System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving an image captured or uploaded by a user; means for pre-processing the received image; means for transmitting the pre-processed image data to a server; means for analyzing the pre-processed image data by the server; means for generating nutrient and food ingredient information based on an image analysis result; means for analyzing a long-term eating and drinking habit of the user; means for generating a dietary improvement suggestion based on an analysis result of the eating and drinking habit; and means for presenting the generated dietary improvement suggestion 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] In modern society, many people continue to have unhealthy eating habits, resulting in health problems. To improve their diet, it is necessary to accurately understand the nutritional balance of each individual meal and provide appropriate guidance and improvement suggestions based on that information. However, many existing systems rely on manual input, which is burdensome for users and prone to errors. Furthermore, they do not cover the analysis of long-term eating habits or individualized suggestions. Therefore, there is a need for a system that can automatically recognize a user's diet, evaluate the nutritional balance, and provide improvement suggestions based on each user's individual eating habits. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] The system includes a means for receiving images taken or uploaded by a user, a means for preprocessing the received images, a means for transmitting the preprocessed image data to a server, a means for the server to analyze the preprocessed image data, a means for generating nutrient and ingredient information based on the image analysis results, a means for analyzing the user's long-term eating and drinking habits, a means for generating dietary improvement suggestions based on the results of the eating and drinking habit analysis, and a means for presenting the generated dietary improvement suggestions to the user. This system allows users to efficiently record and analyze their own dietary information and receive appropriate guidance for improvement. This enables users to improve unhealthy eating habits and promote health.

[0007] "User" refers to an individual who uses the system to upload meal images and receive analysis results and dietary improvement suggestions.

[0008] "Image" refers to photographs or image data related to meals taken or uploaded by users.

[0009] "Preprocessing" refers to the initial processing of received images, such as resizing and noise removal, to prepare the images in a format suitable for analysis.

[0010] "Server" refers to a computer system on a network that stores and analyzes image data, analyzes eating and drinking habits, and generates improvement recommendations.

[0011] "Analysis" refers to the process of using image recognition technology to extract information about ingredients, dish names, and the nutrients they contain.

[0012] "Information on nutrients and ingredients" refers to detailed data such as information on the ingredients, calorie content, vitamins, minerals, etc. contained in the food obtained as a result of the analysis.

[0013] "Analysis of eating and drinking habits" refers to the process of analyzing eating patterns and nutritional intake trends based on food image data uploaded by users over a long period of time.

[0014] "Dietary improvement suggestions" refer to specific meal contents and plans proposed to the user to improve nutritional balance based on the analysis results and the analysis results of eating and drinking habits.

[0015] "Presenting" refers to displaying the generated diet improvement suggestions on the user's terminal.

[0016] The term "system" refers to a comprehensive technical device including a series of information processing means that combines the above-mentioned means to analyze a user's food images, analyze their eating habits, and present dietary improvement suggestions. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[0039] Image upload and preprocessing

[0040] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[0041] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[0042] Image Recognition and Data Analysis

[0043] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0044] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[0045] Analysis of eating and drinking habits

[0046] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. The server analyzes the user's eating and drinking patterns and nutritional intake trends, and identifies any nutrients that are clearly lacking or in excess based on data over a certain period of time (e.g., the past month). This is done by using a proprietary algorithm to perform a detailed analysis of the user's eating pattern trends.

[0047] Generate and present improvement proposals

[0048] The server generates specific dietary recommendations for the user based on the analysis of their eating habits. These recommendations are tailored to the user's individual eating habits and include short-term meal suggestions and long-term meal plans. For example, the server may recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[0049] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0050] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[0051] Specific examples

[0052] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and discovers that they are lacking in protein. Based on this, the server suggests adding chicken to the next meal. The device then presents this suggestion to the user along with a specific recipe and encourages them to follow through.

[0053] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[0057] Step 2:

[0058] The device processes the image received from the user, resizing it (e.g., to 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[0059] Step 3:

[0060] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[0061] Step 4:

[0062] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[0063] Step 5:

[0064] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[0065] Step 6:

[0066] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[0067] Step 7:

[0068] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[0069] Step 8:

[0070] The server collects the user's past meal data. Specifically, it retrieves all meal data for a specific period (e.g., the past month) from the database.

[0071] Step 9:

[0072] The server analyzes the user's eating habits, specifically analyzing daily nutrient balance, calorie intake, and food types to identify the user's eating patterns and identify any obvious nutrient deficiencies or excesses.

[0073] Step 10:

[0074] The server generates dietary improvement recommendations based on the analysis of eating and drinking habits, using an algorithm supervised by a nutritionist to create short-term meal suggestions and long-term meal plans.

[0075] Step 11:

[0076] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0077] Step 12:

[0078] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[0079] Example 1

[0080] 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."

[0081] In recent years, health problems such as lifestyle-related diseases and obesity have been increasing, and approaches to prevent and improve these problems are needed. However, it is difficult to obtain a detailed understanding of each user's dietary content and eating habits and provide individualized improvement suggestions. Furthermore, users need specialized knowledge and time to record their own meals and properly manage their nutrition. The present invention aims to solve these problems and provide a system that allows users to easily analyze their own dietary content and obtain effective dietary improvement suggestions.

[0082] 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.

[0083] In this invention, the server includes means for collecting a user's past dietary data and analyzing their long-term eating and drinking habits, means for generating dietary improvement suggestions using a generative AI model based on the analysis results of the eating and drinking habits, and means for transmitting the generated dietary improvement suggestions to a terminal and visually presenting them to the user. This allows users to receive detailed nutritional analysis and visually receive individual improvement suggestions simply by uploading meal images.

[0084] A "user" is an entity that uses the system to analyze their own diet and receive dietary improvement suggestions.

[0085] "Terminal" refers to a device used by a user, such as a smartphone or tablet, that has functions such as receiving images, preprocessing, and sending data to a server.

[0086] The "server" is a central processing unit that receives data sent from the terminal, stores it in a database, analyzes images, and generates dietary improvement suggestions.

[0087] "Preprocessing" refers to the process of resizing the received image to a standard size, removing noise, and converting the format.

[0088] An "image recognition API" is an application programming interface for analyzing preprocessed image data and extracting information about ingredients and nutrients.

[0089] A "generative AI model" is an artificial intelligence model that generates individual dietary improvement suggestions based on the analysis of eating and drinking habits.

[0090] "Dietary improvement suggestions" refer to specific suggestions and recipes for optimizing nutritional balance based on the user's diet.

[0091] The "database" is a data storage location where the server saves and manages the image data and analysis results it receives, as well as the user's dietary history.

[0092] "User interface" refers to the screen and operating environment for visually presenting the generated dietary improvement suggestions to the user.

[0093] A "prompt sentence" is a natural language sentence that is input into a generative AI model based on data collected from the user.

[0094] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[0095] Image upload and preprocessing

[0096] Users open the application on their smartphones, tablets, or other devices and take or select from their camera roll an image of their meal to upload. The device then resizes the received image to a standard size (e.g., 512x512 pixels) and performs noise reduction. It also converts the image format from JPEG to PNG if necessary. This preprocessed image data is then sent to the server.

[0097] Image Recognition and Data Analysis

[0098] The server receives the image data sent from the device and stores it in a database. The stored image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API, which analyzes the image using a generative AI model. This image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0099] The server receives the analysis results returned by the generative AI model and stores them in a database, which includes the ingredient list, the amount of each ingredient, calories, and detailed nutrition information.

[0100] Analysis of eating and drinking habits

[0101] The server also collects the user's past dietary data and uses a proprietary algorithm to analyze their long-term eating and drinking habits over a certain period of time (e.g., the past month), and can identify any obvious nutrient deficiencies or excesses.

[0102] Generate and present improvement proposals

[0103] The server generates specific dietary recommendations for the user based on the analysis of their eating and drinking habits. These recommendations are created using a generative AI model and are tailored to the individual user's eating habits. They include short-term meal suggestions and long-term meal plans. For example, they recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[0104] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists). The device visually presents the improvement suggestions received from the server in a user interface, which is designed to be easy for users to understand.

[0105] Specific examples

[0106] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's eating habits and discovers, for example, that they are lacking in protein. Based on this analysis, the server suggests adding chicken to the next meal. The device then provides this suggestion to the user along with a specific recipe and encourages them to act. For example, a prompt might be, "Please add chicken to your next meal."

[0107] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] Users open the app on their smartphone or tablet and take a picture of their meal or select one from their camera roll and upload it. The input is the image taken or selected by the user, and the output is the uploaded image file. Specifically, the image file is selected or taken by operating the app's buttons, and is prepared to be sent to the server.

[0111] Step 2:

[0112] The device preprocesses the images received from the user by resizing them to a standard size (e.g., 512x512 pixels) and removing noise. It also converts the image format from JPEG to PNG if necessary. The input is the uploaded image, and the output is a preprocessed image file. Specifically, it uses an image processing library to change the resolution, apply a noise filter, and convert the format.

[0113] Step 3:

[0114] The terminal sends the preprocessed image data to the server. The input is the preprocessed image file, and the output is the image data sent to the server. Specifically, the terminal sends the image data to the server using an HTTP request.

[0115] Step 4:

[0116] The server receives image data sent from the terminal and stores it in a database. The input is the image data sent from the terminal, and the output is the image information stored in the database. Specifically, the reception listener on the server side receives the image data and writes it to the database.

[0117] Step 5:

[0118] The server sends a request to the image recognition API and analyzes the preprocessed image data. The input is the image data stored in the database, and the output is the analysis results. Specifically, the image recognition API is called and processing is performed to extract information about ingredients and components in the image.

[0119] Step 6:

[0120] The server saves the analysis results in a database. The input is the analysis results returned from the image recognition API, and the output is the analysis information saved in the database. Specifically, it analyzes the data structure of the analysis results and writes them to the database in an appropriate format.

[0121] Step 7:

[0122] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits using a proprietary algorithm. The input is the user's past dietary data stored in the database, and the output is the analysis results of their eating and drinking habits. Specifically, the server uses a data analysis library to aggregate past dietary data and analyze nutrient intake trends.

[0123] Step 8:

[0124] The server uses a generative AI model to generate dietary improvement suggestions based on the analysis results of eating and drinking habits. The input is the analysis results of eating and drinking habits, and the output is the generated dietary improvement suggestions. Specifically, the server inputs the eating and drinking habit data into the generative AI model, creates a prompt sentence and supplies it to the model, which then generates specific dietary improvement suggestions.

[0125] Step 9:

[0126] The server sends the generated dietary improvement suggestions to the terminal. The input is the generated dietary improvement suggestions, and the output is the dietary improvement suggestions sent to the terminal. Specifically, the server sends the generated text and data to the terminal via an HTTP request.

[0127] Step 10:

[0128] The device visually presents the improvement suggestions received from the server on a user interface. The input is the dietary improvement suggestions sent from the server, and the output is the suggestions displayed on the user interface. Specifically, the data received within the application is visually formatted and displayed in a format that is easy for the user to understand.

[0129] (Application example 1)

[0130] 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."

[0131] In modern society, with the development of the restaurant industry, many people are increasingly relying on eating out. However, when eating out, it can be difficult to accurately understand the nutritional balance and health effects of the meal. In particular, people who prioritize health management have limited means of verifying whether the meal they eat at a restaurant is in line with their nutritional goals. This has led to a need for an effective system to support dietary choices and health management.

[0132] 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.

[0133] In this invention, the server includes means for receiving images taken or uploaded by a user, means for preprocessing the received images, means for transmitting the preprocessed image data to the server, means for the server to analyze the preprocessed image data, means for generating nutrient and ingredient information based on the image analysis results, means for analyzing the user's long-term eating and drinking habits, means for generating dietary improvement suggestions based on the analysis results of the eating and drinking habits, means for presenting the generated dietary improvement suggestions to the user, means for taking images of dishes using smart glasses and transmitting them to the server, and means for the server to suggest alternative menu items to the user based on the analysis results, thereby enabling users to easily understand nutritional information for meals even when eating out and supporting healthy meal selection.

