

[0617] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[0618] Example 2: Real-time support

[0619] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[0620] Example 3: Behavioral analysis and feedback

[0621] If user A actually stir-fries vegetables for only 3 minutes, the device will capture this behavior and send it to the server, which will then identify the different behavior and store it in the AI ​​model.

[0622] Example 4: Rating and improving recipes

[0623] User B also cooks the dish and sends a rating to the server saying it was "delicious." The server uses this rating data to provide a new recipe to the next user.

[0624] In this way, recipes are dynamically improved based on user behavior and feedback, helping everyone cook better.

[0625] The processing flow will be explained below.

[0626] Step 1:

[0627] user

[0628] Cooking videos are filmed and uploaded to the system through the application.

[0629] Step 2:

[0630] Terminal

[0631] Send the uploaded video to the server.

[0632] Step 3:

[0633] server

[0634] Receives video files and requests the AI ​​model to analyze them.

[0635] Step 4:

[0636] server

[0637] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[0638] Step 5:

[0639] server

[0640] Based on the analysis results, the next cooking procedure to be carried out is determined and sent to the terminal.

[0641] Step 6:

[0642] Terminal

[0643] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[0644] Step 7:

[0645] user

[0646] Follow the displayed instructions to continue cooking.

[0647] Step 8:

[0648] Terminal

[0649] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[0650] Step 9:

[0651] server

[0652] Analyze the received behavioral data and confirm that it matches the instructed procedures.

[0653] Step 10:

[0654] server

[0655] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[0656] Step 11:

[0657] user

[0658] Once cooking is complete, the food is tasted and evaluated.

[0659] Step 12:

[0660] Terminal

[0661] Send user rating data to the server.

[0662] Step 13:

[0663] server

[0664] Provide feedback to the AI ​​model based on the collected evaluation data.

[0665] Step 14:

[0666] server

[0667] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[0668] Step 15:

[0669] server

[0670] The generated new recipes and tips are sent to the device.

[0671] Step 16:

[0672] Terminal

[0673] The device will display new recipes and tips to the user.

[0674] Step 17:

[0675] user

[0676] Use new recipes and advice to prepare your next meal.

[0677] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[0678] Example 1

[0679] 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."

[0680] It is difficult for beginners and inexperienced users to cook accurately while following a recipe. It is also difficult to provide optimal support based on each individual's cooking skills and preferences. Furthermore, the inability to fully utilize user behavioral data and feedback limits improvements to the quality of recipes. This creates the challenge of making high-quality meals due to the lack of appropriate cooking support.

[0681] 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.

[0682] In this invention, the server includes means for receiving and analyzing cooking videos from users, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior with cameras and sensors and detecting behavior that deviates from the instructed procedures, means for aggregating behavioral data and feedback from multiple users to generate optimal recipes, and means for providing the generated recipes and cooking advice to other users. This makes it possible to provide optimal cooking support based on each user's skills and preferences and to improve the quality of recipes by utilizing accumulated data.

[0683] "User" refers to an individual who performs cooking operations, uploads videos, and rates them.

[0684] "Server" refers to a computing device that analyzes received cooking videos, generates cooking instructions, and aggregates user behavior data and feedback.

[0685] "Terminal" refers to a device such as a user's smartphone, tablet, or PC, which displays cooking instructions from the server and monitors the user's behavior.

[0686] "Means for receiving and analyzing videos" refers to the technology in which a server receives cooking videos uploaded by users and analyzes their content using a generative AI model.

[0687] "Means for instructing the user on cooking instructions" refers to a technology in which the analyzed cooking instructions are sent from the server to the terminal, and the terminal displays them to the user.

[0688] "Means of monitoring using cameras and sensors" refers to technology that uses cameras and sensors installed on the device to monitor the user's cooking operations in real time and transmits that data to a server.

[0689] "Means for aggregating behavioral data and feedback" refers to the technology by which a server collects user behavioral data and evaluation data and statistically analyzes it.

[0690] "Means for generating optimal recipes" refers to technology in which an AI model creates more efficient and appropriate cooking procedures and recipes based on aggregated data.

[0691] "Means for providing generated recipes and cooking advice" refers to technology for transmitting optimized recipes and cooking advice from a server to other users and displaying them on their terminals.

[0692] "Means for collecting evaluation data" refers to the technology that collects food evaluations from multiple users and stores them in a database.

[0693] "Means for training an AI model" refers to the technology of inputting collected behavioral data and evaluation data into an AI model and allowing the model to acquire new knowledge through its learning process.

[0694] This invention relates to a system that uses AI to load cooking videos and provide step-by-step support in real time. The main components of the system are a server, a terminal, and a user, all of which work together. The details of the system and how to use it are explained below.

[0695] System configuration

[0696] server

[0697] The server plays a central role in this system. It receives cooking videos, analyzes them, generates instructions, collects behavioral data, and generates optimal recipes. Specifically, the server analyzes various data using a generative AI model (e.g., OpenAI's GPT-4).

[0698] Terminal

[0699] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends it to the server. The terminal is also equipped with a camera and sensors that capture the user's cooking operations in real time.

[0700] User

[0701] Users film cooking videos and upload them to the server via the application. They then follow instructions on their device to cook, and once the dish is complete, they provide feedback to the system.

[0702] Program processing

[0703] Video upload and analysis

[0704] 1. A user shoots a cooking video on their smartphone. The user launches the application, selects the recorded video, and presses the upload button.

[0705] 2. The device sends the video uploaded by the user to the server.

[0706] 3. The server receives the video data and analyzes the video using the generative AI model, using the prompt "Please extract the cooking steps and ingredients from this video." Based on this prompt, the AI ​​model extracts the cooking steps and ingredients from the video in text format.

[0707] Providing real-time support

[0708] 1. The server receives the analysis results and determines the next cooking step, for example, "sauté the vegetables for 5 minutes."

[0709] 2. The device displays the cooking instructions sent from the server to the user, who then follows the instructions to proceed with the cooking.

[0710] User behavior analysis

[0711] 1. The device captures the user's cooking operations using cameras and sensors and transmits them to the server in real time, for example, monitoring frying time and temperature.

[0712] 2. The server analyzes the received behavioral data and compares the instructed steps with the actual behavior. If any discrepancies are detected, the data is passed to the generative AI model and saved as training data.

[0713] Feedback and Learning

[0714] 1. After the cooking is complete, the user enters their evaluation into the app, such as "It was delicious" or "I wish it was a little saltier."

[0715] 2. The terminal sends the evaluation data entered by the user to the server.

[0716] 3. The server aggregates the evaluation data and provides it as feedback to the generative AI model. It also aggregates evaluation data from other users to generate the optimal recipe.

[0717] Recipe Improvement and Serving

[0718] 1. The server learns more efficient cooking procedures based on aggregated behavioral and feedback data, and uses generative AI models to create new recipes and cooking advice.

[0719] 2. The device displays the newly generated recipes and advice to the user.

[0720] Specific examples

[0721] Example 1: Uploading and analyzing a video

[0722] User A films a cooking video on their smartphone and uploads it to a server via an application. The device sends the video to the server, which then analyzes it using a generative AI model (e.g., OpenAI's GPT-4) based on the prompt, "Please extract the cooking steps and ingredients from this video." The AI ​​model then generates the instruction, "Stir-fry the vegetables for 5 minutes."

[0723] Example 2: Real-time support

[0724] The server sends the generated instructions to the terminal, and the terminal displays the instruction "Stir-fry vegetables for 5 minutes" to User A. User A cooks according to the instructions.

[0725] Example 3: Behavioral analysis and feedback

[0726] If user A actually stir-fries the vegetables for only 3 minutes, the device captures this behavior and sends it to the server, which then identifies the different behavior and stores it in the generative AI model.

[0727] Example 4: Rating and improving recipes

[0728] User B also cooks the dish and sends a rating of "delicious" to the server. Based on this rating data, the server provides new recipes and advice to other users.

[0729] In this way, recipes are constantly improved based on user actions and feedback, helping everyone cook better.

[0730] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0731] Step 1:

[0732] The user shoots a cooking video on their smartphone, launches the application, selects the recorded video, and presses the upload button.

[0733] Input: Filmed cooking video

[0734] Output: Video file selected by user

[0735] Step 2:

[0736] The terminal receives a video upload request from the user and transmits the video file to the server.

[0737] Input: User's video upload request and video file

[0738] Output: Video file sent to the server

[0739] Step 3:

[0740] The server receives the video data and sends an analysis prompt to the generative AI model. The prompt is "Please extract the cooking steps and ingredients from this video." The AI ​​model analyzes the video and outputs the cooking steps and ingredients in text format.

[0741] Input: Video file sent to the server, analysis prompt

[0742] Output: Extracted text data of cooking instructions and ingredients

[0743] Step 4:

[0744] The server receives the analysis results and determines the next cooking steps, which are then used to provide specific instructions to the user.

[0745] Input: Extracted text data of cooking instructions and ingredients

[0746] Output: Cooking instructions text to the user

[0747] Step 5:

[0748] The device receives cooking instructions from the server and displays them to the user. For example, specific instructions such as "sauté vegetables for 5 minutes" are displayed. The user then follows the displayed instructions to cook.

[0749] Input: Cooking instruction text from the server

[0750] Output: Cooking instructions displayed to the user

[0751] Step 6:

[0752] The device captures the user's cooking operations in real time using cameras and sensors and sends the data, including frying time and temperature, to a server.

[0753] Input: User's real-time cooking operation data

[0754] Output: Cooking operation data sent to the server

[0755] Step 7:

[0756] The server analyzes the behavioral data and compares the instructions with the actual behavior. For example, it checks whether the user actually stir-fried vegetables for five minutes. If a different behavior is detected, the data is passed to the generative AI model for future feedback and learning.

[0757] Input: Cooking operation data sent

[0758] Output: Analyzed behavior data, detected abnormal behavior data

[0759] Step 8:

[0760] After the user has finished cooking, they can enter their evaluation of the dish through the application, for example, by entering comments such as "It was delicious" or "It wasn't spicy enough."

[0761] Input: User food rating data

[0762] Output: Rating data input to the app

[0763] Step 9:

[0764] The terminal transmits the user's evaluation data to the server.

[0765] Input: Food rating data from users

[0766] Output: Rating data sent to the server

[0767] Step 10:

[0768] The server aggregates the evaluation data and provides it as feedback to the generative AI model, which also aggregates evaluation data from other users to generate the optimal recipe.

[0769] Input: Aggregated rating data

[0770] Output: Feedback data for generative AI model, optimal recipe data

[0771] Step 11:

[0772] The server generates new recipes and cooking advice based on the collected behavioral data and feedback data, and provides the generated recipes and advice to other users.

[0773] Input: Behavioral data, feedback data

[0774] Output: New recipes, cooking advice

[0775] Step 12:

[0776] The device displays the newly generated recipes and advice to the user, who can then follow the new recipes and advice to create even better dishes.

[0777] Input: New recipes and cooking advice from the server

[0778] Output: New recipes and cooking advice displayed to the user

[0779] (Application example 1)

[0780] 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."

[0781] In recent years, the number of beginners and busy people has increased, and the need for easy and efficient cooking has grown. However, existing cooking support systems lack sufficient support for how to use individual ingredients and real-time cooking procedures, making it difficult for users to proceed with cooking at the appropriate time. It is also difficult to receive real-time feedback during the cooking process, resulting in an increased failure rate.

[0782] 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.

[0783] In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior and detecting behavior that differs from the instructed procedures, means for aggregating behavioral data and feedback from multiple users and generating optimal recipes, means for providing the generated recipes to other users, means for recognizing ingredients with a camera on a smart device and generating corresponding recipes, and means for displaying cooking procedures on a visual display in real time, thereby enabling users to efficiently select ingredients in the supermarket and receive real-time support when cooking.

[0784] "Cooking videos" refer to footage recorded by users during the cooking process, and cooking steps are extracted by analyzing this video data.

[0785] "Analysis" refers to the process of analyzing the received cooking video using AI models and image recognition technology, and extracting the cooking steps and ingredient manipulations in text format.

[0786] "Cooking procedure" refers to each step in the process of cooking ingredients, specifically including operations such as preparing ingredients, cutting, frying, and boiling.

[0787] "Users" refer to people who use this system to cook, upload videos, check cooking instructions, and provide feedback.

[0788] "Monitoring" refers to the process of monitoring the user's cooking behavior using cameras and sensors and sending the data to a server in real time.

[0789] "Behavioral data" refers to data on the cooking actions actually performed by the user, and includes specific action data obtained from video and sensors.

[0790] "Feedback" refers to the user inputting their evaluation and impressions of the completed dish and sending it to the system, which the system uses as learning data.

[0791] The "optimal recipe" is a recipe generated based on behavioral data and feedback from multiple users, and improves taste and cooking efficiency.

[0792] "Smart device" refers to an electronic device with a camera and display function, and specifically includes smart glasses and smartphones.

[0793] "Ingredient recognition" refers to capturing an image of an ingredient using a smart device's camera and analyzing that image to identify a specific ingredient.

[0794] "Visual display" refers to the screen or display of a smart device, in this case intended to show cooking instructions or recipes to the user in real time.

[0795] This invention provides a system that uses AI to read cooking videos and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a device, and a user. The details are described below.

[0796] System Configuration

[0797] server

[0798] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses a generative AI model to analyze various data and provide users with cooking instructions tailored to their needs. It also optimizes recipes based on user feedback. Specifically, it uses TensorFlow or PyTorch to operate a deep learning model.

[0799] Terminal

[0800] The user's device (smart glasses, smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the results to the server. In addition, the terminal recognizes ingredients in real time using the user's camera, and displays the results analyzed by the server on the display. The terminal usually uses an image recognition library such as OpenCV.

[0801] user

[0802] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system, including evaluations of cooking efficiency and taste. User behavior data is captured by cameras and sensors and sent to the server in real time.

[0803] Explanation of program processing

[0804] Video upload and analysis

[0805] 1. The user takes a video of the cooking using a smartphone or other device and uploads it to the server via the application.

[0806] 2. The device sends the video selected by the user to the server.

[0807] 3. The server receives the video and passes it to the AI ​​model to begin analysis. The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[0808] Providing real-time support

[0809] 1. The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[0810] 2. The device displays the cooking instructions to the user, for example, "Sauté the vegetables for 5 minutes."

[0811] 3. The user follows the displayed instructions to proceed with cooking.

[0812] Food ingredient recognition using smart devices

[0813] 1. The device sends the ingredients identified by the smart glasses camera to the server.

[0814] 2. The server analyzes the ingredients, generates a corresponding recipe, and sends it to the device.

[0815] 3. The device will display the recipe and cooking instructions on the screen, for example, "Here's how to make a salad using these carrots."

[0816] Specific examples

[0817] Imagine a user is in a supermarket, putting on smart glasses and pointing a carrot at the camera.

[0818] The device recognizes the carrot and sends the data to the server.

[0819] The server generates a recipe based on carrots and sends the recipe and cooking instructions for "Healthy Salad with Carrots" to the terminal.

[0820] The device displays this information on its screen and guides the user through the cooking process in real time.

[0821] Example prompts to input to the generative AI model

[0822] The user will take a photo of the ingredients and send it to us, and we will generate a recommended recipe using those ingredients. We will also output cooking instructions in real time.

[0823] In this way, users can efficiently select ingredients and receive real-time cooking instructions while shopping in a physical store.

