System

Abstract

A system is provided.SOLUTION: The system includes a means for uploading a photograph taken by a user, a means for transmitting the uploaded photograph to a server, a means for analyzing the photograph by the server and specifying the ingredient and processing method of the dish, a means for returning the specified ingredient and processing method from the server, and a means for displaying the returned ingredient and processing method to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional recipe search systems require users to search for ingredients and recipe names by text input, which is time-consuming and difficult to use intuitively. Furthermore, many users have photos of their dishes, but there are few ways to easily obtain ingredients and recipes based on those photos. The purpose of this invention is to solve these problems and provide a system that allows users to easily obtain ingredients and recipes simply by taking a photo of a dish. [Means for solving the problem]

[0005] The present invention solves the problem by providing a system that includes a means for uploading photos taken by a user, a means for transmitting the uploaded photos to a server, a means for analyzing the photos on the server and identifying ingredients and processing methods for a dish, a means for returning the identified ingredients and processing methods from the server, and a means for displaying the returned ingredients and processing methods to the user. Furthermore, the system includes a means for extracting features from the photos using a machine learning algorithm when analyzing the photos on the server, and a means for collating the information identified on the server with a database to derive an optimal recipe, thereby improving the accuracy of the analysis and providing the user with more accurate ingredients and processing methods.

[0006] "User" refers to an individual or organization that uses the system to take and upload photos of food.

[0007] "Terminal" refers to an electronic device used by a user, such as a smartphone, tablet, or PC.

[0008] "Photo" refers to image data of a dish that a user takes using a terminal and uploads to the system.

[0009] "Server" refers to a central processing unit that receives uploaded photos, performs analysis, and returns the results.

[0010] "Uploading means" refers to the function or process for sending photos taken by the user from the terminal to the server.

[0011] "Photo analysis means" refers to the algorithms and hardware used to analyze the photos received by the server and identify the ingredients and processing methods of the food.

[0012] "Machine learning algorithms" refers to artificial intelligence techniques used to extract and analyze features within photos.

[0013] A "database" refers to a collection of information that stores cooking recipes, ingredient information, etc., which the server uses to match information identified from photos.

[0014] "Return means" refers to the functions and processes that allow the server to send the analysis results (materials and processing method) to the terminal.

[0015] "Display means" refers to a function (for example, the user interface of the application) for displaying the materials and processing methods received by the terminal to the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[0038] Program processing

[0039] 1. User Input

[0040] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[0041] 2. Sending photos

[0042] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[0043] 3. Photo Analysis

[0044] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[0045] 4. Identifying materials and processing methods

[0046] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[0047] 5. Return of results

[0048] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[0049] 6. User Display

[0050] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[0051] Specific examples

[0052] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[0053] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[0054] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[0055] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[0056] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[0057] The present invention allows users to intuitively know the ingredients and cooking methods needed based on photos of dishes, thereby broadening the range of dishes they can make.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The user takes a photo of the dish using the device. The user opens the app, selects the photo, and presses the upload button. The photo is then saved to the device's internal storage.

[0061] Step 2:

[0062] The device sends the photos selected by the user to the server via the network, and the photos are sent along with metadata such as the user ID and a timestamp.

[0063] Step 3:

[0064] The server receives the photo data sent from the device, stores it internally, and begins analyzing it.

[0065] Step 4:

[0066] The server feeds the photo data into machine learning algorithms, such as applying a convolutional neural network (CNN), to extract features within the photo, which then identify the ingredients and type of dish.

[0067] Step 5:

[0068] The server compares the extracted feature data with its internal database, which contains numerous recipes with their ingredients and procedures, and searches for the most suitable recipe.

[0069] Step 6:

[0070] The server generates a list of identified materials and processing instructions from the search results and creates a response to return this information to the user.

[0071] Step 7:

[0072] The server then sends the generated response to the device, which includes the identified ingredients and specific cooking instructions.

[0073] Step 8:

[0074] The terminal receives the response sent from the server, and then displays the ingredient list and cooking instructions to the user through the user interface.

[0075] Step 9:

[0076] Users can check the ingredients list and cooking instructions on the device screen and follow them to prepare the dish. The user prepares the necessary ingredients and proceeds with cooking according to the displayed instructions.

[0077] Through these steps, the system provides an environment where users can easily obtain ingredients and processing methods by simply uploading a photo of the dish.

[0078] Example 1

[0079] 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."

[0080] Currently, many users post photos of the dishes they have cooked on social media and blogs, but it is difficult to know the specific ingredients and cooking methods from those photos. Beginners in cooking and users who want to try new recipes need a system that can automatically find detailed ingredients and cooking steps from a photo of a dish. Furthermore, existing methods require users to perform complex operations, so an intuitive and simple operation is required.

[0081] 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.

[0082] In this invention, the server includes a means for uploading photos taken by users, a means for transmitting the uploaded photos to the server, and a means for analyzing the photos on the server and identifying the ingredients and processing methods of the dish. This allows users to intuitively learn the necessary ingredients and cooking methods simply by uploading a photo of the dish without performing complex operations. This invention also includes a means for extracting features from the photo using a machine learning algorithm when analyzing the photo on the server, and for deriving the optimal recipe based on the analysis results by comparing them with recipe information in a database. This provides more accurate recipe information, allowing users to broaden their cooking options.

[0083] A "user" is an individual who uses the system to take photos of dishes and use the reverse recipe engine app.

[0084] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0085] A "server" is a central processing unit that receives and analyzes data sent from a user and returns the results to the terminal.

[0086] "Uploading" is the act of a user sending data (in this case, photos of food) from a terminal to a server.

[0087] A "machine learning algorithm" is a program the server uses to analyze features in a photo and identify ingredients and types of dishes.

[0088] The "JSON format" is a lightweight data format used for data exchange that is easy to read for both humans and machines.

[0089] An "image analysis algorithm" is a program for extracting and analyzing feature data from photographs.

[0090] A "database" is a system that systematically stores information about cooking ingredients and processing methods and is used by the server to collate the information.

[0091] "Metadata" is information that is sent along with the photo data, and includes a timestamp, user ID, and so on.

[0092] A "response" is response data that the server returns to the terminal, including analysis results and necessary information.

[0093] "User interface" refers to the screen and operation method that allows the user to interact with the system and intuitively confirm the results.

[0094] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[0095] Program processing

[0096] 1. User Input

[0097] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[0098] 2. Sending photos

[0099] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[0100] 3. Photo Analysis

[0101] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[0102] 4. Identifying materials and processing methods

[0103] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[0104] 5. Return of results

[0105] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[0106] 6. User Display

[0107] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[0108] Specific examples

[0109] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[0110] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[0111] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[0112] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[0113] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[0114] Prompt Sentence Examples

[0115] Here is an example of inputting the following prompt sentence to a generative AI model:

[0116] I want to have an AI analyze photos of food taken by users and identify the ingredients and cooking method. Please explain the steps required to upload a photo and the specific processing action to be taken based on the submitted photo. Furthermore, please explain in more detail using a photo of a pasta dish as an example.

[0117] With the present invention configured as described above, a user can intuitively learn the ingredients and cooking methods needed based on a photo of a dish, thereby broadening the range of dishes they can make.

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

[0119] Step 1:

[0120] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. Specifically, the user opens the device's camera app and takes a photo of the dish. This photo is saved in the device's local storage. Next, the user launches the reverse recipe engine app, presses the "Select Photo" button to select the photo they took, and presses the "Upload" button. The input is the photo they took, and the output is the selected photo being displayed in the app.

[0121] Step 2:

[0122] The device sends the photo selected by the user to the server via the network. At this time, metadata such as a timestamp and user ID are added to the photo data. Specifically, the device sends the photo data and metadata to the server using an HTTP POST request. The input is the selected photo data and metadata, and the output is a transmission completion message to the server.

[0123] Step 3:

[0124] The server applies an image analysis algorithm to the received photos. This image analysis uses a machine learning algorithm (for example, a convolutional neural network (CNN)). Specifically, the server analyzes the photos using libraries such as TensorFlow or PyTorch. The input is the transmitted photo data and metadata, and the output is feature data within the photo (for example, the type of ingredients or characteristics of the dish).

[0125] Step 4:

[0126] The server then uses the results of the photo analysis to match recipe information in the database. Specifically, the server uses an SQL query to access the database and search for recipe information that matches the features in the photo. The input is the analyzed feature data, and the output is the identified ingredients list and processing instructions.

[0127] Step 5:

[0128] The server generates a response to send back to the user based on the matching results. Specifically, the server converts the analysis results into JSON format and sends it to the terminal as an HTTP response. The input is the identified material list and processing instructions, and the output is the generated response (JSON format).

[0129] Step 6:

[0130] The device parses the response received from the server and displays the results on the user interface of the reverse recipe engine app. Specifically, the device parses the JSON response and displays the data in the UI components. The user accesses the required information using the "Ingredient List" and "Cooking Instructions" tabs. The input is the received JSON response, and the output is the displayed ingredient list and cooking instructions.

[0131] This allows users to take a photo of a dish and easily find out the ingredients and cooking instructions needed.

[0132] (Application example 1)

[0133] 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."

[0134] There is a demand for a system that can identify ingredients and processing methods for a dish simply by taking a photo, allowing users to easily recreate the dish. Especially for use in brick-and-mortar stores, it is desirable to support users in cooking on-site or at home using ingredients purchased at the store. However, few existing systems are specifically designed for use in brick-and-mortar stores, and an improved user experience is desired. To solve this problem, a new system is needed.

[0135] 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.

[0136] In this invention, the server includes means for uploading photos taken by users to a terminal, means for transmitting the uploaded photos to the server via a network, means for the server to analyze the photos and identify ingredients and processing methods for the dish, means for returning the identified ingredients and processing methods from the server to the terminal, means for displaying the returned ingredients and processing methods to the user, and means for using the system in a physical store. This enables users to immediately learn cooking methods using ingredients purchased in the physical store and recreate the dish on the spot.

[0137] "Device" refers to an electronic device that allows a user to take photos and operate applications.

[0138] "Network" refers to a digital communications infrastructure for transmitting and receiving data.

[0139] "Server" refers to a computer system that provides the computational resources to analyze data and process and return results.

[0140] "Machine learning algorithms" refer to artificial intelligence techniques used for image analysis and feature extraction.

[0141] "Photo" refers to image data of food taken by the user.

[0142] "Ingredients" refers to the ingredients needed to prepare a dish.

[0143] "Processing method" refers to the steps or techniques used to create a specific dish.

[0144] "Database" refers to a system that stores and manages cooking recipe information.

[0145] A "physical store" refers to a commercial establishment such as a retail store or restaurant that a user can physically visit.

[0146] "User" refers to an individual who uses this system to take photos of food and obtain recipe information.

[0147] "Display" refers to the act of visually providing information to a user through a terminal.

[0148] System Configuration

[0149] A system for implementing this invention comprises a user terminal, a server, and an image analysis system equipped with a machine learning algorithm. The user takes a photo of a dish using a terminal such as a smartphone. The taken photo is sent to the server via a network. The server has computing resources to execute the machine learning algorithm for image analysis.

[0150] Hardware and Software

[0151] The hardware includes the user's device (e.g., a smartphone), the computer network, and the server, while the software includes the application that runs on the user's device, the image analysis algorithm that runs on the server (e.g., TensorFlow's ResNet50), and the database software.

[0152] Data processing and calculation

[0153] 1. Take and send images:

[0154] Users take a photo of their food using their device's camera, and an application on their device uploads the photo to a server, including the photo itself and other metadata such as a timestamp and user ID.

[0155] 2. Image Analysis:

[0156] The server inputs the received images into a machine learning algorithm (e.g., TensorFlow's ResNet50) to extract features to identify the ingredients of the dish. The algorithm then matches the images with a large number of existing food images to identify the most suitable ingredients.

[0157] 3. Verification of information:

[0158] The server then matches the identified ingredient information with recipe information in a database, which stores information about ingredients for various dishes and their processing methods, to find the appropriate recipe.

[0159] 4. Return of results:

[0160] The server sends the identified ingredients and processing method back to the user's device. The application on the device receives this information and displays it in the user interface. The user can then create a dish based on the displayed information.

[0161] Adding specific examples

[0162] As a concrete example, let's say a user takes a photo of a "pasta dish" at a restaurant. The photo is uploaded to the application and sent to the server. The server analyzes the photo and identifies ingredients such as pasta, tomato sauce, basil, and cheese. Based on the analysis results, the most suitable recipe information is extracted from the database. Finally, the ingredients and cooking instructions are sent back to the user's device, where the user can check the information and prepare the dish.

[0163] Prompt Sentence Examples

[0164] Use the following prompt to input the generative AI model:

[0165] text

[0166] A user has uploaded a photo of a pasta dish. Identify the ingredients and cooking method extracted from the photo. Return the ingredients list and simple cooking instructions.

[0167] This allows users to immediately find out how to cook ingredients purchased in a physical store, greatly improving user convenience.

[0168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0169] Step 1:

[0170] The user takes a photo of the food using the device's camera. The photo is saved in the device's local storage. The input is the food photo, and the output is the photo data.

[0171] Step 2:

[0172] When the user presses the upload button, the application on the device sends the saved photo data to the server. At this time, metadata (timestamp and user ID) is added to the photo data. The input is the photo data and metadata, and the output is a notification to the server that the data has been sent.

[0173] Step 3:

[0174] The server inputs the received photo data into an image analysis algorithm (TensorFlow's ResNet50), which extracts features within the photo and identifies the ingredients of a particular dish. The input is the photo data, and the output is a list of identified ingredients.

[0175] Step 4:

[0176] The server matches the identified ingredient list with the recipe information stored in the database, which searches for the relevant recipe and processing method. The input is the ingredient list, and the output is the optimal recipe and processing method.

[0177] Step 5:

[0178] The server returns the identified ingredients and processing method to the user's device. The returned information includes an ingredient list and cooking instructions. The input is the recipe information processed on the server side, and the output is data sent to the user's device.

[0179] Step 6:

[0180] The terminal displays the recipe information received from the server on the user interface. The user can check the cooking procedure by viewing this information. The input is the recipe information from the server, and the output is the recipe information displayed to the user.

[0181] Step 7:

[0182] The user recreates the dish based on the ingredients list and cooking instructions displayed on the device. The input is the cooking information displayed on the device, and the output is the completed dish.

[0183] 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.

[0184] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[0185] Program processing

[0186] 1. User Input

[0187] Users take photos of their dishes using their devices and upload them to the reverse recipe engine app. The devices are equipped with devices such as a camera and microphone to recognize the user's emotions.

[0188] 2. Emotional Recognition

[0189] The device analyzes the user's facial expressions and tone of voice when taking a photo and uses an emotion engine to identify the user's emotional state, which is then sent to the server along with the photo data.

[0190] 3. Sending photos

[0191] The device sends the user-selected photo and emotional information to the server via the network, along with metadata such as the user ID and timestamp in addition to the photo data.

[0192] 4. Photo Analysis

[0193] The server then runs the received photo through image analysis algorithms, such as applying a convolutional neural network (CNN) to extract features within the photo, which then identifies the ingredients and type of dish.

[0194] 5. Identifying materials and processing methods

[0195] The server compares the extracted feature data with an internal database, which stores a wide variety of recipes, along with information on ingredients and processing methods. The server also takes emotional information into account to select the optimal recipe.

[0196] 6. Generating Results

[0197] The server generates a response to send back to the user based on the identified recipe information, including an optimal list of ingredients and processing instructions based on the analysis results of the emotion engine.

[0198] 7. Return of results

[0199] The server generates a response and sends it to the device, which then analyzes it and displays the results in the app's user interface.

[0200] 8. User Display

[0201] The device displays optimal recipe information based on emotions to the user through a user interface, and the user can check the ingredients list and cooking instructions on the device screen and follow them to cook the dish.