[0134] "User" refers to a person who uses the system.

[0135] "Photographing" refers to the act of acquiring an image using a camera device.

[0136] "Upload" refers to the act of sending data from a local device to a server.

[0137] "Image" refers to visual information acquired using a digital camera, smartphone, etc.

[0138] "Means of receiving" refers to the technical mechanism for obtaining data from outside.

[0139] "Preprocessing" refers to the processing of image data to convert it into a format suitable for analysis.

[0140] "Preprocessing means" refers to functions that perform processing on image data, such as noise removal and resizing.

[0141] "Preprocessed image data" refers to image data that has been subjected to appropriate processing before analysis.

[0142] "Server" refers to a computer system for processing and storing data.

[0143] "Transmission mechanism" refers to the technical mechanisms by which data is sent to other systems or devices.

[0144] "Means of analysis" refers to the technical capabilities to extract useful information from data.

[0145] "Nutrients" refer to the energy and components contained in food ingredients.

[0146] "Ingredients" refers to the raw materials that make up a dish.

[0147] "Means of generating information" refers to the technical mechanisms that create new information from the results of data analysis.

[0148] "Eating habits" refers to the eating patterns and tendencies that a user has chosen in the past.

[0149] "Means of analysis" refers to the technical function of finding patterns and characteristics in data.

[0150] "Means for generating dietary improvement suggestions" refers to the function of creating appropriate dietary suggestions based on the analysis results.

[0151] "Means of presentation" refers to the technical mechanisms by which information is visually displayed to the user.

[0152] "Smart glasses" refers to wearable devices with image capture capabilities.

[0153] "Menu Alternatives" refer to other meal choices that meet the user's health goals.

[0154] "Means of suggestion" refers to the technical functionality that presents options to the user.

[0155] The present invention provides a system for assisting users in making healthy food choices when eating out. Specific embodiments of the system are described below.

[0156] 1. Image Reception and Preprocessing

[0157] A user uses smart glasses to take an image of the food they want to choose at a restaurant. The smart glasses capture the image and store the data locally. The application on the smart glasses has a function to preprocess the image. Specifically, it resizes the image to 512x512 pixels and performs noise reduction using the OpenCV library. This preprocessed image data is then sent to the server.

[0158] 2. Image analysis and data generation

[0159] The server receives and analyzes the preprocessed image data sent from the device. The server then uses a generative AI model to analyze the image. This generative AI model extracts the ingredients and nutritional information contained in the dish from the image. The analysis results include a list of ingredients and detailed information about each nutrient (protein, fat, calories, etc.).

[0160] 3. Analysis of eating habits and generation of dietary improvement suggestions

[0161] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess. Based on the results of this analysis, the server generates specific dietary recommendations for the user. For example, it suggests ingredients to add to the user's next meal or alternative menu items.

[0162] 4. Proposal for improvement

[0163] The server sends the generated dietary suggestions to the smart glasses and visually presents them to the user through the smart glasses' user interface, allowing the user to understand the nutritional information of their own meals and alternative menus that meet their health goals in real time.

[0164] Examples and prompts

[0165] For example, if a user orders a steak at a restaurant, they can take a picture of the steak with the smart glasses. The app will analyze the image and display the steak's nutritional information (protein, fat, calories, etc.) and suggest alternative dishes like salads or vegetable soups based on the user's nutritional goals.

[0166] Prompt Sentence Examples

[0167] "I'm planning to have steak for lunch today. Could you please provide me with nutritional information for this dish and suggest alternatives to make it more nutritious?"

[0168] Thus, by leveraging image capture using smart glasses and generative AI models, the system of the present invention helps users make healthy food choices even when dining out.

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

[0170] Step 1: Image capture and pre-processing

[0171] A user uses smart glasses to take an image of the dish they are selecting at a restaurant. The smart glasses then use their image capture function to capture the image data of the dish and store it on their local device. The image is then preprocessed. Specifically, the image is resized (to 512x512 pixels) and noise is removed. This generates preprocessed image data suitable for analysis.

[0172] Input: Raw food image data

[0173] Data processing: resizing, noise removal

[0174] Output: Preprocessed image data

[0175] Step 2: Sending preprocessed image data

[0176] The device (smart glasses) sends the preprocessed image data to the server, where it is encoded in an appropriate format (e.g., PNG format) and uploaded to the server via the network.

[0177] Input: Preprocessed image data

[0178] Data processing: Encoding image data

[0179] Output: Image data sent to the server

[0180] Step 3: Image analysis

[0181] The server receives the image data sent from the device and performs image analysis using a generative AI model. This generative AI model (e.g., YOLO or ResNet) extracts the ingredients and nutritional information contained in the dish from the image. The analysis results are output as an ingredient list and detailed information on each nutrient.

[0182] Input: Preprocessed image data

[0183] Data Computing: Image Analysis with Generative AI Models

[0184] Output: Ingredient list, nutritional information

[0185] Step 4: Analyze eating and drinking habits

[0186] The server retrieves the user's past dietary data from a database and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess.

[0187] Input: User's past meal data

[0188] Data Computing: Algorithms for Analyzing Eating and Drinking Habits

[0189] Output: Nutritional intake trends and problems

[0190] Step 5: Generate dietary improvement suggestions

[0191] Based on the analysis of the eating and drinking habits, the server generates specific dietary recommendations for the user, including suggestions for alternative menu items to supplement necessary nutrients. The recommendations are customized for each user.

[0192] Input: Nutritional intake trends, problems

[0193] Data Computing: Diet Improvement Algorithms

[0194] Output: Specific dietary improvement suggestions

[0195] Step 6: Propose improvements

[0196] The server transmits the generated dietary suggestions to the smart glasses, which visually display the suggestions to the user in real time through a user interface, allowing the user to make healthy eating choices on the spot.

[0197] Input: Specific dietary improvement suggestions

[0198] Data processing: Display on the user interface

[0199] Output: Visually presented improvement suggestions to the user

[0200] This series of steps helps users make healthy food choices even when eating out.

[0201] 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.

[0202] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system operates in cooperation with the user's terminal, a server, and an emotion engine, and a specific embodiment thereof is described below.

[0203] Image upload and preprocessing

[0204] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[0205] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[0206] Image Recognition and Data Analysis

[0207] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0208] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[0209] Analysis of eating and drinking habits and emotional states

[0210] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. It also uses an emotion engine to recognize the user's emotional state in real time. The emotion engine detects emotions from the user's facial expressions and voice, and records the results in a database.

[0211] The server combines the collected emotion data with data on eating and drinking habits and analyzes them, for example, to analyze how a particular meal affects the user's emotions and determine the state of the user when they ate a particular meal.

[0212] Generate and present improvement proposals

[0213] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[0214] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0215] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[0216] Specific examples

[0217] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and their emotional state while eating the salad. Based on this, the server can suggest relaxing foods to add to the user's next meal, taking into account the emotional impact of a particular meal.

[0218] In this way, by combining image recognition technology, data analysis technology, and emotion recognition technology, the present invention can realize a system that analyzes the eating habits and emotional state of each individual user in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[0222] Step 2:

[0223] The device preprocesses the image received from the user by resizing it to a standard size (e.g., 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[0224] Step 3:

[0225] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[0226] Step 4:

[0227] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[0228] Step 5:

[0229] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[0230] Step 6:

[0231] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[0232] Step 7:

[0233] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[0234] Step 8:

[0235] The server uses an emotion engine to recognize the user's emotional state. Specifically, it acquires emotion data from the user's facial expressions and voice and records the results in a database.

[0236] Step 9:

[0237] The server collects the user's past meal data and emotion data. It retrieves all meal data and emotion data for a specific period (e.g., the past month) from the database.

[0238] Step 10:

[0239] The server analyzes the trends in eating habits and emotional state. Specifically, it analyzes daily nutrient balance, calorie intake, food types, and emotional state to identify the user's eating patterns and emotional trends. It identifies obvious nutrient deficiencies or excesses, as well as factors that cause emotional fluctuations.

[0240] Step 11:

[0241] The server generates dietary improvement suggestions based on the analysis of the user's eating habits and emotional state. Specifically, it makes dietary suggestions that address the user's emotional state, such as stress or fatigue. Using an algorithm supervised by a nutritionist, it creates short-term dietary suggestions and long-term meal plans.

[0242] Step 12:

[0243] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0244] Step 13:

[0245] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[0246] Example 2

[0247] 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."

[0248] In today's world, healthy eating habits are becoming increasingly important, but it is difficult for users to obtain appropriate dietary improvement suggestions based on their own eating habits and emotional state. Conventional systems have had difficulty analyzing a user's eating habits and emotional state in detail and providing dietary improvement suggestions tailored to individual needs. In particular, few systems provide improvement suggestions that take into account the relationship between dietary content and emotional state. As a result, users are unable to receive optimal dietary suggestions tailored to their emotional state. The present invention aims to provide a system that analyzes a user's eating habits and emotional state in detail and provides specific and effective dietary improvement suggestions tailored to the needs of each individual user.

[0249] 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.

[0250] In this invention, the server includes a means for generating information on nutrients and ingredients based on the image analysis results, a means for analyzing the user's long-term eating habits, and a means for analyzing the user's emotional state, which allows for detailed analysis of the user's eating habits and emotional state and the generation of dietary improvement proposals tailored to each individual user.

[0251] A "user" is someone who uses the system to upload photos of their meals and receive suggestions for improving their meals.

[0252] A "terminal" is a device such as a smartphone or tablet that a user uses to take or upload images.

[0253] A "server" is a computer system that receives image data sent from a user's terminal and analyzes and stores the image data.

[0254] "Image data" is data based on photos of meals taken or uploaded by users.

[0255] "Preprocessing" refers to the process of converting image data into a format suitable for analysis, and specifically includes resizing, noise removal, and format conversion.

[0256] "Image analysis" is the process of analyzing pre-processed image data to identify its contents, such as ingredients, nutrients, and calories.

[0257] "Nutrient and ingredient information" refers to information such as the ingredients contained in a meal, their amounts, and calories, as identified through image analysis.

[0258] "Dietary habits" refers to the history of meals a user has eaten in the past and their patterns.

[0259] The "emotional state" is the psychological state of the user that is detected from the user's facial expression, voice, and the like.

[0260] "Improvement suggestions" are specific dietary suggestions provided to the user based on the results of image analysis, as well as the analysis of eating habits and emotional state.

[0261] A "user interface" is a display means for visually presenting information to a user on a terminal.

[0262] The present invention is a system that analyzes food images taken or uploaded by a user and provides dietary improvement suggestions based on the user's eating habits and emotional state. Specifically, the system operates by linking the user's terminal, a server, and an emotion engine. Specific embodiments of the system are described below.

[0263] Image upload and preprocessing

[0264] Users upload photos of their meals to the app using their smartphones, tablets, or other devices. They can either select an image from their camera roll or take a photo of their meal in real time using their camera. The app guides users through the process.

[0265] The device preprocesses the images received from the user. This includes resizing the image (e.g., resizing to 512x512 pixels), removing noise, and converting the image format (e.g., converting from JPEG to PNG). An open-source image processing library (e.g., OpenCV) is used for preprocessing. The preprocessed images are then sent to the server.

[0266] Image Recognition and Data Analysis

[0267] The server receives the preprocessed image data sent from the device and stores it in a database. The database uses a storage management system (e.g., MySQL). The server then calls an image recognition API (e.g., Google Vision API) to analyze the image. The image recognition API of this generative AI model identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0268] The analysis results are stored in a database as a list of ingredients, nutrient amounts, calories, and other details, which can then be used for further data analysis and to generate dietary improvement recommendations.