[0824] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0825] Step 1:

[0826] The user takes a picture of the food with the camera on the smart glasses. The camera captures the food image data and stores it on the device. The input is the food image taken by the camera, and the output is the image data stored on the device.

[0827] Step 2:

[0828] The device sends the image of the food taken by the user to the server. The image data is sent via the HTTPS protocol. The input is the image data stored on the device, and the output is the image data sent to the server.

[0829] Step 3:

[0830] The server passes the received image data to the generative AI model for analysis. This analysis uses image recognition technology (e.g., OpenCV) to recognize ingredients and inputs that information into the AI ​​model. The input is the image data sent to the server, and the output is the recognized ingredient information.

[0831] Step 4:

[0832] The server generates an appropriate recipe based on the recognized ingredient information. At this time, the generative AI model uses past data and feedback to propose optimal cooking procedures. The input is the recognized ingredient information and past feedback data, and the output is the generated recipe and cooking procedures.

[0833] Step 5:

[0834] The server sends the generated recipe and cooking instructions to the terminal. Again, the HTTPS protocol is used. The input is the generated recipe and cooking instructions, and the output is the recipe and cooking instructions sent to the terminal.

[0835] Step 6:

[0836] The terminal displays the received recipe and cooking instructions on a visual display, allowing the user to see the next action in real time. The input is the recipe and cooking instructions sent to the terminal, and the output is the cooking instructions shown on the display.

[0837] Step 7:

[0838] The user follows the visual display to proceed with the cooking. For example, if the instruction is "sauté carrots for 5 minutes," the user follows the instructions to cook. The output is the cooking action performed by the user.

[0839] Step 8:

[0840] The device monitors the user's cooking behavior using cameras and sensors and sends the data to a server. The input is the user's cooking behavior data, and the output is the behavior data sent to the server.

[0841] Step 9:

[0842] The server analyzes the received behavioral data and detects any behavior that deviates from the instructed procedure. Furthermore, this behavioral data is provided as feedback to the AI ​​model and saved as training data for the model. The input is the behavioral data sent to the server, and the output is the training data provided to the AI ​​model.

[0843] Step 10:

[0844] The user rates the cooked dish and inputs the rating into the terminal. The terminal sends the rating data to the server. The input is the rating data entered by the user, and the output is the rating data sent to the server.

[0845] Step 11:

[0846] The server provides optimal recipes to other users based on the received rating data. It also improves the recipes using the aggregated rating data and behavioral data. The input is the rating data and behavioral data sent to the server, and the output is an improved recipe and helpful advice.

[0847] 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.

[0848] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[0849] System Configuration

[0850] server

[0851] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotion data from the emotion engine and adjusts cooking procedures and timings.

[0852] Terminal

[0853] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server.

[0854] Emotion Engine

[0855] The emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice.

[0856] user

[0857] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[0858] Program processing

[0859] Video upload and analysis

[0860] 1. Users

[0861] Users film their cooking and upload it to a server through the application.

[0862] 2. Terminal

[0863] The device sends the video selected by the user to the server.

[0864] 3. Server

[0865] The server receives the video and asks the AI ​​model to analyze it.

[0866] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[0867] Providing real-time support

[0868] 1. Server

[0869] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[0870] 2. Terminal

[0871] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[0872] 3. Users

[0873] The user follows the displayed instructions to proceed with cooking.

[0874] User behavior analysis and emotion recognition

[0875] 1. Terminal

[0876] The device captures user actions in real time using cameras and sensors and sends them to the emotion engine.

[0877] 2. Emotion Engine

[0878] The emotion engine analyzes facial expressions and voice to recognize the user's emotional state.

[0879] The recognized emotion data is sent to the server.

[0880] 3. Server

[0881] The server analyzes the user's behavioral and emotional data and checks whether it matches the instructed steps.

[0882] If different behaviors or emotional changes are detected, the data is passed to the AI ​​model and saved as learning data.

[0883] Feedback and Learning

[0884] 1. Users

[0885] Users rate the finished dish and enter their rating into the app.

[0886] 2. Terminal

[0887] The terminal transmits the user's evaluation data to the server.

[0888] 3. Server

[0889] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[0890] It also aggregates other users' rating data to generate optimal recipes.

[0891] Recipe Improvement and Serving

[0892] 1. Server

[0893] The server learns more efficient cooking procedures based on aggregated behavioral data, emotional data, and feedback.

[0894] Generate new optimized recipes and tips and share them with other users.

[0895] 2. Terminal

[0896] The device will display new recipes and tips to the user.

[0897] Specific examples

[0898] Example 1: Uploading and analyzing a video

[0899] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[0900] Example 2: Real-time support

[0901] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[0902] Example 3: Behavioral analysis and emotion recognition

[0903] If User A actually stir-fries vegetables for only 3 minutes, the device will capture User A's actions and facial expressions with the camera and send them to the server. The emotion engine will recognize User A's emotional state and report it to the server. The server will review the different behavioral and emotional data and store it in the AI ​​model.

[0904] Example 4: Rating and improving recipes

[0905] User B also cooks the dish and sends a rating of "delicious" to the server. The server uses this rating data and emotion data to provide new recipes and advice to the next user.

[0906] In this way, recipes are dynamically improved based on user behavior, sentiment, and feedback, helping everyone cook better.

[0907] The processing flow will be explained below.

[0908] Step 1:

[0909] user

[0910] Cooking videos are filmed and uploaded to the system through the application.

[0911] Step 2:

[0912] Terminal

[0913] Send the uploaded video to the server.

[0914] Step 3:

[0915] server

[0916] Receives video files and requests the AI ​​model to analyze them.

[0917] Step 4:

[0918] server

[0919] The AI ​​model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format.

[0920] Step 5:

[0921] server

[0922] Based on the analysis results, the next cooking procedure is determined and the instructions are sent to the terminal.

[0923] Step 6:

[0924] Terminal

[0925] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[0926] Step 7:

[0927] user

[0928] Follow the displayed instructions to continue cooking.

[0929] Step 8:

[0930] Terminal

[0931] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[0932] Step 9:

[0933] Emotion Engine

[0934] It analyzes the user's facial expressions and voice to recognize their emotional state, and sends the acquired emotional data to the server.

[0935] Step 10:

[0936] server

[0937] The received behavioral and emotional data is analyzed and compared with the instructed procedures.

[0938] Step 11:

[0939] server

[0940] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[0941] Step 12:

[0942] server

[0943] Based on the recognized emotional data, the cooking instructions and timing of advice are adjusted.

[0944] Step 13:

[0945] user

[0946] Once cooking is complete, the food is tasted and evaluated.

[0947] Step 14:

[0948] Terminal

[0949] Send user rating data to the server.

[0950] Step 15:

[0951] server

[0952] Provide feedback to the AI ​​model based on the collected evaluation data.

[0953] Step 16:

[0954] server

[0955] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[0956] Step 17:

[0957] server

[0958] The generated new recipes and tips are sent to the device.

[0959] Step 18:

[0960] Terminal

[0961] The device will display new recipes and tips to the user.

[0962] Step 19:

[0963] user

[0964] Use new recipes and advice to prepare your next meal.

[0965] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[0966] Example 2

[0967] 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."

[0968] Conventional cooking assistance systems can only monitor user behavior and lack support that reflects user emotions. Furthermore, methods that improve recipes based solely on user feedback may not provide effective real-time cooking assistance. As a result, follow-up during cooking is insufficient, resulting in a lack of improvement in the user's cooking experience.

[0969] 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 means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and emotions and detecting behavioral and emotional changes that differ from the instructed procedures, means for aggregating behavioral data, emotional data, and feedback from multiple users and generating optimal cooking procedures, and means for providing the generated cooking procedures and advice to other users. This enables real-time cooking assistance that reflects both the user's behavior and emotions.

[0970] "Cooking videos" are digital data that record cooking steps and how to prepare ingredients.

[0971] "Analysis" refers to the process of analyzing cooking videos based on an AI model and extracting cooking steps and ingredient manipulations in text format.

[0972] A "cooking procedure" is each step required to complete a dish, and includes specific actions, time, and conditions.

[0973] "User" refers to an individual user of the cooking assistance system.

[0974] "Monitoring" is the means of observing and recording a user's behavior and emotional state in real time.

[0975] "Emotional changes" refers to changes in emotions recognized by analyzing changes in the user's facial expressions and voice.

[0976] "Feedback" refers to data on the evaluations and impressions users provide about the completed dishes.

[0977] The "optimal cooking procedure" is a method generated as the most effective and efficient cooking procedure based on the user's behavioral data, emotional data, and feedback.

[0978] "Advice" is information containing additional instructions or suggestions that will be helpful during cooking or for your next cooking session.

[0979] A "server" is a computer system that performs central processing such as analysis, data collection, and instruction generation.

[0980] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[0981] System Configuration

[0982] server

[0983] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotional data from the emotion engine and adjusts cooking steps and timing. Specifically, the server receives the video and requests analysis from the AI ​​model. The AI ​​model analyzes the video and extracts cooking steps and ingredient manipulations for each frame in text format.

[0984] Terminal

[0985] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server. The terminal can capture the user's actions and facial expressions in real time using cameras and sensors.

[0986] Emotion Engine

[0987] The emotion engine analyzes the user's facial expressions and voice to provide a function for recognizing their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice. The emotion engine analyzes the captured facial and voice data to detect emotions such as "happy" or "troubled."

[0988] user

[0989] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[0990] Specific examples

[0991] User A takes a video of "how to make spaghetti" on their smartphone and uploads it to the server using the app. The device sends the video to the server, which then analyzes it with an AI model. The AI ​​model analyzes the cooking steps and generates specific instructions, such as "boil the spaghetti for 8 to 10 minutes."

[0992] The server sends the instruction "Boil the spaghetti for 8 to 10 minutes" to the device. The device displays this instruction to User A and provides a voice message saying "Boil the spaghetti for 8 to 10 minutes." User A then follows the displayed instructions to continue cooking.

[0993] If User A shows a confused expression while cooking, the device's camera captures that expression and sends it to the emotion engine. The emotion engine recognizes User A's confusion and sends that information to the server. The server uses this data to generate additional instructions, such as "Please check the detailed instructions for making the sauce again."

[0994] After the dish is complete, User A enters a rating into the app, saying "The sauce is a little sour," and sends that rating to the server. The server compiles the ratings and provides the next user with advice, such as "Try adding a little sugar to the sauce." User B then receives that advice the next time they cook and can try it out.

[0995] Example prompts to input to the generative AI model

[0996] Here are some examples of prompts to input to a generative AI model:

[0997] "We are building a system that allows users to upload cooking videos and provides cooking instructions. The text returned from analyzing the video should be in the following format: "Instructions: Do △△". Also, please provide instructions on how to recognize user emotions and reflect them in real-time instructions."

[0998] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0999] Step 1:

[1000] Users film cooking videos and upload them to the server through the application. The input is the cooking video filmed by the user, and the output is the video being sent to the server.

[1001] Step 2:

[1002] The device sends the video file selected by the user to the server and confirms that the transmission is complete. The input is the video uploaded by the user, and the output is the video data sent to the server.

[1003] Step 3:

[1004] The server receives the video data and requests the AI ​​model to analyze it. The AI ​​model extracts cooking instructions and ingredient handling information from each frame of the video. The input is the received video data, and the output is analyzed text data of cooking instructions and ingredient handling information.

[1005] Step 4:

[1006] The server determines the next cooking steps based on the analysis results obtained from the AI ​​model. Specifically, it organizes the cooking steps for each frame based on the analysis results and generates specific instructions such as "mince the onion." The input is the analysis results from the AI ​​model, and the output is the organized cooking steps.

[1007] Step 5:

[1008] The server sends the generated recipe to the terminal. The input is the organized recipe instructions, and the output is the recipe data sent to the terminal.

[1009] Step 6:

[1010] The device displays the cooking instructions received from the server to the user. When displaying the instructions, the voice assistant function is used to allow voice instructions. The input is the cooking instructions data received from the server, and the output is the cooking instructions information displayed to the user. Voice instructions are also provided as a specific action.

[1011] Step 7:

[1012] The user follows the instructions displayed on the device to cook. For example, the user actually stir-fries vegetables in a frying pan based on the instruction "Stir-fry vegetables for 5 minutes." The input is the cooking instructions displayed on the device, and the output is the cooking behavior according to those instructions.

[1013] Step 8:

[1014] The device uses cameras and sensors to capture the user's operations and facial expressions in real time and send them to the emotion engine. The input is the user's real-time operations and facial expression data, and the output is the captured data sent to the emotion engine.

[1015] Step 9:

[1016] The emotion engine analyzes the captured data and recognizes the user's emotional state. For example, it detects emotions such as "happy" or "troubled." The input is the captured operation and facial expression data, and the output is the analyzed emotional state data.

[1017] Step 10:

[1018] The emotion engine sends the recognized emotion data to the server. The input is the analyzed emotional state data, and the output is the emotion data sent to the server.

[1019] Step 11:

[1020] The server analyzes the user's behavioral and emotional data to confirm that it matches the current cooking instructions. For example, if the user appears anxious, it generates instructions to explain the cooking instructions again more slowly. The input is the user's behavioral and emotional data, and the output is instruction data for additional cooking steps.

[1021] Step 12:

[1022] The server generates additional instructions and sends them to the terminal. The input is the instruction data for the additional cooking steps, and the output is the instruction data sent to the terminal.

[1023] Step 13:

[1024] The terminal displays additional instructions to the user and provides voice guidance such as, "Please check the detailed instructions for making the sauce again." The input is the additional instruction data received from the server, and the output is the additional cooking procedure information displayed to the user and the voice guidance.

[1025] Step 14:

[1026] The user rates the completed dish and inputs the rating into the application. The input is the user's rating, and the output is the rating data sent to the server.

[1027] Step 15:

[1028] The terminal transmits the user's rating data to the server. The input is the user's rating data, and the output is the rating data transmitted to the server.

[1029] Step 16:

[1030] The server aggregates the collected evaluation data and provides it as feedback to the AI ​​model. The input is the collected evaluation data, and the output is the feedback data provided to the AI ​​model.

[1031] Step 17:

[1032] The server also aggregates behavioral and emotional data from other users to learn more efficient cooking procedures. The input is behavioral and emotional data from other users, and the output is optimized new cooking procedures and advice.

[1033] Step 18:

[1034] The server generates new optimized cooking recipes and tips and sends them to the device. The input is the optimized cooking recipes and tips, and the output is the cooking recipes and tips sent to the device.

[1035] Step 19:

[1036] The device notifies the user of the newly generated recipe or advice and displays it on the screen, for example, "Next time, add one teaspoon of salt." The input is the optimized cooking instructions or advice received from the server, and the output is the recipe or advice notified to the user.

[1037] (Application example 2)

[1038] 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."

[1039] Conventional cooking support systems only provide instructions for cooking procedures and lack appropriate feedback or support for the user's emotional state. As a result, users can feel stressed while cooking and have difficulty following instructions. Furthermore, there are insufficient means to effectively utilize feedback data from multiple users and optimize recipes. This makes it difficult to improve the cooking experience and recipes.

[1040] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and detecting behavior that differs from the instructed procedures, means for analyzing the user's emotional state and reflecting this in cooking procedures and feedback, means for aggregating behavioral data and feedback from multiple users and generating an optimal recipe, and means for providing the generated recipe to other users. This enables real-time feedback according to the user's emotional state, improving the quality of the cooking experience and enabling recipe optimization by effectively utilizing data from multiple users.

[1041] A "cooking video" is a video that records the cooking process.