[0202] Specific examples

[0203] For example, if a user takes a photo of a pasta dish, the process will proceed as follows:

[0204] 1. Photo and emotion recognition:

[0205] As the user takes a photo of the food, the device uses an emotion engine to analyze the user's facial expressions and tone of voice to identify their emotional state, such as "happy" or "tired."

[0206] 2. Sending photos and emotional information:

[0207] The device sends the captured photo data and emotional information to the server.

[0208] 3. Photo analysis and database matching:

[0209] The server analyzes the received photo, extracts features from the photo, and compares them with an internal database, taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[0210] 4. Generate and return results:

[0211] Based on the selected recipe information, the server generates a response including a list of ingredients and specific cooking instructions and sends it back to the terminal.

[0212] 5. Displaying the results:

[0213] The device displays the received information on a user interface, allowing the user to prepare meals based on that information. For example, a user who is "tired" will be shown recipes for meals that are easy to prepare in a short time.

[0214] This system not only obtains ingredients and processing methods from photos of food, but also provides optimal recipes according to the user's emotional state, thereby further increasing user satisfaction.

[0215] The processing flow will be explained below.

[0216] Step 1:

[0217] The user takes a photo of the food using the device. The user activates the device's camera function and takes a photo of the food. At this time, the photo is saved in the device's internal storage.

[0218] Step 2:

[0219] Users can enable emotion recognition within the app, which allows the device's camera and microphone to analyze the user's facial expressions and voice.

[0220] Step 3:

[0221] The user uploads the photos they have taken to the app. The user opens the app, selects the photos they have taken, and presses the upload button.

[0222] Step 4:

[0223] The device recognizes and analyzes the user's emotions. The device uses a camera to capture the user's facial expressions and a microphone to capture the user's tone of voice, and sends these to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state.

[0224] Step 5:

[0225] The device sends the emotional information along with the photo data to the server. The data sent includes the photo data, emotional information, metadata such as the user ID and timestamp.

[0226] Step 6:

[0227] The server receives the photo data and emotion information sent from the device, stores this data in its internal storage, and begins the analysis process.

[0228] Step 7:

[0229] The server inputs the photo data into a machine learning algorithm for analysis, using a convolutional neural network (CNN) to extract features from the photo and identify the ingredients and type of dish.

[0230] Step 8:

[0231] The server compares the extracted feature data and emotion information with the database. The server then compares this with recipe information in its internal database to find the optimal recipe. For example, if the user is "tired," it will select a dish that is easy to prepare and can be made quickly.

[0232] Step 9:

[0233] The server generates a response based on the identified recipe information, including an ingredient list, specific cooking instructions, and emotion-based advice.

[0234] Step 10:

[0235] The server sends the generated response to the terminal, and the server returns the response data to the terminal via the network.

[0236] Step 11:

[0237] The device analyzes the response received from the server and displays it in the user interface, allowing the user to view the ingredients list and cooking instructions through the app.

[0238] Step 12:

[0239] The user cooks a dish based on the displayed recipe. The user can check the necessary ingredients and cooking steps on the device screen and proceed with the cooking in the order displayed. For example, a user who is "tired" can be shown a recipe that can be made quickly, reducing the burden on the user.

[0240] Example 2

[0241] 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."

[0242] Conventional systems cannot consider the emotional state of the user in the process of taking a photo of a dish and using a reverse recipe engine system to identify ingredients and processing methods, making it difficult to improve user satisfaction. Furthermore, the provided recipes may not be suitable for the user's current situation, which can impair the user's enjoyable cooking experience.

[0243] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0244] In this invention, the server includes means for uploading photos and emotional data taken by the user, means for transmitting the uploaded photos and emotional data to the server, means for analyzing the photos in the server and identifying ingredients and processing methods for cooking, means for selecting an optimal recipe in the server based on the emotional data, means for returning the identified ingredients, processing method, and optimal recipe from the server, and means for displaying the returned ingredients, processing method, and optimal recipe to the user. This makes it possible to provide an appropriate recipe that takes into account the emotional state of the user.

[0245] "Means for uploading photos and emotional data taken by the user" refers to a function that allows users to take and record photos of food and emotional data using the device's camera and microphone, and send them to the system via the Internet.

[0246] "Means for transmitting uploaded photos and emotional data to the server" refers to the function that packets the data captured and recorded by the device and transfers it to the server via the network.

[0247] "Means for analyzing photos on the server and identifying the ingredients and processing method of a dish" refers to a function that uses image analysis technology provided by the server to analyze photos of food taken by the user and identify the ingredients and type of dish in the image, thereby identifying the ingredients and cooking method.

[0248] "Means for selecting the optimal recipe based on emotional data on the server" refers to a function that allows the server to select an appropriate recipe from its internal database, taking into account the analyzed emotional data of the user. This allows the server to provide a recipe that matches the user's current emotional state.

[0249] The "means for returning the identified materials, processing method, and optimal recipe from the server" is a function that allows the server to generate a response including the analysis results and selected recipe information, and send it to the user's terminal via the network.

[0250] The "means for displaying the returned ingredients, processing method, and optimal recipe to the user" is a function for visually displaying to the user on the user's terminal the received recipe information, cooking procedures, and advice based on emotional data.

[0251] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[0252] The user first takes a photo of the food using the device. The device is equipped with a camera and microphone, which not only allows the device to take photos of the food but also recognizes the user's emotions using their facial expressions and tone of voice. An app for uploading food photos is installed on the device, and the user uses the app to send the photos and emotional data to the server.

[0253] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The emotion engine uses existing software libraries such as OpenCV and AutoML to recognize emotional states such as "happy" or "tired." This emotional information is then sent to the server along with the photo data.

[0254] The server then uses machine learning algorithms to analyze the received photos. For example, it uses machine learning libraries such as TensorFlow and PyTorch to extract features from the photos using a convolutional neural network (CNN). This analysis allows it to identify the ingredients and types of food contained in the photos.

[0255] The server then checks the identified ingredients and type of dish against an internal database, which contains various recipes, their ingredients, and processing methods. The server also takes emotional information into account. For example, if the user's emotional state is "tired," it will prioritize simple recipes that can be made quickly.

[0256] The server generates a response based on the selected recipe information. This response includes a list of specific ingredients and cooking instructions for the dish, as well as a recommended recipe based on the analysis results of the emotion engine. The generated response is then sent back to the user's device via the network.

[0257] The device receives the response from the server and displays it to the user through a user interface. Based on the displayed information, the user can prepare ingredients and follow the provided cooking instructions to cook the dish. Emotion-based advice is also displayed, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[0258] For example, suppose a user takes a photo of pasta for dinner and uploads it to the app. In this case, if the user's emotion is recognized as "tired," the server will provide a recipe for pasta that can be made quickly. An example of a prompt in this case would be, "Enter a photo of the dish, retrieve recipes based on that photo, and suggest the best recipe based on the user's emotion."

[0259] This system allows users to not only upload photos of their food, but also provides them with the best recipes tailored to their emotional state, thereby increasing their satisfaction when cooking.

[0260] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0261] Step 1:

[0262] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. The input here is the photo of the dish taken with the camera, and the output is the photo data uploaded to the app. This upload operation saves the photo data within the app.

[0263] Step 2:

[0264] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The input is the user's facial expressions and tone of voice, and the output is emotion data. The device analyzes this data using OpenCV and audio processing libraries to generate emotion information such as "happy" or "tired."

[0265] Step 3:

[0266] The device sends photo data and emotion data to the server. The input here is the uploaded photo data and analyzed emotion data, and the output is a data packet sent to the server. This data packet also contains metadata such as the user ID and timestamp.

[0267] Step 4:

[0268] The server analyzes the received photo data. The input here is the transmitted photo data, and the output is the analysis results, which are the ingredients and type of dish. The server applies a convolutional neural network (CNN) using TensorFlow or PyTorch to extract features from the photo, thereby identifying the ingredients and type of dish.

[0269] Step 5:

[0270] The server compares the extracted feature data and emotion data with its internal database. The input here is the analysis results of ingredients, types of dishes, and emotion data, and the output is the optimal recipe. For example, if the user's emotional state is "tired," it will prioritize recipes that are easy to make and can be made quickly.

[0271] Step 6:

[0272] The server generates a response based on the selected recipe information. The inputs are the optimal recipe, ingredient list, cooking instructions, and sentiment analysis results, and the output is the generated response, which includes the specific ingredient list and cooking instructions for the dish, as well as the sentiment-based recommended recipe.

[0273] Step 7:

[0274] The server sends the generated response to the terminal. The input here is the generated response, and the output is the response sent to the terminal. This information is quickly delivered to the terminal via the network.

[0275] Step 8:

[0276] The device receives the response sent back from the server and displays it to the user through a user interface. The input here is the response sent from the server, and the output is the recipe information displayed on the device screen. The user can prepare and cook the dish based on this information. Emotion-based advice is also displayed on the screen, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[0277] Through this series of processes, users not only upload photos of their food, but are also suggested optimal recipes tailored to their individual emotional state, increasing their satisfaction when cooking.

[0278] (Application example 2)

[0279] 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."

[0280] Conventional recipe provision systems allow users to take photos of dishes and identify ingredients and processing methods from the photos, but they are unable to provide optimal recipes that take into account the user's emotional state. This means that when users cook, they have to go through the trouble of selecting an appropriate recipe that matches their emotional state at the time. Another issue is that they do not provide enough support to help users enjoy cooking.

[0281] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's facial expression and tone of voice to identify their emotional state, means for selecting an optimal recipe based on the identified emotional state, and means for returning the identified ingredients, processing method, and optimal recipe. This makes it possible for the user to simply take a photo of a dish and be provided with an optimal recipe based on their current emotional state.

[0282] A "user" is a person who uses the system to take photos and obtain recipe information.

[0283] "Photo" refers to image data of food or an object photographed by a user with a camera.

[0284] "Upload" refers to the act of sending photo data from a user's device to a server.

[0285] The "server" refers to a central processing unit that analyzes photos and processes information on materials, processing methods, and the user's emotions.

[0286] "Emotional state" refers to a psychological state that is determined by analyzing a user's facial expressions and tone of voice.

[0287] "Machine learning algorithm" refers to an artificial intelligence technique that extracts features from photos based on large amounts of data.

[0288] "Database" refers to a collection of information that stores a wide variety of cooking recipes, their ingredients, processing methods, and additional information.

[0289] "Recipe" refers to a cooking instruction manual that includes specified ingredients and processing steps.

[0290] The "optimal recipe" refers to a cooking recipe that is most suitable for the user's situation, selected based on the user's emotional state and photo data.

[0291] This invention combines a system that allows users to take photos of food with a function that recognizes the user's emotions. This system not only allows users to take photos of food, but also provides them with the optimal recipe that corresponds to their current emotional state. The specific configuration and operation of the system are as follows.

[0292] Hardware and Software Configuration

[0293] 1. User device: Smart glasses or smartphones equipped with a camera and microphone are used. It includes an image and voice input device that allows the user to take photos of the food and analyze emotions from facial expressions and voice.

[0294] 2. Server: A central processing unit that analyzes photo and emotion data, equipped with machine learning algorithms and a database. Software used includes Python, OpenCV, a facial recognition library, and an AI model for emotion analysis.

[0295] Data processing and calculation

[0296] 1. User input: The user takes a photo of the food using the device and uploads it to the device, which then captures the user's facial expressions and tone of voice and sends them to the sentiment analysis module.

[0297] 2. Emotion Recognition: The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state, and the results of this analysis are sent to the server along with the photo data.

[0298] 3. Photo analysis: The server analyzes the received photos using machine learning algorithms (e.g., convolutional neural networks) to extract features from the photos.

[0299] 4. Identifying ingredients and processing methods: The server checks the database and identifies the ingredients and processing methods based on the feature data in the photo. It also selects the optimal recipe based on the emotion data.

[0300] 5. Generate and return results: The server returns the generated recipe information (ingredients list and cooking instructions) to the terminal and displays it to the user.

[0301] Specific examples

[0302] For example, when a user takes a photo of a pasta dish, the process proceeds as follows.

[0303] 1. Photo and emotion recognition: The user takes a photo of the food, and the device analyzes the user's facial expressions and tone of voice to identify emotional states such as "tired" or "happy."

[0304] 2. Sending photos and emotional information: The device sends photos and emotional information to the server.

[0305] 3. Photo analysis and database matching: The server analyzes the photo, extracts features, and compares them with the database taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[0306] 4. Generate and return results: The server returns the generated results to the terminal and displays them to the user, who can then use them to prepare the dish.

[0307] Prompt Sentence Examples

[0308] When a user visits the store, the smart glasses are used to photograph the user's face and analyze their emotions based on their facial expressions. If the user's emotion is determined to be "tired," the system will suggest products or services that have a relaxing effect (such as relaxation services).

[0309] This system allows users to receive optimal cooking recipes and suggestions based on their emotional state, improving the efficiency and satisfaction of cooking.

[0310] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0311] Step 1:

[0312] The user takes a photo of the food and uploads it to the device. Specifically, the user takes a photo of the food using smart glasses or a smartphone camera. The device then stores the photo in its local memory, and the emotion recognition module begins to operate. The input is the photo taken by the user, and the output is the photo data stored on the device.

[0313] Step 2:

[0314] The device analyzes the user's facial expressions and tone of voice to identify their emotional state. It uses an emotion engine to analyze the user's facial images and voice data at the time of capture. The input is the user's facial expressions and tone of voice, and the output is identified emotional state data. Specifically, it uses a facial recognition algorithm to analyze facial expressions and analyzes psychological state from tone of voice.

[0315] Step 3:

[0316] The device transmits the photo data and emotion data to the server. The input is the captured photo data and the identified emotion state data, and the output is the data transmitted to the server via the network. The device uploads the photo data and emotion data to the server in text and image format.

[0317] Step 4:

[0318] The server analyzes the received photos using a machine learning algorithm (e.g., a convolutional neural network) to extract features from the photos. The input is the photo data sent from the device, and the output is the extracted feature data. The server uses an image processing library to extract features that identify the type of food and ingredients.

[0319] Step 5:

[0320] The server compares the extracted feature data and emotional data with an internal database to select the optimal recipe. The input is the extracted feature data and the identified emotional state data, and the output is the optimal recipe data. When comparing the database, the server takes the emotional data into consideration and selects a recipe that can be made in a short time, for example, if the user is "tired."

[0321] Step 6:

[0322] The server generates a response based on the identified materials, processing steps, and optimal recipe information. The input is the selected recipe data, and the output is response data to send back to the user. The server constructs the response data and includes the necessary recipe information and materials list.

[0323] Step 7:

[0324] The server sends the generated response to the terminal. The input is the response data constructed by the server, and the output is the data sent back to the terminal via the network. The server encodes the response data and transfers it to the terminal.

[0325] Step 8:

[0326] The terminal analyzes the received response data and displays it on the user interface. The input is the response data sent from the server, and the output is the ingredient list and cooking instructions displayed on the user interface. Specifically, the terminal parses the response data and displays recipe information to the user based on it.

[0327] Through the above processing steps, the user can obtain optimal recipe information suited to their emotional state at the time simply by taking a photo of the food.

[0328] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0330] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0331] [Second embodiment]

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

[0333] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0334] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0335] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0336] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0337] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0338] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0339] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0340] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0341] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0342] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0344] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[0345] Program processing

[0346] 1. User Input

[0347] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[0348] 2. Sending photos

[0349] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[0350] 3. Photo Analysis

[0351] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[0352] 4. Identifying materials and processing methods

[0353] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[0354] 5. Return of results

[0355] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[0356] 6. User Display

[0357] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[0358] Specific examples

[0359] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[0360] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[0361] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[0362] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[0363] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[0364] The present invention allows users to intuitively know the ingredients and cooking methods needed based on photos of dishes, thereby broadening the range of dishes they can make.