[0269] Analysis of eating and drinking habits and emotional states

[0270] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits. The past dietary data is retrieved from a database and analyzed using statistical analysis tools (e.g., Python and the pandas library). The server also has the ability to recognize the user's emotional state in real time using an emotion engine (e.g., Affectiva). The emotion engine detects emotions from the user's facial expressions and voice and records the results in a database.

[0271] The server combines and analyzes the collected emotional data with data on eating and drinking habits, allowing it to understand the emotional impact of a particular meal on the user and the state of mind in which the user ate a particular meal.

[0272] Generate and present improvement proposals

[0273] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[0274] The improvement proposal also includes details of the meal suggestion (for example, a specific recipe or a list of foods). An example of a prompt generated using a generative AI model is as follows:

[0275] "Analyze a salad image uploaded by a user, identify the ingredients and the amounts of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide next meal suggestions that take into account the user's emotional state."

[0276] The server sends the generated improvement proposals to the terminal, which visually displays them on a user interface that is designed to be easy for the user to understand and put into practice.

[0277] Specific examples

[0278] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the ingredients (lettuce, tomato, cheese, etc.) and their nutrients. Based on the analysis results, the server analyzes the user's long-term eating habits and emotional state. This allows the server to consider the emotional impact of a particular meal and suggest relaxing foods to add to the user's next meal.

[0279] In this way, the present invention combines image recognition technology, data analysis technology, and emotion recognition technology to realize a system that analyzes a user's eating habits and emotional state in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[0280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0281] Step 1:

[0282] Users upload photos of their meals using an app on their smartphone or tablet.

[0283] Input: An image of a meal taken or selected by the user.

[0284] How it works: The user uses the camera to take a photo in real time or selects an image from the camera roll.

[0285] Output: Image files of the selected or photographed meal.

[0286] Step 2:

[0287] The terminal pre-processes the received image.

[0288] Input: Raw image files uploaded by the user.

[0289] What it does: The device resizes the image to 512x512 pixels, denoises it, and optionally converts it from JPEG to PNG format using an image processing library such as OpenCV.

[0290] Output: Preprocessed image files.

[0291] Step 3:

[0292] The terminal transmits the preprocessed image to the server.

[0293] Input: Preprocessed image files.

[0294] Operation: The terminal uploads preprocessed image data to the server via the network.

[0295] Output: Preprocessed image data sent to the server.

[0296] Step 4:

[0297] The server receives the pre-processed image data and stores it in a database.

[0298] Input: Preprocessed image data sent from the device.

[0299] Operation: The server stores the received image data in a database using a storage management system such as MySQL.

[0300] Output: Image data stored in a database.

[0301] Step 5:

[0302] The server uses an image recognition API to analyze the meal contents.

[0303] Input: Preprocessed image data stored in a database.

[0304] How it works: The server calls an image recognition API, such as the Google Vision API, to analyze the stored image and identify the ingredients, dish name, amount of each ingredient, and calories.

[0305] Output: A list of ingredients, their amounts, and calorie analysis results.

[0306] Step 6:

[0307] The server stores the analysis results in a database.

[0308] Input: Analysis results obtained from the image recognition API.

[0309] How it works: The server stores the results of the analysis in a database, which is done by writing data using SQL queries.

[0310] Output: A list of ingredients stored in a database, along with their amounts and calorie information.

[0311] Step 7:

[0312] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits.

[0313] Input: Historical dietary data stored in a database.

[0314] How it works: The server collects historical dietary data and uses statistical analysis tools (e.g., Python's pandas library) to analyze long-term eating and drinking habits.

[0315] Output: Analysis results about the user's eating and drinking habits.

[0316] Step 8:

[0317] The server uses an emotion engine to analyze the user's emotional state.

[0318] Input: User's facial and voice data.

[0319] How it works: The server uses an emotion engine such as Affectiva to detect the user's emotional state from their facial expressions and voice, and records the results in a database.

[0320] Output: Analysis results about the user's emotional state.

[0321] Step 9:

[0322] The server generates dietary improvement suggestions based on the analysis of eating habits and emotional state.

[0323] Input: Analysis of eating and drinking habits and emotional state.

[0324] How it works: The server integrates this data and uses a generative AI model to generate specific, personalized dietary recommendations. Prompts include: "Analyze a salad image uploaded by the user, identify its ingredients and the amount of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide the next meal suggestion, taking into account the user's emotional state."

[0325] Output: Improvement proposal generation results.

[0326] Step 10:

[0327] The server transmits the generated improvement plan to the terminal.

[0328] Input: The data of the generated improvement proposal.

[0329] Operation: The server transfers data using a network protocol to send the generated improvement proposal to the terminal.

[0330] Output: Improvement suggestion data sent to the device.

[0331] Step 11:

[0332] The terminal presents improvement proposals to the user.

[0333] Input: Improvement proposal data sent from the server.

[0334] Operation: The device visually displays the received improvement suggestions in the user interface, making it easier for the user to understand the suggestions.

[0335] Output: Suggested improvements displayed in the user interface.

[0336] Through the above processing steps, the system of the present invention can analyze the user's eating habits and emotional state, generate dietary improvement suggestions based on the analysis, and provide them to the user.

[0337] (Application example 2)

[0338] 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."

[0339] While conventional dietary analysis systems can suggest meals based on a user's eating habits, they are unable to make suggestions that take into account the user's emotional state. Furthermore, systems designed for use in brick-and-mortar establishments such as restaurants and cafes have not yet become widespread. This has made it difficult to effectively support the improvement of a user's health and psychological state.

[0340] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state in real time, means for generating diet improvement suggestions based on the analysis results of the emotional state, and means for presenting the generated diet improvement suggestions to the user. This makes it possible to make diet suggestions that take the user's emotional state into consideration.

[0341] "Means for receiving images" refers to a mechanism by which the terminal receives image data taken or uploaded by the user.

[0342] The "means for preprocessing images" is a mechanism for resizing received image data to a certain standard size and performing preprocessing such as noise removal and format conversion.

[0343] The "means for transmitting image data to a server" is a mechanism for transferring preprocessed image data to a server.

[0344] "Means for the server to analyze preprocessed image data" refers to a mechanism for receiving preprocessed image data on the server and analyzing it using an image recognition API.

[0345] The "means for generating information on nutrients and ingredients based on the image analysis results" is a mechanism for generating information on ingredients and nutrients extracted from the analyzed image data.

[0346] The "means for analyzing a user's long-term eating and drinking habits" is a mechanism for collecting a user's past dietary data and analyzing the user's long-term eating and drinking habits based on that data.

[0347] "Means for analyzing the user's emotional state in real time" refers to a mechanism for detecting and analyzing the user's emotions in real time from facial expressions, voice, etc.

[0348] The "means for generating dietary improvement suggestions based on the results of the analysis of the emotional state" is a mechanism for generating individual dietary improvement suggestions based on the results of the user's emotional analysis and long-term eating and drinking habits.

[0349] The "means for presenting the generated diet improvement suggestions to the user" is a mechanism for transmitting the diet improvement suggestions generated by the server to the terminal and visually displaying them on the user interface.

[0350] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system is implemented in the following steps.

[0351] Hardware and Software Configuration

[0352] User's device

[0353] The user's smartphone or tablet device is used to take and upload images and display dietary improvement suggestions. The following applications are installed on the device:

[0354] Camera application: Ability to take photos of meals

[0355] Image processing application: Functions for pre-processing captured images

[0356] server

[0357] The server is the central component that analyzes images, stores data, analyzes emotions, and generates improvement recommendations. The main software used includes:

[0358] Image Recognition API: Generative AI models (e.g., TensorFlow, OpenCV) for extracting ingredient and nutrient information from images

[0359] Database: A database (e.g., MySQL) to store analysis results and user eating habits and emotion data.

[0360] Emotion analysis engine: Software for analyzing emotions from a user's facial expressions and voice (e.g., Microsoft Azure Cognitive Services)

[0361] Data processing flow

[0362] Image preprocessing

[0363] Users take a photo of their meal using their smartphone's camera application or select it from their camera roll, and then the image is preprocessed using the application's image processing function, which involves resizing the image (to 512x512 pixels) and removing noise.

[0364] Image analysis

[0365] The preprocessed image data is sent to a server, which uses an image recognition API to analyze the image content. The analysis extracts information about ingredients and nutrients, which is then stored in a database.

[0366] Analysis of eating and drinking habits and emotional states

[0367] The server retrieves the user's past dietary data from the database and analyzes their long-term eating and drinking habits. It also uses an emotion analysis engine to analyze the user's emotional state in real time. The analysis results are recorded in the database.

[0368] Generating and presenting dietary improvement suggestions

[0369] The server comprehensively analyzes eating habits and emotional states to generate personalized dietary improvement recommendations. This generation process uses the following generative AI model:

[0370] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[0371] The server then sends the generated dietary improvement suggestions to the user's device, which then displays the suggestions on a user interface. For example, if the user is feeling stressed, the server can suggest a relaxing herbal tea.

[0372] In this way, the present invention provides a system that combines image recognition technology, data analysis technology, and emotion recognition technology to realize effective meal suggestions in physical stores.

[0373] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0374] Step 1: User takes or uploads an image

[0375] The user takes a picture of the meal using the smartphone's camera application or selects an image from the camera roll. The input image is in a common image format such as JPEG or PNG. The output is the selected or captured raw image data.

[0376] Step 2: The device preprocesses the image

[0377] The device preprocesses the image taken or selected by the user. Specifically, it resizes the image (e.g., to 512x512 pixels) and denoises it. This process uses libraries such as Pillow and OpenCV. The input is raw image data. The output is preprocessed, clean image data.

[0378] Step 3: Send the preprocessed image data to the server

[0379] The device sends the preprocessed image data to the server. This communication is performed using an HTTP POST request. The input is the preprocessed image data. The output is the status of completion of transmission to the server.

[0380] Step 4: The server analyzes the image data

[0381] The server analyzes the received image data, using an image recognition API (e.g., TensorFlow or OpenCV) to extract information about ingredients and nutrients from the image. The input is the preprocessed image data, and the output is a detailed list of ingredients and nutrients.

[0382] Step 5: Save your ingredient and nutrition data

[0383] The server stores the resulting food and nutrient data in a database. This data is managed individually for each user. The input is a detailed list of food ingredients and nutrients. The output is a data entry stored in the database.

[0384] Step 6: The server analyzes your past eating and drinking habits

[0385] The server retrieves the user's past eating and drinking data from the database and analyzes their long-term eating and drinking habits. The input is the past eating and drinking data in the database. The output is the analyzed long-term eating and drinking habits data.

[0386] Step 7: The server analyzes the emotional state in real time

[0387] The server uses an emotion analysis engine (e.g., Microsoft Azure Cognitive Services) to analyze the user's real-time emotional state. In this process, facial and voice data are input. The input is real-time facial and voice data. The output is analyzed emotional state data.

[0388] Step 8: Generate dietary recommendations based on your emotional state

[0389] The server generates personalized dietary recommendations based on long-term eating and drinking habits and real-time emotional state, using a generative AI model and prompts such as:

[0390] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[0391] The input is data on eating habits and emotional state, and the output is detailed dietary improvement recommendations.

[0392] Step 9: Present the improvement suggestions to the user

[0393] The server sends the generated dietary improvement suggestions to the terminal, which then visually displays the improvement suggestions on a user interface. The input is the generated dietary improvement suggestions. The output is the improvement suggestions displayed to the user.

[0394] In this way, through each processing step, the user can be provided with dietary improvement suggestions that take into account their emotional state.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] [Second embodiment]

[0399] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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."

[0411] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[0412] Image upload and preprocessing

[0413] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[0414] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[0415] Image Recognition and Data Analysis

[0416] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0417] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[0418] Analysis of eating and drinking habits

[0419] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. The server analyzes the user's eating and drinking patterns and nutritional intake trends, and identifies any nutrients that are clearly lacking or in excess based on data over a certain period of time (e.g., the past month). This is done by using a proprietary algorithm to perform a detailed analysis of the user's eating pattern trends.