[1042] The "analysis results" are information about cooking procedures and ingredient manipulations extracted from cooking videos.

[1043] "Cooking steps" are the steps required to complete a dish.

[1044] "User behavior" refers to the steps and operations performed by the user while cooking.

[1045] "Emotional state" refers to the psychological state that can be read from the user's facial expression, tone of voice, etc.

[1046] "Feedback" refers to evaluations and advice on users' actions.

[1047] A "recipe" is a collection of information about ingredients and steps for making a dish.

[1048] The "server" is a central computer system that receives cooking videos, analyzes them, generates cooking instructions, and compiles data.

[1049] "Monitoring" is a means of observing a user's behavior and emotional state and obtaining the data.

[1050] An "optimized recipe" is a combination of cooking steps and ingredients that has been refined to maximize effectiveness based on feedback and behavioral data from multiple users.

[1051] "Means" are technical components or methods used to achieve a specific function or purpose.

[1052] The "described system" is a collection of a series of devices and programs having specific functions and purposes proposed by the present invention.

[1053] To put this invention into practice, a system is required in which a server, a user's terminal, and an emotion engine work in cooperation with each other. The specific configuration and operation of this system will be described below.

[1054] The server is a central computer system that receives and analyzes cooking videos, generates cooking instructions, collects behavioral data, and processes emotional data. Specifically, when a user uploads a cooking video, the server receives the video and requests an AI model to analyze it. This AI model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format. The server then generates cooking instructions based on the extracted results and sends the instructions to the user's device.

[1055] The user's device (smartphone, tablet, etc.) receives the cooking instructions sent from the server and displays them to the user. The device also monitors the user's cooking operations in real time using cameras and sensors and sends the data to the emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state and sends the data to the server. Based on this, the server generates feedback according to the user's emotional state and sends it to the device.

[1056] Below is an example of how the system works:

[1057] Example 1: Uploading and analyzing a video

[1058] Users film cooking videos on their smartphones and upload them to a server via the app. The videos are then sent to the server and analyzed by an AI model, which then generates specific cooking instructions, such as "stir-fry vegetables for five minutes."

[1059] Example 2: Real-time support

[1060] The server sends the cooking instructions to the user's device, which displays them to the user, who then follows the instructions to proceed with the cooking.

[1061] Example 3: Behavioral analysis and emotion recognition

[1062] If the user does not stir-fry the vegetables for five minutes as instructed (for example, if they only stir-fry for three minutes), the device captures the user's behavior through the camera and sends it to the emotion engine. The emotion engine analyzes the user's emotional state from facial expressions and voice and sends it to the server. The server then adjusts the feedback content based on this data and sends appropriate advice to the user.

[1063] Example 4: Rating and improving recipes

[1064] After a user completes a dish, they rate it within the app. The rating data is sent to the server, which aggregates it and feeds it back into the AI ​​model. The server then analyzes the data from other users to generate an optimized recipe and serve it to the next user.

[1065] This allows users to cook while receiving emotional support in real time, and recipes can be optimized by effectively utilizing data from multiple users.

[1066] For example, a prompt such as "What is the next cooking step?" can be answered with "Stir-fry the vegetables for 5 minutes." This allows the system to provide appropriate answers to the user's questions and doubts.

[1067] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1068] Step 1: Upload your video

[1069] A user shoots a cooking video on their smartphone and uploads it to a server via an application. The input is the cooking video shot by the user, and the output is the video data sent to the server. Specifically, the application selects the user's video file and performs communication processing to upload it to the server.

[1070] Step 2: Analyze the video

[1071] The server requests the AI ​​model to analyze the received video. The input is the video data uploaded in step 1, and the output is text data on the analyzed cooking steps and ingredient manipulations. Specifically, the server analyzes the video frame by frame, and the AI ​​model extracts cooking steps from each frame.

[1072] Step 3: Generate and provide cooking instructions

[1073] The server generates appropriate cooking instructions based on the analysis results and sends them to the user's device. The input is the text-format cooking instruction data obtained in step 2, and the output is the cooking instructions sent to the user's device. Specifically, the server organizes the analysis results, generates cooking instructions in a format that is easy for the user to understand, and sends them to the device.

[1074] Step 4: Display cooking instructions

[1075] The user's device displays the cooking instructions received from the server to the user. The input is the cooking instructions sent from the server in step 3, and the output is the cooking instructions displayed on the device screen. Specifically, the device renders the received data appropriately on the display screen.

[1076] Step 5: Monitor behavior and capture emotions

[1077] The device monitors the user's actions and emotions in real time using cameras and sensors and sends them to the emotion engine. The input is the user's actual actions, facial expressions, and voice data, and the output is the data sent to the emotion engine. Specifically, the device uses a camera and microphone to capture the user's actions and voice, and sends the data to the emotion engine for analysis.

[1078] Step 6: Sentiment analysis and feedback generation

[1079] The emotion engine analyzes the user's emotional state and sends the data to the server. The input is the facial expression and voice data sent from the device in step 5, and the output is the analyzed emotional data and its feedback. Specifically, the emotion engine performs analysis using an emotion analysis algorithm and sends the results to the server.

[1080] Step 7: Provide feedback

[1081] The server generates feedback based on the emotional data and sends it to the user's device. The input is the emotional data and cooking instructions obtained in step 6, and the output is a feedback message sent to the user's device. Specifically, the server generates a feedback message taking into account the user's emotional state and sends it to the device.

[1082] Step 8: Evaluation and data aggregation

[1083] The user rates the completed dish and sends the data to the server through the application. The input is the user's rating data, and the output is the rating data compiled by the server. Specifically, the user fills out a rating form within the application and sends it to the server.

[1084] Step 9: Optimize the recipe

[1085] The server aggregates behavioral data, emotional data, and evaluation data from multiple users and feeds it back to the AI ​​model. The input is the data aggregated in step 8, and the output is a new optimized recipe. Specifically, the server analyzes the data collected by the server using the AI ​​model to generate a new recipe.

[1086] Step 10: Serving an optimized recipe

[1087] The server generates an optimized recipe and provides it to other users. The input is the optimized recipe generated in step 9, and the output is the new recipe displayed on the user's device. Specifically, the server sends the new recipe data to the other user's device, and the application displays it.

[1088] Through these steps, users can receive real-time support for cooking procedures and receive appropriate feedback based on their emotions, improving their cooking experience. By utilizing data from multiple users, recipes are optimized daily, enabling better cooking suggestions.

[1089] 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.

[1090] 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.

[1091] 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.

[1092] [Third embodiment]

[1093] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1094] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1095] 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).

[1096] 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.

[1097] 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.

[1098] 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).

[1099] 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.

[1100] 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.

[1101] 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.

[1102] 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.

[1103] 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.

[1104] 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."

[1105] This invention provides a system that loads cooking videos into AI and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a terminal, and a user. The details are explained below.

[1106] System Configuration

[1107] server

[1108] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses AI models to analyze various data and provide users with cooking instructions tailored to their needs.

[1109] Terminal

[1110] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the information to the server.

[1111] user

[1112] Users upload cooking videos, follow instructions on their devices to cook, and then provide feedback to the system after completing the dish.

[1113] Program processing

[1114] Video upload and analysis

[1115] 1. Users

[1116] Users film their cooking and upload it to a server through the application.

[1117] 2. Terminal

[1118] The device sends the video selected by the user to the server.

[1119] 3. Server

[1120] The server receives the video and passes it to the AI ​​model to begin analysis.

[1121] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[1122] Providing real-time support

[1123] 1. Server

[1124] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[1125] 2. Terminal

[1126] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[1127] 3. Users

[1128] The user follows the displayed instructions to proceed with cooking.

[1129] User behavior analysis

[1130] 1. Terminal

[1131] The device captures user actions using cameras and sensors and transmits them to the server in real time.

[1132] 2. Server

[1133] The server analyzes the user's behavioral data and compares it with the instructions.

[1134] If different behavior is detected, the data is passed to the AI ​​model and saved as learning data.

[1135] Feedback and Learning

[1136] 1. Users

[1137] Users rate the finished dish and enter their rating into the app.

[1138] 2. Terminal

[1139] The terminal transmits the user's evaluation data to the server.

[1140] 3. Server

[1141] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[1142] It also aggregates other users' rating data to generate optimal recipes.

[1143] Recipe Improvement and Serving

[1144] 1. Server

[1145] The server learns more efficient cooking procedures based on aggregated behavioral data and feedback.

[1146] Generate new optimized recipes and tips and share them with other users.

[1147] 2. Terminal

[1148] The device will display new recipes and tips to the user.

[1149] Specific examples

[1150] Example 1: Uploading and analyzing a video

[1151] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[1152] Example 2: Real-time support

[1153] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[1154] Example 3: Behavioral analysis and feedback

[1155] If user A actually stir-fries vegetables for only 3 minutes, the device will capture this behavior and send it to the server, which will then identify the different behavior and store it in the AI ​​model.

[1156] Example 4: Rating and improving recipes

[1157] User B also cooks the dish and sends a rating to the server saying it was "delicious." The server uses this rating data to provide a new recipe to the next user.

[1158] In this way, recipes are dynamically improved based on user behavior and feedback, helping everyone cook better.

[1159] The processing flow will be explained below.

[1160] Step 1:

[1161] user

[1162] Cooking videos are filmed and uploaded to the system through the application.

[1163] Step 2:

[1164] Terminal

[1165] Send the uploaded video to the server.

[1166] Step 3:

[1167] server

[1168] Receives video files and requests the AI ​​model to analyze them.

[1169] Step 4:

[1170] server

[1171] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[1172] Step 5:

[1173] server

[1174] Based on the analysis results, the next cooking procedure to be carried out is determined and sent to the terminal.

[1175] Step 6:

[1176] Terminal

[1177] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[1178] Step 7:

[1179] user

[1180] Follow the displayed instructions to continue cooking.

[1181] Step 8:

[1182] Terminal

[1183] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[1184] Step 9:

[1185] server

[1186] Analyze the received behavioral data and confirm that it matches the instructed procedures.

[1187] Step 10:

[1188] server

[1189] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[1190] Step 11:

[1191] user

[1192] Once cooking is complete, the food is tasted and evaluated.

[1193] Step 12:

[1194] Terminal

[1195] Send user rating data to the server.

[1196] Step 13:

[1197] server

[1198] Provide feedback to the AI ​​model based on the collected evaluation data.

[1199] Step 14:

[1200] server

[1201] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[1202] Step 15:

[1203] server

[1204] The generated new recipes and tips are sent to the device.

[1205] Step 16:

[1206] Terminal

[1207] The device will display new recipes and tips to the user.

[1208] Step 17:

[1209] user

[1210] Use new recipes and advice to prepare your next meal.

[1211] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[1212] Example 1

[1213] 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."

[1214] It is difficult for beginners and inexperienced users to cook accurately while following a recipe. It is also difficult to provide optimal support based on each individual's cooking skills and preferences. Furthermore, the inability to fully utilize user behavioral data and feedback limits improvements to the quality of recipes. This creates the challenge of making high-quality meals due to the lack of appropriate cooking support.

[1215] 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.

[1216] In this invention, the server includes means for receiving and analyzing cooking videos from users, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior with cameras and sensors and detecting behavior that deviates from the instructed procedures, means for aggregating behavioral data and feedback from multiple users to generate optimal recipes, and means for providing the generated recipes and cooking advice to other users. This makes it possible to provide optimal cooking support based on each user's skills and preferences and to improve the quality of recipes by utilizing accumulated data.

[1217] "User" refers to an individual who performs cooking operations, uploads videos, and rates them.

[1218] "Server" refers to a computing device that analyzes received cooking videos, generates cooking instructions, and aggregates user behavior data and feedback.

[1219] "Terminal" refers to a device such as a user's smartphone, tablet, or PC, which displays cooking instructions from the server and monitors the user's behavior.

[1220] "Means for receiving and analyzing videos" refers to the technology in which a server receives cooking videos uploaded by users and analyzes their content using a generative AI model.

[1221] "Means for instructing the user on cooking instructions" refers to a technology in which the analyzed cooking instructions are sent from the server to the terminal, and the terminal displays them to the user.

[1222] "Means of monitoring using cameras and sensors" refers to technology that uses cameras and sensors installed on the device to monitor the user's cooking operations in real time and transmits that data to a server.

[1223] "Means for aggregating behavioral data and feedback" refers to the technology by which a server collects user behavioral data and evaluation data and statistically analyzes it.

[1224] "Means for generating optimal recipes" refers to technology in which an AI model creates more efficient and appropriate cooking procedures and recipes based on aggregated data.

[1225] "Means for providing generated recipes and cooking advice" refers to technology for transmitting optimized recipes and cooking advice from a server to other users and displaying them on their terminals.

[1226] "Means for collecting evaluation data" refers to the technology that collects food evaluations from multiple users and stores them in a database.

[1227] "Means for training an AI model" refers to the technology of inputting collected behavioral data and evaluation data into an AI model and allowing the model to acquire new knowledge through its learning process.

[1228] This invention relates to a system that uses AI to load cooking videos and provide step-by-step support in real time. The main components of the system are a server, a terminal, and a user, all of which work together. The details of the system and how to use it are explained below.

[1229] System configuration

[1230] server

[1231] The server plays a central role in this system. It receives cooking videos, analyzes them, generates instructions, collects behavioral data, and generates optimal recipes. Specifically, the server analyzes various data using a generative AI model (e.g., OpenAI's GPT-4).

[1232] Terminal

[1233] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends it to the server. The terminal is also equipped with a camera and sensors that capture the user's cooking operations in real time.

[1234] User

[1235] Users film cooking videos and upload them to the server via the application. They then follow instructions on their device to cook, and once the dish is complete, they provide feedback to the system.

[1236] Program processing

[1237] Video upload and analysis

[1238] 1. A user shoots a cooking video on their smartphone. The user launches the application, selects the recorded video, and presses the upload button.

[1239] 2. The device sends the video uploaded by the user to the server.

[1240] 3. The server receives the video data and analyzes the video using the generative AI model, using the prompt "Please extract the cooking steps and ingredients from this video." Based on this prompt, the AI ​​model extracts the cooking steps and ingredients from the video in text format.

[1241] Providing real-time support

[1242] 1. The server receives the analysis results and determines the next cooking step, for example, "sauté the vegetables for 5 minutes."

[1243] 2. The device displays the cooking instructions sent from the server to the user, who then follows the instructions to proceed with the cooking.

[1244] User behavior analysis

[1245] 1. The device captures the user's cooking operations using cameras and sensors and transmits them to the server in real time, for example, monitoring frying time and temperature.

[1246] 2. The server analyzes the received behavioral data and compares the instructed steps with the actual behavior. If any discrepancies are detected, the data is passed to the generative AI model and saved as training data.

[1247] Feedback and Learning

[1248] 1. After the cooking is complete, the user enters their evaluation into the app, such as "It was delicious" or "I wish it was a little saltier."

[1249] 2. The terminal sends the evaluation data entered by the user to the server.

[1250] 3. The server aggregates the evaluation data and provides it as feedback to the generative AI model. It also aggregates evaluation data from other users to generate the optimal recipe.

[1251] Recipe Improvement and Serving

[1252] 1. The server learns more efficient cooking procedures based on aggregated behavioral and feedback data, and uses generative AI models to create new recipes and cooking advice.

[1253] 2. The device displays the newly generated recipes and advice to the user.