[0365] The processing flow will be explained below.

[0366] Step 1:

[0367] The user takes a photo of the dish using the device. The user opens the app, selects the photo, and presses the upload button. The photo is then saved to the device's internal storage.

[0368] Step 2:

[0369] The device sends the photos selected by the user to the server via the network, and the photos are sent along with metadata such as the user ID and a timestamp.

[0370] Step 3:

[0371] The server receives the photo data sent from the device, stores it internally, and begins analyzing it.

[0372] Step 4:

[0373] The server feeds the photo data into machine learning algorithms, such as applying a convolutional neural network (CNN), to extract features within the photo, which then identify the ingredients and type of dish.

[0374] Step 5:

[0375] The server compares the extracted feature data with its internal database, which contains numerous recipes with their ingredients and procedures, and searches for the most suitable recipe.

[0376] Step 6:

[0377] The server generates a list of identified materials and processing instructions from the search results and creates a response to return this information to the user.

[0378] Step 7:

[0379] The server then sends the generated response to the device, which includes the identified ingredients and specific cooking instructions.

[0380] Step 8:

[0381] The terminal receives the response sent from the server, and then displays the ingredient list and cooking instructions to the user through the user interface.

[0382] Step 9:

[0383] Users can check the ingredients list and cooking instructions on the device screen and follow them to prepare the dish. The user prepares the necessary ingredients and proceeds with cooking according to the displayed instructions.

[0384] Through these steps, the system provides an environment where users can easily obtain ingredients and processing methods by simply uploading a photo of the dish.

[0385] Example 1

[0386] 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."

[0387] Currently, many users post photos of the dishes they have cooked on social media and blogs, but it is difficult to know the specific ingredients and cooking methods from those photos. Beginners in cooking and users who want to try new recipes need a system that can automatically find detailed ingredients and cooking steps from a photo of a dish. Furthermore, existing methods require users to perform complex operations, so an intuitive and simple operation is required.

[0388] 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.

[0389] In this invention, the server includes a means for uploading photos taken by users, a means for transmitting the uploaded photos to the server, and a means for analyzing the photos on the server and identifying the ingredients and processing methods of the dish. This allows users to intuitively learn the necessary ingredients and cooking methods simply by uploading a photo of the dish without performing complex operations. This invention also includes a means for extracting features from the photo using a machine learning algorithm when analyzing the photo on the server, and for deriving the optimal recipe based on the analysis results by comparing them with recipe information in a database. This provides more accurate recipe information, allowing users to broaden their cooking options.

[0390] A "user" is an individual who uses the system to take photos of dishes and use the reverse recipe engine app.

[0391] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0392] A "server" is a central processing unit that receives and analyzes data sent from a user and returns the results to the terminal.

[0393] "Uploading" is the act of a user sending data (in this case, photos of food) from a terminal to a server.

[0394] A "machine learning algorithm" is a program the server uses to analyze features in a photo and identify ingredients and types of dishes.

[0395] The "JSON format" is a lightweight data format used for data exchange that is easy to read for both humans and machines.

[0396] An "image analysis algorithm" is a program for extracting and analyzing feature data from photographs.

[0397] A "database" is a system that systematically stores information about cooking ingredients and processing methods and is used by the server to collate the information.

[0398] "Metadata" is information that is sent along with the photo data, and includes a timestamp, user ID, and so on.

[0399] A "response" is response data that the server returns to the terminal, including analysis results and necessary information.

[0400] "User interface" refers to the screen and operation method that allows the user to interact with the system and intuitively confirm the results.

[0401] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[0402] Program processing

[0403] 1. User Input

[0404] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[0405] 2. Sending photos

[0406] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[0407] 3. Photo Analysis

[0408] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[0409] 4. Identifying materials and processing methods

[0410] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[0411] 5. Return of results

[0412] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[0413] 6. User Display

[0414] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[0415] Specific examples

[0416] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[0417] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[0418] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[0419] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[0420] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[0421] Prompt Sentence Examples

[0422] Here is an example of inputting the following prompt sentence to a generative AI model:

[0423] I want to have an AI analyze photos of food taken by users and identify the ingredients and cooking method. Please explain the steps required to upload a photo and the specific processing action to be taken based on the submitted photo. Furthermore, please explain in more detail using a photo of a pasta dish as an example.

[0424] With the present invention configured as described above, a user can intuitively learn the ingredients and cooking methods needed based on a photo of a dish, thereby broadening the range of dishes they can make.

[0425] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0426] Step 1:

[0427] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. Specifically, the user opens the device's camera app and takes a photo of the dish. This photo is saved in the device's local storage. Next, the user launches the reverse recipe engine app, presses the "Select Photo" button to select the photo they took, and presses the "Upload" button. The input is the photo they took, and the output is the selected photo being displayed in the app.

[0428] Step 2:

[0429] The device sends the photo selected by the user to the server via the network. At this time, metadata such as a timestamp and user ID are added to the photo data. Specifically, the device sends the photo data and metadata to the server using an HTTP POST request. The input is the selected photo data and metadata, and the output is a transmission completion message to the server.

[0430] Step 3:

[0431] The server applies an image analysis algorithm to the received photos. This image analysis uses a machine learning algorithm (for example, a convolutional neural network (CNN)). Specifically, the server analyzes the photos using libraries such as TensorFlow or PyTorch. The input is the transmitted photo data and metadata, and the output is feature data within the photo (for example, the type of ingredients or characteristics of the dish).

[0432] Step 4:

[0433] The server then uses the results of the photo analysis to match recipe information in the database. Specifically, the server uses an SQL query to access the database and search for recipe information that matches the features in the photo. The input is the analyzed feature data, and the output is the identified ingredients list and processing instructions.

[0434] Step 5:

[0435] The server generates a response to send back to the user based on the matching results. Specifically, the server converts the analysis results into JSON format and sends it to the terminal as an HTTP response. The input is the identified material list and processing instructions, and the output is the generated response (JSON format).

[0436] Step 6:

[0437] The device parses the response received from the server and displays the results on the user interface of the reverse recipe engine app. Specifically, the device parses the JSON response and displays the data in the UI components. The user accesses the required information using the "Ingredient List" and "Cooking Instructions" tabs. The input is the received JSON response, and the output is the displayed ingredient list and cooking instructions.

[0438] This allows users to take a photo of a dish and easily find out the ingredients and cooking instructions needed.

[0439] (Application example 1)

[0440] 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."

[0441] There is a demand for a system that can identify ingredients and processing methods for a dish simply by taking a photo, allowing users to easily recreate the dish. Especially for use in brick-and-mortar stores, it is desirable to support users in cooking on-site or at home using ingredients purchased at the store. However, few existing systems are specifically designed for use in brick-and-mortar stores, and an improved user experience is desired. To solve this problem, a new system is needed.

[0442] 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.

[0443] In this invention, the server includes means for uploading photos taken by users to a terminal, means for transmitting the uploaded photos to the server via a network, means for the server to analyze the photos and identify ingredients and processing methods for the dish, means for returning the identified ingredients and processing methods from the server to the terminal, means for displaying the returned ingredients and processing methods to the user, and means for using the system in a physical store. This enables users to immediately learn cooking methods using ingredients purchased in the physical store and recreate the dish on the spot.

[0444] "Device" refers to an electronic device that allows a user to take photos and operate applications.

[0445] "Network" refers to a digital communications infrastructure for transmitting and receiving data.

[0446] "Server" refers to a computer system that provides the computational resources to analyze data and process and return results.

[0447] "Machine learning algorithms" refer to artificial intelligence techniques used for image analysis and feature extraction.

[0448] "Photo" refers to image data of food taken by the user.

[0449] "Ingredients" refers to the ingredients needed to prepare a dish.

[0450] "Processing method" refers to the steps or techniques used to create a specific dish.

[0451] "Database" refers to a system that stores and manages cooking recipe information.

[0452] A "physical store" refers to a commercial establishment such as a retail store or restaurant that a user can physically visit.

[0453] "User" refers to an individual who uses this system to take photos of food and obtain recipe information.

[0454] "Display" refers to the act of visually providing information to a user through a terminal.

[0455] System Configuration

[0456] A system for implementing this invention comprises a user terminal, a server, and an image analysis system equipped with a machine learning algorithm. The user takes a photo of a dish using a terminal such as a smartphone. The taken photo is sent to the server via a network. The server has computing resources to execute the machine learning algorithm for image analysis.

[0457] Hardware and Software

[0458] The hardware includes the user's device (e.g., a smartphone), the computer network, and the server, while the software includes the application that runs on the user's device, the image analysis algorithm that runs on the server (e.g., TensorFlow's ResNet50), and the database software.

[0459] Data processing and calculation

[0460] 1. Take and send images:

[0461] Users take a photo of their food using their device's camera, and an application on their device uploads the photo to a server, including the photo itself and other metadata such as a timestamp and user ID.

[0462] 2. Image Analysis:

[0463] The server inputs the received images into a machine learning algorithm (e.g., TensorFlow's ResNet50) to extract features to identify the ingredients of the dish. The algorithm then matches the images with a large number of existing food images to identify the most suitable ingredients.

[0464] 3. Verification of information:

[0465] The server then matches the identified ingredient information with recipe information in a database, which stores information about ingredients for various dishes and their processing methods, to find the appropriate recipe.

[0466] 4. Return of results:

[0467] The server sends the identified ingredients and processing method back to the user's device. The application on the device receives this information and displays it in the user interface. The user can then create a dish based on the displayed information.

[0468] Adding specific examples

[0469] As a concrete example, let's say a user takes a photo of a "pasta dish" at a restaurant. The photo is uploaded to the application and sent to the server. The server analyzes the photo and identifies ingredients such as pasta, tomato sauce, basil, and cheese. Based on the analysis results, the most suitable recipe information is extracted from the database. Finally, the ingredients and cooking instructions are sent back to the user's device, where the user can check the information and prepare the dish.

[0470] Prompt Sentence Examples

[0471] Use the following prompt to input the generative AI model:

[0472] text

[0473] A user has uploaded a photo of a pasta dish. Identify the ingredients and cooking method extracted from the photo. Return the ingredients list and simple cooking instructions.

[0474] This allows users to immediately find out how to cook ingredients purchased in a physical store, greatly improving user convenience.

[0475] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0476] Step 1:

[0477] The user takes a photo of the food using the device's camera. The photo is saved in the device's local storage. The input is the food photo, and the output is the photo data.

[0478] Step 2:

[0479] When the user presses the upload button, the application on the device sends the saved photo data to the server. At this time, metadata (timestamp and user ID) is added to the photo data. The input is the photo data and metadata, and the output is a notification to the server that the data has been sent.

[0480] Step 3:

[0481] The server inputs the received photo data into an image analysis algorithm (TensorFlow's ResNet50), which extracts features within the photo and identifies the ingredients of a particular dish. The input is the photo data, and the output is a list of identified ingredients.

[0482] Step 4:

[0483] The server matches the identified ingredient list with the recipe information stored in the database, which searches for the relevant recipe and processing method. The input is the ingredient list, and the output is the optimal recipe and processing method.

[0484] Step 5:

[0485] The server returns the identified ingredients and processing method to the user's device. The returned information includes an ingredient list and cooking instructions. The input is the recipe information processed on the server side, and the output is data sent to the user's device.

[0486] Step 6:

[0487] The terminal displays the recipe information received from the server on the user interface. The user can check the cooking procedure by viewing this information. The input is the recipe information from the server, and the output is the recipe information displayed to the user.

[0488] Step 7:

[0489] The user recreates the dish based on the ingredients list and cooking instructions displayed on the device. The input is the cooking information displayed on the device, and the output is the completed dish.

[0490] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0491] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[0492] Program processing

[0493] 1. User Input

[0494] Users take photos of their dishes using their devices and upload them to the reverse recipe engine app. The devices are equipped with devices such as a camera and microphone to recognize the user's emotions.

[0495] 2. Emotional Recognition

[0496] The device analyzes the user's facial expressions and tone of voice when taking a photo and uses an emotion engine to identify the user's emotional state, which is then sent to the server along with the photo data.

[0497] 3. Sending photos

[0498] The device sends the user-selected photo and emotional information to the server via the network, along with metadata such as the user ID and timestamp in addition to the photo data.

[0499] 4. Photo Analysis

[0500] The server then runs the received photo through image analysis algorithms, such as applying a convolutional neural network (CNN) to extract features within the photo, which then identifies the ingredients and type of dish.

[0501] 5. Identifying materials and processing methods

[0502] The server compares the extracted feature data with an internal database, which stores a wide variety of recipes, along with information on ingredients and processing methods. The server also takes emotional information into account to select the optimal recipe.

[0503] 6. Generating Results

[0504] The server generates a response to send back to the user based on the identified recipe information, including an optimal list of ingredients and processing instructions based on the analysis results of the emotion engine.

[0505] 7. Return of results

[0506] The server generates a response and sends it to the device, which then analyzes it and displays the results in the app's user interface.

[0507] 8. User Display

[0508] The device displays optimal recipe information based on emotions to the user through a user interface, and the user can check the ingredients list and cooking instructions on the device screen and follow them to cook the dish.

[0509] Specific examples

[0510] For example, if a user takes a photo of a pasta dish, the process will proceed as follows:

[0511] 1. Photo and emotion recognition:

[0512] As the user takes a photo of the food, the device uses an emotion engine to analyze the user's facial expressions and tone of voice to identify their emotional state, such as "happy" or "tired."

[0513] 2. Sending photos and emotional information:

[0514] The device sends the captured photo data and emotional information to the server.

[0515] 3. Photo analysis and database matching:

[0516] The server analyzes the received photo, extracts features from the photo, and compares them with an internal database, taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[0517] 4. Generate and return results:

[0518] Based on the selected recipe information, the server generates a response including a list of ingredients and specific cooking instructions and sends it back to the terminal.

[0519] 5. Displaying the results:

[0520] The device displays the received information on a user interface, allowing the user to prepare meals based on that information. For example, a user who is "tired" will be shown recipes for meals that are easy to prepare in a short time.

[0521] This system not only obtains ingredients and processing methods from photos of food, but also provides optimal recipes according to the user's emotional state, thereby further increasing user satisfaction.

[0522] The processing flow will be explained below.

[0523] Step 1:

[0524] The user takes a photo of the food using the device. The user activates the device's camera function and takes a photo of the food. At this time, the photo is saved in the device's internal storage.

[0525] Step 2:

[0526] Users can enable emotion recognition within the app, which allows the device's camera and microphone to analyze the user's facial expressions and voice.

[0527] Step 3:

[0528] The user uploads the photos they have taken to the app. The user opens the app, selects the photos they have taken, and presses the upload button.

[0529] Step 4:

[0530] The device recognizes and analyzes the user's emotions. The device uses a camera to capture the user's facial expressions and a microphone to capture the user's tone of voice, and sends these to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state.

[0531] Step 5:

[0532] The device sends the emotional information along with the photo data to the server. The data sent includes the photo data, emotional information, metadata such as the user ID and timestamp.

[0533] Step 6:

[0534] The server receives the photo data and emotion information sent from the device, stores this data in its internal storage, and begins the analysis process.

[0535] Step 7:

[0536] The server inputs the photo data into a machine learning algorithm for analysis, using a convolutional neural network (CNN) to extract features from the photo and identify the ingredients and type of dish.

[0537] Step 8:

[0538] The server compares the extracted feature data and emotion information with the database. The server then compares this with recipe information in its internal database to find the optimal recipe. For example, if the user is "tired," it will select a dish that is easy to prepare and can be made quickly.