[0420] Generate and present improvement proposals

[0421] The server generates specific dietary recommendations for the user based on the analysis of their eating habits. These recommendations are tailored to the user's individual eating habits and include short-term meal suggestions and long-term meal plans. For example, the server may recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[0422] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0423] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[0424] Specific examples

[0425] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and discovers that they are lacking in protein. Based on this, the server suggests adding chicken to the next meal. The device then presents this suggestion to the user along with a specific recipe and encourages them to follow through.

[0426] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[0427] The processing flow will be explained below.

[0428] Step 1:

[0429] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[0430] Step 2:

[0431] The device processes the image received from the user, resizing it (e.g., to 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[0432] Step 3:

[0433] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[0434] Step 4:

[0435] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[0436] Step 5:

[0437] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[0438] Step 6:

[0439] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[0440] Step 7:

[0441] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[0442] Step 8:

[0443] The server collects the user's past meal data. Specifically, it retrieves all meal data for a specific period (e.g., the past month) from the database.

[0444] Step 9:

[0445] The server analyzes the user's eating habits, specifically analyzing daily nutrient balance, calorie intake, and food types to identify the user's eating patterns and identify any obvious nutrient deficiencies or excesses.

[0446] Step 10:

[0447] The server generates dietary improvement recommendations based on the analysis of eating and drinking habits, using an algorithm supervised by a nutritionist to create short-term meal suggestions and long-term meal plans.

[0448] Step 11:

[0449] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0450] Step 12:

[0451] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[0452] Example 1

[0453] 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."

[0454] In recent years, health problems such as lifestyle-related diseases and obesity have been increasing, and approaches to prevent and improve these problems are needed. However, it is difficult to obtain a detailed understanding of each user's dietary content and eating habits and provide individualized improvement suggestions. Furthermore, users need specialized knowledge and time to record their own meals and properly manage their nutrition. The present invention aims to solve these problems and provide a system that allows users to easily analyze their own dietary content and obtain effective dietary improvement suggestions.

[0455] 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.

[0456] In this invention, the server includes means for collecting a user's past dietary data and analyzing their long-term eating and drinking habits, means for generating dietary improvement suggestions using a generative AI model based on the analysis results of the eating and drinking habits, and means for transmitting the generated dietary improvement suggestions to a terminal and visually presenting them to the user. This allows users to receive detailed nutritional analysis and visually receive individual improvement suggestions simply by uploading meal images.

[0457] A "user" is an entity that uses the system to analyze their own diet and receive dietary improvement suggestions.

[0458] "Terminal" refers to a device used by a user, such as a smartphone or tablet, that has functions such as receiving images, preprocessing, and sending data to a server.

[0459] The "server" is a central processing unit that receives data sent from the terminal, stores it in a database, analyzes images, and generates dietary improvement suggestions.

[0460] "Preprocessing" refers to the process of resizing the received image to a standard size, removing noise, and converting the format.

[0461] An "image recognition API" is an application programming interface for analyzing preprocessed image data and extracting information about ingredients and nutrients.

[0462] A "generative AI model" is an artificial intelligence model that generates individual dietary improvement suggestions based on the analysis of eating and drinking habits.

[0463] "Dietary improvement suggestions" refer to specific suggestions and recipes for optimizing nutritional balance based on the user's diet.

[0464] The "database" is a data storage location where the server saves and manages the image data and analysis results it receives, as well as the user's dietary history.

[0465] "User interface" refers to the screen and operating environment for visually presenting the generated dietary improvement suggestions to the user.

[0466] A "prompt sentence" is a natural language sentence that is input into a generative AI model based on data collected from the user.

[0467] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[0468] Image upload and preprocessing

[0469] Users open the application on their smartphones, tablets, or other devices and take or select from their camera roll an image of their meal to upload. The device then resizes the received image to a standard size (e.g., 512x512 pixels) and performs noise reduction. It also converts the image format from JPEG to PNG if necessary. This preprocessed image data is then sent to the server.

[0470] Image Recognition and Data Analysis

[0471] The server receives the image data sent from the device and stores it in a database. The stored image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API, which analyzes the image using a generative AI model. This image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0472] The server receives the analysis results returned by the generative AI model and stores them in a database, which includes the ingredient list, the amount of each ingredient, calories, and detailed nutrition information.

[0473] Analysis of eating and drinking habits

[0474] The server also collects the user's past dietary data and uses a proprietary algorithm to analyze their long-term eating and drinking habits over a certain period of time (e.g., the past month), and can identify any obvious nutrient deficiencies or excesses.

[0475] Generate and present improvement proposals

[0476] The server generates specific dietary recommendations for the user based on the analysis of their eating and drinking habits. These recommendations are created using a generative AI model and are tailored to the individual user's eating habits. They include short-term meal suggestions and long-term meal plans. For example, they recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[0477] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists). The device visually presents the improvement suggestions received from the server in a user interface, which is designed to be easy for users to understand.

[0478] Specific examples

[0479] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's eating habits and discovers, for example, that they are lacking in protein. Based on this analysis, the server suggests adding chicken to the next meal. The device then provides this suggestion to the user along with a specific recipe and encourages them to act. For example, a prompt might be, "Please add chicken to your next meal."

[0480] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[0481] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0482] Step 1:

[0483] Users open the app on their smartphone or tablet and take a picture of their meal or select one from their camera roll and upload it. The input is the image taken or selected by the user, and the output is the uploaded image file. Specifically, the image file is selected or taken by operating the app's buttons, and is prepared to be sent to the server.

[0484] Step 2:

[0485] The device preprocesses the images received from the user by resizing them to a standard size (e.g., 512x512 pixels) and removing noise. It also converts the image format from JPEG to PNG if necessary. The input is the uploaded image, and the output is a preprocessed image file. Specifically, it uses an image processing library to change the resolution, apply a noise filter, and convert the format.

[0486] Step 3:

[0487] The terminal sends the preprocessed image data to the server. The input is the preprocessed image file, and the output is the image data sent to the server. Specifically, the terminal sends the image data to the server using an HTTP request.

[0488] Step 4:

[0489] The server receives image data sent from the terminal and stores it in a database. The input is the image data sent from the terminal, and the output is the image information stored in the database. Specifically, the reception listener on the server side receives the image data and writes it to the database.

[0490] Step 5:

[0491] The server sends a request to the image recognition API and analyzes the preprocessed image data. The input is the image data stored in the database, and the output is the analysis results. Specifically, the image recognition API is called and processing is performed to extract information about ingredients and components in the image.

[0492] Step 6:

[0493] The server saves the analysis results in a database. The input is the analysis results returned from the image recognition API, and the output is the analysis information saved in the database. Specifically, it analyzes the data structure of the analysis results and writes them to the database in an appropriate format.

[0494] Step 7:

[0495] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits using a proprietary algorithm. The input is the user's past dietary data stored in the database, and the output is the analysis results of their eating and drinking habits. Specifically, the server uses a data analysis library to aggregate past dietary data and analyze nutrient intake trends.

[0496] Step 8:

[0497] The server uses a generative AI model to generate dietary improvement suggestions based on the analysis results of eating and drinking habits. The input is the analysis results of eating and drinking habits, and the output is the generated dietary improvement suggestions. Specifically, the server inputs the eating and drinking habit data into the generative AI model, creates a prompt sentence and supplies it to the model, which then generates specific dietary improvement suggestions.

[0498] Step 9:

[0499] The server sends the generated dietary improvement suggestions to the terminal. The input is the generated dietary improvement suggestions, and the output is the dietary improvement suggestions sent to the terminal. Specifically, the server sends the generated text and data to the terminal via an HTTP request.

[0500] Step 10:

[0501] The device visually presents the improvement suggestions received from the server on a user interface. The input is the dietary improvement suggestions sent from the server, and the output is the suggestions displayed on the user interface. Specifically, the data received within the application is visually formatted and displayed in a format that is easy for the user to understand.

[0502] (Application example 1)

[0503] 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."

[0504] In modern society, with the development of the restaurant industry, many people are increasingly relying on eating out. However, when eating out, it can be difficult to accurately understand the nutritional balance and health effects of the meal. In particular, people who prioritize health management have limited means of verifying whether the meal they eat at a restaurant is in line with their nutritional goals. This has led to a need for an effective system to support dietary choices and health management.

[0505] 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.

[0506] In this invention, the server includes means for receiving images taken or uploaded by a user, means for preprocessing the received images, means for transmitting the preprocessed image data to the server, means for the server to analyze the preprocessed image data, means for generating nutrient and ingredient information based on the image analysis results, means for analyzing the user's long-term eating and drinking habits, means for generating dietary improvement suggestions based on the analysis results of the eating and drinking habits, means for presenting the generated dietary improvement suggestions to the user, means for taking images of dishes using smart glasses and transmitting them to the server, and means for the server to suggest alternative menu items to the user based on the analysis results, thereby enabling users to easily understand nutritional information for meals even when eating out and supporting healthy meal selection.

[0507] "User" refers to a person who uses the system.

[0508] "Photographing" refers to the act of acquiring an image using a camera device.

[0509] "Upload" refers to the act of sending data from a local device to a server.

[0510] "Image" refers to visual information acquired using a digital camera, smartphone, etc.

[0511] "Means of receiving" refers to the technical mechanism for obtaining data from outside.

[0512] "Preprocessing" refers to the processing of image data to convert it into a format suitable for analysis.

[0513] "Preprocessing means" refers to functions that perform processing on image data, such as noise removal and resizing.

[0514] "Preprocessed image data" refers to image data that has been subjected to appropriate processing before analysis.

[0515] "Server" refers to a computer system for processing and storing data.

[0516] "Transmission mechanism" refers to the technical mechanisms by which data is sent to other systems or devices.

[0517] "Means of analysis" refers to the technical capabilities to extract useful information from data.

[0518] "Nutrients" refer to the energy and components contained in food ingredients.

[0519] "Ingredients" refers to the raw materials that make up a dish.

[0520] "Means of generating information" refers to the technical mechanisms that create new information from the results of data analysis.

[0521] "Eating habits" refers to the eating patterns and tendencies that a user has chosen in the past.

[0522] "Means of analysis" refers to the technical function of finding patterns and characteristics in data.

[0523] "Means for generating dietary improvement suggestions" refers to the function of creating appropriate dietary suggestions based on the analysis results.

[0524] "Means of presentation" refers to the technical mechanisms by which information is visually displayed to the user.

[0525] "Smart glasses" refers to wearable devices with image capture capabilities.

[0526] "Menu Alternatives" refer to other meal choices that meet the user's health goals.

[0527] "Means of suggestion" refers to the technical functionality that presents options to the user.

[0528] The present invention provides a system for assisting users in making healthy food choices when eating out. Specific embodiments of the system are described below.

[0529] 1. Image Reception and Preprocessing

[0530] A user uses smart glasses to take an image of the food they want to choose at a restaurant. The smart glasses capture the image and store the data locally. The application on the smart glasses has a function to preprocess the image. Specifically, it resizes the image to 512x512 pixels and performs noise reduction using the OpenCV library. This preprocessed image data is then sent to the server.

[0531] 2. Image analysis and data generation

[0532] The server receives and analyzes the preprocessed image data sent from the device. The server then uses a generative AI model to analyze the image. This generative AI model extracts the ingredients and nutritional information contained in the dish from the image. The analysis results include a list of ingredients and detailed information about each nutrient (protein, fat, calories, etc.).

[0533] 3. Analysis of eating habits and generation of dietary improvement suggestions

[0534] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess. Based on the results of this analysis, the server generates specific dietary recommendations for the user. For example, it suggests ingredients to add to the user's next meal or alternative menu items.