[1254] Specific examples

[1255] Example 1: Uploading and analyzing a video

[1256] User A films a cooking video on their smartphone and uploads it to a server via an application. The device sends the video to the server, which then analyzes it using a generative AI model (e.g., OpenAI's GPT-4) based on the prompt, "Please extract the cooking steps and ingredients from this video." The AI ​​model then generates the instruction, "Stir-fry the vegetables for 5 minutes."

[1257] Example 2: Real-time support

[1258] The server sends the generated instructions to the terminal, and the terminal displays the instruction "Stir-fry vegetables for 5 minutes" to User A. User A cooks according to the instructions.

[1259] Example 3: Behavioral analysis and feedback

[1260] If user A actually stir-fries the vegetables for only 3 minutes, the device captures this behavior and sends it to the server, which then identifies the different behavior and stores it in the generative AI model.

[1261] Example 4: Rating and improving recipes

[1262] User B also cooks the dish and sends a rating of "delicious" to the server. Based on this rating data, the server provides new recipes and advice to other users.

[1263] In this way, recipes are constantly improved based on user actions and feedback, helping everyone cook better.

[1264] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1265] Step 1:

[1266] The user shoots a cooking video on their smartphone, launches the application, selects the recorded video, and presses the upload button.

[1267] Input: Filmed cooking video

[1268] Output: Video file selected by user

[1269] Step 2:

[1270] The terminal receives a video upload request from the user and transmits the video file to the server.

[1271] Input: User's video upload request and video file

[1272] Output: Video file sent to the server

[1273] Step 3:

[1274] The server receives the video data and sends an analysis prompt to the generative AI model. The prompt is "Please extract the cooking steps and ingredients from this video." The AI ​​model analyzes the video and outputs the cooking steps and ingredients in text format.

[1275] Input: Video file sent to the server, analysis prompt

[1276] Output: Extracted text data of cooking instructions and ingredients

[1277] Step 4:

[1278] The server receives the analysis results and determines the next cooking steps, which are then used to provide specific instructions to the user.

[1279] Input: Extracted text data of cooking instructions and ingredients

[1280] Output: Cooking instructions text to the user

[1281] Step 5:

[1282] The device receives cooking instructions from the server and displays them to the user. For example, specific instructions such as "sauté vegetables for 5 minutes" are displayed. The user then follows the displayed instructions to cook.

[1283] Input: Cooking instruction text from the server

[1284] Output: Cooking instructions displayed to the user

[1285] Step 6:

[1286] The device captures the user's cooking operations in real time using cameras and sensors and sends the data, including frying time and temperature, to a server.

[1287] Input: User's real-time cooking operation data

[1288] Output: Cooking operation data sent to the server

[1289] Step 7:

[1290] The server analyzes the behavioral data and compares the instructions with the actual behavior. For example, it checks whether the user actually stir-fried vegetables for five minutes. If a different behavior is detected, the data is passed to the generative AI model for future feedback and learning.

[1291] Input: Cooking operation data sent

[1292] Output: Analyzed behavior data, detected abnormal behavior data

[1293] Step 8:

[1294] After the user has finished cooking, they can enter their evaluation of the dish through the application, for example, by entering comments such as "It was delicious" or "It wasn't spicy enough."

[1295] Input: User food rating data

[1296] Output: Rating data input to the app

[1297] Step 9:

[1298] The terminal transmits the user's evaluation data to the server.

[1299] Input: Food rating data from users

[1300] Output: Rating data sent to the server

[1301] Step 10:

[1302] The server aggregates the evaluation data and provides it as feedback to the generative AI model, which also aggregates evaluation data from other users to generate the optimal recipe.

[1303] Input: Aggregated rating data

[1304] Output: Feedback data for generative AI model, optimal recipe data

[1305] Step 11:

[1306] The server generates new recipes and cooking advice based on the collected behavioral data and feedback data, and provides the generated recipes and advice to other users.

[1307] Input: Behavioral data, feedback data

[1308] Output: New recipes, cooking advice

[1309] Step 12:

[1310] The device displays the newly generated recipes and advice to the user, who can then follow the new recipes and advice to create even better dishes.

[1311] Input: New recipes and cooking advice from the server

[1312] Output: New recipes and cooking advice displayed to the user

[1313] (Application example 1)

[1314] 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."

[1315] In recent years, the number of beginners and busy people has increased, and the need for easy and efficient cooking has grown. However, existing cooking support systems lack sufficient support for how to use individual ingredients and real-time cooking procedures, making it difficult for users to proceed with cooking at the appropriate time. It is also difficult to receive real-time feedback during the cooking process, resulting in an increased failure rate.

[1316] 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.

[1317] In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior and detecting behavior that differs from the instructed procedures, means for aggregating behavioral data and feedback from multiple users and generating optimal recipes, means for providing the generated recipes to other users, means for recognizing ingredients with a camera on a smart device and generating corresponding recipes, and means for displaying cooking procedures on a visual display in real time, thereby enabling users to efficiently select ingredients in the supermarket and receive real-time support when cooking.

[1318] "Cooking videos" refer to footage recorded by users during the cooking process, and cooking steps are extracted by analyzing this video data.

[1319] "Analysis" refers to the process of analyzing the received cooking video using AI models and image recognition technology, and extracting the cooking steps and ingredient manipulations in text format.

[1320] "Cooking procedure" refers to each step in the process of cooking ingredients, specifically including operations such as preparing ingredients, cutting, frying, and boiling.

[1321] "Users" refer to people who use this system to cook, upload videos, check cooking instructions, and provide feedback.

[1322] "Monitoring" refers to the process of monitoring the user's cooking behavior using cameras and sensors and sending the data to a server in real time.

[1323] "Behavioral data" refers to data on the cooking actions actually performed by the user, and includes specific action data obtained from video and sensors.

[1324] "Feedback" refers to the user inputting their evaluation and impressions of the completed dish and sending it to the system, which the system uses as learning data.

[1325] The "optimal recipe" is a recipe generated based on behavioral data and feedback from multiple users, and improves taste and cooking efficiency.

[1326] "Smart device" refers to an electronic device with a camera and display function, and specifically includes smart glasses and smartphones.

[1327] "Ingredient recognition" refers to capturing an image of an ingredient using a smart device's camera and analyzing that image to identify a specific ingredient.

[1328] "Visual display" refers to the screen or display of a smart device, in this case intended to show cooking instructions or recipes to the user in real time.

[1329] This invention provides a system that uses AI to read cooking videos and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a device, and a user. The details are described below.

[1330] System Configuration

[1331] server

[1332] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses a generative AI model to analyze various data and provide users with cooking instructions tailored to their needs. It also optimizes recipes based on user feedback. Specifically, it uses TensorFlow or PyTorch to operate a deep learning model.

[1333] Terminal

[1334] The user's device (smart glasses, smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the results to the server. In addition, the terminal recognizes ingredients in real time using the user's camera, and displays the results analyzed by the server on the display. The terminal usually uses an image recognition library such as OpenCV.

[1335] user

[1336] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system, including evaluations of cooking efficiency and taste. User behavior data is captured by cameras and sensors and sent to the server in real time.

[1337] Explanation of program processing

[1338] Video upload and analysis

[1339] 1. The user takes a video of the cooking using a smartphone or other device and uploads it to the server via the application.

[1340] 2. The device sends the video selected by the user to the server.

[1341] 3. The server receives the video and passes it to the AI ​​model to begin analysis. The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[1342] Providing real-time support

[1343] 1. The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[1344] 2. The device displays the cooking instructions to the user, for example, "Sauté the vegetables for 5 minutes."

[1345] 3. The user follows the displayed instructions to proceed with cooking.

[1346] Food ingredient recognition using smart devices

[1347] 1. The device sends the ingredients identified by the smart glasses camera to the server.

[1348] 2. The server analyzes the ingredients, generates a corresponding recipe, and sends it to the device.

[1349] 3. The device will display the recipe and cooking instructions on the screen, for example, "Here's how to make a salad using these carrots."

[1350] Specific examples

[1351] Imagine a user is in a supermarket, putting on smart glasses and pointing a carrot at the camera.

[1352] The device recognizes the carrot and sends the data to the server.

[1353] The server generates a recipe based on carrots and sends the recipe and cooking instructions for "Healthy Salad with Carrots" to the terminal.

[1354] The device displays this information on its screen and guides the user through the cooking process in real time.

[1355] Example prompts to input to the generative AI model

[1356] The user will take a photo of the ingredients and send it to us, and we will generate a recommended recipe using those ingredients. We will also output cooking instructions in real time.

[1357] In this way, users can efficiently select ingredients and receive real-time cooking instructions while shopping in a physical store.

[1358] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1359] Step 1:

[1360] The user takes a picture of the food with the camera on the smart glasses. The camera captures the food image data and stores it on the device. The input is the food image taken by the camera, and the output is the image data stored on the device.

[1361] Step 2:

[1362] The device sends the image of the food taken by the user to the server. The image data is sent via the HTTPS protocol. The input is the image data stored on the device, and the output is the image data sent to the server.

[1363] Step 3:

[1364] The server passes the received image data to the generative AI model for analysis. This analysis uses image recognition technology (e.g., OpenCV) to recognize ingredients and inputs that information into the AI ​​model. The input is the image data sent to the server, and the output is the recognized ingredient information.

[1365] Step 4:

[1366] The server generates an appropriate recipe based on the recognized ingredient information. At this time, the generative AI model uses past data and feedback to propose optimal cooking procedures. The input is the recognized ingredient information and past feedback data, and the output is the generated recipe and cooking procedures.

[1367] Step 5:

[1368] The server sends the generated recipe and cooking instructions to the terminal. Again, the HTTPS protocol is used. The input is the generated recipe and cooking instructions, and the output is the recipe and cooking instructions sent to the terminal.

[1369] Step 6:

[1370] The terminal displays the received recipe and cooking instructions on a visual display, allowing the user to see the next action in real time. The input is the recipe and cooking instructions sent to the terminal, and the output is the cooking instructions shown on the display.

[1371] Step 7:

[1372] The user follows the visual display to proceed with the cooking. For example, if the instruction is "sauté carrots for 5 minutes," the user follows the instructions to cook. The output is the cooking action performed by the user.

[1373] Step 8:

[1374] The device monitors the user's cooking behavior using cameras and sensors and sends the data to a server. The input is the user's cooking behavior data, and the output is the behavior data sent to the server.

[1375] Step 9:

[1376] The server analyzes the received behavioral data and detects any behavior that deviates from the instructed procedure. Furthermore, this behavioral data is provided as feedback to the AI ​​model and saved as training data for the model. The input is the behavioral data sent to the server, and the output is the training data provided to the AI ​​model.

[1377] Step 10:

[1378] The user rates the cooked dish and inputs the rating into the terminal. The terminal sends the rating data to the server. The input is the rating data entered by the user, and the output is the rating data sent to the server.

[1379] Step 11:

[1380] The server provides optimal recipes to other users based on the received rating data. It also improves the recipes using the aggregated rating data and behavioral data. The input is the rating data and behavioral data sent to the server, and the output is an improved recipe and helpful advice.

[1381] 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.

[1382] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[1383] System Configuration

[1384] server

[1385] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotion data from the emotion engine and adjusts cooking procedures and timings.

[1386] Terminal

[1387] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server.

[1388] Emotion Engine

[1389] The emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice.

[1390] user

[1391] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[1392] Program processing

[1393] Video upload and analysis

[1394] 1. Users

[1395] Users film their cooking and upload it to a server through the application.

[1396] 2. Terminal

[1397] The device sends the video selected by the user to the server.

[1398] 3. Server

[1399] The server receives the video and asks the AI ​​model to analyze it.

[1400] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[1401] Providing real-time support

[1402] 1. Server

[1403] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[1404] 2. Terminal

[1405] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[1406] 3. Users

[1407] The user follows the displayed instructions to proceed with cooking.

[1408] User behavior analysis and emotion recognition

[1409] 1. Terminal

[1410] The device captures user actions in real time using cameras and sensors and sends them to the emotion engine.

[1411] 2. Emotion Engine

[1412] The emotion engine analyzes facial expressions and voice to recognize the user's emotional state.

[1413] The recognized emotion data is sent to the server.

[1414] 3. Server

[1415] The server analyzes the user's behavioral and emotional data and checks whether it matches the instructed steps.

[1416] If different behaviors or emotional changes are detected, the data is passed to the AI ​​model and saved as learning data.

[1417] Feedback and Learning

[1418] 1. Users

[1419] Users rate the finished dish and enter their rating into the app.

[1420] 2. Terminal

[1421] The terminal transmits the user's evaluation data to the server.

[1422] 3. Server

[1423] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[1424] It also aggregates other users' rating data to generate optimal recipes.

[1425] Recipe Improvement and Serving

[1426] 1. Server

[1427] The server learns more efficient cooking procedures based on aggregated behavioral data, emotional data, and feedback.

[1428] Generate new optimized recipes and tips and share them with other users.

[1429] 2. Terminal

[1430] The device will display new recipes and tips to the user.

[1431] Specific examples

[1432] Example 1: Uploading and analyzing a video

[1433] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[1434] Example 2: Real-time support

[1435] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[1436] Example 3: Behavioral analysis and emotion recognition

[1437] If User A actually stir-fries vegetables for only 3 minutes, the device will capture User A's actions and facial expressions with the camera and send them to the server. The emotion engine will recognize User A's emotional state and report it to the server. The server will review the different behavioral and emotional data and store it in the AI ​​model.

[1438] Example 4: Rating and improving recipes

[1439] User B also cooks the dish and sends a rating of "delicious" to the server. The server uses this rating data and emotion data to provide new recipes and advice to the next user.

[1440] In this way, recipes are dynamically improved based on user behavior, sentiment, and feedback, helping everyone cook better.

[1441] The processing flow will be explained below.

[1442] Step 1:

[1443] user

[1444] Cooking videos are filmed and uploaded to the system through the application.

[1445] Step 2:

[1446] Terminal

[1447] Send the uploaded video to the server.

[1448] Step 3:

[1449] server

[1450] Receives video files and requests the AI ​​model to analyze them.

[1451] Step 4:

[1452] server

[1453] The AI ​​model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format.

[1454] Step 5:

[1455] server

[1456] Based on the analysis results, the next cooking procedure is determined and the instructions are sent to the terminal.

[1457] Step 6:

[1458] Terminal

[1459] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[1460] Step 7:

[1461] user

[1462] Follow the displayed instructions to continue cooking.

[1463] Step 8:

[1464] Terminal

[1465] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[1466] Step 9:

[1467] Emotion Engine

[1468] It analyzes the user's facial expressions and voice to recognize their emotional state, and sends the acquired emotional data to the server.

[1469] Step 10:

[1470] server

[1471] The received behavioral and emotional data is analyzed and compared with the instructed procedures.

[1472] Step 11:

[1473] server

[1474] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[1475] Step 12:

[1476] server

[1477] Based on the recognized emotional data, the cooking instructions and timing of advice are adjusted.

[1478] Step 13:

[1479] user

[1480] Once cooking is complete, the food is tasted and evaluated.

[1481] Step 14:

[1482] Terminal

[1483] Send user rating data to the server.

[1484] Step 15:

[1485] server

[1486] Provide feedback to the AI ​​model based on the collected evaluation data.

[1487] Step 16:

[1488] server

[1489] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[1490] Step 17:

[1491] server

[1492] The generated new recipes and tips are sent to the device.

[1493] Step 18:

[1494] Terminal

[1495] The device will display new recipes and tips to the user.

[1496] Step 19:

[1497] user

[1498] Use new recipes and advice to prepare your next meal.