[0539] Step 9:

[0540] The server generates a response based on the identified recipe information, including an ingredient list, specific cooking instructions, and emotion-based advice.

[0541] Step 10:

[0542] The server sends the generated response to the terminal, and the server returns the response data to the terminal via the network.

[0543] Step 11:

[0544] The device analyzes the response received from the server and displays it in the user interface, allowing the user to view the ingredients list and cooking instructions through the app.

[0545] Step 12:

[0546] The user cooks a dish based on the displayed recipe. The user can check the necessary ingredients and cooking steps on the device screen and proceed with the cooking in the order displayed. For example, a user who is "tired" can be shown a recipe that can be made quickly, reducing the burden on the user.

[0547] Example 2

[0548] 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."

[0549] Conventional systems cannot consider the emotional state of the user in the process of taking a photo of a dish and using a reverse recipe engine system to identify ingredients and processing methods, making it difficult to improve user satisfaction. Furthermore, the provided recipes may not be suitable for the user's current situation, which can impair the user's enjoyable cooking experience.

[0550] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0551] In this invention, the server includes means for uploading photos and emotional data taken by the user, means for transmitting the uploaded photos and emotional data to the server, means for analyzing the photos in the server and identifying ingredients and processing methods for cooking, means for selecting an optimal recipe in the server based on the emotional data, means for returning the identified ingredients, processing method, and optimal recipe from the server, and means for displaying the returned ingredients, processing method, and optimal recipe to the user. This makes it possible to provide an appropriate recipe that takes into account the emotional state of the user.

[0552] "Means for uploading photos and emotional data taken by the user" refers to a function that allows users to take and record photos of food and emotional data using the device's camera and microphone, and send them to the system via the Internet.

[0553] "Means for transmitting uploaded photos and emotional data to the server" refers to the function that packets the data captured and recorded by the device and transfers it to the server via the network.

[0554] "Means for analyzing photos on the server and identifying the ingredients and processing method of a dish" refers to a function that uses image analysis technology provided by the server to analyze photos of food taken by the user and identify the ingredients and type of dish in the image, thereby identifying the ingredients and cooking method.

[0555] "Means for selecting the optimal recipe based on emotional data on the server" refers to a function that allows the server to select an appropriate recipe from its internal database, taking into account the analyzed emotional data of the user. This allows the server to provide a recipe that matches the user's current emotional state.

[0556] The "means for returning the identified materials, processing method, and optimal recipe from the server" is a function that allows the server to generate a response including the analysis results and selected recipe information, and send it to the user's terminal via the network.

[0557] The "means for displaying the returned ingredients, processing method, and optimal recipe to the user" is a function for visually displaying to the user on the user's terminal the received recipe information, cooking procedures, and advice based on emotional data.

[0558] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[0559] The user first takes a photo of the food using the device. The device is equipped with a camera and microphone, which not only allows the device to take photos of the food but also recognizes the user's emotions using their facial expressions and tone of voice. An app for uploading food photos is installed on the device, and the user uses the app to send the photos and emotional data to the server.

[0560] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The emotion engine uses existing software libraries such as OpenCV and AutoML to recognize emotional states such as "happy" or "tired." This emotional information is then sent to the server along with the photo data.

[0561] The server then uses machine learning algorithms to analyze the received photos. For example, it uses machine learning libraries such as TensorFlow and PyTorch to extract features from the photos using a convolutional neural network (CNN). This analysis allows it to identify the ingredients and types of food contained in the photos.

[0562] The server then checks the identified ingredients and type of dish against an internal database, which contains various recipes, their ingredients, and processing methods. The server also takes emotional information into account. For example, if the user's emotional state is "tired," it will prioritize simple recipes that can be made quickly.

[0563] The server generates a response based on the selected recipe information. This response includes a list of specific ingredients and cooking instructions for the dish, as well as a recommended recipe based on the analysis results of the emotion engine. The generated response is then sent back to the user's device via the network.

[0564] The device receives the response from the server and displays it to the user through a user interface. Based on the displayed information, the user can prepare ingredients and follow the provided cooking instructions to cook the dish. Emotion-based advice is also displayed, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[0565] For example, suppose a user takes a photo of pasta for dinner and uploads it to the app. In this case, if the user's emotion is recognized as "tired," the server will provide a recipe for pasta that can be made quickly. An example of a prompt in this case would be, "Enter a photo of the dish, retrieve recipes based on that photo, and suggest the best recipe based on the user's emotion."

[0566] This system allows users to not only upload photos of their food, but also provides them with the best recipes tailored to their emotional state, thereby increasing their satisfaction when cooking.

[0567] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0568] Step 1:

[0569] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. The input here is the photo of the dish taken with the camera, and the output is the photo data uploaded to the app. This upload operation saves the photo data within the app.

[0570] Step 2:

[0571] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The input is the user's facial expressions and tone of voice, and the output is emotion data. The device analyzes this data using OpenCV and audio processing libraries to generate emotion information such as "happy" or "tired."

[0572] Step 3:

[0573] The device sends photo data and emotion data to the server. The input here is the uploaded photo data and analyzed emotion data, and the output is a data packet sent to the server. This data packet also contains metadata such as the user ID and timestamp.

[0574] Step 4:

[0575] The server analyzes the received photo data. The input here is the transmitted photo data, and the output is the analysis results, which are the ingredients and type of dish. The server applies a convolutional neural network (CNN) using TensorFlow or PyTorch to extract features from the photo, thereby identifying the ingredients and type of dish.

[0576] Step 5:

[0577] The server compares the extracted feature data and emotion data with its internal database. The input here is the analysis results of ingredients, types of dishes, and emotion data, and the output is the optimal recipe. For example, if the user's emotional state is "tired," it will prioritize recipes that are easy to make and can be made quickly.

[0578] Step 6:

[0579] The server generates a response based on the selected recipe information. The inputs are the optimal recipe, ingredient list, cooking instructions, and sentiment analysis results, and the output is the generated response, which includes the specific ingredient list and cooking instructions for the dish, as well as the sentiment-based recommended recipe.

[0580] Step 7:

[0581] The server sends the generated response to the terminal. The input here is the generated response, and the output is the response sent to the terminal. This information is quickly delivered to the terminal via the network.

[0582] Step 8:

[0583] The device receives the response sent back from the server and displays it to the user through a user interface. The input here is the response sent from the server, and the output is the recipe information displayed on the device screen. The user can prepare and cook the dish based on this information. Emotion-based advice is also displayed on the screen, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[0584] Through this series of processes, users not only upload photos of their food, but are also suggested optimal recipes tailored to their individual emotional state, increasing their satisfaction when cooking.

[0585] (Application example 2)

[0586] 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."

[0587] Conventional recipe provision systems allow users to take photos of dishes and identify ingredients and processing methods from the photos, but they are unable to provide optimal recipes that take into account the user's emotional state. This means that when users cook, they have to go through the trouble of selecting an appropriate recipe that matches their emotional state at the time. Another issue is that they do not provide enough support to help users enjoy cooking.

[0588] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's facial expression and tone of voice to identify their emotional state, means for selecting an optimal recipe based on the identified emotional state, and means for returning the identified ingredients, processing method, and optimal recipe. This makes it possible for the user to simply take a photo of a dish and be provided with an optimal recipe based on their current emotional state.

[0589] A "user" is a person who uses the system to take photos and obtain recipe information.

[0590] "Photo" refers to image data of food or an object photographed by a user with a camera.

[0591] "Upload" refers to the act of sending photo data from a user's device to a server.

[0592] The "server" refers to a central processing unit that analyzes photos and processes information on materials, processing methods, and the user's emotions.

[0593] "Emotional state" refers to a psychological state that is determined by analyzing a user's facial expressions and tone of voice.

[0594] "Machine learning algorithm" refers to an artificial intelligence technique that extracts features from photos based on large amounts of data.

[0595] "Database" refers to a collection of information that stores a wide variety of cooking recipes, their ingredients, processing methods, and additional information.

[0596] "Recipe" refers to a cooking instruction manual that includes specified ingredients and processing steps.

[0597] The "optimal recipe" refers to a cooking recipe that is most suitable for the user's situation, selected based on the user's emotional state and photo data.

[0598] This invention combines a system that allows users to take photos of food with a function that recognizes the user's emotions. This system not only allows users to take photos of food, but also provides them with the optimal recipe that corresponds to their current emotional state. The specific configuration and operation of the system are as follows.

[0599] Hardware and Software Configuration

[0600] 1. User device: Smart glasses or smartphones equipped with a camera and microphone are used. It includes an image and voice input device that allows the user to take photos of the food and analyze emotions from facial expressions and voice.

[0601] 2. Server: A central processing unit that analyzes photo and emotion data, equipped with machine learning algorithms and a database. Software used includes Python, OpenCV, a facial recognition library, and an AI model for emotion analysis.

[0602] Data processing and calculation

[0603] 1. User input: The user takes a photo of the food using the device and uploads it to the device, which then captures the user's facial expressions and tone of voice and sends them to the sentiment analysis module.

[0604] 2. Emotion Recognition: The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state, and the results of this analysis are sent to the server along with the photo data.

[0605] 3. Photo analysis: The server analyzes the received photos using machine learning algorithms (e.g., convolutional neural networks) to extract features from the photos.

[0606] 4. Identifying ingredients and processing methods: The server checks the database and identifies the ingredients and processing methods based on the feature data in the photo. It also selects the optimal recipe based on the emotion data.

[0607] 5. Generate and return results: The server returns the generated recipe information (ingredients list and cooking instructions) to the terminal and displays it to the user.

[0608] Specific examples

[0609] For example, when a user takes a photo of a pasta dish, the process proceeds as follows.

[0610] 1. Photo and emotion recognition: The user takes a photo of the food, and the device analyzes the user's facial expressions and tone of voice to identify emotional states such as "tired" or "happy."

[0611] 2. Sending photos and emotional information: The device sends photos and emotional information to the server.

[0612] 3. Photo analysis and database matching: The server analyzes the photo, extracts features, and compares them with the database taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[0613] 4. Generate and return results: The server returns the generated results to the terminal and displays them to the user, who can then use them to prepare the dish.

[0614] Prompt Sentence Examples

[0615] When a user visits the store, the smart glasses are used to photograph the user's face and analyze their emotions based on their facial expressions. If the user's emotion is determined to be "tired," the system will suggest products or services that have a relaxing effect (such as relaxation services).

[0616] This system allows users to receive optimal cooking recipes and suggestions based on their emotional state, improving the efficiency and satisfaction of cooking.

[0617] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0618] Step 1:

[0619] The user takes a photo of the food and uploads it to the device. Specifically, the user takes a photo of the food using smart glasses or a smartphone camera. The device then stores the photo in its local memory, and the emotion recognition module begins to operate. The input is the photo taken by the user, and the output is the photo data stored on the device.

[0620] Step 2:

[0621] The device analyzes the user's facial expressions and tone of voice to identify their emotional state. It uses an emotion engine to analyze the user's facial images and voice data at the time of capture. The input is the user's facial expressions and tone of voice, and the output is identified emotional state data. Specifically, it uses a facial recognition algorithm to analyze facial expressions and analyzes psychological state from tone of voice.

[0622] Step 3:

[0623] The device transmits the photo data and emotion data to the server. The input is the captured photo data and the identified emotion state data, and the output is the data transmitted to the server via the network. The device uploads the photo data and emotion data to the server in text and image format.

[0624] Step 4:

[0625] The server analyzes the received photos using a machine learning algorithm (e.g., a convolutional neural network) to extract features from the photos. The input is the photo data sent from the device, and the output is the extracted feature data. The server uses an image processing library to extract features that identify the type of food and ingredients.

[0626] Step 5:

[0627] The server compares the extracted feature data and emotional data with an internal database to select the optimal recipe. The input is the extracted feature data and the identified emotional state data, and the output is the optimal recipe data. When comparing the database, the server takes the emotional data into consideration and selects a recipe that can be made in a short time, for example, if the user is "tired."

[0628] Step 6:

[0629] The server generates a response based on the identified materials, processing steps, and optimal recipe information. The input is the selected recipe data, and the output is response data to send back to the user. The server constructs the response data and includes the necessary recipe information and materials list.

[0630] Step 7:

[0631] The server sends the generated response to the terminal. The input is the response data constructed by the server, and the output is the data sent back to the terminal via the network. The server encodes the response data and transfers it to the terminal.

[0632] Step 8:

[0633] The terminal analyzes the received response data and displays it on the user interface. The input is the response data sent from the server, and the output is the ingredient list and cooking instructions displayed on the user interface. Specifically, the terminal parses the response data and displays recipe information to the user based on it.

[0634] Through the above processing steps, the user can obtain optimal recipe information suited to their emotional state at the time simply by taking a photo of the food.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] [Third embodiment]

[0639] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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."

[0651] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[0652] Program processing

[0653] 1. User Input

[0654] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[0655] 2. Sending photos

[0656] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[0657] 3. Photo Analysis

[0658] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[0659] 4. Identifying materials and processing methods

[0660] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[0661] 5. Return of results

[0662] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[0663] 6. User Display

[0664] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[0665] Specific examples

[0666] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[0667] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[0668] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[0669] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[0670] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[0671] The present invention allows users to intuitively know the ingredients and cooking methods needed based on photos of dishes, thereby broadening the range of dishes they can make.

[0672] The processing flow will be explained below.

[0673] Step 1:

[0674] The user takes a photo of the dish using the device. The user opens the app, selects the photo, and presses the upload button. The photo is then saved to the device's internal storage.

[0675] Step 2:

[0676] The device sends the photos selected by the user to the server via the network, and the photos are sent along with metadata such as the user ID and a timestamp.

[0677] Step 3:

[0678] The server receives the photo data sent from the device, stores it internally, and begins analyzing it.

[0679] Step 4:

[0680] The server feeds the photo data into machine learning algorithms, such as applying a convolutional neural network (CNN), to extract features within the photo, which then identify the ingredients and type of dish.

[0681] Step 5:

[0682] The server compares the extracted feature data with its internal database, which contains numerous recipes with their ingredients and procedures, and searches for the most suitable recipe.

[0683] Step 6:

[0684] The server generates a list of identified materials and processing instructions from the search results and creates a response to return this information to the user.

[0685] Step 7:

[0686] The server then sends the generated response to the device, which includes the identified ingredients and specific cooking instructions.

[0687] Step 8:

[0688] The terminal receives the response sent from the server, and then displays the ingredient list and cooking instructions to the user through the user interface.

[0689] Step 9:

[0690] Users can check the ingredients list and cooking instructions on the device screen and follow them to prepare the dish. The user prepares the necessary ingredients and proceeds with cooking according to the displayed instructions.

[0691] Through these steps, the system provides an environment where users can easily obtain ingredients and processing methods by simply uploading a photo of the dish.

[0692] Example 1

[0693] 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."

[0694] Currently, many users post photos of the dishes they have cooked on social media and blogs, but it is difficult to know the specific ingredients and cooking methods from those photos. Beginners in cooking and users who want to try new recipes need a system that can automatically find detailed ingredients and cooking steps from a photo of a dish. Furthermore, existing methods require users to perform complex operations, so an intuitive and simple operation is required.

[0695] 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.

[0696] In this invention, the server includes a means for uploading photos taken by users, a means for transmitting the uploaded photos to the server, and a means for analyzing the photos on the server and identifying the ingredients and processing methods of the dish. This allows users to intuitively learn the necessary ingredients and cooking methods simply by uploading a photo of the dish without performing complex operations. This invention also includes a means for extracting features from the photo using a machine learning algorithm when analyzing the photo on the server, and for deriving the optimal recipe based on the analysis results by comparing them with recipe information in a database. This provides more accurate recipe information, allowing users to broaden their cooking options.

[0697] A "user" is an individual who uses the system to take photos of dishes and use the reverse recipe engine app.