[0535] 4. Proposal for improvement

[0536] The server sends the generated dietary suggestions to the smart glasses and visually presents them to the user through the smart glasses' user interface, allowing the user to understand the nutritional information of their own meals and alternative menus that meet their health goals in real time.

[0537] Examples and prompts

[0538] For example, if a user orders a steak at a restaurant, they can take a picture of the steak with the smart glasses. The app will analyze the image and display the steak's nutritional information (protein, fat, calories, etc.) and suggest alternative dishes like salads or vegetable soups based on the user's nutritional goals.

[0539] Prompt Sentence Examples

[0540] "I'm planning to have steak for lunch today. Could you please provide me with nutritional information for this dish and suggest alternatives to make it more nutritious?"

[0541] Thus, by leveraging image capture using smart glasses and generative AI models, the system of the present invention helps users make healthy food choices even when dining out.

[0542] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0543] Step 1: Image capture and pre-processing

[0544] A user uses smart glasses to take an image of the dish they are selecting at a restaurant. The smart glasses then use their image capture function to capture the image data of the dish and store it on their local device. The image is then preprocessed. Specifically, the image is resized (to 512x512 pixels) and noise is removed. This generates preprocessed image data suitable for analysis.

[0545] Input: Raw food image data

[0546] Data processing: resizing, noise removal

[0547] Output: Preprocessed image data

[0548] Step 2: Sending preprocessed image data

[0549] The device (smart glasses) sends the preprocessed image data to the server, where it is encoded in an appropriate format (e.g., PNG format) and uploaded to the server via the network.

[0550] Input: Preprocessed image data

[0551] Data processing: Encoding image data

[0552] Output: Image data sent to the server

[0553] Step 3: Image analysis

[0554] The server receives the image data sent from the device and performs image analysis using a generative AI model. This generative AI model (e.g., YOLO or ResNet) extracts the ingredients and nutritional information contained in the dish from the image. The analysis results are output as an ingredient list and detailed information on each nutrient.

[0555] Input: Preprocessed image data

[0556] Data Computing: Image Analysis with Generative AI Models

[0557] Output: Ingredient list, nutritional information

[0558] Step 4: Analyze eating and drinking habits

[0559] The server retrieves the user's past dietary data from a database and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess.

[0560] Input: User's past meal data

[0561] Data Computing: Algorithms for Analyzing Eating and Drinking Habits

[0562] Output: Nutritional intake trends and problems

[0563] Step 5: Generate dietary improvement suggestions

[0564] Based on the analysis of the eating and drinking habits, the server generates specific dietary recommendations for the user, including suggestions for alternative menu items to supplement necessary nutrients. The recommendations are customized for each user.

[0565] Input: Nutritional intake trends, problems

[0566] Data Computing: Diet Improvement Algorithms

[0567] Output: Specific dietary improvement suggestions

[0568] Step 6: Propose improvements

[0569] The server transmits the generated dietary suggestions to the smart glasses, which visually display the suggestions to the user in real time through a user interface, allowing the user to make healthy eating choices on the spot.

[0570] Input: Specific dietary improvement suggestions

[0571] Data processing: Display on the user interface

[0572] Output: Visually presented improvement suggestions to the user

[0573] This series of steps helps users make healthy food choices even when eating out.

[0574] 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.

[0575] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system operates in cooperation with the user's terminal, a server, and an emotion engine, and a specific embodiment thereof is described below.

[0576] Image upload and preprocessing

[0577] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[0578] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[0579] Image Recognition and Data Analysis

[0580] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0581] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[0582] Analysis of eating and drinking habits and emotional states

[0583] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. It also uses an emotion engine to recognize the user's emotional state in real time. The emotion engine detects emotions from the user's facial expressions and voice, and records the results in a database.

[0584] The server combines the collected emotion data with data on eating and drinking habits and analyzes them, for example, to analyze how a particular meal affects the user's emotions and determine the state of the user when they ate a particular meal.

[0585] Generate and present improvement proposals

[0586] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[0587] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0588] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[0589] Specific examples

[0590] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and their emotional state while eating the salad. Based on this, the server can suggest relaxing foods to add to the user's next meal, taking into account the emotional impact of a particular meal.

[0591] In this way, by combining image recognition technology, data analysis technology, and emotion recognition technology, the present invention can realize a system that analyzes the eating habits and emotional state of each individual user in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[0592] The processing flow will be explained below.

[0593] Step 1:

[0594] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[0595] Step 2:

[0596] The device preprocesses the image received from the user by resizing it to a standard size (e.g., 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[0597] Step 3:

[0598] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[0599] Step 4:

[0600] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[0601] Step 5:

[0602] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[0603] Step 6:

[0604] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[0605] Step 7:

[0606] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[0607] Step 8:

[0608] The server uses an emotion engine to recognize the user's emotional state. Specifically, it acquires emotion data from the user's facial expressions and voice and records the results in a database.

[0609] Step 9:

[0610] The server collects the user's past meal data and emotion data. It retrieves all meal data and emotion data for a specific period (e.g., the past month) from the database.

[0611] Step 10:

[0612] The server analyzes the trends in eating habits and emotional state. Specifically, it analyzes daily nutrient balance, calorie intake, food types, and emotional state to identify the user's eating patterns and emotional trends. It identifies obvious nutrient deficiencies or excesses, as well as factors that cause emotional fluctuations.

[0613] Step 11:

[0614] The server generates dietary improvement suggestions based on the analysis of the user's eating habits and emotional state. Specifically, it makes dietary suggestions that address the user's emotional state, such as stress or fatigue. Using an algorithm supervised by a nutritionist, it creates short-term dietary suggestions and long-term meal plans.

[0615] Step 12:

[0616] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0617] Step 13:

[0618] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[0619] Example 2

[0620] 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."

[0621] In today's world, healthy eating habits are becoming increasingly important, but it is difficult for users to obtain appropriate dietary improvement suggestions based on their own eating habits and emotional state. Conventional systems have had difficulty analyzing a user's eating habits and emotional state in detail and providing dietary improvement suggestions tailored to individual needs. In particular, few systems provide improvement suggestions that take into account the relationship between dietary content and emotional state. As a result, users are unable to receive optimal dietary suggestions tailored to their emotional state. The present invention aims to provide a system that analyzes a user's eating habits and emotional state in detail and provides specific and effective dietary improvement suggestions tailored to the needs of each individual user.

[0622] 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.

[0623] In this invention, the server includes a means for generating information on nutrients and ingredients based on the image analysis results, a means for analyzing the user's long-term eating habits, and a means for analyzing the user's emotional state, which allows for detailed analysis of the user's eating habits and emotional state and the generation of dietary improvement proposals tailored to each individual user.

[0624] A "user" is someone who uses the system to upload photos of their meals and receive suggestions for improving their meals.

[0625] A "terminal" is a device such as a smartphone or tablet that a user uses to take or upload images.

[0626] A "server" is a computer system that receives image data sent from a user's terminal and analyzes and stores the image data.

[0627] "Image data" is data based on photos of meals taken or uploaded by users.

[0628] "Preprocessing" refers to the process of converting image data into a format suitable for analysis, and specifically includes resizing, noise removal, and format conversion.

[0629] "Image analysis" is the process of analyzing pre-processed image data to identify its contents, such as ingredients, nutrients, and calories.

[0630] "Nutrient and ingredient information" refers to information such as the ingredients contained in a meal, their amounts, and calories, as identified through image analysis.

[0631] "Dietary habits" refers to the history of meals a user has eaten in the past and their patterns.

[0632] The "emotional state" is the psychological state of the user that is detected from the user's facial expression, voice, and the like.

[0633] "Improvement suggestions" are specific dietary suggestions provided to the user based on the results of image analysis, as well as the analysis of eating habits and emotional state.

[0634] A "user interface" is a display means for visually presenting information to a user on a terminal.

[0635] The present invention is a system that analyzes food images taken or uploaded by a user and provides dietary improvement suggestions based on the user's eating habits and emotional state. Specifically, the system operates by linking the user's terminal, a server, and an emotion engine. Specific embodiments of the system are described below.

[0636] Image upload and preprocessing

[0637] Users upload photos of their meals to the app using their smartphones, tablets, or other devices. They can either select an image from their camera roll or take a photo of their meal in real time using their camera. The app guides users through the process.

[0638] The device preprocesses the images received from the user. This includes resizing the image (e.g., resizing to 512x512 pixels), removing noise, and converting the image format (e.g., converting from JPEG to PNG). An open-source image processing library (e.g., OpenCV) is used for preprocessing. The preprocessed images are then sent to the server.

[0639] Image Recognition and Data Analysis

[0640] The server receives the preprocessed image data sent from the device and stores it in a database. The database uses a storage management system (e.g., MySQL). The server then calls an image recognition API (e.g., Google Vision API) to analyze the image. The image recognition API of this generative AI model identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0641] The analysis results are stored in a database as a list of ingredients, nutrient amounts, calories, and other details, which can then be used for further data analysis and to generate dietary improvement recommendations.

[0642] Analysis of eating and drinking habits and emotional states

[0643] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits. The past dietary data is retrieved from a database and analyzed using statistical analysis tools (e.g., Python and the pandas library). The server also has the ability to recognize the user's emotional state in real time using an emotion engine (e.g., Affectiva). The emotion engine detects emotions from the user's facial expressions and voice and records the results in a database.

[0644] The server combines and analyzes the collected emotional data with data on eating and drinking habits, allowing it to understand the emotional impact of a particular meal on the user and the state of mind in which the user ate a particular meal.

[0645] Generate and present improvement proposals

[0646] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[0647] The improvement proposal also includes details of the meal suggestion (for example, a specific recipe or a list of foods). An example of a prompt generated using a generative AI model is as follows:

[0648] "Analyze a salad image uploaded by a user, identify the ingredients and the amounts of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide next meal suggestions that take into account the user's emotional state."

[0649] The server sends the generated improvement proposals to the terminal, which visually displays them on a user interface that is designed to be easy for the user to understand and put into practice.

[0650] Specific examples

[0651] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the ingredients (lettuce, tomato, cheese, etc.) and their nutrients. Based on the analysis results, the server analyzes the user's long-term eating habits and emotional state. This allows the server to consider the emotional impact of a particular meal and suggest relaxing foods to add to the user's next meal.

[0652] In this way, the present invention combines image recognition technology, data analysis technology, and emotion recognition technology to realize a system that analyzes a user's eating habits and emotional state in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[0653] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0654] Step 1:

[0655] Users upload photos of their meals using an app on their smartphone or tablet.

[0656] Input: An image of a meal taken or selected by the user.

[0657] How it works: The user uses the camera to take a photo in real time or selects an image from the camera roll.

[0658] Output: Image files of the selected or photographed meal.

[0659] Step 2:

[0660] The terminal pre-processes the received image.

[0661] Input: Raw image files uploaded by the user.

[0662] What it does: The device resizes the image to 512x512 pixels, denoises it, and optionally converts it from JPEG to PNG format using an image processing library such as OpenCV.

[0663] Output: Preprocessed image files.

[0664] Step 3:

[0665] The terminal transmits the preprocessed image to the server.

[0666] Input: Preprocessed image files.

[0667] Operation: The terminal uploads preprocessed image data to the server via the network.

[0668] Output: Preprocessed image data sent to the server.

[0669] Step 4:

[0670] The server receives the pre-processed image data and stores it in a database.

[0671] Input: Preprocessed image data sent from the device.

[0672] Operation: The server stores the received image data in a database using a storage management system such as MySQL.

[0673] Output: Image data stored in a database.

[0674] Step 5:

[0675] The server uses an image recognition API to analyze the meal contents.

[0676] Input: Preprocessed image data stored in a database.

[0677] How it works: The server calls an image recognition API, such as the Google Vision API, to analyze the stored image and identify the ingredients, dish name, amount of each ingredient, and calories.

[0678] Output: A list of ingredients, their amounts, and calorie analysis results.

[0679] Step 6:

[0680] The server stores the analysis results in a database.