[1499] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[1500] Example 2

[1501] 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."

[1502] Conventional cooking assistance systems can only monitor user behavior and lack support that reflects user emotions. Furthermore, methods that improve recipes based solely on user feedback may not provide effective real-time cooking assistance. As a result, follow-up during cooking is insufficient, resulting in a lack of improvement in the user's cooking experience.

[1503] 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 means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and emotions and detecting behavioral and emotional changes that differ from the instructed procedures, means for aggregating behavioral data, emotional data, and feedback from multiple users and generating optimal cooking procedures, and means for providing the generated cooking procedures and advice to other users. This enables real-time cooking assistance that reflects both the user's behavior and emotions.

[1504] "Cooking videos" are digital data that record cooking steps and how to prepare ingredients.

[1505] "Analysis" refers to the process of analyzing cooking videos based on an AI model and extracting cooking steps and ingredient manipulations in text format.

[1506] A "cooking procedure" is each step required to complete a dish, and includes specific actions, time, and conditions.

[1507] "User" refers to an individual user of the cooking assistance system.

[1508] "Monitoring" is the means of observing and recording a user's behavior and emotional state in real time.

[1509] "Emotional changes" refers to changes in emotions recognized by analyzing changes in the user's facial expressions and voice.

[1510] "Feedback" refers to data on the evaluations and impressions users provide about the completed dishes.

[1511] The "optimal cooking procedure" is a method generated as the most effective and efficient cooking procedure based on the user's behavioral data, emotional data, and feedback.

[1512] "Advice" is information containing additional instructions or suggestions that will be helpful during cooking or for your next cooking session.

[1513] A "server" is a computer system that performs central processing such as analysis, data collection, and instruction generation.

[1514] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[1515] System Configuration

[1516] server

[1517] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotional data from the emotion engine and adjusts cooking steps and timing. Specifically, the server receives the video and requests analysis from the AI ​​model. The AI ​​model analyzes the video and extracts cooking steps and ingredient manipulations for each frame in text format.

[1518] Terminal

[1519] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server. The terminal can capture the user's actions and facial expressions in real time using cameras and sensors.

[1520] Emotion Engine

[1521] The emotion engine analyzes the user's facial expressions and voice to provide a function for recognizing their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice. The emotion engine analyzes the captured facial and voice data to detect emotions such as "happy" or "troubled."

[1522] user

[1523] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[1524] Specific examples

[1525] User A takes a video of "how to make spaghetti" on their smartphone and uploads it to the server using the app. The device sends the video to the server, which then analyzes it with an AI model. The AI ​​model analyzes the cooking steps and generates specific instructions, such as "boil the spaghetti for 8 to 10 minutes."

[1526] The server sends the instruction "Boil the spaghetti for 8 to 10 minutes" to the device. The device displays this instruction to User A and provides a voice message saying "Boil the spaghetti for 8 to 10 minutes." User A then follows the displayed instructions to continue cooking.

[1527] If User A shows a confused expression while cooking, the device's camera captures that expression and sends it to the emotion engine. The emotion engine recognizes User A's confusion and sends that information to the server. The server uses this data to generate additional instructions, such as "Please check the detailed instructions for making the sauce again."

[1528] After the dish is complete, User A enters a rating into the app, saying "The sauce is a little sour," and sends that rating to the server. The server compiles the ratings and provides the next user with advice, such as "Try adding a little sugar to the sauce." User B then receives that advice the next time they cook and can try it out.

[1529] Example prompts to input to the generative AI model

[1530] Here are some examples of prompts to input to a generative AI model:

[1531] "We are building a system that allows users to upload cooking videos and provides cooking instructions. The text returned from analyzing the video should be in the following format: "Instructions: Do △△". Also, please provide instructions on how to recognize user emotions and reflect them in real-time instructions."

[1532] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1533] Step 1:

[1534] Users film cooking videos and upload them to the server through the application. The input is the cooking video filmed by the user, and the output is the video being sent to the server.

[1535] Step 2:

[1536] The device sends the video file selected by the user to the server and confirms that the transmission is complete. The input is the video uploaded by the user, and the output is the video data sent to the server.

[1537] Step 3:

[1538] The server receives the video data and requests the AI ​​model to analyze it. The AI ​​model extracts cooking instructions and ingredient handling information from each frame of the video. The input is the received video data, and the output is the analyzed cooking instructions and ingredient handling information in text format.

[1539] Step 4:

[1540] The server determines the next cooking steps based on the analysis results obtained from the AI ​​model. Specifically, it organizes the cooking steps for each frame based on the analysis results and generates specific instructions such as "mince the onion." The input is the analysis results from the AI ​​model, and the output is the organized cooking steps.

[1541] Step 5:

[1542] The server sends the generated recipe to the terminal. The input is the organized recipe instructions, and the output is the recipe data sent to the terminal.

[1543] Step 6:

[1544] The device displays the cooking instructions received from the server to the user. When displaying the instructions, the voice assistant function is used to allow voice instructions. The input is the cooking instructions data received from the server, and the output is the cooking instructions information displayed to the user. Voice instructions are also provided as a specific action.

[1545] Step 7:

[1546] The user follows the instructions displayed on the device to cook. For example, the user actually stir-fries vegetables in a frying pan based on the instruction "Stir-fry vegetables for 5 minutes." The input is the cooking instructions displayed on the device, and the output is the cooking behavior according to those instructions.

[1547] Step 8:

[1548] The device uses cameras and sensors to capture the user's operations and facial expressions in real time and send them to the emotion engine. The input is the user's real-time operations and facial expression data, and the output is the captured data sent to the emotion engine.

[1549] Step 9:

[1550] The emotion engine analyzes the captured data and recognizes the user's emotional state. For example, it detects emotions such as "happy" or "troubled." The input is the captured operation and facial expression data, and the output is the analyzed emotional state data.

[1551] Step 10:

[1552] The emotion engine sends the recognized emotion data to the server. The input is the analyzed emotional state data, and the output is the emotion data sent to the server.

[1553] Step 11:

[1554] The server analyzes the user's behavioral and emotional data to confirm that it matches the current cooking instructions. For example, if the user appears anxious, it generates instructions to explain the cooking instructions again more slowly. The input is the user's behavioral and emotional data, and the output is instruction data for additional cooking steps.

[1555] Step 12:

[1556] The server generates additional instructions and sends them to the terminal. The input is the instruction data for the additional cooking steps, and the output is the instruction data sent to the terminal.

[1557] Step 13:

[1558] The terminal displays additional instructions to the user and provides voice guidance such as, "Please check the detailed instructions for making the sauce again." The input is the additional instruction data received from the server, and the output is the additional cooking procedure information displayed to the user and the voice guidance.

[1559] Step 14:

[1560] The user rates the completed dish and inputs the rating into the application. The input is the user's rating, and the output is the rating data sent to the server.

[1561] Step 15:

[1562] The terminal transmits the user's rating data to the server. The input is the user's rating data, and the output is the rating data transmitted to the server.

[1563] Step 16:

[1564] The server aggregates the collected evaluation data and provides it as feedback to the AI ​​model. The input is the collected evaluation data, and the output is the feedback data provided to the AI ​​model.

[1565] Step 17:

[1566] The server also aggregates behavioral and emotional data from other users to learn more efficient cooking procedures. The input is behavioral and emotional data from other users, and the output is optimized new cooking procedures and advice.

[1567] Step 18:

[1568] The server generates new optimized cooking recipes and tips and sends them to the device. The input is the optimized cooking recipes and tips, and the output is the cooking recipes and tips sent to the device.

[1569] Step 19:

[1570] The device notifies the user of the newly generated recipe or advice and displays it on the screen, for example, "Next time, add one teaspoon of salt." The input is the optimized cooking instructions or advice received from the server, and the output is the recipe or advice notified to the user.

[1571] (Application example 2)

[1572] 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."

[1573] Conventional cooking support systems only provide instructions for cooking procedures and lack appropriate feedback or support for the user's emotional state. As a result, users can feel stressed while cooking and have difficulty following instructions. Furthermore, there are insufficient means to effectively utilize feedback data from multiple users and optimize recipes. This makes it difficult to improve the cooking experience and recipes.

[1574] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and detecting behavior that differs from the instructed procedures, means for analyzing the user's emotional state and reflecting this in cooking procedures and feedback, means for aggregating behavioral data and feedback from multiple users and generating an optimal recipe, and means for providing the generated recipe to other users. This enables real-time feedback according to the user's emotional state, improving the quality of the cooking experience and enabling recipe optimization by effectively utilizing data from multiple users.

[1575] A "cooking video" is a video that records the cooking process.

[1576] The "analysis results" are information about cooking procedures and ingredient manipulations extracted from cooking videos.

[1577] "Cooking steps" are the steps required to complete a dish.

[1578] "User behavior" refers to the steps and operations performed by the user while cooking.

[1579] "Emotional state" refers to the psychological state that can be read from the user's facial expression, tone of voice, etc.

[1580] "Feedback" refers to evaluations and advice on users' actions.

[1581] A "recipe" is a collection of information about ingredients and steps for making a dish.

[1582] The "server" is a central computer system that receives cooking videos, analyzes them, generates cooking instructions, and compiles data.

[1583] "Monitoring" is a means of observing a user's behavior and emotional state and obtaining the data.

[1584] An "optimized recipe" is a combination of cooking steps and ingredients that has been refined to maximize effectiveness based on feedback and behavioral data from multiple users.

[1585] "Means" are technical components or methods used to achieve a specific function or purpose.

[1586] The "described system" is a collection of a series of devices and programs having specific functions and purposes proposed by the present invention.

[1587] To put this invention into practice, a system is required in which a server, a user's terminal, and an emotion engine work in cooperation with each other. The specific configuration and operation of this system will be described below.

[1588] The server is a central computer system that receives and analyzes cooking videos, generates cooking instructions, collects behavioral data, and processes emotional data. Specifically, when a user uploads a cooking video, the server receives the video and requests an AI model to analyze it. This AI model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format. The server then generates cooking instructions based on the extracted results and sends the instructions to the user's device.

[1589] The user's device (smartphone, tablet, etc.) receives the cooking instructions sent from the server and displays them to the user. The device also monitors the user's cooking operations in real time using cameras and sensors and sends the data to the emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state and sends the data to the server. Based on this, the server generates feedback according to the user's emotional state and sends it to the device.

[1590] Below is an example of how the system works:

[1591] Example 1: Uploading and analyzing a video

[1592] Users film cooking videos on their smartphones and upload them to a server via the app. The videos are then sent to the server and analyzed by an AI model, which then generates specific cooking instructions, such as "stir-fry vegetables for five minutes."

[1593] Example 2: Real-time support

[1594] The server sends the cooking instructions to the user's device, which displays them to the user, who then follows the instructions to proceed with the cooking.

[1595] Example 3: Behavioral analysis and emotion recognition

[1596] If the user does not stir-fry the vegetables for five minutes as instructed (for example, if they only stir-fry for three minutes), the device captures the user's behavior through the camera and sends it to the emotion engine. The emotion engine analyzes the user's emotional state from facial expressions and voice and sends it to the server. The server then adjusts the feedback content based on this data and sends appropriate advice to the user.

[1597] Example 4: Rating and improving recipes

[1598] After a user completes a dish, they rate it within the app. The rating data is sent to the server, which aggregates it and feeds it back into the AI ​​model. The server then analyzes the data from other users to generate an optimized recipe and serve it to the next user.

[1599] This allows users to cook while receiving emotional support in real time, and recipes can be optimized by effectively utilizing data from multiple users.

[1600] For example, a prompt such as "What is the next cooking step?" can be answered with "Stir-fry the vegetables for 5 minutes." This allows the system to provide appropriate answers to the user's questions and doubts.

[1601] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1602] Step 1: Upload your video

[1603] A user shoots a cooking video on their smartphone and uploads it to a server via an application. The input is the cooking video shot by the user, and the output is the video data sent to the server. Specifically, the application selects the user's video file and performs communication processing to upload it to the server.

[1604] Step 2: Analyze the video

[1605] The server requests the AI ​​model to analyze the received video. The input is the video data uploaded in step 1, and the output is text data on the analyzed cooking steps and ingredient manipulations. Specifically, the server analyzes the video frame by frame, and the AI ​​model extracts cooking steps from each frame.

[1606] Step 3: Generate and provide cooking instructions

[1607] The server generates appropriate cooking instructions based on the analysis results and sends them to the user's device. The input is the text-format cooking instruction data obtained in step 2, and the output is the cooking instructions sent to the user's device. Specifically, the server organizes the analysis results, generates cooking instructions in a format that is easy for the user to understand, and sends them to the device.

[1608] Step 4: Display cooking instructions

[1609] The user's device displays the cooking instructions received from the server to the user. The input is the cooking instructions sent from the server in step 3, and the output is the cooking instructions displayed on the device screen. Specifically, the device renders the received data appropriately on the display screen.

[1610] Step 5: Monitor behavior and capture emotions

[1611] The device monitors the user's actions and emotions in real time using cameras and sensors and sends them to the emotion engine. The input is the user's actual actions, facial expressions, and voice data, and the output is the data sent to the emotion engine. Specifically, the device uses a camera and microphone to capture the user's actions and voice, and sends the data to the emotion engine for analysis.

[1612] Step 6: Sentiment analysis and feedback generation

[1613] The emotion engine analyzes the user's emotional state and sends the data to the server. The input is the facial expression and voice data sent from the device in step 5, and the output is the analyzed emotional data and its feedback. Specifically, the emotion engine performs analysis using an emotion analysis algorithm and sends the results to the server.

[1614] Step 7: Provide feedback

[1615] The server generates feedback based on the emotional data and sends it to the user's device. The input is the emotional data and cooking instructions obtained in step 6, and the output is a feedback message sent to the user's device. Specifically, the server generates a feedback message taking into account the user's emotional state and sends it to the device.

[1616] Step 8: Evaluation and data aggregation

[1617] The user rates the completed dish and sends the data to the server through the application. The input is the user's rating data, and the output is the rating data compiled by the server. Specifically, the user fills out a rating form within the application and sends it to the server.

[1618] Step 9: Optimize the recipe

[1619] The server aggregates behavioral data, emotional data, and evaluation data from multiple users and feeds it back to the AI ​​model. The input is the data aggregated in step 8, and the output is a new optimized recipe. Specifically, the server analyzes the data collected by the server using the AI ​​model to generate a new recipe.

[1620] Step 10: Serving an optimized recipe

[1621] The server generates an optimized recipe and provides it to other users. The input is the optimized recipe generated in step 9, and the output is the new recipe displayed on the user's device. Specifically, the server sends the new recipe data to the other user's device, and the application displays it.

[1622] Through these steps, users can receive real-time support for cooking procedures and receive appropriate feedback based on their emotions, improving their cooking experience. By utilizing data from multiple users, recipes are optimized daily, enabling better cooking suggestions.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] [Fourth embodiment]

[1627] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1628] 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.

[1629] 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).

[1630] 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.

[1631] 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.

[1632] 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).

[1633] 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.

[1634] 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.

[1635] 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.

[1636] 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.

[1637] 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.

[1638] 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.

[1639] 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."

[1640] This invention provides a system that loads cooking videos into AI and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a terminal, and a user. The details are explained below.

[1641] System Configuration

[1642] server

[1643] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses AI models to analyze various data and provide users with cooking instructions tailored to their needs.

[1644] Terminal

[1645] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the information to the server.

[1646] user

[1647] Users upload cooking videos, follow instructions on their devices to cook, and then provide feedback to the system after completing the dish.