[0698] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0699] A "server" is a central processing unit that receives and analyzes data sent from a user and returns the results to the terminal.

[0700] "Uploading" is the act of a user sending data (in this case, photos of food) from a terminal to a server.

[0701] A "machine learning algorithm" is a program the server uses to analyze features in a photo and identify ingredients and types of dishes.

[0702] The "JSON format" is a lightweight data format used for data exchange that is easy to read for both humans and machines.

[0703] An "image analysis algorithm" is a program for extracting and analyzing feature data from photographs.

[0704] A "database" is a system that systematically stores information about cooking ingredients and processing methods and is used by the server to collate the information.

[0705] "Metadata" is information that is sent along with the photo data, and includes a timestamp, user ID, and so on.

[0706] A "response" is response data that the server returns to the terminal, including analysis results and necessary information.

[0707] "User interface" refers to the screen and operation method that allows the user to interact with the system and intuitively confirm the results.

[0708] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[0709] Program processing

[0710] 1. User Input

[0711] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[0712] 2. Sending photos

[0713] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[0714] 3. Photo Analysis

[0715] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[0716] 4. Identifying materials and processing methods

[0717] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[0718] 5. Return of results

[0719] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[0720] 6. User Display

[0721] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[0722] Specific examples

[0723] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[0724] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[0725] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[0726] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[0727] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[0728] Prompt Sentence Examples

[0729] Here is an example of inputting the following prompt sentence to a generative AI model:

[0730] I want to have an AI analyze photos of food taken by users and identify the ingredients and cooking method. Please explain the steps required to upload a photo and the specific processing action to be taken based on the submitted photo. Furthermore, please explain in more detail using a photo of a pasta dish as an example.

[0731] With the present invention configured as described above, a user can intuitively learn the ingredients and cooking methods needed based on a photo of a dish, thereby broadening the range of dishes they can make.

[0732] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0733] Step 1:

[0734] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. Specifically, the user opens the device's camera app and takes a photo of the dish. This photo is saved in the device's local storage. Next, the user launches the reverse recipe engine app, presses the "Select Photo" button to select the photo they took, and presses the "Upload" button. The input is the photo they took, and the output is the selected photo being displayed in the app.

[0735] Step 2:

[0736] The device sends the photo selected by the user to the server via the network. At this time, metadata such as a timestamp and user ID are added to the photo data. Specifically, the device sends the photo data and metadata to the server using an HTTP POST request. The input is the selected photo data and metadata, and the output is a transmission completion message to the server.

[0737] Step 3:

[0738] The server applies an image analysis algorithm to the received photos. This image analysis uses a machine learning algorithm (for example, a convolutional neural network (CNN)). Specifically, the server analyzes the photos using libraries such as TensorFlow or PyTorch. The input is the transmitted photo data and metadata, and the output is feature data within the photo (for example, the type of ingredients or characteristics of the dish).

[0739] Step 4:

[0740] The server then uses the results of the photo analysis to match recipe information in the database. Specifically, the server uses an SQL query to access the database and search for recipe information that matches the features in the photo. The input is the analyzed feature data, and the output is the identified ingredients list and processing instructions.

[0741] Step 5:

[0742] The server generates a response to send back to the user based on the matching results. Specifically, the server converts the analysis results into JSON format and sends it to the terminal as an HTTP response. The input is the identified material list and processing instructions, and the output is the generated response (JSON format).

[0743] Step 6:

[0744] The device parses the response received from the server and displays the results on the user interface of the reverse recipe engine app. Specifically, the device parses the JSON response and displays the data in the UI components. The user accesses the required information using the "Ingredient List" and "Cooking Instructions" tabs. The input is the received JSON response, and the output is the displayed ingredient list and cooking instructions.

[0745] This allows users to take a photo of a dish and easily find out the ingredients and cooking instructions needed.

[0746] (Application example 1)

[0747] 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."

[0748] There is a demand for a system that can identify ingredients and processing methods for a dish simply by taking a photo, allowing users to easily recreate the dish. Especially for use in brick-and-mortar stores, it is desirable to support users in cooking on-site or at home using ingredients purchased at the store. However, few existing systems are specifically designed for use in brick-and-mortar stores, and an improved user experience is desired. To solve this problem, a new system is needed.

[0749] 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.

[0750] In this invention, the server includes means for uploading photos taken by users to a terminal, means for transmitting the uploaded photos to the server via a network, means for the server to analyze the photos and identify ingredients and processing methods for the dish, means for returning the identified ingredients and processing methods from the server to the terminal, means for displaying the returned ingredients and processing methods to the user, and means for using the system in a physical store. This enables users to immediately learn cooking methods using ingredients purchased in the physical store and recreate the dish on the spot.

[0751] "Device" refers to an electronic device that allows a user to take photos and operate applications.

[0752] "Network" refers to a digital communications infrastructure for transmitting and receiving data.

[0753] "Server" refers to a computer system that provides the computational resources to analyze data and process and return results.

[0754] "Machine learning algorithms" refer to artificial intelligence techniques used for image analysis and feature extraction.

[0755] "Photo" refers to image data of food taken by the user.

[0756] "Ingredients" refers to the ingredients needed to prepare a dish.

[0757] "Processing method" refers to the steps or techniques used to create a specific dish.

[0758] "Database" refers to a system that stores and manages cooking recipe information.

[0759] A "physical store" refers to a commercial establishment such as a retail store or restaurant that a user can physically visit.

[0760] "User" refers to an individual who uses this system to take photos of food and obtain recipe information.

[0761] "Display" refers to the act of visually providing information to a user through a terminal.

[0762] System Configuration

[0763] A system for implementing this invention comprises a user terminal, a server, and an image analysis system equipped with a machine learning algorithm. The user takes a photo of a dish using a terminal such as a smartphone. The taken photo is sent to the server via a network. The server has computing resources to execute the machine learning algorithm for image analysis.

[0764] Hardware and Software

[0765] The hardware includes the user's device (e.g., a smartphone), the computer network, and the server, while the software includes the application that runs on the user's device, the image analysis algorithm that runs on the server (e.g., TensorFlow's ResNet50), and the database software.

[0766] Data processing and calculation

[0767] 1. Take and send images:

[0768] Users take a photo of their food using their device's camera, and an application on their device uploads the photo to a server, including the photo itself and other metadata such as a timestamp and user ID.

[0769] 2. Image Analysis:

[0770] The server inputs the received images into a machine learning algorithm (e.g., TensorFlow's ResNet50) to extract features to identify the ingredients of the dish. The algorithm then matches the images with a large number of existing food images to identify the most suitable ingredients.

[0771] 3. Verification of information:

[0772] The server then matches the identified ingredient information with recipe information in a database, which stores information about ingredients for various dishes and their processing methods, to find the appropriate recipe.

[0773] 4. Return of results:

[0774] The server sends the identified ingredients and processing method back to the user's device. The application on the device receives this information and displays it in the user interface. The user can then create a dish based on the displayed information.

[0775] Adding specific examples

[0776] As a concrete example, let's say a user takes a photo of a "pasta dish" at a restaurant. The photo is uploaded to the application and sent to the server. The server analyzes the photo and identifies ingredients such as pasta, tomato sauce, basil, and cheese. Based on the analysis results, the most suitable recipe information is extracted from the database. Finally, the ingredients and cooking instructions are sent back to the user's device, where the user can check the information and prepare the dish.

[0777] Prompt Sentence Examples

[0778] Use the following prompt to input the generative AI model:

[0779] text

[0780] A user has uploaded a photo of a pasta dish. Identify the ingredients and cooking method extracted from the photo. Return the ingredients list and simple cooking instructions.

[0781] This allows users to immediately find out how to cook ingredients purchased in a physical store, greatly improving user convenience.

[0782] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0783] Step 1:

[0784] The user takes a photo of the food using the device's camera. The photo is saved in the device's local storage. The input is the food photo, and the output is the photo data.

[0785] Step 2:

[0786] When the user presses the upload button, the application on the device sends the saved photo data to the server. At this time, metadata (timestamp and user ID) is added to the photo data. The input is the photo data and metadata, and the output is a notification to the server that the data has been sent.

[0787] Step 3:

[0788] The server inputs the received photo data into an image analysis algorithm (TensorFlow's ResNet50), which extracts features within the photo and identifies the ingredients of a particular dish. The input is the photo data, and the output is a list of identified ingredients.

[0789] Step 4:

[0790] The server matches the identified ingredient list with the recipe information stored in the database, which searches for the relevant recipe and processing method. The input is the ingredient list, and the output is the optimal recipe and processing method.

[0791] Step 5:

[0792] The server returns the identified ingredients and processing method to the user's device. The returned information includes an ingredient list and cooking instructions. The input is the recipe information processed on the server side, and the output is data sent to the user's device.

[0793] Step 6:

[0794] The terminal displays the recipe information received from the server on the user interface. The user can check the cooking procedure by viewing this information. The input is the recipe information from the server, and the output is the recipe information displayed to the user.

[0795] Step 7:

[0796] The user recreates the dish based on the ingredients list and cooking instructions displayed on the device. The input is the cooking information displayed on the device, and the output is the completed dish.

[0797] 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.

[0798] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[0799] Program processing

[0800] 1. User Input

[0801] Users take photos of their dishes using their devices and upload them to the reverse recipe engine app. The devices are equipped with devices such as a camera and microphone to recognize the user's emotions.

[0802] 2. Emotional Recognition

[0803] The device analyzes the user's facial expressions and tone of voice when taking a photo and uses an emotion engine to identify the user's emotional state, which is then sent to the server along with the photo data.

[0804] 3. Sending photos

[0805] The device sends the user-selected photo and emotional information to the server via the network, along with metadata such as the user ID and timestamp in addition to the photo data.

[0806] 4. Photo Analysis

[0807] The server then runs the received photo through image analysis algorithms, such as applying a convolutional neural network (CNN) to extract features within the photo, which then identifies the ingredients and type of dish.

[0808] 5. Identifying materials and processing methods

[0809] The server compares the extracted feature data with an internal database, which stores a wide variety of recipes, along with information on ingredients and processing methods. The server also takes emotional information into account to select the optimal recipe.

[0810] 6. Generating Results

[0811] The server generates a response to send back to the user based on the identified recipe information, including an optimal list of ingredients and processing instructions based on the analysis results of the emotion engine.

[0812] 7. Return of results

[0813] The server generates a response and sends it to the device, which then analyzes it and displays the results in the app's user interface.

[0814] 8. User Display

[0815] The device displays optimal recipe information based on emotions to the user through a user interface, and the user can check the ingredients list and cooking instructions on the device screen and follow them to cook the dish.

[0816] Specific examples

[0817] For example, if a user takes a photo of a pasta dish, the process will proceed as follows:

[0818] 1. Photo and emotion recognition:

[0819] As the user takes a photo of the food, the device uses an emotion engine to analyze the user's facial expressions and tone of voice to identify their emotional state, such as "happy" or "tired."

[0820] 2. Sending photos and emotional information:

[0821] The device sends the captured photo data and emotional information to the server.

[0822] 3. Photo analysis and database matching:

[0823] The server analyzes the received photo, extracts features from the photo, and compares them with an internal database, taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[0824] 4. Generate and return results:

[0825] Based on the selected recipe information, the server generates a response including a list of ingredients and specific cooking instructions and sends it back to the terminal.

[0826] 5. Displaying the results:

[0827] The device displays the received information on a user interface, allowing the user to prepare meals based on that information. For example, a user who is "tired" will be shown recipes for meals that are easy to prepare in a short time.

[0828] This system not only obtains ingredients and processing methods from photos of food, but also provides optimal recipes according to the user's emotional state, thereby further increasing user satisfaction.

[0829] The processing flow will be explained below.

[0830] Step 1:

[0831] The user takes a photo of the food using the device. The user activates the device's camera function and takes a photo of the food. At this time, the photo is saved in the device's internal storage.

[0832] Step 2:

[0833] Users can enable emotion recognition within the app, which allows the device's camera and microphone to analyze the user's facial expressions and voice.

[0834] Step 3:

[0835] The user uploads the photos they have taken to the app. The user opens the app, selects the photos they have taken, and presses the upload button.

[0836] Step 4:

[0837] The device recognizes and analyzes the user's emotions. The device uses a camera to capture the user's facial expressions and a microphone to capture the user's tone of voice, and sends these to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state.

[0838] Step 5:

[0839] The device sends the emotional information along with the photo data to the server. The data sent includes the photo data, emotional information, metadata such as the user ID and timestamp.

[0840] Step 6:

[0841] The server receives the photo data and emotion information sent from the device, stores this data in its internal storage, and begins the analysis process.

[0842] Step 7:

[0843] The server inputs the photo data into a machine learning algorithm for analysis, using a convolutional neural network (CNN) to extract features from the photo and identify the ingredients and type of dish.

[0844] Step 8:

[0845] The server compares the extracted feature data and emotion information with the database. The server then compares this with recipe information in its internal database to find the optimal recipe. For example, if the user is "tired," it will select a dish that is easy to prepare and can be made quickly.

[0846] Step 9:

[0847] The server generates a response based on the identified recipe information, including an ingredient list, specific cooking instructions, and emotion-based advice.

[0848] Step 10:

[0849] The server sends the generated response to the terminal, and the server returns the response data to the terminal via the network.

[0850] Step 11:

[0851] The device analyzes the response received from the server and displays it in the user interface, allowing the user to view the ingredients list and cooking instructions through the app.

[0852] Step 12:

[0853] The user cooks a dish based on the displayed recipe. The user can check the necessary ingredients and cooking steps on the device screen and proceed with the cooking in the order displayed. For example, a user who is "tired" can be shown a recipe that can be made quickly, reducing the burden on the user.

[0854] Example 2

[0855] 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."

[0856] Conventional systems cannot consider the emotional state of the user in the process of taking a photo of a dish and using a reverse recipe engine system to identify ingredients and processing methods, making it difficult to improve user satisfaction. Furthermore, the provided recipes may not be suitable for the user's current situation, which can impair the user's enjoyable cooking experience.

[0857] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0858] In this invention, the server includes means for uploading photos and emotional data taken by the user, means for transmitting the uploaded photos and emotional data to the server, means for analyzing the photos in the server and identifying ingredients and processing methods for cooking, means for selecting an optimal recipe in the server based on the emotional data, means for returning the identified ingredients, processing method, and optimal recipe from the server, and means for displaying the returned ingredients, processing method, and optimal recipe to the user. This makes it possible to provide an appropriate recipe that takes into account the emotional state of the user.

[0859] "Means for uploading photos and emotional data taken by the user" refers to a function that allows users to take and record photos of food and emotional data using the device's camera and microphone, and send them to the system via the Internet.

[0860] "Means for transmitting uploaded photos and emotional data to the server" refers to the function that packets the data captured and recorded by the device and transfers it to the server via the network.

[0861] "Means for analyzing photos on the server and identifying the ingredients and processing method of a dish" refers to a function that uses image analysis technology provided by the server to analyze photos of food taken by the user and identify the ingredients and type of dish in the image, thereby identifying the ingredients and cooking method.

[0862] "Means for selecting the optimal recipe based on emotional data on the server" refers to a function that allows the server to select an appropriate recipe from its internal database, taking into account the analyzed emotional data of the user. This allows the server to provide a recipe that matches the user's current emotional state.

[0863] The "means for returning the identified materials, processing method, and optimal recipe from the server" is a function that allows the server to generate a response including the analysis results and selected recipe information, and send it to the user's terminal via the network.

[0864] The "means for displaying the returned ingredients, processing method, and optimal recipe to the user" is a function for visually displaying to the user on the user's terminal the received recipe information, cooking procedures, and advice based on emotional data.