[0681] Input: Analysis results obtained from the image recognition API.

[0682] How it works: The server stores the results of the analysis in a database, which is done by writing data using SQL queries.

[0683] Output: A list of ingredients stored in a database, along with their amounts and calorie information.

[0684] Step 7:

[0685] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits.

[0686] Input: Historical dietary data stored in a database.

[0687] How it works: The server collects historical dietary data and uses statistical analysis tools (e.g., Python's pandas library) to analyze long-term eating and drinking habits.

[0688] Output: Analysis results about the user's eating and drinking habits.

[0689] Step 8:

[0690] The server uses an emotion engine to analyze the user's emotional state.

[0691] Input: User's facial and voice data.

[0692] How it works: The server uses an emotion engine such as Affectiva to detect the user's emotional state from their facial expressions and voice, and records the results in a database.

[0693] Output: Analysis results about the user's emotional state.

[0694] Step 9:

[0695] The server generates dietary improvement suggestions based on the analysis of eating habits and emotional state.

[0696] Input: Analysis of eating and drinking habits and emotional state.

[0697] How it works: The server integrates this data and uses a generative AI model to generate specific, personalized dietary recommendations. Prompts include: "Analyze a salad image uploaded by the user, identify its ingredients and the amount of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide the next meal suggestion, taking into account the user's emotional state."

[0698] Output: Improvement proposal generation results.

[0699] Step 10:

[0700] The server transmits the generated improvement plan to the terminal.

[0701] Input: The data of the generated improvement proposal.

[0702] Operation: The server transfers data using a network protocol to send the generated improvement proposal to the terminal.

[0703] Output: Improvement suggestion data sent to the device.

[0704] Step 11:

[0705] The terminal presents improvement proposals to the user.

[0706] Input: Improvement proposal data sent from the server.

[0707] Operation: The device visually displays the received improvement suggestions in the user interface, making it easier for the user to understand the suggestions.

[0708] Output: Suggested improvements displayed in the user interface.

[0709] Through the above processing steps, the system of the present invention can analyze the user's eating habits and emotional state, generate dietary improvement suggestions based on the analysis, and provide them to the user.

[0710] (Application example 2)

[0711] 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."

[0712] While conventional dietary analysis systems can suggest meals based on a user's eating habits, they are unable to make suggestions that take into account the user's emotional state. Furthermore, systems designed for use in brick-and-mortar establishments such as restaurants and cafes have not yet become widespread. This has made it difficult to effectively support the improvement of a user's health and psychological state.

[0713] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state in real time, means for generating diet improvement suggestions based on the analysis results of the emotional state, and means for presenting the generated diet improvement suggestions to the user. This makes it possible to make diet suggestions that take the user's emotional state into consideration.

[0714] "Means for receiving images" refers to a mechanism by which the terminal receives image data taken or uploaded by the user.

[0715] The "means for preprocessing images" is a mechanism for resizing received image data to a certain standard size and performing preprocessing such as noise removal and format conversion.

[0716] The "means for transmitting image data to a server" is a mechanism for transferring preprocessed image data to a server.

[0717] "Means for the server to analyze preprocessed image data" refers to a mechanism for receiving preprocessed image data on the server and analyzing it using an image recognition API.

[0718] The "means for generating information on nutrients and ingredients based on the image analysis results" is a mechanism for generating information on ingredients and nutrients extracted from the analyzed image data.

[0719] The "means for analyzing a user's long-term eating and drinking habits" is a mechanism for collecting a user's past dietary data and analyzing the user's long-term eating and drinking habits based on that data.

[0720] "Means for analyzing the user's emotional state in real time" refers to a mechanism for detecting and analyzing the user's emotions in real time from facial expressions, voice, etc.

[0721] The "means for generating dietary improvement suggestions based on the results of the analysis of the emotional state" is a mechanism for generating individual dietary improvement suggestions based on the results of the user's emotional analysis and long-term eating and drinking habits.

[0722] The "means for presenting the generated diet improvement suggestions to the user" is a mechanism for transmitting the diet improvement suggestions generated by the server to the terminal and visually displaying them on the user interface.

[0723] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system is implemented in the following steps.

[0724] Hardware and Software Configuration

[0725] User's device

[0726] The user's smartphone or tablet device is used to take and upload images and display dietary improvement suggestions. The following applications are installed on the device:

[0727] Camera application: Ability to take photos of meals

[0728] Image processing application: Functions for pre-processing captured images

[0729] server

[0730] The server is the central component that analyzes images, stores data, analyzes emotions, and generates improvement recommendations. The main software used includes:

[0731] Image Recognition API: Generative AI models (e.g., TensorFlow, OpenCV) for extracting ingredient and nutrient information from images

[0732] Database: A database (e.g., MySQL) to store analysis results and user eating habits and emotion data.

[0733] Emotion analysis engine: Software for analyzing emotions from a user's facial expressions and voice (e.g., Microsoft Azure Cognitive Services)

[0734] Data processing flow

[0735] Image preprocessing

[0736] Users take a photo of their meal using their smartphone's camera application or select it from their camera roll, and then the image is preprocessed using the application's image processing function, which involves resizing the image (to 512x512 pixels) and removing noise.

[0737] Image analysis

[0738] The preprocessed image data is sent to a server, which uses an image recognition API to analyze the image content. The analysis extracts information about ingredients and nutrients, which is then stored in a database.

[0739] Analysis of eating and drinking habits and emotional states

[0740] The server retrieves the user's past dietary data from the database and analyzes their long-term eating and drinking habits. It also uses an emotion analysis engine to analyze the user's emotional state in real time. The analysis results are recorded in the database.

[0741] Generating and presenting dietary improvement suggestions

[0742] The server comprehensively analyzes eating habits and emotional states to generate personalized dietary improvement recommendations. This generation process uses the following generative AI model:

[0743] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[0744] The server then sends the generated dietary improvement suggestions to the user's device, which then displays the suggestions on a user interface. For example, if the user is feeling stressed, the server can suggest a relaxing herbal tea.

[0745] In this way, the present invention provides a system that combines image recognition technology, data analysis technology, and emotion recognition technology to realize effective meal suggestions in physical stores.

[0746] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0747] Step 1: User takes or uploads an image

[0748] The user takes a picture of the meal using the smartphone's camera application or selects an image from the camera roll. The input image is in a common image format such as JPEG or PNG. The output is the selected or captured raw image data.

[0749] Step 2: The device preprocesses the image

[0750] The device preprocesses the image taken or selected by the user. Specifically, it resizes the image (e.g., to 512x512 pixels) and denoises it. This process uses libraries such as Pillow and OpenCV. The input is raw image data. The output is preprocessed, clean image data.

[0751] Step 3: Send the preprocessed image data to the server

[0752] The device sends the preprocessed image data to the server. This communication is performed using an HTTP POST request. The input is the preprocessed image data. The output is the status of completion of transmission to the server.

[0753] Step 4: The server analyzes the image data

[0754] The server analyzes the received image data, using an image recognition API (e.g., TensorFlow or OpenCV) to extract information about ingredients and nutrients from the image. The input is the preprocessed image data, and the output is a detailed list of ingredients and nutrients.

[0755] Step 5: Save your ingredient and nutrition data

[0756] The server stores the resulting food and nutrient data in a database. This data is managed individually for each user. The input is a detailed list of food ingredients and nutrients. The output is a data entry stored in the database.

[0757] Step 6: The server analyzes your past eating and drinking habits

[0758] The server retrieves the user's past eating and drinking data from the database and analyzes their long-term eating and drinking habits. The input is the past eating and drinking data in the database. The output is the analyzed long-term eating and drinking habits data.

[0759] Step 7: The server analyzes the emotional state in real time

[0760] The server uses an emotion analysis engine (e.g., Microsoft Azure Cognitive Services) to analyze the user's real-time emotional state. In this process, facial and voice data are input. The input is real-time facial and voice data. The output is analyzed emotional state data.

[0761] Step 8: Generate dietary recommendations based on your emotional state

[0762] The server generates personalized dietary recommendations based on long-term eating and drinking habits and real-time emotional state, using a generative AI model and prompts such as:

[0763] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[0764] The input is data on eating habits and emotional state, and the output is detailed dietary improvement recommendations.

[0765] Step 9: Present the improvement suggestions to the user

[0766] The server sends the generated dietary improvement suggestions to the terminal, which then visually displays the improvement suggestions on a user interface. The input is the generated dietary improvement suggestions. The output is the improvement suggestions displayed to the user.

[0767] In this way, through each processing step, the user can be provided with dietary improvement suggestions that take into account their emotional state.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] [Third embodiment]

[0772] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0773] 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.

[0774] 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).

[0775] 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.

[0776] 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.

[0777] 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).

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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."

[0784] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[0785] Image upload and preprocessing

[0786] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[0787] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[0788] Image Recognition and Data Analysis

[0789] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0790] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[0791] Analysis of eating and drinking habits

[0792] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. The server analyzes the user's eating and drinking patterns and nutritional intake trends, and identifies any nutrients that are clearly lacking or in excess based on data over a certain period of time (e.g., the past month). This is done by using a proprietary algorithm to perform a detailed analysis of the user's eating pattern trends.

[0793] Generate and present improvement proposals

[0794] The server generates specific dietary recommendations for the user based on the analysis of their eating habits. These recommendations are tailored to the user's individual eating habits and include short-term meal suggestions and long-term meal plans. For example, the server may recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[0795] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0796] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[0797] Specific examples

[0798] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and discovers that they are lacking in protein. Based on this, the server suggests adding chicken to the next meal. The device then presents this suggestion to the user along with a specific recipe and encourages them to follow through.

[0799] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[0800] The processing flow will be explained below.

[0801] Step 1:

[0802] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[0803] Step 2:

[0804] The device processes the image received from the user, resizing it (e.g., to 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[0805] Step 3:

[0806] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[0807] Step 4:

[0808] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[0809] Step 5:

[0810] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[0811] Step 6:

[0812] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[0813] Step 7:

[0814] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[0815] Step 8:

[0816] The server collects the user's past meal data. Specifically, it retrieves all meal data for a specific period (e.g., the past month) from the database.

[0817] Step 9:

[0818] The server analyzes the user's eating habits, specifically analyzing daily nutrient balance, calorie intake, and food types to identify the user's eating patterns and identify any obvious nutrient deficiencies or excesses.

[0819] Step 10:

[0820] The server generates dietary improvement recommendations based on the analysis of eating and drinking habits, using an algorithm supervised by a nutritionist to create short-term meal suggestions and long-term meal plans.

[0821] Step 11:

[0822] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0823] Step 12:

[0824] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[0825] Example 1

[0826] 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."

[0827] In recent years, health problems such as lifestyle-related diseases and obesity have been increasing, and approaches to prevent and improve these problems are needed. However, it is difficult to obtain a detailed understanding of each user's dietary content and eating habits and provide individualized improvement suggestions. Furthermore, users need specialized knowledge and time to record their own meals and properly manage their nutrition. The present invention aims to solve these problems and provide a system that allows users to easily analyze their own dietary content and obtain effective dietary improvement suggestions.

[0828] 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.

[0829] In this invention, the server includes means for collecting a user's past dietary data and analyzing their long-term eating and drinking habits, means for generating dietary improvement suggestions using a generative AI model based on the analysis results of the eating and drinking habits, and means for transmitting the generated dietary improvement suggestions to a terminal and visually presenting them to the user. This allows users to receive detailed nutritional analysis and visually receive individual improvement suggestions simply by uploading meal images.

[0830] A "user" is an entity that uses the system to analyze their own diet and receive dietary improvement suggestions.

[0831] "Terminal" refers to a device used by a user, such as a smartphone or tablet, that has functions such as receiving images, preprocessing, and sending data to a server.

[0832] The "server" is a central processing unit that receives data sent from the terminal, stores it in a database, analyzes images, and generates dietary improvement suggestions.