[1648] Program processing

[1649] Video upload and analysis

[1650] 1. Users

[1651] Users film their cooking and upload it to a server through the application.

[1652] 2. Terminal

[1653] The device sends the video selected by the user to the server.

[1654] 3. Server

[1655] The server receives the video and passes it to the AI ​​model to begin analysis.

[1656] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[1657] Providing real-time support

[1658] 1. Server

[1659] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[1660] 2. Terminal

[1661] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[1662] 3. Users

[1663] The user follows the displayed instructions to proceed with cooking.

[1664] User behavior analysis

[1665] 1. Terminal

[1666] The device captures user actions using cameras and sensors and transmits them to the server in real time.

[1667] 2. Server

[1668] The server analyzes the user's behavioral data and compares it with the instructions.

[1669] If different behavior is detected, the data is passed to the AI ​​model and saved as learning data.

[1670] Feedback and Learning

[1671] 1. Users

[1672] Users rate the finished dish and enter their rating into the app.

[1673] 2. Terminal

[1674] The terminal transmits the user's evaluation data to the server.

[1675] 3. Server

[1676] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[1677] It also aggregates other users' rating data to generate optimal recipes.

[1678] Recipe Improvement and Serving

[1679] 1. Server

[1680] The server learns more efficient cooking procedures based on aggregated behavioral data and feedback.

[1681] Generate new optimized recipes and tips and share them with other users.

[1682] 2. Terminal

[1683] The device will display new recipes and tips to the user.

[1684] Specific examples

[1685] Example 1: Uploading and analyzing a video

[1686] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[1687] Example 2: Real-time support

[1688] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[1689] Example 3: Behavioral analysis and feedback

[1690] If user A actually stir-fries vegetables for only 3 minutes, the device will capture this behavior and send it to the server, which will then identify the different behavior and store it in the AI ​​model.

[1691] Example 4: Rating and improving recipes

[1692] User B also cooks the dish and sends a rating to the server saying it was "delicious." The server uses this rating data to provide a new recipe to the next user.

[1693] In this way, recipes are dynamically improved based on user behavior and feedback, helping everyone cook better.

[1694] The processing flow will be explained below.

[1695] Step 1:

[1696] user

[1697] Cooking videos are filmed and uploaded to the system through the application.

[1698] Step 2:

[1699] Terminal

[1700] Send the uploaded video to the server.

[1701] Step 3:

[1702] server

[1703] Receives video files and requests the AI ​​model to analyze them.

[1704] Step 4:

[1705] server

[1706] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[1707] Step 5:

[1708] server

[1709] Based on the analysis results, the next cooking procedure to be carried out is determined and sent to the terminal.

[1710] Step 6:

[1711] Terminal

[1712] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[1713] Step 7:

[1714] user

[1715] Follow the displayed instructions to continue cooking.

[1716] Step 8:

[1717] Terminal

[1718] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[1719] Step 9:

[1720] server

[1721] Analyze the received behavioral data and confirm that it matches the instructed procedures.

[1722] Step 10:

[1723] server

[1724] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[1725] Step 11:

[1726] user

[1727] Once cooking is complete, the food is tasted and evaluated.

[1728] Step 12:

[1729] Terminal

[1730] Send user rating data to the server.

[1731] Step 13:

[1732] server

[1733] Provide feedback to the AI ​​model based on the collected evaluation data.

[1734] Step 14:

[1735] server

[1736] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[1737] Step 15:

[1738] server

[1739] The generated new recipes and tips are sent to the device.

[1740] Step 16:

[1741] Terminal

[1742] The device will display new recipes and tips to the user.

[1743] Step 17:

[1744] user

[1745] Use new recipes and advice to prepare your next meal.

[1746] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[1747] Example 1

[1748] 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."

[1749] It is difficult for beginners and inexperienced users to cook accurately while following a recipe. It is also difficult to provide optimal support based on each individual's cooking skills and preferences. Furthermore, the inability to fully utilize user behavioral data and feedback limits improvements to the quality of recipes. This creates the challenge of making high-quality meals due to the lack of appropriate cooking support.

[1750] 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.

[1751] In this invention, the server includes means for receiving and analyzing cooking videos from users, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior with cameras and sensors and detecting behavior that deviates from the instructed procedures, means for aggregating behavioral data and feedback from multiple users to generate optimal recipes, and means for providing the generated recipes and cooking advice to other users. This makes it possible to provide optimal cooking support based on each user's skills and preferences and to improve the quality of recipes by utilizing accumulated data.

[1752] "User" refers to an individual who performs cooking operations, uploads videos, and rates them.

[1753] "Server" refers to a computing device that analyzes received cooking videos, generates cooking instructions, and aggregates user behavior data and feedback.

[1754] "Terminal" refers to a device such as a user's smartphone, tablet, or PC, which displays cooking instructions from the server and monitors the user's behavior.

[1755] "Means for receiving and analyzing videos" refers to the technology in which a server receives cooking videos uploaded by users and analyzes their content using a generative AI model.

[1756] "Means for instructing the user on cooking instructions" refers to a technology in which the analyzed cooking instructions are sent from the server to the terminal, and the terminal displays them to the user.

[1757] "Means of monitoring using cameras and sensors" refers to technology that uses cameras and sensors installed on the device to monitor the user's cooking operations in real time and transmits that data to a server.

[1758] "Means for aggregating behavioral data and feedback" refers to the technology by which a server collects user behavioral data and evaluation data and statistically analyzes it.

[1759] "Means for generating optimal recipes" refers to technology in which an AI model creates more efficient and appropriate cooking procedures and recipes based on aggregated data.

[1760] "Means for providing generated recipes and cooking advice" refers to technology for transmitting optimized recipes and cooking advice from a server to other users and displaying them on their terminals.

[1761] "Means for collecting evaluation data" refers to the technology that collects food evaluations from multiple users and stores them in a database.

[1762] "Means for training an AI model" refers to the technology of inputting collected behavioral data and evaluation data into an AI model and allowing the model to acquire new knowledge through its learning process.

[1763] This invention relates to a system that uses AI to load cooking videos and provide step-by-step support in real time. The main components of the system are a server, a terminal, and a user, all of which work together. The details of the system and how to use it are explained below.

[1764] System configuration

[1765] server

[1766] The server plays a central role in this system. It receives cooking videos, analyzes them, generates instructions, collects behavioral data, and generates optimal recipes. Specifically, the server analyzes various data using a generative AI model (e.g., OpenAI's GPT-4).

[1767] Terminal

[1768] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends it to the server. The terminal is also equipped with a camera and sensors that capture the user's cooking operations in real time.

[1769] User

[1770] Users film cooking videos and upload them to the server via the application. They then follow instructions on their device to cook, and once the dish is complete, they provide feedback to the system.

[1771] Program processing

[1772] Video upload and analysis

[1773] 1. A user shoots a cooking video on their smartphone. The user launches the application, selects the recorded video, and presses the upload button.

[1774] 2. The device sends the video uploaded by the user to the server.

[1775] 3. The server receives the video data and analyzes the video using the generative AI model, using the prompt "Please extract the cooking steps and ingredients from this video." Based on this prompt, the AI ​​model extracts the cooking steps and ingredients from the video in text format.

[1776] Providing real-time support

[1777] 1. The server receives the analysis results and determines the next cooking step, for example, "sauté the vegetables for 5 minutes."

[1778] 2. The device displays the cooking instructions sent from the server to the user, who then follows the instructions to proceed with the cooking.

[1779] User behavior analysis

[1780] 1. The device captures the user's cooking operations using cameras and sensors and transmits them to the server in real time, for example, monitoring frying time and temperature.

[1781] 2. The server analyzes the received behavioral data and compares the instructed steps with the actual behavior. If any discrepancies are detected, the data is passed to the generative AI model and saved as training data.

[1782] Feedback and Learning

[1783] 1. After the cooking is complete, the user enters their evaluation into the app, such as "It was delicious" or "I wish it was a little saltier."

[1784] 2. The terminal sends the evaluation data entered by the user to the server.

[1785] 3. The server aggregates the evaluation data and provides it as feedback to the generative AI model. It also aggregates evaluation data from other users to generate the optimal recipe.

[1786] Recipe Improvement and Serving

[1787] 1. The server learns more efficient cooking procedures based on aggregated behavioral and feedback data, and uses generative AI models to create new recipes and cooking advice.

[1788] 2. The device displays the newly generated recipes and advice to the user.

[1789] Specific examples

[1790] Example 1: Uploading and analyzing a video

[1791] User A films a cooking video on their smartphone and uploads it to a server via an application. The device sends the video to the server, which then analyzes it using a generative AI model (e.g., OpenAI's GPT-4) based on the prompt, "Please extract the cooking steps and ingredients from this video." The AI ​​model then generates the instruction, "Stir-fry the vegetables for 5 minutes."

[1792] Example 2: Real-time support

[1793] The server sends the generated instructions to the terminal, and the terminal displays the instruction "Stir-fry vegetables for 5 minutes" to User A. User A cooks according to the instructions.

[1794] Example 3: Behavioral analysis and feedback

[1795] If user A actually stir-fries the vegetables for only 3 minutes, the device captures this behavior and sends it to the server, which then identifies the different behavior and stores it in the generative AI model.

[1796] Example 4: Rating and improving recipes

[1797] User B also cooks the dish and sends a rating of "delicious" to the server. Based on this rating data, the server provides new recipes and advice to other users.

[1798] In this way, recipes are constantly improved based on user actions and feedback, helping everyone cook better.

[1799] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1800] Step 1:

[1801] The user shoots a cooking video on their smartphone, launches the application, selects the recorded video, and presses the upload button.

[1802] Input: Filmed cooking video

[1803] Output: Video file selected by user

[1804] Step 2:

[1805] The terminal receives a video upload request from the user and transmits the video file to the server.

[1806] Input: User's video upload request and video file

[1807] Output: Video file sent to the server

[1808] Step 3:

[1809] The server receives the video data and sends an analysis prompt to the generative AI model. The prompt is "Please extract the cooking steps and ingredients from this video." The AI ​​model analyzes the video and outputs the cooking steps and ingredients in text format.

[1810] Input: Video file sent to the server, analysis prompt

[1811] Output: Extracted text data of cooking instructions and ingredients

[1812] Step 4:

[1813] The server receives the analysis results and determines the next cooking steps, which are then used to provide specific instructions to the user.

[1814] Input: Extracted text data of cooking instructions and ingredients

[1815] Output: Cooking instructions text to the user

[1816] Step 5:

[1817] The device receives cooking instructions from the server and displays them to the user. For example, specific instructions such as "sauté vegetables for 5 minutes" are displayed. The user then follows the displayed instructions to cook.

[1818] Input: Cooking instruction text from the server

[1819] Output: Cooking instructions displayed to the user

[1820] Step 6:

[1821] The device captures the user's cooking operations in real time using cameras and sensors and sends the data, including frying time and temperature, to a server.

[1822] Input: User's real-time cooking operation data

[1823] Output: Cooking operation data sent to the server

[1824] Step 7:

[1825] The server analyzes the behavioral data and compares the instructions with the actual behavior. For example, it checks whether the user actually stir-fried vegetables for five minutes. If a different behavior is detected, the data is passed to the generative AI model for future feedback and learning.

[1826] Input: Cooking operation data sent

[1827] Output: Analyzed behavior data, detected abnormal behavior data

[1828] Step 8:

[1829] After the user has finished cooking, they can enter their evaluation of the dish through the application, for example, by entering comments such as "It was delicious" or "It wasn't spicy enough."

[1830] Input: User food rating data

[1831] Output: Rating data input to the app

[1832] Step 9:

[1833] The terminal transmits the user's evaluation data to the server.

[1834] Input: Food rating data from users

[1835] Output: Rating data sent to the server

[1836] Step 10:

[1837] The server aggregates the evaluation data and provides it as feedback to the generative AI model, which also aggregates evaluation data from other users to generate the optimal recipe.

[1838] Input: Aggregated rating data

[1839] Output: Feedback data for generative AI model, optimal recipe data

[1840] Step 11:

[1841] The server generates new recipes and cooking advice based on the collected behavioral data and feedback data, and provides the generated recipes and advice to other users.

[1842] Input: Behavioral data, feedback data

[1843] Output: New recipes, cooking advice

[1844] Step 12:

[1845] The device displays the newly generated recipes and advice to the user, who can then follow the new recipes and advice to create even better dishes.

[1846] Input: New recipes and cooking advice from the server

[1847] Output: New recipes and cooking advice displayed to the user

[1848] (Application example 1)

[1849] 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."

[1850] In recent years, the number of beginners and busy people has increased, and the need for easy and efficient cooking has grown. However, existing cooking support systems lack sufficient support for how to use individual ingredients and real-time cooking procedures, making it difficult for users to proceed with cooking at the appropriate time. It is also difficult to receive real-time feedback during the cooking process, resulting in an increased failure rate.

[1851] 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.

[1852] In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing users on cooking procedures based on the analysis results, means for monitoring user behavior and detecting behavior that differs from the instructed procedures, means for aggregating behavioral data and feedback from multiple users and generating optimal recipes, means for providing the generated recipes to other users, means for recognizing ingredients with a camera on a smart device and generating corresponding recipes, and means for displaying cooking procedures on a visual display in real time, thereby enabling users to efficiently select ingredients in the supermarket and receive real-time support when cooking.

[1853] "Cooking videos" refer to footage recorded by users during the cooking process, and cooking steps are extracted by analyzing this video data.

[1854] "Analysis" refers to the process of analyzing the received cooking video using AI models and image recognition technology, and extracting the cooking steps and ingredient manipulations in text format.

[1855] "Cooking procedure" refers to each step in the process of cooking ingredients, specifically including operations such as preparing ingredients, cutting, frying, and boiling.

[1856] "Users" refer to people who use this system to cook, upload videos, check cooking instructions, and provide feedback.

[1857] "Monitoring" refers to the process of monitoring the user's cooking behavior using cameras and sensors and sending the data to a server in real time.

[1858] "Behavioral data" refers to data on the cooking actions actually performed by the user, and includes specific action data obtained from video and sensors.

[1859] "Feedback" refers to the user inputting their evaluation and impressions of the completed dish and sending it to the system, which the system uses as learning data.

[1860] The "optimal recipe" is a recipe generated based on behavioral data and feedback from multiple users, and improves taste and cooking efficiency.

[1861] "Smart device" refers to an electronic device with a camera and display function, and specifically includes smart glasses and smartphones.

[1862] "Ingredient recognition" refers to capturing an image of an ingredient using a smart device's camera and analyzing that image to identify a specific ingredient.

[1863] "Visual display" refers to the screen or display of a smart device, in this case intended to show cooking instructions or recipes to the user in real time.

[1864] This invention provides a system that uses AI to read cooking videos and provides step-by-step support in real time. Specifically, it works in cooperation with a server, a device, and a user. The details are described below.

[1865] System Configuration

[1866] server

[1867] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. The server uses a generative AI model to analyze various data and provide users with cooking instructions tailored to their needs. It also optimizes recipes based on user feedback. Specifically, it uses TensorFlow or PyTorch to operate a deep learning model.

[1868] Terminal

[1869] The user's device (smart glasses, smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior, and sends the results to the server. In addition, the terminal recognizes ingredients in real time using the user's camera, and displays the results analyzed by the server on the display. The terminal usually uses an image recognition library such as OpenCV.

[1870] user

[1871] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system, including evaluations of cooking efficiency and taste. User behavior data is captured by cameras and sensors and sent to the server in real time.