[0865] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[0866] The user first takes a photo of the food using the device. The device is equipped with a camera and microphone, which not only allows the device to take photos of the food but also recognizes the user's emotions using their facial expressions and tone of voice. An app for uploading food photos is installed on the device, and the user uses the app to send the photos and emotional data to the server.

[0867] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The emotion engine uses existing software libraries such as OpenCV and AutoML to recognize emotional states such as "happy" or "tired." This emotional information is then sent to the server along with the photo data.

[0868] The server then uses machine learning algorithms to analyze the received photos. For example, it uses machine learning libraries such as TensorFlow and PyTorch to extract features from the photos using a convolutional neural network (CNN). This analysis allows it to identify the ingredients and types of food contained in the photos.

[0869] The server then checks the identified ingredients and type of dish against an internal database, which contains various recipes, their ingredients, and processing methods. The server also takes emotional information into account. For example, if the user's emotional state is "tired," it will prioritize simple recipes that can be made quickly.

[0870] The server generates a response based on the selected recipe information. This response includes a list of specific ingredients and cooking instructions for the dish, as well as a recommended recipe based on the analysis results of the emotion engine. The generated response is then sent back to the user's device via the network.

[0871] The device receives the response from the server and displays it to the user through a user interface. Based on the displayed information, the user can prepare ingredients and follow the provided cooking instructions to cook the dish. Emotion-based advice is also displayed, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[0872] For example, suppose a user takes a photo of pasta for dinner and uploads it to the app. In this case, if the user's emotion is recognized as "tired," the server will provide a recipe for pasta that can be made quickly. An example of a prompt in this case would be, "Enter a photo of the dish, retrieve recipes based on that photo, and suggest the best recipe based on the user's emotion."

[0873] This system allows users to not only upload photos of their food, but also provides them with the best recipes tailored to their emotional state, thereby increasing their satisfaction when cooking.

[0874] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0875] Step 1:

[0876] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. The input here is the photo of the dish taken with the camera, and the output is the photo data uploaded to the app. This upload operation saves the photo data within the app.

[0877] Step 2:

[0878] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The input is the user's facial expressions and tone of voice, and the output is emotion data. The device analyzes this data using OpenCV and audio processing libraries to generate emotion information such as "happy" or "tired."

[0879] Step 3:

[0880] The device sends photo data and emotion data to the server. The input here is the uploaded photo data and analyzed emotion data, and the output is a data packet sent to the server. This data packet also contains metadata such as the user ID and timestamp.

[0881] Step 4:

[0882] The server analyzes the received photo data. The input here is the transmitted photo data, and the output is the analysis results, which are the ingredients and type of dish. The server applies a convolutional neural network (CNN) using TensorFlow or PyTorch to extract features from the photo, thereby identifying the ingredients and type of dish.

[0883] Step 5:

[0884] The server compares the extracted feature data and emotion data with its internal database. The input here is the analysis results of ingredients, types of dishes, and emotion data, and the output is the optimal recipe. For example, if the user's emotional state is "tired," it will prioritize recipes that are easy to make and can be made quickly.

[0885] Step 6:

[0886] The server generates a response based on the selected recipe information. The inputs are the optimal recipe, ingredient list, cooking instructions, and sentiment analysis results, and the output is the generated response, which includes the specific ingredient list and cooking instructions for the dish, as well as the sentiment-based recommended recipe.

[0887] Step 7:

[0888] The server sends the generated response to the terminal. The input here is the generated response, and the output is the response sent to the terminal. This information is quickly delivered to the terminal via the network.

[0889] Step 8:

[0890] The device receives the response sent back from the server and displays it to the user through a user interface. The input here is the response sent from the server, and the output is the recipe information displayed on the device screen. The user can prepare and cook the dish based on this information. Emotion-based advice is also displayed on the screen, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[0891] Through this series of processes, users not only upload photos of their food, but are also suggested optimal recipes tailored to their individual emotional state, increasing their satisfaction when cooking.

[0892] (Application example 2)

[0893] 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."

[0894] Conventional recipe provision systems allow users to take photos of dishes and identify ingredients and processing methods from the photos, but they are unable to provide optimal recipes that take into account the user's emotional state. This means that when users cook, they have to go through the trouble of selecting an appropriate recipe that matches their emotional state at the time. Another issue is that they do not provide enough support to help users enjoy cooking.

[0895] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's facial expression and tone of voice to identify their emotional state, means for selecting an optimal recipe based on the identified emotional state, and means for returning the identified ingredients, processing method, and optimal recipe. This makes it possible for the user to simply take a photo of a dish and be provided with an optimal recipe based on their current emotional state.

[0896] A "user" is a person who uses the system to take photos and obtain recipe information.

[0897] "Photo" refers to image data of food or an object photographed by a user with a camera.

[0898] "Upload" refers to the act of sending photo data from a user's device to a server.

[0899] The "server" refers to a central processing unit that analyzes photos and processes information on materials, processing methods, and the user's emotions.

[0900] "Emotional state" refers to a psychological state that is determined by analyzing a user's facial expressions and tone of voice.

[0901] "Machine learning algorithm" refers to an artificial intelligence technique that extracts features from photos based on large amounts of data.

[0902] "Database" refers to a collection of information that stores a wide variety of cooking recipes, their ingredients, processing methods, and additional information.

[0903] "Recipe" refers to a cooking instruction manual that includes specified ingredients and processing steps.

[0904] The "optimal recipe" refers to a cooking recipe that is most suitable for the user's situation, selected based on the user's emotional state and photo data.

[0905] This invention combines a system that allows users to take photos of food with a function that recognizes the user's emotions. This system not only allows users to take photos of food, but also provides them with the optimal recipe that corresponds to their current emotional state. The specific configuration and operation of the system are as follows.

[0906] Hardware and Software Configuration

[0907] 1. User device: Smart glasses or smartphones equipped with a camera and microphone are used. It includes an image and voice input device that allows the user to take photos of the food and analyze emotions from facial expressions and voice.

[0908] 2. Server: A central processing unit that analyzes photo and emotion data, equipped with machine learning algorithms and a database. Software used includes Python, OpenCV, a facial recognition library, and an AI model for emotion analysis.

[0909] Data processing and calculation

[0910] 1. User input: The user takes a photo of the food using the device and uploads it to the device, which then captures the user's facial expressions and tone of voice and sends them to the sentiment analysis module.

[0911] 2. Emotion Recognition: The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state, and the results of this analysis are sent to the server along with the photo data.

[0912] 3. Photo analysis: The server analyzes the received photos using machine learning algorithms (e.g., convolutional neural networks) to extract features from the photos.

[0913] 4. Identifying ingredients and processing methods: The server checks the database and identifies the ingredients and processing methods based on the feature data in the photo. It also selects the optimal recipe based on the emotion data.

[0914] 5. Generate and return results: The server returns the generated recipe information (ingredients list and cooking instructions) to the terminal and displays it to the user.

[0915] Specific examples

[0916] For example, when a user takes a photo of a pasta dish, the process proceeds as follows.

[0917] 1. Photo and emotion recognition: The user takes a photo of the food, and the device analyzes the user's facial expressions and tone of voice to identify emotional states such as "tired" or "happy."

[0918] 2. Sending photos and emotional information: The device sends photos and emotional information to the server.

[0919] 3. Photo analysis and database matching: The server analyzes the photo, extracts features, and compares them with the database taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[0920] 4. Generate and return results: The server returns the generated results to the terminal and displays them to the user, who can then use them to prepare the dish.

[0921] Prompt Sentence Examples

[0922] When a user visits the store, the smart glasses are used to photograph the user's face and analyze their emotions based on their facial expressions. If the user's emotion is determined to be "tired," the system will suggest products or services that have a relaxing effect (such as relaxation services).

[0923] This system allows users to receive optimal cooking recipes and suggestions based on their emotional state, improving the efficiency and satisfaction of cooking.

[0924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0925] Step 1:

[0926] The user takes a photo of the food and uploads it to the device. Specifically, the user takes a photo of the food using smart glasses or a smartphone camera. The device then stores the photo in its local memory, and the emotion recognition module begins to operate. The input is the photo taken by the user, and the output is the photo data stored on the device.

[0927] Step 2:

[0928] The device analyzes the user's facial expressions and tone of voice to identify their emotional state. It uses an emotion engine to analyze the user's facial images and voice data at the time of capture. The input is the user's facial expressions and tone of voice, and the output is identified emotional state data. Specifically, it uses a facial recognition algorithm to analyze facial expressions and analyzes psychological state from tone of voice.

[0929] Step 3:

[0930] The device transmits the photo data and emotion data to the server. The input is the captured photo data and the identified emotion state data, and the output is the data transmitted to the server via the network. The device uploads the photo data and emotion data to the server in text and image format.

[0931] Step 4:

[0932] The server analyzes the received photos using a machine learning algorithm (e.g., a convolutional neural network) to extract features from the photos. The input is the photo data sent from the device, and the output is the extracted feature data. The server uses an image processing library to extract features that identify the type of food and ingredients.

[0933] Step 5:

[0934] The server compares the extracted feature data and emotional data with an internal database to select the optimal recipe. The input is the extracted feature data and the identified emotional state data, and the output is the optimal recipe data. When comparing the database, the server takes the emotional data into consideration and selects a recipe that can be made in a short time, for example, if the user is "tired."

[0935] Step 6:

[0936] The server generates a response based on the identified materials, processing steps, and optimal recipe information. The input is the selected recipe data, and the output is response data to send back to the user. The server constructs the response data and includes the necessary recipe information and materials list.

[0937] Step 7:

[0938] The server sends the generated response to the terminal. The input is the response data constructed by the server, and the output is the data sent back to the terminal via the network. The server encodes the response data and transfers it to the terminal.

[0939] Step 8:

[0940] The terminal analyzes the received response data and displays it on the user interface. The input is the response data sent from the server, and the output is the ingredient list and cooking instructions displayed on the user interface. Specifically, the terminal parses the response data and displays recipe information to the user based on it.

[0941] Through the above processing steps, the user can obtain optimal recipe information suited to their emotional state at the time simply by taking a photo of the food.

[0942] 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.

[0943] 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.

[0944] 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.

[0945] [Fourth embodiment]

[0946] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0947] 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.

[0948] 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).

[0949] 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.

[0950] 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.

[0951] 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).

[0952] 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.

[0953] 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.

[0954] 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.

[0955] 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.

[0956] 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.

[0957] 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.

[0958] 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."

[0959] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[0960] Program processing

[0961] 1. User Input

[0962] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[0963] 2. Sending photos

[0964] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[0965] 3. Photo Analysis

[0966] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[0967] 4. Identifying materials and processing methods

[0968] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[0969] 5. Return of results

[0970] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[0971] 6. User Display

[0972] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[0973] Specific examples

[0974] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[0975] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[0976] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[0977] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[0978] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[0979] The present invention allows users to intuitively know the ingredients and cooking methods needed based on photos of dishes, thereby broadening the range of dishes they can make.

[0980] The processing flow will be explained below.

[0981] Step 1:

[0982] The user takes a photo of the dish using the device. The user opens the app, selects the photo, and presses the upload button. The photo is then saved to the device's internal storage.

[0983] Step 2:

[0984] The device sends the photos selected by the user to the server via the network, and the photos are sent along with metadata such as the user ID and a timestamp.

[0985] Step 3:

[0986] The server receives the photo data sent from the device, stores it internally, and begins analyzing it.

[0987] Step 4:

[0988] The server feeds the photo data into machine learning algorithms, such as applying a convolutional neural network (CNN), to extract features within the photo, which then identify the ingredients and type of dish.

[0989] Step 5:

[0990] The server compares the extracted feature data with its internal database, which contains numerous recipes with their ingredients and procedures, and searches for the most suitable recipe.

[0991] Step 6:

[0992] The server generates a list of identified materials and processing instructions from the search results and creates a response to return this information to the user.

[0993] Step 7:

[0994] The server then sends the generated response to the device, which includes the identified ingredients and specific cooking instructions.

[0995] Step 8:

[0996] The terminal receives the response sent from the server, and then displays the ingredient list and cooking instructions to the user through the user interface.

[0997] Step 9:

[0998] Users can check the ingredients list and cooking instructions on the device screen and follow them to prepare the dish. The user prepares the necessary ingredients and proceeds with cooking according to the displayed instructions.

[0999] Through these steps, the system provides an environment where users can easily obtain ingredients and processing methods by simply uploading a photo of the dish.

[1000] Example 1

[1001] 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."

[1002] Currently, many users post photos of the dishes they have cooked on social media and blogs, but it is difficult to know the specific ingredients and cooking methods from those photos. Beginners in cooking and users who want to try new recipes need a system that can automatically find detailed ingredients and cooking steps from a photo of a dish. Furthermore, existing methods require users to perform complex operations, so an intuitive and simple operation is required.

[1003] 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.

[1004] In this invention, the server includes a means for uploading photos taken by users, a means for transmitting the uploaded photos to the server, and a means for analyzing the photos on the server and identifying the ingredients and processing methods of the dish. This allows users to intuitively learn the necessary ingredients and cooking methods simply by uploading a photo of the dish without performing complex operations. This invention also includes a means for extracting features from the photo using a machine learning algorithm when analyzing the photo on the server, and for deriving the optimal recipe based on the analysis results by comparing them with recipe information in a database. This provides more accurate recipe information, allowing users to broaden their cooking options.

[1005] A "user" is an individual who uses the system to take photos of dishes and use the reverse recipe engine app.

[1006] A "terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[1007] A "server" is a central processing unit that receives and analyzes data sent from a user and returns the results to the terminal.

[1008] "Uploading" is the act of a user sending data (in this case, photos of food) from a terminal to a server.

[1009] A "machine learning algorithm" is a program the server uses to analyze features in a photo and identify ingredients and types of dishes.

[1010] The "JSON format" is a lightweight data format used for data exchange that is easy to read for both humans and machines.

[1011] An "image analysis algorithm" is a program for extracting and analyzing feature data from photographs.

[1012] A "database" is a system that systematically stores information about cooking ingredients and processing methods and is used by the server to collate the information.

[1013] "Metadata" is information that is sent along with the photo data, and includes a timestamp, user ID, and so on.

[1014] A "response" is response data that the server returns to the terminal, including analysis results and necessary information.

[1015] "User interface" refers to the screen and operation method that allows the user to interact with the system and intuitively confirm the results.

[1016] The present invention relates to a reverse recipe engine system that allows users to take photos of dishes and identify the ingredients and processing methods of the dish based on the photos. In this system, users take photos of the dish using their device and send the photos to a server. The server analyzes the photos, identifies the ingredients and processing methods of the dish, and returns the results to the device. This allows users to easily find out the ingredients and processing methods of the dish from the photo.

[1017] Program processing

[1018] 1. User Input

[1019] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. This action saves the photo to the device's local storage. The user then selects the photo within the app and presses the upload button to send it to the server.

[1020] 2. Sending photos

[1021] The device sends the photos selected by the user to the server via the network. The photos also include metadata about the photo data (e.g., timestamp and user ID). This metadata provides information necessary for subsequent analysis.

[1022] 3. Photo Analysis

[1023] The server then applies an image analysis algorithm to the received photo. This image analysis uses a machine learning algorithm (for example, a convolutional neural network). The server extracts features from the photo and identifies the ingredients and type of dish based on these. This analysis process compares the data with the feature data of numerous dishes to derive the most suitable recipe information.

[1024] 4. Identifying materials and processing methods

[1025] The server then matches the results of the photo analysis with recipes stored in a database containing information on ingredients and preparation methods for a wide variety of dishes. The matching process searches for information that matches the feature data in the photo, resulting in a specific ingredient list and preparation steps.

[1026] 5. Return of results

[1027] The server generates a response based on the analysis results, which includes a list of identified materials and processing instructions, and sends the response to the terminal.