[0833] "Preprocessing" refers to the process of resizing the received image to a standard size, removing noise, and converting the format.

[0834] An "image recognition API" is an application programming interface for analyzing preprocessed image data and extracting information about ingredients and nutrients.

[0835] A "generative AI model" is an artificial intelligence model that generates individual dietary improvement suggestions based on the analysis of eating and drinking habits.

[0836] "Dietary improvement suggestions" refer to specific suggestions and recipes for optimizing nutritional balance based on the user's diet.

[0837] The "database" is a data storage location where the server saves and manages the image data and analysis results it receives, as well as the user's dietary history.

[0838] "User interface" refers to the screen and operating environment for visually presenting the generated dietary improvement suggestions to the user.

[0839] A "prompt sentence" is a natural language sentence that is input into a generative AI model based on data collected from the user.

[0840] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[0841] Image upload and preprocessing

[0842] Users open the application on their smartphones, tablets, or other devices and take or select from their camera roll an image of their meal to upload. The device then resizes the received image to a standard size (e.g., 512x512 pixels) and performs noise reduction. It also converts the image format from JPEG to PNG if necessary. This preprocessed image data is then sent to the server.

[0843] Image Recognition and Data Analysis

[0844] The server receives the image data sent from the device and stores it in a database. The stored image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API, which analyzes the image using a generative AI model. This image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0845] The server receives the analysis results returned by the generative AI model and stores them in a database, which includes the ingredient list, the amount of each ingredient, calories, and detailed nutrition information.

[0846] Analysis of eating and drinking habits

[0847] The server also collects the user's past dietary data and uses a proprietary algorithm to analyze their long-term eating and drinking habits over a certain period of time (e.g., the past month), and can identify any obvious nutrient deficiencies or excesses.

[0848] Generate and present improvement proposals

[0849] The server generates specific dietary recommendations for the user based on the analysis of their eating and drinking habits. These recommendations are created using a generative AI model and are tailored to the individual user's eating habits. They include short-term meal suggestions and long-term meal plans. For example, they recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[0850] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists). The device visually presents the improvement suggestions received from the server in a user interface, which is designed to be easy for users to understand.

[0851] Specific examples

[0852] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's eating habits and discovers, for example, that they are lacking in protein. Based on this analysis, the server suggests adding chicken to the next meal. The device then provides this suggestion to the user along with a specific recipe and encourages them to act. For example, a prompt might be, "Please add chicken to your next meal."

[0853] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[0854] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0855] Step 1:

[0856] Users open the app on their smartphone or tablet and take a picture of their meal or select one from their camera roll and upload it. The input is the image taken or selected by the user, and the output is the uploaded image file. Specifically, the image file is selected or taken by operating the app's buttons, and is prepared to be sent to the server.

[0857] Step 2:

[0858] The device preprocesses the images received from the user by resizing them to a standard size (e.g., 512x512 pixels) and removing noise. It also converts the image format from JPEG to PNG if necessary. The input is the uploaded image, and the output is a preprocessed image file. Specifically, it uses an image processing library to change the resolution, apply a noise filter, and convert the format.

[0859] Step 3:

[0860] The terminal sends the preprocessed image data to the server. The input is the preprocessed image file, and the output is the image data sent to the server. Specifically, the terminal sends the image data to the server using an HTTP request.

[0861] Step 4:

[0862] The server receives image data sent from the terminal and stores it in a database. The input is the image data sent from the terminal, and the output is the image information stored in the database. Specifically, the reception listener on the server side receives the image data and writes it to the database.

[0863] Step 5:

[0864] The server sends a request to the image recognition API and analyzes the preprocessed image data. The input is the image data stored in the database, and the output is the analysis results. Specifically, the image recognition API is called and processing is performed to extract information about ingredients and components in the image.

[0865] Step 6:

[0866] The server saves the analysis results in a database. The input is the analysis results returned from the image recognition API, and the output is the analysis information saved in the database. Specifically, it analyzes the data structure of the analysis results and writes them to the database in an appropriate format.

[0867] Step 7:

[0868] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits using a proprietary algorithm. The input is the user's past dietary data stored in the database, and the output is the analysis results of their eating and drinking habits. Specifically, the server uses a data analysis library to aggregate past dietary data and analyze nutrient intake trends.

[0869] Step 8:

[0870] The server uses a generative AI model to generate dietary improvement suggestions based on the analysis results of eating and drinking habits. The input is the analysis results of eating and drinking habits, and the output is the generated dietary improvement suggestions. Specifically, the server inputs the eating and drinking habit data into the generative AI model, creates a prompt sentence and supplies it to the model, which then generates specific dietary improvement suggestions.

[0871] Step 9:

[0872] The server sends the generated dietary improvement suggestions to the terminal. The input is the generated dietary improvement suggestions, and the output is the dietary improvement suggestions sent to the terminal. Specifically, the server sends the generated text and data to the terminal via an HTTP request.

[0873] Step 10:

[0874] The device visually presents the improvement suggestions received from the server on a user interface. The input is the dietary improvement suggestions sent from the server, and the output is the suggestions displayed on the user interface. Specifically, the data received within the application is visually formatted and displayed in a format that is easy for the user to understand.

[0875] (Application example 1)

[0876] 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."

[0877] In modern society, with the development of the restaurant industry, many people are increasingly relying on eating out. However, when eating out, it can be difficult to accurately understand the nutritional balance and health effects of the meal. In particular, people who prioritize health management have limited means of verifying whether the meal they eat at a restaurant is in line with their nutritional goals. This has led to a need for an effective system to support dietary choices and health management.

[0878] 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.

[0879] In this invention, the server includes means for receiving images taken or uploaded by a user, means for preprocessing the received images, means for transmitting the preprocessed image data to the server, means for the server to analyze the preprocessed image data, means for generating nutrient and ingredient information based on the image analysis results, means for analyzing the user's long-term eating and drinking habits, means for generating dietary improvement suggestions based on the analysis results of the eating and drinking habits, means for presenting the generated dietary improvement suggestions to the user, means for taking images of dishes using smart glasses and transmitting them to the server, and means for the server to suggest alternative menu items to the user based on the analysis results, thereby enabling users to easily understand nutritional information for meals even when eating out and supporting healthy meal selection.

[0880] "User" refers to a person who uses the system.

[0881] "Photographing" refers to the act of acquiring an image using a camera device.

[0882] "Upload" refers to the act of sending data from a local device to a server.

[0883] "Image" refers to visual information acquired using a digital camera, smartphone, etc.

[0884] "Means of receiving" refers to the technical mechanism for obtaining data from outside.

[0885] "Preprocessing" refers to the processing of image data to convert it into a format suitable for analysis.

[0886] "Preprocessing means" refers to functions that perform processing on image data, such as noise removal and resizing.

[0887] "Preprocessed image data" refers to image data that has been subjected to appropriate processing before analysis.

[0888] "Server" refers to a computer system for processing and storing data.

[0889] "Transmission mechanism" refers to the technical mechanisms by which data is sent to other systems or devices.

[0890] "Means of analysis" refers to the technical capabilities to extract useful information from data.

[0891] "Nutrients" refer to the energy and components contained in food ingredients.

[0892] "Ingredients" refers to the raw materials that make up a dish.

[0893] "Means of generating information" refers to the technical mechanisms that create new information from the results of data analysis.

[0894] "Eating habits" refers to the eating patterns and tendencies that a user has chosen in the past.

[0895] "Means of analysis" refers to the technical function of finding patterns and characteristics in data.

[0896] "Means for generating dietary improvement suggestions" refers to the function of creating appropriate dietary suggestions based on the analysis results.

[0897] "Means of presentation" refers to the technical mechanisms by which information is visually displayed to the user.

[0898] "Smart glasses" refers to wearable devices with image capture capabilities.

[0899] "Menu Alternatives" refer to other meal choices that meet the user's health goals.

[0900] "Means of suggestion" refers to the technical functionality that presents options to the user.

[0901] The present invention provides a system for assisting users in making healthy food choices when eating out. Specific embodiments of the system are described below.

[0902] 1. Image Reception and Preprocessing

[0903] A user uses smart glasses to take an image of the food they want to choose at a restaurant. The smart glasses capture the image and store the data locally. The application on the smart glasses has a function to preprocess the image. Specifically, it resizes the image to 512x512 pixels and performs noise reduction using the OpenCV library. This preprocessed image data is then sent to the server.

[0904] 2. Image analysis and data generation

[0905] The server receives and analyzes the preprocessed image data sent from the device. The server then uses a generative AI model to analyze the image. This generative AI model extracts the ingredients and nutritional information contained in the dish from the image. The analysis results include a list of ingredients and detailed information about each nutrient (protein, fat, calories, etc.).

[0906] 3. Analysis of eating habits and generation of dietary improvement suggestions

[0907] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess. Based on the results of this analysis, the server generates specific dietary recommendations for the user. For example, it suggests ingredients to add to the user's next meal or alternative menu items.

[0908] 4. Proposal for improvement

[0909] The server sends the generated dietary suggestions to the smart glasses and visually presents them to the user through the smart glasses' user interface, allowing the user to understand the nutritional information of their own meals and alternative menus that meet their health goals in real time.

[0910] Examples and prompts

[0911] For example, if a user orders a steak at a restaurant, they can take a picture of the steak with the smart glasses. The app will analyze the image and display the steak's nutritional information (protein, fat, calories, etc.) and suggest alternative dishes like salads or vegetable soups based on the user's nutritional goals.

[0912] Prompt Sentence Examples

[0913] "I'm planning to have steak for lunch today. Could you please provide me with nutritional information for this dish and suggest alternatives to make it more nutritious?"

[0914] Thus, by leveraging image capture using smart glasses and generative AI models, the system of the present invention helps users make healthy food choices even when dining out.

[0915] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0916] Step 1: Image capture and pre-processing

[0917] A user uses smart glasses to take an image of the dish they are selecting at a restaurant. The smart glasses then use their image capture function to capture the image data of the dish and store it on their local device. The image is then preprocessed. Specifically, the image is resized (to 512x512 pixels) and noise is removed. This generates preprocessed image data suitable for analysis.

[0918] Input: Raw food image data

[0919] Data processing: resizing, noise removal

[0920] Output: Preprocessed image data

[0921] Step 2: Sending preprocessed image data

[0922] The device (smart glasses) sends the preprocessed image data to the server, where it is encoded in an appropriate format (e.g., PNG format) and uploaded to the server via the network.

[0923] Input: Preprocessed image data

[0924] Data processing: Encoding image data

[0925] Output: Image data sent to the server

[0926] Step 3: Image analysis

[0927] The server receives the image data sent from the device and performs image analysis using a generative AI model. This generative AI model (e.g., YOLO or ResNet) extracts the ingredients and nutritional information contained in the dish from the image. The analysis results are output as an ingredient list and detailed information on each nutrient.

[0928] Input: Preprocessed image data

[0929] Data Computing: Image Analysis with Generative AI Models

[0930] Output: Ingredient list, nutritional information

[0931] Step 4: Analyze eating and drinking habits

[0932] The server retrieves the user's past dietary data from a database and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess.

[0933] Input: User's past meal data

[0934] Data Computing: Algorithms for Analyzing Eating and Drinking Habits

[0935] Output: Nutritional intake trends and problems

[0936] Step 5: Generate dietary improvement suggestions

[0937] Based on the analysis of the eating and drinking habits, the server generates specific dietary recommendations for the user, including suggestions for alternative menu items to supplement necessary nutrients. The recommendations are customized for each user.

[0938] Input: Nutritional intake trends, problems

[0939] Data Computing: Diet Improvement Algorithms

[0940] Output: Specific dietary improvement suggestions

[0941] Step 6: Propose improvements

[0942] The server transmits the generated dietary suggestions to the smart glasses, which visually display the suggestions to the user in real time through a user interface, allowing the user to make healthy eating choices on the spot.