[1872] Explanation of program processing

[1873] Video upload and analysis

[1874] 1. The user takes a video of the cooking using a smartphone or other device and uploads it to the server via the application.

[1875] 2. The device sends the video selected by the user to the server.

[1876] 3. The server receives the video and passes it to the AI ​​model to begin analysis. The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format.

[1877] Providing real-time support

[1878] 1. The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[1879] 2. The device displays the cooking instructions to the user, for example, "Sauté the vegetables for 5 minutes."

[1880] 3. The user follows the displayed instructions to proceed with cooking.

[1881] Food ingredient recognition using smart devices

[1882] 1. The device sends the ingredients identified by the smart glasses camera to the server.

[1883] 2. The server analyzes the ingredients, generates a corresponding recipe, and sends it to the device.

[1884] 3. The device will display the recipe and cooking instructions on the screen, for example, "Here's how to make a salad using these carrots."

[1885] Specific examples

[1886] Imagine a user is in a supermarket, putting on smart glasses and pointing a carrot at the camera.

[1887] The device recognizes the carrot and sends the data to the server.

[1888] The server generates a recipe based on carrots and sends the recipe and cooking instructions for "Healthy Salad with Carrots" to the terminal.

[1889] The device displays this information on its screen and guides the user through the cooking process in real time.

[1890] Example prompts to input to the generative AI model

[1891] The user will take a photo of the ingredients and send it to us, and we will generate a recommended recipe using those ingredients. We will also output cooking instructions in real time.

[1892] In this way, users can efficiently select ingredients and receive real-time cooking instructions while shopping in a physical store.

[1893] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1894] Step 1:

[1895] The user takes a picture of the food with the camera on the smart glasses. The camera captures the food image data and stores it on the device. The input is the food image taken by the camera, and the output is the image data stored on the device.

[1896] Step 2:

[1897] The device sends the image of the food taken by the user to the server. The image data is sent via the HTTPS protocol. The input is the image data stored on the device, and the output is the image data sent to the server.

[1898] Step 3:

[1899] The server passes the received image data to the generative AI model for analysis. This analysis uses image recognition technology (e.g., OpenCV) to recognize ingredients and inputs that information into the AI ​​model. The input is the image data sent to the server, and the output is the recognized ingredient information.

[1900] Step 4:

[1901] The server generates an appropriate recipe based on the recognized ingredient information. At this time, the generative AI model uses past data and feedback to propose optimal cooking procedures. The input is the recognized ingredient information and past feedback data, and the output is the generated recipe and cooking procedures.

[1902] Step 5:

[1903] The server sends the generated recipe and cooking instructions to the terminal. Again, the HTTPS protocol is used. The input is the generated recipe and cooking instructions, and the output is the recipe and cooking instructions sent to the terminal.

[1904] Step 6:

[1905] The terminal displays the received recipe and cooking instructions on a visual display, allowing the user to see the next action in real time. The input is the recipe and cooking instructions sent to the terminal, and the output is the cooking instructions shown on the display.

[1906] Step 7:

[1907] The user follows the visual display to proceed with the cooking. For example, if the instruction is "sauté carrots for 5 minutes," the user follows the instructions to cook. The output is the cooking action performed by the user.

[1908] Step 8:

[1909] The device monitors the user's cooking behavior using cameras and sensors and sends the data to a server. The input is the user's cooking behavior data, and the output is the behavior data sent to the server.

[1910] Step 9:

[1911] The server analyzes the received behavioral data and detects any behavior that deviates from the instructed procedure. Furthermore, this behavioral data is provided as feedback to the AI ​​model and saved as training data for the model. The input is the behavioral data sent to the server, and the output is the training data provided to the AI ​​model.

[1912] Step 10:

[1913] The user rates the cooked dish and inputs the rating into the terminal. The terminal sends the rating data to the server. The input is the rating data entered by the user, and the output is the rating data sent to the server.

[1914] Step 11:

[1915] The server provides optimal recipes to other users based on the received rating data. It also improves the recipes using the aggregated rating data and behavioral data. The input is the rating data and behavioral data sent to the server, and the output is an improved recipe and helpful advice.

[1916] 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.

[1917] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[1918] System Configuration

[1919] server

[1920] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotion data from the emotion engine and adjusts cooking procedures and timings.

[1921] Terminal

[1922] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server.

[1923] Emotion Engine

[1924] The emotion engine analyzes the user's facial expressions and voice to recognize their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice.

[1925] user

[1926] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[1927] Program processing

[1928] Video upload and analysis

[1929] 1. Users

[1930] Users film their cooking and upload it to a server through the application.

[1931] 2. Terminal

[1932] The device sends the video selected by the user to the server.

[1933] 3. Server

[1934] The server receives the video and asks the AI ​​model to analyze it.

[1935] The AI ​​model analyzes the video and extracts cooking instructions and ingredient manipulations in text format for each frame.

[1936] Providing real-time support

[1937] 1. Server

[1938] The server determines the next cooking procedure based on the analysis results and sends the instructions to the terminal.

[1939] 2. Terminal

[1940] The device will then display the cooking instructions to the user, e.g. "Sauté vegetables for 5 minutes."

[1941] 3. Users

[1942] The user follows the displayed instructions to proceed with cooking.

[1943] User behavior analysis and emotion recognition

[1944] 1. Terminal

[1945] The device captures user actions in real time using cameras and sensors and sends them to the emotion engine.

[1946] 2. Emotion Engine

[1947] The emotion engine analyzes facial expressions and voice to recognize the user's emotional state.

[1948] The recognized emotion data is sent to the server.

[1949] 3. Server

[1950] The server analyzes the user's behavioral and emotional data and checks whether it matches the instructed steps.

[1951] If different behaviors or emotional changes are detected, the data is passed to the AI ​​model and saved as learning data.

[1952] Feedback and Learning

[1953] 1. Users

[1954] Users rate the finished dish and enter their rating into the app.

[1955] 2. Terminal

[1956] The terminal transmits the user's evaluation data to the server.

[1957] 3. Server

[1958] The server aggregates the evaluation data and provides it as feedback to the AI ​​model.

[1959] It also aggregates other users' rating data to generate optimal recipes.

[1960] Recipe Improvement and Serving

[1961] 1. Server

[1962] The server learns more efficient cooking procedures based on aggregated behavioral data, emotional data, and feedback.

[1963] Generate new optimized recipes and tips and share them with other users.

[1964] 2. Terminal

[1965] The device will display new recipes and tips to the user.

[1966] Specific examples

[1967] Example 1: Uploading and analyzing a video

[1968] User A takes a video of the cooking process on their smartphone and uploads it to the server via an application. The device sends the video to the server, which then analyzes it using an AI model. The AI ​​model analyzes the cooking steps and generates instructions such as "stir-fry the vegetables for 5 minutes."

[1969] Example 2: Real-time support

[1970] The server sends this instruction to the terminal, which displays it to User A. User A then proceeds with cooking by following the displayed instructions.

[1971] Example 3: Behavioral analysis and emotion recognition

[1972] If User A actually stir-fries vegetables for only 3 minutes, the device will capture User A's actions and facial expressions with the camera and send them to the server. The emotion engine will recognize User A's emotional state and report it to the server. The server will review the different behavioral and emotional data and store it in the AI ​​model.

[1973] Example 4: Rating and improving recipes

[1974] User B also cooks the dish and sends a rating of "delicious" to the server. The server uses this rating data and emotion data to provide new recipes and advice to the next user.

[1975] In this way, recipes are dynamically improved based on user behavior, sentiment, and feedback, helping everyone cook better.

[1976] The processing flow will be explained below.

[1977] Step 1:

[1978] user

[1979] Cooking videos are filmed and uploaded to the system through the application.

[1980] Step 2:

[1981] Terminal

[1982] Send the uploaded video to the server.

[1983] Step 3:

[1984] server

[1985] Receives video files and requests the AI ​​model to analyze them.

[1986] Step 4:

[1987] server

[1988] The AI ​​model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format.

[1989] Step 5:

[1990] server

[1991] Based on the analysis results, the next cooking procedure is determined and the instructions are sent to the terminal.

[1992] Step 6:

[1993] Terminal

[1994] Show the received cooking instructions to the user. For example, "Sauté the vegetables for 5 minutes."

[1995] Step 7:

[1996] user

[1997] Follow the displayed instructions to continue cooking.

[1998] Step 8:

[1999] Terminal

[2000] The user's cooking behavior is captured in real time using cameras and sensors and sent to the server.

[2001] Step 9:

[2002] Emotion Engine

[2003] It analyzes the user's facial expressions and voice to recognize their emotional state, and sends the acquired emotional data to the server.

[2004] Step 10:

[2005] server

[2006] The received behavioral and emotional data is analyzed and compared with the instructed procedures.

[2007] Step 11:

[2008] server

[2009] If the user behaves differently from the instructions, the data is passed to the AI ​​model and saved as learning data.

[2010] Step 12:

[2011] server

[2012] Based on the recognized emotional data, the cooking instructions and timing of advice are adjusted.

[2013] Step 13:

[2014] user

[2015] Once cooking is complete, the food is tasted and evaluated.

[2016] Step 14:

[2017] Terminal

[2018] Send user rating data to the server.

[2019] Step 15:

[2020] server

[2021] Provide feedback to the AI ​​model based on the collected evaluation data.

[2022] Step 16:

[2023] server

[2024] The optimal recipe is generated by comprehensively analyzing the behavioral data and ratings of other users.

[2025] Step 17:

[2026] server

[2027] The generated new recipes and tips are sent to the device.

[2028] Step 18:

[2029] Terminal

[2030] The device will display new recipes and tips to the user.

[2031] Step 19:

[2032] user

[2033] Use new recipes and advice to prepare your next meal.

[2034] By repeating this process, the entire system will be improved based on user feedback, providing a better cooking experience.

[2035] Example 2

[2036] 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."

[2037] Conventional cooking assistance systems can only monitor user behavior and lack support that reflects user emotions. Furthermore, methods that improve recipes based solely on user feedback may not provide effective real-time cooking assistance. As a result, follow-up during cooking is insufficient, resulting in a lack of improvement in the user's cooking experience.

[2038] 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 means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and emotions and detecting behavioral and emotional changes that differ from the instructed procedures, means for aggregating behavioral data, emotional data, and feedback from multiple users and generating optimal cooking procedures, and means for providing the generated cooking procedures and advice to other users. This enables real-time cooking assistance that reflects both the user's behavior and emotions.

[2039] "Cooking videos" are digital data that record cooking steps and how to prepare ingredients.

[2040] "Analysis" refers to the process of analyzing cooking videos based on an AI model and extracting cooking steps and ingredient manipulations in text format.

[2041] A "cooking procedure" is each step required to complete a dish, and includes specific actions, time, and conditions.

[2042] "User" refers to an individual user of the cooking assistance system.

[2043] "Monitoring" is the means of observing and recording a user's behavior and emotional state in real time.

[2044] "Emotional changes" refers to changes in emotions recognized by analyzing changes in the user's facial expressions and voice.

[2045] "Feedback" refers to data on the evaluations and impressions users provide about the completed dishes.

[2046] The "optimal cooking procedure" is a method generated as the most effective and efficient cooking procedure based on the user's behavioral data, emotional data, and feedback.

[2047] "Advice" is information containing additional instructions or suggestions that will be helpful during cooking or for your next cooking session.

[2048] A "server" is a computer system that performs central processing such as analysis, data collection, and instruction generation.

[2049] This invention provides a system that not only loads cooking videos into AI and provides step-by-step support in real time, but also combines an emotion engine to recognize the user's emotions and improve the cooking experience. Specifically, the server, terminal, and user work together, and the emotion engine additionally analyzes emotional data and provides feedback.

[2050] System Configuration

[2051] server

[2052] The server plays a central role in receiving cooking videos, analyzing them, generating instructions, collecting behavioral data, and generating optimal recipes. It also processes emotional data from the emotion engine and adjusts cooking steps and timing. Specifically, the server receives the video and requests analysis from the AI ​​model. The AI ​​model analyzes the video and extracts cooking steps and ingredient manipulations for each frame in text format.

[2053] Terminal

[2054] The user's device (smartphone, tablet, PC, etc.) functions as the terminal. The terminal displays cooking instructions from the server to the user, monitors the user's behavior and emotions, and sends them to the server. The terminal can capture the user's actions and facial expressions in real time using cameras and sensors.

[2055] Emotion Engine

[2056] The emotion engine analyzes the user's facial expressions and voice to provide a function for recognizing their current emotional state. Emotional data is sent to the server via the device and reflected in cooking instructions and advice. The emotion engine analyzes the captured facial and voice data to detect emotions such as "happy" or "troubled."

[2057] user

[2058] Users upload cooking videos and follow instructions on their devices to cook. After completing the dish, they provide feedback to the system and receive advice from the emotion engine.

[2059] Specific examples

[2060] User A takes a video of "how to make spaghetti" on their smartphone and uploads it to the server using the app. The device sends the video to the server, which then analyzes it with an AI model. The AI ​​model analyzes the cooking steps and generates specific instructions, such as "boil the spaghetti for 8 to 10 minutes."

[2061] The server sends the instruction "Boil the spaghetti for 8 to 10 minutes" to the device. The device displays this instruction to User A and provides a voice message saying "Boil the spaghetti for 8 to 10 minutes." User A then follows the displayed instructions to continue cooking.

[2062] If User A shows a confused expression while cooking, the device's camera captures that expression and sends it to the emotion engine. The emotion engine recognizes User A's confusion and sends that information to the server. The server uses this data to generate additional instructions, such as "Please check the detailed instructions for making the sauce again."

[2063] After the dish is complete, User A enters a rating into the app, saying "The sauce is a little sour," and sends that rating to the server. The server compiles the ratings and provides the next user with advice, such as "Try adding a little sugar to the sauce." User B then receives that advice the next time they cook and can try it out.

[2064] Example prompts to input to the generative AI model

[2065] Here are some examples of prompts to input to a generative AI model:

[2066] "We are building a system that allows users to upload cooking videos and provides cooking instructions. The text returned from analyzing the video should be in the following format: "Instructions: Do △△". Also, please provide instructions on how to recognize user emotions and reflect them in real-time instructions."

[2067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2068] Step 1:

[2069] Users film cooking videos and upload them to the server through the application. The input is the cooking video filmed by the user, and the output is the video being sent to the server.

[2070] Step 2:

[2071] The device sends the video file selected by the user to the server and confirms that the transmission is complete. The input is the video uploaded by the user, and the output is the video data sent to the server.

[2072] Step 3:

[2073] The server receives the video data and requests the AI ​​model to analyze it. The AI ​​model extracts cooking instructions and ingredient handling information from each frame of the video. The input is the received video data, and the output is the analyzed cooking instructions and ingredient handling information in text format.

[2074] Step 4:

[2075] The server determines the next cooking steps based on the analysis results obtained from the AI ​​model. Specifically, it organizes the cooking steps for each frame based on the analysis results and generates specific instructions such as "mince the onion." The input is the analysis results from the AI ​​model, and the output is the organized cooking steps.

[2076] Step 5:

[2077] The server sends the generated recipe to the terminal. The input is the organized recipe instructions, and the output is the recipe data sent to the terminal.

[2078] Step 6:

[2079] The device displays the cooking instructions received from the server to the user. When displaying the instructions, the voice assistant function is used to allow voice instructions. The input is the cooking instructions data received from the server, and the output is the cooking instructions information displayed to the user. Voice instructions are also provided as a specific action.