[1028] 6. User Display

[1029] The device analyzes the response received from the server and displays the results on the app's user interface, allowing the user to view the ingredients list and cooking instructions and follow them to recreate the dish.

[1030] Specific examples

[1031] For example, if a user takes a photo of a pasta dish, they upload the photo to the app and send it to the server, which processes it as follows:

[1032] 1. Photo analysis: The server receives the photo and runs it through a machine learning algorithm. After analyzing the image, ingredients such as pasta, tomato sauce, basil, and cheese are identified.

[1033] 2. Information matching: The server matches the identified ingredients with recipe information in the database, thereby searching for the optimal recipe.

[1034] 3. Generate and return results: Based on the identified recipe information, the server generates a response containing a list of ingredients (pasta, tomato sauce, basil, cheese) and specific cooking instructions (boil the pasta, mix with the tomato sauce and basil, top with cheese and serve), and returns it to the device.

[1035] 4. Displaying the results: The device displays the received information on the user interface, allowing the user to prepare the dish based on that information.

[1036] Prompt Sentence Examples

[1037] Here is an example of inputting the following prompt sentence to a generative AI model:

[1038] I want to have an AI analyze photos of food taken by users and identify the ingredients and cooking method. Please explain the steps required to upload a photo and the specific processing action to be taken based on the submitted photo. Furthermore, please explain in more detail using a photo of a pasta dish as an example.

[1039] With the present invention configured as described above, a user can intuitively learn the ingredients and cooking methods needed based on a photo of a dish, thereby broadening the range of dishes they can make.

[1040] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1041] Step 1:

[1042] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. Specifically, the user opens the device's camera app and takes a photo of the dish. This photo is saved in the device's local storage. Next, the user launches the reverse recipe engine app, presses the "Select Photo" button to select the photo they took, and presses the "Upload" button. The input is the photo they took, and the output is the selected photo being displayed in the app.

[1043] Step 2:

[1044] The device sends the photo selected by the user to the server via the network. At this time, metadata such as a timestamp and user ID are added to the photo data. Specifically, the device sends the photo data and metadata to the server using an HTTP POST request. The input is the selected photo data and metadata, and the output is a transmission completion message to the server.

[1045] Step 3:

[1046] The server applies an image analysis algorithm to the received photos. This image analysis uses a machine learning algorithm (for example, a convolutional neural network (CNN)). Specifically, the server analyzes the photos using libraries such as TensorFlow or PyTorch. The input is the transmitted photo data and metadata, and the output is feature data within the photo (for example, the type of ingredients or characteristics of the dish).

[1047] Step 4:

[1048] The server then uses the results of the photo analysis to match recipe information in the database. Specifically, the server uses an SQL query to access the database and search for recipe information that matches the features in the photo. The input is the analyzed feature data, and the output is the identified ingredients list and processing instructions.

[1049] Step 5:

[1050] The server generates a response to send back to the user based on the matching results. Specifically, the server converts the analysis results into JSON format and sends it to the terminal as an HTTP response. The input is the identified material list and processing instructions, and the output is the generated response (JSON format).

[1051] Step 6:

[1052] The device parses the response received from the server and displays the results on the user interface of the reverse recipe engine app. Specifically, the device parses the JSON response and displays the data in the UI components. The user accesses the required information using the "Ingredient List" and "Cooking Instructions" tabs. The input is the received JSON response, and the output is the displayed ingredient list and cooking instructions.

[1053] This allows users to take a photo of a dish and easily find out the ingredients and cooking instructions needed.

[1054] (Application example 1)

[1055] 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."

[1056] There is a demand for a system that can identify ingredients and processing methods for a dish simply by taking a photo, allowing users to easily recreate the dish. Especially for use in brick-and-mortar stores, it is desirable to support users in cooking on-site or at home using ingredients purchased at the store. However, few existing systems are specifically designed for use in brick-and-mortar stores, and an improved user experience is desired. To solve this problem, a new system is needed.

[1057] 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.

[1058] In this invention, the server includes means for uploading photos taken by users to a terminal, means for transmitting the uploaded photos to the server via a network, means for the server to analyze the photos and identify ingredients and processing methods for the dish, means for returning the identified ingredients and processing methods from the server to the terminal, means for displaying the returned ingredients and processing methods to the user, and means for using the system in a physical store. This enables users to immediately learn cooking methods using ingredients purchased in the physical store and recreate the dish on the spot.

[1059] "Device" refers to an electronic device that allows a user to take photos and operate applications.

[1060] "Network" refers to a digital communications infrastructure for transmitting and receiving data.

[1061] "Server" refers to a computer system that provides the computational resources to analyze data and process and return results.

[1062] "Machine learning algorithms" refer to artificial intelligence techniques used for image analysis and feature extraction.

[1063] "Photo" refers to image data of food taken by the user.

[1064] "Ingredients" refers to the ingredients needed to prepare a dish.

[1065] "Processing method" refers to the steps or techniques used to create a specific dish.

[1066] "Database" refers to a system that stores and manages cooking recipe information.

[1067] A "physical store" refers to a commercial establishment such as a retail store or restaurant that a user can physically visit.

[1068] "User" refers to an individual who uses this system to take photos of food and obtain recipe information.

[1069] "Display" refers to the act of visually providing information to a user through a terminal.

[1070] System Configuration

[1071] A system for implementing this invention comprises a user terminal, a server, and an image analysis system equipped with a machine learning algorithm. The user takes a photo of a dish using a terminal such as a smartphone. The taken photo is sent to the server via a network. The server has computing resources to execute the machine learning algorithm for image analysis.

[1072] Hardware and Software

[1073] The hardware includes the user's device (e.g., a smartphone), the computer network, and the server, while the software includes the application that runs on the user's device, the image analysis algorithm that runs on the server (e.g., TensorFlow's ResNet50), and the database software.

[1074] Data processing and calculation

[1075] 1. Take and send images:

[1076] Users take a photo of their food using their device's camera, and an application on their device uploads the photo to a server, including the photo itself and other metadata such as a timestamp and user ID.

[1077] 2. Image Analysis:

[1078] The server inputs the received images into a machine learning algorithm (e.g., TensorFlow's ResNet50) to extract features to identify the ingredients of the dish. The algorithm then matches the images with a large number of existing food images to identify the most suitable ingredients.

[1079] 3. Verification of information:

[1080] The server then matches the identified ingredient information with recipe information in a database, which stores information about ingredients for various dishes and their processing methods, to find the appropriate recipe.

[1081] 4. Return of results:

[1082] The server sends the identified ingredients and processing method back to the user's device. The application on the device receives this information and displays it in the user interface. The user can then create a dish based on the displayed information.

[1083] Adding specific examples

[1084] As a concrete example, let's say a user takes a photo of a "pasta dish" at a restaurant. The photo is uploaded to the application and sent to the server. The server analyzes the photo and identifies ingredients such as pasta, tomato sauce, basil, and cheese. Based on the analysis results, the most suitable recipe information is extracted from the database. Finally, the ingredients and cooking instructions are sent back to the user's device, where the user can check the information and prepare the dish.

[1085] Prompt Sentence Examples

[1086] Use the following prompt to input the generative AI model:

[1087] text

[1088] A user has uploaded a photo of a pasta dish. Identify the ingredients and cooking method extracted from the photo. Return the ingredients list and simple cooking instructions.

[1089] This allows users to immediately find out how to cook ingredients purchased in a physical store, greatly improving user convenience.

[1090] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1091] Step 1:

[1092] The user takes a photo of the food using the device's camera. The photo is saved in the device's local storage. The input is the food photo, and the output is the photo data.

[1093] Step 2:

[1094] When the user presses the upload button, the application on the device sends the saved photo data to the server. At this time, metadata (timestamp and user ID) is added to the photo data. The input is the photo data and metadata, and the output is a notification to the server that the data has been sent.

[1095] Step 3:

[1096] The server inputs the received photo data into an image analysis algorithm (TensorFlow's ResNet50), which extracts features within the photo and identifies the ingredients of a particular dish. The input is the photo data, and the output is a list of identified ingredients.

[1097] Step 4:

[1098] The server matches the identified ingredient list with the recipe information stored in the database, which searches for the relevant recipe and processing method. The input is the ingredient list, and the output is the optimal recipe and processing method.

[1099] Step 5:

[1100] The server returns the identified ingredients and processing method to the user's device. The returned information includes an ingredient list and cooking instructions. The input is the recipe information processed on the server side, and the output is data sent to the user's device.

[1101] Step 6:

[1102] The terminal displays the recipe information received from the server on the user interface. The user can check the cooking procedure by viewing this information. The input is the recipe information from the server, and the output is the recipe information displayed to the user.

[1103] Step 7:

[1104] The user recreates the dish based on the ingredients list and cooking instructions displayed on the device. The input is the cooking information displayed on the device, and the output is the completed dish.

[1105] 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.

[1106] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[1107] Program processing

[1108] 1. User Input

[1109] Users take photos of their dishes using their devices and upload them to the reverse recipe engine app. The devices are equipped with devices such as a camera and microphone to recognize the user's emotions.

[1110] 2. Emotional Recognition

[1111] The device analyzes the user's facial expressions and tone of voice when taking a photo and uses an emotion engine to identify the user's emotional state, which is then sent to the server along with the photo data.

[1112] 3. Sending photos

[1113] The device sends the user-selected photo and emotional information to the server via the network, along with metadata such as the user ID and timestamp in addition to the photo data.

[1114] 4. Photo Analysis

[1115] The server then runs the received photo through image analysis algorithms, such as applying a convolutional neural network (CNN) to extract features within the photo, which then identifies the ingredients and type of dish.

[1116] 5. Identifying materials and processing methods

[1117] The server compares the extracted feature data with an internal database, which stores a wide variety of recipes, along with information on ingredients and processing methods. The server also takes emotional information into account to select the optimal recipe.

[1118] 6. Generating Results

[1119] The server generates a response to send back to the user based on the identified recipe information, including an optimal list of ingredients and processing instructions based on the analysis results of the emotion engine.

[1120] 7. Return of results

[1121] The server generates a response and sends it to the device, which then analyzes it and displays the results in the app's user interface.

[1122] 8. User Display

[1123] The device displays optimal recipe information based on emotions to the user through a user interface, and the user can check the ingredients list and cooking instructions on the device screen and follow them to cook the dish.

[1124] Specific examples

[1125] For example, if a user takes a photo of a pasta dish, the process will proceed as follows:

[1126] 1. Photo and emotion recognition:

[1127] As the user takes a photo of the food, the device uses an emotion engine to analyze the user's facial expressions and tone of voice to identify their emotional state, such as "happy" or "tired."

[1128] 2. Sending photos and emotional information:

[1129] The device sends the captured photo data and emotional information to the server.

[1130] 3. Photo analysis and database matching:

[1131] The server analyzes the received photo, extracts features from the photo, and compares them with an internal database, taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[1132] 4. Generate and return results:

[1133] Based on the selected recipe information, the server generates a response including a list of ingredients and specific cooking instructions and sends it back to the terminal.

[1134] 5. Displaying the results:

[1135] The device displays the received information on a user interface, allowing the user to prepare meals based on that information. For example, a user who is "tired" will be shown recipes for meals that are easy to prepare in a short time.

[1136] This system not only obtains ingredients and processing methods from photos of food, but also provides optimal recipes according to the user's emotional state, thereby further increasing user satisfaction.

[1137] The processing flow will be explained below.

[1138] Step 1:

[1139] The user takes a photo of the food using the device. The user activates the device's camera function and takes a photo of the food. At this time, the photo is saved in the device's internal storage.

[1140] Step 2:

[1141] Users can enable emotion recognition within the app, which allows the device's camera and microphone to analyze the user's facial expressions and voice.

[1142] Step 3:

[1143] The user uploads the photos they have taken to the app. The user opens the app, selects the photos they have taken, and presses the upload button.

[1144] Step 4:

[1145] The device recognizes and analyzes the user's emotions. The device uses a camera to capture the user's facial expressions and a microphone to capture the user's tone of voice, and sends these to the emotion engine. The emotion engine analyzes this data to identify the user's emotional state.

[1146] Step 5:

[1147] The device sends the emotional information along with the photo data to the server. The data sent includes the photo data, emotional information, metadata such as the user ID and timestamp.

[1148] Step 6:

[1149] The server receives the photo data and emotion information sent from the device, stores this data in its internal storage, and begins the analysis process.

[1150] Step 7:

[1151] The server inputs the photo data into a machine learning algorithm for analysis, using a convolutional neural network (CNN) to extract features from the photo and identify the ingredients and type of dish.

[1152] Step 8:

[1153] The server compares the extracted feature data and emotion information with the database. The server then compares this with recipe information in its internal database to find the optimal recipe. For example, if the user is "tired," it will select a dish that is easy to prepare and can be made quickly.

[1154] Step 9:

[1155] The server generates a response based on the identified recipe information, including an ingredient list, specific cooking instructions, and emotion-based advice.

[1156] Step 10:

[1157] The server sends the generated response to the terminal, and the server returns the response data to the terminal via the network.

[1158] Step 11:

[1159] The device analyzes the response received from the server and displays it in the user interface, allowing the user to view the ingredients list and cooking instructions through the app.

[1160] Step 12:

[1161] The user cooks a dish based on the displayed recipe. The user can check the necessary ingredients and cooking steps on the device screen and proceed with the cooking in the order displayed. For example, a user who is "tired" can be shown a recipe that can be made quickly, reducing the burden on the user.

[1162] Example 2

[1163] 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."

[1164] Conventional systems cannot consider the emotional state of the user in the process of taking a photo of a dish and using a reverse recipe engine system to identify ingredients and processing methods, making it difficult to improve user satisfaction. Furthermore, the provided recipes may not be suitable for the user's current situation, which can impair the user's enjoyable cooking experience.

[1165] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1166] In this invention, the server includes means for uploading photos and emotional data taken by the user, means for transmitting the uploaded photos and emotional data to the server, means for analyzing the photos in the server and identifying ingredients and processing methods for cooking, means for selecting an optimal recipe in the server based on the emotional data, means for returning the identified ingredients, processing method, and optimal recipe from the server, and means for displaying the returned ingredients, processing method, and optimal recipe to the user. This makes it possible to provide an appropriate recipe that takes into account the emotional state of the user.

[1167] "Means for uploading photos and emotional data taken by the user" refers to a function that allows users to take and record photos of food and emotional data using the device's camera and microphone, and send them to the system via the Internet.

[1168] "Means for transmitting uploaded photos and emotional data to the server" refers to the function that packets the data captured and recorded by the device and transfers it to the server via the network.

[1169] "Means for analyzing photos on the server and identifying the ingredients and processing method of a dish" refers to a function that uses image analysis technology provided by the server to analyze photos of food taken by the user and identify the ingredients and type of dish in the image, thereby identifying the ingredients and cooking method.

[1170] "Means for selecting the optimal recipe based on emotional data on the server" refers to a function that allows the server to select an appropriate recipe from its internal database, taking into account the analyzed emotional data of the user. This allows the server to provide a recipe that matches the user's current emotional state.

[1171] The "means for returning the identified materials, processing method, and optimal recipe from the server" is a function that allows the server to generate a response including the analysis results and selected recipe information, and send it to the user's terminal via the network.

[1172] The "means for displaying the returned ingredients, processing method, and optimal recipe to the user" is a function for visually displaying to the user on the user's terminal the received recipe information, cooking procedures, and advice based on emotional data.

[1173] This invention combines a reverse recipe engine system that allows users to take photos of dishes and identifies the ingredients and processing methods based on the photos with an emotion engine that recognizes the user's emotions. This system allows users to not only take photos of dishes, but also provides them with the optimal recipe based on their current emotional state.