[2080] Step 7:

[2081] The user follows the instructions displayed on the device to cook. For example, the user actually stir-fries vegetables in a frying pan based on the instruction "Stir-fry vegetables for 5 minutes." The input is the cooking instructions displayed on the device, and the output is the cooking behavior according to those instructions.

[2082] Step 8:

[2083] The device uses cameras and sensors to capture the user's operations and facial expressions in real time and send them to the emotion engine. The input is the user's real-time operations and facial expression data, and the output is the captured data sent to the emotion engine.

[2084] Step 9:

[2085] The emotion engine analyzes the captured data and recognizes the user's emotional state. For example, it detects emotions such as "happy" or "troubled." The input is the captured operation and facial expression data, and the output is the analyzed emotional state data.

[2086] Step 10:

[2087] The emotion engine sends the recognized emotion data to the server. The input is the analyzed emotional state data, and the output is the emotion data sent to the server.

[2088] Step 11:

[2089] The server analyzes the user's behavioral and emotional data to confirm that it matches the current cooking instructions. For example, if the user appears anxious, it generates instructions to explain the cooking instructions again more slowly. The input is the user's behavioral and emotional data, and the output is instruction data for additional cooking steps.

[2090] Step 12:

[2091] The server generates additional instructions and sends them to the terminal. The input is the instruction data for the additional cooking steps, and the output is the instruction data sent to the terminal.

[2092] Step 13:

[2093] The terminal displays additional instructions to the user and provides voice guidance such as, "Please check the detailed instructions for making the sauce again." The input is the additional instruction data received from the server, and the output is the additional cooking procedure information displayed to the user and the voice guidance.

[2094] Step 14:

[2095] The user rates the completed dish and inputs the rating into the application. The input is the user's rating, and the output is the rating data sent to the server.

[2096] Step 15:

[2097] The terminal transmits the user's rating data to the server. The input is the user's rating data, and the output is the rating data transmitted to the server.

[2098] Step 16:

[2099] The server aggregates the collected evaluation data and provides it as feedback to the AI ​​model. The input is the collected evaluation data, and the output is the feedback data provided to the AI ​​model.

[2100] Step 17:

[2101] The server also aggregates behavioral and emotional data from other users to learn more efficient cooking procedures. The input is behavioral and emotional data from other users, and the output is optimized new cooking procedures and advice.

[2102] Step 18:

[2103] The server generates new optimized cooking recipes and tips and sends them to the device. The input is the optimized cooking recipes and tips, and the output is the cooking recipes and tips sent to the device.

[2104] Step 19:

[2105] The device notifies the user of the newly generated recipe or advice and displays it on the screen, for example, "Next time, add one teaspoon of salt." The input is the optimized cooking instructions or advice received from the server, and the output is the recipe or advice notified to the user.

[2106] (Application example 2)

[2107] 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."

[2108] Conventional cooking support systems only provide instructions for cooking procedures and lack appropriate feedback or support for the user's emotional state. As a result, users can feel stressed while cooking and have difficulty following instructions. Furthermore, there are insufficient means to effectively utilize feedback data from multiple users and optimize recipes. This makes it difficult to improve the cooking experience and recipes.

[2109] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing cooking videos, means for instructing the user on cooking procedures based on the analysis results, means for monitoring the user's behavior and detecting behavior that differs from the instructed procedures, means for analyzing the user's emotional state and reflecting this in cooking procedures and feedback, means for aggregating behavioral data and feedback from multiple users and generating an optimal recipe, and means for providing the generated recipe to other users. This enables real-time feedback according to the user's emotional state, improving the quality of the cooking experience and enabling recipe optimization by effectively utilizing data from multiple users.

[2110] A "cooking video" is a video that records the cooking process.

[2111] The "analysis results" are information about cooking procedures and ingredient manipulations extracted from cooking videos.

[2112] "Cooking steps" are the steps required to complete a dish.

[2113] "User behavior" refers to the steps and operations performed by the user while cooking.

[2114] "Emotional state" refers to the psychological state that can be read from the user's facial expression, tone of voice, etc.

[2115] "Feedback" refers to evaluations and advice on users' actions.

[2116] A "recipe" is a collection of information about ingredients and steps for making a dish.

[2117] The "server" is a central computer system that receives cooking videos, analyzes them, generates cooking instructions, and compiles data.

[2118] "Monitoring" is a means of observing a user's behavior and emotional state and obtaining the data.

[2119] An "optimized recipe" is a combination of cooking steps and ingredients that has been refined to maximize effectiveness based on feedback and behavioral data from multiple users.

[2120] "Means" are technical components or methods used to achieve a specific function or purpose.

[2121] The "described system" is a collection of a series of devices and programs having specific functions and purposes proposed by the present invention.

[2122] To put this invention into practice, a system is required in which a server, a user's terminal, and an emotion engine work in cooperation with each other. The specific configuration and operation of this system will be described below.

[2123] The server is a central computer system that receives and analyzes cooking videos, generates cooking instructions, collects behavioral data, and processes emotional data. Specifically, when a user uploads a cooking video, the server receives the video and requests an AI model to analyze it. This AI model analyzes the video frame by frame and extracts cooking instructions and ingredient manipulations in text format. The server then generates cooking instructions based on the extracted results and sends the instructions to the user's device.

[2124] The user's device (smartphone, tablet, etc.) receives the cooking instructions sent from the server and displays them to the user. The device also monitors the user's cooking operations in real time using cameras and sensors and sends the data to the emotion engine. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state and sends the data to the server. Based on this, the server generates feedback according to the user's emotional state and sends it to the device.

[2125] Below is an example of how the system works:

[2126] Example 1: Uploading and analyzing a video

[2127] Users film cooking videos on their smartphones and upload them to a server via the app. The videos are then sent to the server and analyzed by an AI model, which then generates specific cooking instructions, such as "stir-fry vegetables for five minutes."

[2128] Example 2: Real-time support

[2129] The server sends the cooking instructions to the user's device, which displays them to the user, who then follows the instructions to proceed with the cooking.

[2130] Example 3: Behavioral analysis and emotion recognition

[2131] If the user does not stir-fry the vegetables for five minutes as instructed (for example, if they only stir-fry for three minutes), the device captures the user's behavior through the camera and sends it to the emotion engine. The emotion engine analyzes the user's emotional state from facial expressions and voice and sends it to the server. The server then adjusts the feedback content based on this data and sends appropriate advice to the user.

[2132] Example 4: Rating and improving recipes

[2133] After a user completes a dish, they rate it within the app. The rating data is sent to the server, which aggregates it and feeds it back into the AI ​​model. The server then analyzes the data from other users to generate an optimized recipe and serve it to the next user.

[2134] This allows users to cook while receiving emotional support in real time, and recipes can be optimized by effectively utilizing data from multiple users.

[2135] For example, a prompt such as "What is the next cooking step?" can be answered with "Stir-fry the vegetables for 5 minutes." This allows the system to provide appropriate answers to the user's questions and doubts.

[2136] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2137] Step 1: Upload your video

[2138] A user shoots a cooking video on their smartphone and uploads it to a server via an application. The input is the cooking video shot by the user, and the output is the video data sent to the server. Specifically, the application selects the user's video file and performs communication processing to upload it to the server.

[2139] Step 2: Analyze the video

[2140] The server requests the AI ​​model to analyze the received video. The input is the video data uploaded in step 1, and the output is text data on the analyzed cooking steps and ingredient manipulations. Specifically, the server analyzes the video frame by frame, and the AI ​​model extracts cooking steps from each frame.

[2141] Step 3: Generate and provide cooking instructions

[2142] The server generates appropriate cooking instructions based on the analysis results and sends them to the user's device. The input is the text-format cooking instruction data obtained in step 2, and the output is the cooking instructions sent to the user's device. Specifically, the server organizes the analysis results, generates cooking instructions in a format that is easy for the user to understand, and sends them to the device.

[2143] Step 4: Display cooking instructions

[2144] The user's device displays the cooking instructions received from the server to the user. The input is the cooking instructions sent from the server in step 3, and the output is the cooking instructions displayed on the device screen. Specifically, the device renders the received data appropriately on the display screen.

[2145] Step 5: Monitor behavior and capture emotions

[2146] The device monitors the user's actions and emotions in real time using cameras and sensors and sends them to the emotion engine. The input is the user's actual actions, facial expressions, and voice data, and the output is the data sent to the emotion engine. Specifically, the device uses a camera and microphone to capture the user's actions and voice, and sends the data to the emotion engine for analysis.

[2147] Step 6: Sentiment analysis and feedback generation

[2148] The emotion engine analyzes the user's emotional state and sends the data to the server. The input is the facial expression and voice data sent from the device in step 5, and the output is the analyzed emotional data and its feedback. Specifically, the emotion engine performs analysis using an emotion analysis algorithm and sends the results to the server.

[2149] Step 7: Provide feedback

[2150] The server generates feedback based on the emotional data and sends it to the user's device. The input is the emotional data and cooking instructions obtained in step 6, and the output is a feedback message sent to the user's device. Specifically, the server generates a feedback message taking into account the user's emotional state and sends it to the device.

[2151] Step 8: Evaluation and data aggregation

[2152] The user rates the completed dish and sends the data to the server through the application. The input is the user's rating data, and the output is the rating data compiled by the server. Specifically, the user fills out a rating form within the application and sends it to the server.

[2153] Step 9: Optimize the recipe

[2154] The server aggregates behavioral data, emotional data, and evaluation data from multiple users and feeds it back to the AI ​​model. The input is the data aggregated in step 8, and the output is a new optimized recipe. Specifically, the server analyzes the data collected by the server using the AI ​​model to generate a new recipe.

[2155] Step 10: Serving an optimized recipe

[2156] The server generates an optimized recipe and provides it to other users. The input is the optimized recipe generated in step 9, and the output is the new recipe displayed on the user's device. Specifically, the server sends the new recipe data to the other user's device, and the application displays it.

[2157] Through these steps, users can receive real-time support for cooking procedures and receive appropriate feedback based on their emotions, improving their cooking experience. By utilizing data from multiple users, recipes are optimized daily, enabling better cooking suggestions.

[2158] 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.

[2159] 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.

[2160] 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.

[2161] 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.

[2162] 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.

[2163] 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.

[2164] 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).

[2165] 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.

[2166] 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."

[2167] 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.

[2168] 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).

[2169] 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.

[2170] 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.

[2171] 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.

[2172] 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.

[2173] 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.

[2174] 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.

[2175] 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.

[2176] 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.

[2177] 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.

[2178] 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.

[2179] The following is further disclosed regarding the above embodiment.

[2180] (Claim 1)

[2181] A means for receiving and analyzing cooking videos;

[2182] a means for instructing a user on cooking procedures based on the analysis results;

[2183] A means for monitoring user behavior and detecting behavior that deviates from instructed procedures;

[2184] A means of aggregating behavioral data and feedback from multiple users to generate optimal recipes;

[2185] A means to provide the generated recipes to other users;

[2186] A system including:

[2187] (Claim 2)

[2188] 10. The system of claim 1, further comprising means for collecting evaluation data from multiple users to evaluate the efficiency and taste of a recipe.

[2189] (Claim 3)

[2190] 2. The system according to claim 1, further comprising means for learning new cooking procedures from the user's actions, and if the procedures are determined to be efficient, providing them to other users as tips.

[2191] "Example 1"

[2192] (Claim 1)

[2193] A means of receiving and analyzing cooking videos from users,

[2194] a means for instructing a user on cooking procedures based on the analysis results;

[2195] A method for monitoring user behavior with cameras and sensors to detect behavior that deviates from the instructed procedures, and

[2196] A means of aggregating behavioral data and feedback from multiple users to generate optimal recipes;

[2197] A means to provide generated recipes and cooking advice to other users;

[2198] A system including:

[2199] (Claim 2)

[2200] 10. The system of claim 1, further comprising means for aggregating rating data from multiple users and providing the same as feedback to the AI ​​model.

[2201] (Claim 3)

[2202] The system of claim 1 further includes means for passing the results of the analysis of user behavior to an AI model, allowing it to learn new cooking procedures, and providing the procedures to other users if they are determined to be efficient.

[2203] "Application Example 1"

[2204] (Claim 1)

[2205] A means for receiving and analyzing cooking videos;

[2206] a means for instructing a user on cooking procedures based on the analysis results;

[2207] A means for monitoring user behavior and detecting behavior that deviates from instructed procedures;

[2208] A means of aggregating behavioral data and feedback from multiple users to generate optimal recipes;

[2209] A means to provide the generated recipes to other users;

[2210] A means for recognizing ingredients using a camera on a smart device and generating corresponding recipes;

[2211] means for displaying cooking instructions on a visual display in real time;

[2212] A system including:

[2213] (Claim 2)

[2214] 10. The system of claim 1, further comprising means for collecting evaluation data from multiple users to evaluate the efficiency and taste of a recipe.

[2215] (Claim 3)

[2216] 2. The system according to claim 1, further comprising means for learning new cooking procedures from the user's actions, and if the procedures are determined to be efficient, providing them to other users as tips.

[2217] "Example 2: Combining Emotion Engines"

[2218] (Claim 1)

[2219] A means for receiving and analyzing cooking videos;

[2220] a means for instructing a user on cooking procedures based on the analysis results;

[2221] A means for monitoring the user's behavior and emotions and detecting behavioral and emotional changes that differ from the instructed procedure;

[2222] A means for aggregating behavioral data, emotional data, and feedback from multiple users to generate optimal cooking instructions;

[2223] a means for providing the generated cooking instructions and advice to other users;

[2224] A system including:

[2225] (Claim 2)

[2226] 10. The system of claim 1, further comprising means for aggregating evaluation data from multiple users to evaluate the efficiency and taste of a recipe.

[2227] (Claim 3)

[2228] 10. The system of claim 1, further comprising means for learning new cooking procedures and advice from the user's behavior and emotions, and providing the procedures and advice to other users if the procedures are determined to be efficient.

[2229] "Application example 2 when combining emotion engines"

[2230] (Claim 1)

[2231] A means for receiving and analyzing cooking videos;

[2232] a means for instructing a user on cooking procedures based on the analysis results;

[2233] A means for monitoring user behavior and detecting behavior that deviates from instructed procedures;

[2234] A means to analyze the user's emotional state and reflect it in cooking instructions and feedback,

[2235] A means of aggregating behavioral data and feedback from multiple users to generate optimal recipes;

[2236] A means to provide the generated recipes to other users;

[2237] A system including:

[2238] (Claim 2)

[2239] 10. The system of claim 1, further comprising means for collecting evaluation data and sentiment data from multiple users to evaluate the efficiency and taste of a recipe.

[2240] (Claim 3)

[2241] 2. The system according to claim 1, further comprising means for learning new cooking procedures from user behavior and emotion data, and providing the procedures as tips to other users if the procedures are determined to be efficient. [Explanation of symbols]

[2242] 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 receiving and analyzing cooking videos; A means for instructing a user on cooking procedures based on the analysis results; A means for monitoring user behavior and detecting deviations from instructed procedures; A means of aggregating behavioral data and feedback from multiple users to generate optimal recipes; A means to provide the generated recipes to other users; A system including:

2. 2. The system according to claim 1, further comprising means for collecting evaluation data from a plurality of users to evaluate the efficiency and taste of a recipe.

3. 2. The system according to claim 1, further comprising means for learning new cooking procedures from the user's actions, and when the procedures are determined to be efficient, providing them to other users as tips.

Images