[1174] The user first takes a photo of the food using the device. The device is equipped with a camera and microphone, which not only allows the device to take photos of the food but also recognizes the user's emotions using their facial expressions and tone of voice. An app for uploading food photos is installed on the device, and the user uses the app to send the photos and emotional data to the server.

[1175] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The emotion engine uses existing software libraries such as OpenCV and AutoML to recognize emotional states such as "happy" or "tired." This emotional information is then sent to the server along with the photo data.

[1176] The server then uses machine learning algorithms to analyze the received photos. For example, it uses machine learning libraries such as TensorFlow and PyTorch to extract features from the photos using a convolutional neural network (CNN). This analysis allows it to identify the ingredients and types of food contained in the photos.

[1177] The server then checks the identified ingredients and type of dish against an internal database, which contains various recipes, their ingredients, and processing methods. The server also takes emotional information into account. For example, if the user's emotional state is "tired," it will prioritize simple recipes that can be made quickly.

[1178] The server generates a response based on the selected recipe information. This response includes a list of specific ingredients and cooking instructions for the dish, as well as a recommended recipe based on the analysis results of the emotion engine. The generated response is then sent back to the user's device via the network.

[1179] The device receives the response from the server and displays it to the user through a user interface. Based on the displayed information, the user can prepare ingredients and follow the provided cooking instructions to cook the dish. Emotion-based advice is also displayed, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[1180] For example, suppose a user takes a photo of pasta for dinner and uploads it to the app. In this case, if the user's emotion is recognized as "tired," the server will provide a recipe for pasta that can be made quickly. An example of a prompt in this case would be, "Enter a photo of the dish, retrieve recipes based on that photo, and suggest the best recipe based on the user's emotion."

[1181] This system allows users to not only upload photos of their food, but also provides them with the best recipes tailored to their emotional state, thereby increasing their satisfaction when cooking.

[1182] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1183] Step 1:

[1184] The user takes a photo of the dish using their device and uploads it to the reverse recipe engine app. The input here is the photo of the dish taken with the camera, and the output is the photo data uploaded to the app. This upload operation saves the photo data within the app.

[1185] Step 2:

[1186] The device analyzes the user's facial expressions and tone of voice in real time using an emotion engine. The input is the user's facial expressions and tone of voice, and the output is emotion data. The device analyzes this data using OpenCV and audio processing libraries to generate emotion information such as "happy" or "tired."

[1187] Step 3:

[1188] The device sends photo data and emotion data to the server. The input here is the uploaded photo data and analyzed emotion data, and the output is a data packet sent to the server. This data packet also contains metadata such as the user ID and timestamp.

[1189] Step 4:

[1190] The server analyzes the received photo data. The input here is the transmitted photo data, and the output is the analysis results, which are the ingredients and type of dish. The server applies a convolutional neural network (CNN) using TensorFlow or PyTorch to extract features from the photo, thereby identifying the ingredients and type of dish.

[1191] Step 5:

[1192] The server compares the extracted feature data and emotion data with its internal database. The input here is the analysis results of ingredients, types of dishes, and emotion data, and the output is the optimal recipe. For example, if the user's emotional state is "tired," it will prioritize recipes that are easy to make and can be made quickly.

[1193] Step 6:

[1194] The server generates a response based on the selected recipe information. The inputs are the optimal recipe, ingredient list, cooking instructions, and sentiment analysis results, and the output is the generated response, which includes the specific ingredient list and cooking instructions for the dish, as well as the sentiment-based recommended recipe.

[1195] Step 7:

[1196] The server sends the generated response to the terminal. The input here is the generated response, and the output is the response sent to the terminal. This information is quickly delivered to the terminal via the network.

[1197] Step 8:

[1198] The device receives the response sent back from the server and displays it to the user through a user interface. The input here is the response sent from the server, and the output is the recipe information displayed on the device screen. The user can prepare and cook the dish based on this information. Emotion-based advice is also displayed on the screen, allowing the user to easily obtain an appropriate recipe that matches their emotional state at the time.

[1199] Through this series of processes, users not only upload photos of their food, but are also suggested optimal recipes tailored to their individual emotional state, increasing their satisfaction when cooking.

[1200] (Application example 2)

[1201] 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."

[1202] Conventional recipe provision systems allow users to take photos of dishes and identify ingredients and processing methods from the photos, but they are unable to provide optimal recipes that take into account the user's emotional state. This means that when users cook, they have to go through the trouble of selecting an appropriate recipe that matches their emotional state at the time. Another issue is that they do not provide enough support to help users enjoy cooking.

[1203] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's facial expression and tone of voice to identify their emotional state, means for selecting an optimal recipe based on the identified emotional state, and means for returning the identified ingredients, processing method, and optimal recipe. This makes it possible for the user to simply take a photo of a dish and be provided with an optimal recipe based on their current emotional state.

[1204] A "user" is a person who uses the system to take photos and obtain recipe information.

[1205] "Photo" refers to image data of food or an object photographed by a user with a camera.

[1206] "Upload" refers to the act of sending photo data from a user's device to a server.

[1207] The "server" refers to a central processing unit that analyzes photos and processes information on materials, processing methods, and the user's emotions.

[1208] "Emotional state" refers to a psychological state that is determined by analyzing a user's facial expressions and tone of voice.

[1209] "Machine learning algorithm" refers to an artificial intelligence technique that extracts features from photos based on large amounts of data.

[1210] "Database" refers to a collection of information that stores a wide variety of cooking recipes, their ingredients, processing methods, and additional information.

[1211] "Recipe" refers to a cooking instruction manual that includes specified ingredients and processing steps.

[1212] The "optimal recipe" refers to a cooking recipe that is most suitable for the user's situation, selected based on the user's emotional state and photo data.

[1213] This invention combines a system that allows users to take photos of food with a function that recognizes the user's emotions. This system not only allows users to take photos of food, but also provides them with the optimal recipe that corresponds to their current emotional state. The specific configuration and operation of the system are as follows.

[1214] Hardware and Software Configuration

[1215] 1. User device: Smart glasses or smartphones equipped with a camera and microphone are used. It includes an image and voice input device that allows the user to take photos of the food and analyze emotions from facial expressions and voice.

[1216] 2. Server: A central processing unit that analyzes photo and emotion data, equipped with machine learning algorithms and a database. Software used includes Python, OpenCV, a facial recognition library, and an AI model for emotion analysis.

[1217] Data processing and calculation

[1218] 1. User input: The user takes a photo of the food using the device and uploads it to the device, which then captures the user's facial expressions and tone of voice and sends them to the sentiment analysis module.

[1219] 2. Emotion Recognition: The device uses an emotion engine to analyze the user's facial expressions and voice to identify their emotional state, and the results of this analysis are sent to the server along with the photo data.

[1220] 3. Photo analysis: The server analyzes the received photos using machine learning algorithms (e.g., convolutional neural networks) to extract features from the photos.

[1221] 4. Identifying ingredients and processing methods: The server checks the database and identifies the ingredients and processing methods based on the feature data in the photo. It also selects the optimal recipe based on the emotion data.

[1222] 5. Generate and return results: The server returns the generated recipe information (ingredients list and cooking instructions) to the terminal and displays it to the user.

[1223] Specific examples

[1224] For example, when a user takes a photo of a pasta dish, the process proceeds as follows.

[1225] 1. Photo and emotion recognition: The user takes a photo of the food, and the device analyzes the user's facial expressions and tone of voice to identify emotional states such as "tired" or "happy."

[1226] 2. Sending photos and emotional information: The device sends photos and emotional information to the server.

[1227] 3. Photo analysis and database matching: The server analyzes the photo, extracts features, and compares them with the database taking into account emotional information. For example, if the user is "tired," it selects a quick recipe.

[1228] 4. Generate and return results: The server returns the generated results to the terminal and displays them to the user, who can then use them to prepare the dish.

[1229] Prompt Sentence Examples

[1230] When a user visits the store, the smart glasses are used to photograph the user's face and analyze their emotions based on their facial expressions. If the user's emotion is determined to be "tired," the system will suggest products or services that have a relaxing effect (such as relaxation services).

[1231] This system allows users to receive optimal cooking recipes and suggestions based on their emotional state, improving the efficiency and satisfaction of cooking.

[1232] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1233] Step 1:

[1234] The user takes a photo of the food and uploads it to the device. Specifically, the user takes a photo of the food using smart glasses or a smartphone camera. The device then stores the photo in its local memory, and the emotion recognition module begins to operate. The input is the photo taken by the user, and the output is the photo data stored on the device.

[1235] Step 2:

[1236] The device analyzes the user's facial expressions and tone of voice to identify their emotional state. It uses an emotion engine to analyze the user's facial images and voice data at the time of capture. The input is the user's facial expressions and tone of voice, and the output is identified emotional state data. Specifically, it uses a facial recognition algorithm to analyze facial expressions and analyzes psychological state from tone of voice.

[1237] Step 3:

[1238] The device transmits the photo data and emotion data to the server. The input is the captured photo data and the identified emotion state data, and the output is the data transmitted to the server via the network. The device uploads the photo data and emotion data to the server in text and image format.

[1239] Step 4:

[1240] The server analyzes the received photos using a machine learning algorithm (e.g., a convolutional neural network) to extract features from the photos. The input is the photo data sent from the device, and the output is the extracted feature data. The server uses an image processing library to extract features that identify the type of food and ingredients.

[1241] Step 5:

[1242] The server compares the extracted feature data and emotional data with an internal database to select the optimal recipe. The input is the extracted feature data and the identified emotional state data, and the output is the optimal recipe data. When comparing the database, the server takes the emotional data into consideration and selects a recipe that can be made in a short time, for example, if the user is "tired."

[1243] Step 6:

[1244] The server generates a response based on the identified materials, processing steps, and optimal recipe information. The input is the selected recipe data, and the output is response data to send back to the user. The server constructs the response data and includes the necessary recipe information and materials list.

[1245] Step 7:

[1246] The server sends the generated response to the terminal. The input is the response data constructed by the server, and the output is the data sent back to the terminal via the network. The server encodes the response data and transfers it to the terminal.

[1247] Step 8:

[1248] The terminal analyzes the received response data and displays it on the user interface. The input is the response data sent from the server, and the output is the ingredient list and cooking instructions displayed on the user interface. Specifically, the terminal parses the response data and displays recipe information to the user based on it.

[1249] Through the above processing steps, the user can obtain optimal recipe information suited to their emotional state at the time simply by taking a photo of the food.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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.

[1256] 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).

[1257] 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.

[1258] 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."

[1259] 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.

[1260] 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).

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] 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.

[1271] The following is further disclosed regarding the above embodiment.

[1272] (Claim 1)

[1273] a means for uploading photographs taken by the user;

[1274] means for transmitting the uploaded photos to a server;

[1275] A means to analyze the photos on the server and identify the ingredients and processing method of the dish,

[1276] means for returning the identified materials and processing methods from the server;

[1277] means for displaying the returned materials and processing methods to the user;

[1278] A system including:

[1279] (Claim 2)

[1280] 10. The system of claim 1, further comprising means for extracting features within the photograph using a machine learning algorithm when analyzing the photograph at the server.

[1281] (Claim 3)

[1282] The system according to claim 1, further comprising means for collating the information identified by the server with a database to derive an optimal recipe.

[1283] "Example 1"

[1284] (Claim 1)

[1285] a means for uploading photographs taken by the user;

[1286] means for transmitting the uploaded photos to a server;

[1287] A means to analyze the photos on the server and identify the ingredients and processing method of the dish,

[1288] means for returning the identified materials and processing methods from the server;

[1289] means for displaying the returned materials and processing methods to the user;

[1290] A system including:

[1291] (Claim 2)

[1292] 10. The system of claim 1, further comprising means for extracting features within the photograph using a machine learning algorithm when analyzing the photograph at the server.

[1293] (Claim 3)

[1294] The system according to claim 1, further comprising means for collating the information identified by the server with a database to derive an optimal recipe.

[1295] (Claim 4)

[1296] a means for the user to take a photo of the dish using the device and upload the photo to the application;

[1297] A method for sending photo data including metadata such as timestamps and user IDs,

[1298] The server receives the photos and runs them through an image analysis algorithm to identify the ingredients and type of dish.

[1299] A means for the server to compare the analysis results with recipe information in a database;

[1300] means for generating and returning a response including a list of materials and processing instructions identified from the matching results;

[1301] 2. The system according to claim 1, wherein the terminal comprises means for analyzing the returned response and displaying it on a user interface.

[1302] (Claim 5)

[1303] 5. The system according to claim 4, further comprising means for transmitting the photographic data together with metadata such as a timestamp and a user ID to a server, and providing information required for subsequent analysis processing.

[1304] (Claim 6)

[1305] 5. The system according to claim 4, further comprising means for analyzing a response in JSON format received by the terminal from the server and displaying a list of ingredients and cooking instructions.

[1306] "Application Example 1"

[1307] (Claim 1)

[1308] A means for uploading photographs taken by the user to the terminal;

[1309] means for transmitting the uploaded photographs to a server via a network;

[1310] A means to analyze the photos on the server and identify the ingredients and processing method of the dish,

[1311] a means for returning the identified material and processing method from the server to the terminal;

[1312] means for displaying the returned materials and processing methods to the user;

[1313] A means to use this system in a physical store,

[1314] A system including:

[1315] (Claim 2)

[1316] 10. The system of claim 1, further comprising means for extracting features within the photograph using a machine learning algorithm when analyzing the photograph at the server.

[1317] (Claim 3)

[1318] The system according to claim 1, further comprising means for collating the information identified by the server with a database to derive an optimal recipe.

[1319] "Example 2: Combining Emotion Engines"

[1320] (Claim 1)

[1321] A means for uploading a photograph and emotion data taken by a user;

[1322] means for transmitting the uploaded photo and emotion data to a server;

[1323] A means to analyze the photos on the server and identify the ingredients and processing method of the dish,

[1324] A method for selecting the optimal recipe based on emotion data on the server,

[1325] A means for returning the identified ingredients, processing methods and optimal recipes from the server;

[1326] means for displaying the returned materials, processing methods and optimal recipes to the user;

[1327] A system including:

[1328] (Claim 2)

[1329] 10. The system of claim 1, further comprising means for extracting features within the photograph using a machine learning algorithm when analyzing the photograph at the server.

[1330] (Claim 3)

[1331] The system according to claim 1, further comprising means for collating the information identified by the server with a database to derive an optimal recipe.

[1332] "Application example 2 when combining emotion engines"

[1333] (Claim 1)

[1334] a means for uploading photographs taken by the user;

[1335] means for transmitting the uploaded photos to a server;

[1336] A means to analyze the photos on the server and identify the ingredients and processing method of the dish,

[1337] means for analyzing a user's facial expressions and tone of voice to identify an emotional state;

[1338] means for selecting an optimal recipe based on the identified emotional state;

[1339] A means for returning the identified ingredients, processing methods, and optimal recipes from the server;

[1340] A means for displaying the returned materials, processing methods, and optimal recipes to the user;

[1341] A system including:

[1342] (Claim 2)

[1343] 10. The system of claim 1, further comprising means for extracting features within the photograph using a machine learning algorithm when analyzing the photograph at the server.

[1344] (Claim 3)

[1345] The system according to claim 1, further comprising means for collating the information identified by the server with a database to derive an optimal recipe. [Explanation of symbols]

[1346] 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 uploading photographs taken by the user; means for transmitting the uploaded photos to a server; A means to analyze the photos on the server and identify the ingredients and processing method of the dish, means for returning the identified materials and processing methods from the server; means for displaying the returned materials and processing methods to the user; A system including:

2. The system of claim 1 , further comprising means for extracting features within the photograph using a machine learning algorithm when analyzing the photograph at the server.

3. 2. The system according to claim 1, further comprising means for collating the information specified by the server with a database to derive an optimum recipe.

Images