[0943] Input: Specific dietary improvement suggestions

[0944] Data processing: Display on the user interface

[0945] Output: Visually presented improvement suggestions to the user

[0946] This series of steps helps users make healthy food choices even when eating out.

[0947] 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.

[0948] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system operates in cooperation with the user's terminal, a server, and an emotion engine, and a specific embodiment thereof is described below.

[0949] Image upload and preprocessing

[0950] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[0951] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[0952] Image Recognition and Data Analysis

[0953] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[0954] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[0955] Analysis of eating and drinking habits and emotional states

[0956] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. It also uses an emotion engine to recognize the user's emotional state in real time. The emotion engine detects emotions from the user's facial expressions and voice, and records the results in a database.

[0957] The server combines the collected emotion data with data on eating and drinking habits and analyzes them, for example, to analyze how a particular meal affects the user's emotions and determine the state of the user when they ate a particular meal.

[0958] Generate and present improvement proposals

[0959] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[0960] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0961] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[0962] Specific examples

[0963] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and their emotional state while eating the salad. Based on this, the server can suggest relaxing foods to add to the user's next meal, taking into account the emotional impact of a particular meal.

[0964] In this way, by combining image recognition technology, data analysis technology, and emotion recognition technology, the present invention can realize a system that analyzes the eating habits and emotional state of each individual user in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[0965] The processing flow will be explained below.

[0966] Step 1:

[0967] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[0968] Step 2:

[0969] The device preprocesses the image received from the user by resizing it to a standard size (e.g., 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[0970] Step 3:

[0971] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[0972] Step 4:

[0973] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[0974] Step 5:

[0975] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[0976] Step 6:

[0977] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[0978] Step 7:

[0979] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[0980] Step 8:

[0981] The server uses an emotion engine to recognize the user's emotional state. Specifically, it acquires emotion data from the user's facial expressions and voice and records the results in a database.

[0982] Step 9:

[0983] The server collects the user's past meal data and emotion data. It retrieves all meal data and emotion data for a specific period (e.g., the past month) from the database.

[0984] Step 10:

[0985] The server analyzes the trends in eating habits and emotional state. Specifically, it analyzes daily nutrient balance, calorie intake, food types, and emotional state to identify the user's eating patterns and emotional trends. It identifies obvious nutrient deficiencies or excesses, as well as factors that cause emotional fluctuations.

[0986] Step 11:

[0987] The server generates dietary improvement suggestions based on the analysis of the user's eating habits and emotional state. Specifically, it makes dietary suggestions that address the user's emotional state, such as stress or fatigue. Using an algorithm supervised by a nutritionist, it creates short-term dietary suggestions and long-term meal plans.

[0988] Step 12:

[0989] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[0990] Step 13:

[0991] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[0992] Example 2

[0993] 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."

[0994] In today's world, healthy eating habits are becoming increasingly important, but it is difficult for users to obtain appropriate dietary improvement suggestions based on their own eating habits and emotional state. Conventional systems have had difficulty analyzing a user's eating habits and emotional state in detail and providing dietary improvement suggestions tailored to individual needs. In particular, few systems provide improvement suggestions that take into account the relationship between dietary content and emotional state. As a result, users are unable to receive optimal dietary suggestions tailored to their emotional state. The present invention aims to provide a system that analyzes a user's eating habits and emotional state in detail and provides specific and effective dietary improvement suggestions tailored to the needs of each individual user.

[0995] 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.

[0996] In this invention, the server includes a means for generating information on nutrients and ingredients based on the image analysis results, a means for analyzing the user's long-term eating habits, and a means for analyzing the user's emotional state, which allows for detailed analysis of the user's eating habits and emotional state and the generation of dietary improvement proposals tailored to each individual user.

[0997] A "user" is someone who uses the system to upload photos of their meals and receive suggestions for improving their meals.

[0998] A "terminal" is a device such as a smartphone or tablet that a user uses to take or upload images.

[0999] A "server" is a computer system that receives image data sent from a user's terminal and analyzes and stores the image data.

[1000] "Image data" is data based on photos of meals taken or uploaded by users.

[1001] "Preprocessing" refers to the process of converting image data into a format suitable for analysis, and specifically includes resizing, noise removal, and format conversion.

[1002] "Image analysis" is the process of analyzing pre-processed image data to identify its contents, such as ingredients, nutrients, and calories.

[1003] "Nutrient and ingredient information" refers to information such as the ingredients contained in a meal, their amounts, and calories, as identified through image analysis.

[1004] "Dietary habits" refers to the history of meals a user has eaten in the past and their patterns.

[1005] The "emotional state" is the psychological state of the user that is detected from the user's facial expression, voice, and the like.

[1006] "Improvement suggestions" are specific dietary suggestions provided to the user based on the results of image analysis, as well as the analysis of eating habits and emotional state.

[1007] A "user interface" is a display means for visually presenting information to a user on a terminal.

[1008] The present invention is a system that analyzes food images taken or uploaded by a user and provides dietary improvement suggestions based on the user's eating habits and emotional state. Specifically, the system operates by linking the user's terminal, a server, and an emotion engine. Specific embodiments of the system are described below.

[1009] Image upload and preprocessing

[1010] Users upload photos of their meals to the app using their smartphones, tablets, or other devices. They can either select an image from their camera roll or take a photo of their meal in real time using their camera. The app guides users through the process.

[1011] The device preprocesses the images received from the user. This includes resizing the image (e.g., resizing to 512x512 pixels), removing noise, and converting the image format (e.g., converting from JPEG to PNG). An open-source image processing library (e.g., OpenCV) is used for preprocessing. The preprocessed images are then sent to the server.

[1012] Image Recognition and Data Analysis

[1013] The server receives the preprocessed image data sent from the device and stores it in a database. The database uses a storage management system (e.g., MySQL). The server then calls an image recognition API (e.g., Google Vision API) to analyze the image. The image recognition API of this generative AI model identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[1014] The analysis results are stored in a database as a list of ingredients, nutrient amounts, calories, and other details, which can then be used for further data analysis and to generate dietary improvement recommendations.

[1015] Analysis of eating and drinking habits and emotional states

[1016] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits. The past dietary data is retrieved from a database and analyzed using statistical analysis tools (e.g., Python and the pandas library). The server also has the ability to recognize the user's emotional state in real time using an emotion engine (e.g., Affectiva). The emotion engine detects emotions from the user's facial expressions and voice and records the results in a database.

[1017] The server combines and analyzes the collected emotional data with data on eating and drinking habits, allowing it to understand the emotional impact of a particular meal on the user and the state of mind in which the user ate a particular meal.

[1018] Generate and present improvement proposals

[1019] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[1020] The improvement proposal also includes details of the meal suggestion (for example, a specific recipe or a list of foods). An example of a prompt generated using a generative AI model is as follows:

[1021] "Analyze a salad image uploaded by a user, identify the ingredients and the amounts of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide next meal suggestions that take into account the user's emotional state."

[1022] The server sends the generated improvement proposals to the terminal, which visually displays them on a user interface that is designed to be easy for the user to understand and put into practice.

[1023] Specific examples

[1024] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the ingredients (lettuce, tomato, cheese, etc.) and their nutrients. Based on the analysis results, the server analyzes the user's long-term eating habits and emotional state. This allows the server to consider the emotional impact of a particular meal and suggest relaxing foods to add to the user's next meal.

[1025] In this way, the present invention combines image recognition technology, data analysis technology, and emotion recognition technology to realize a system that analyzes a user's eating habits and emotional state in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[1026] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1027] Step 1:

[1028] Users upload photos of their meals using an app on their smartphone or tablet.

[1029] Input: An image of a meal taken or selected by the user.

[1030] How it works: The user uses the camera to take a photo in real time or selects an image from the camera roll.

[1031] Output: Image files of the selected or photographed meal.

[1032] Step 2:

[1033] The terminal pre-processes the received image.

[1034] Input: Raw image files uploaded by the user.

[1035] What it does: The device resizes the image to 512x512 pixels, denoises it, and optionally converts it from JPEG to PNG format using an image processing library such as OpenCV.

[1036] Output: Preprocessed image files.

[1037] Step 3:

[1038] The terminal transmits the preprocessed image to the server.

[1039] Input: Preprocessed image files.

[1040] Operation: The terminal uploads preprocessed image data to the server via the network.

[1041] Output: Preprocessed image data sent to the server.

[1042] Step 4:

[1043] The server receives the pre-processed image data and stores it in a database.

[1044] Input: Preprocessed image data sent from the device.

[1045] Operation: The server stores the received image data in a database using a storage management system such as MySQL.

[1046] Output: Image data stored in a database.

[1047] Step 5:

[1048] The server uses an image recognition API to analyze the meal contents.

[1049] Input: Preprocessed image data stored in a database.

[1050] How it works: The server calls an image recognition API, such as the Google Vision API, to analyze the stored image and identify the ingredients, dish name, amount of each ingredient, and calories.

[1051] Output: A list of ingredients, their amounts, and calorie analysis results.

[1052] Step 6:

[1053] The server stores the analysis results in a database.

[1054] Input: Analysis results obtained from the image recognition API.

[1055] How it works: The server stores the results of the analysis in a database, which is done by writing data using SQL queries.

[1056] Output: A list of ingredients stored in a database, along with their amounts and calorie information.

[1057] Step 7:

[1058] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits.

[1059] Input: Historical dietary data stored in a database.

[1060] How it works: The server collects historical dietary data and uses statistical analysis tools (e.g., Python's pandas library) to analyze long-term eating and drinking habits.

[1061] Output: Analysis results about the user's eating and drinking habits.

[1062] Step 8:

[1063] The server uses an emotion engine to analyze the user's emotional state.

[1064] Input: User's facial and voice data.

[1065] How it works: The server uses an emotion engine such as Affectiva to detect the user's emotional state from their facial expressions and voice, and records the results in a database.

[1066] Output: Analysis results about the user's emotional state.

[1067] Step 9:

[1068] The server generates dietary improvement suggestions based on the analysis of eating habits and emotional state.

[1069] Input: Analysis of eating and drinking habits and emotional state.

[1070] How it works: The server integrates this data and uses a generative AI model to generate specific, personalized dietary recommendations. Prompts include: "Analyze a salad image uploaded by the user, identify its ingredients and the amount of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide the next meal suggestion, taking into account the user's emotional state."

[1071] Output: Improvement proposal generation results.

[1072] Step 10:

[1073] The server transmits the generated improvement plan to the terminal.

[1074] Input: The data of the generated improvement proposal.

[1075] Operation: The server transfers data using a network protocol to send the generated improvement proposal to the terminal.

[1076] Output: Improvement suggestion data sent to the device.

[1077] Step 11:

[1078] The terminal presents improvement proposals to the user.

[1079] Input: Improvement proposal data sent from the server.

[1080] Operation: The device visually displays the received improvement suggestions in the user interface, making it easier for the user to understand the suggestions.

[1081] Output: Suggested improvements displayed in the user interface.

[1082] Through the above processing steps, the system of the present invention can analyze the user's eating habits and emotional state, generate dietary improvement suggestions based on the analysis, and provide them to the user.

[1083] (Application example 2)

[1084] 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."

[1085] While conventional dietary analysis systems can suggest meals based on a user's eating habits, they are unable to make suggestions that take into account the user's emotional state. Furthermore, systems designed for use in brick-and-mortar establishments such as restaurants and cafes have not yet become widespread. This has made it difficult to effectively support the improvement of a user's health and psychological state.

[1086] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state in real time, means for generating diet improvement suggestions based on the analysis results of the emotional state, and means for presenting the generated diet improvement suggestions to the user. This makes it possible to make diet suggestions that take the user's emotional state into consideration.

[1087] "Means for receiving images" refers to a mechanism by which the terminal receives image data taken or uploaded by the user.

[1088] The "means for preprocessing images" is a mechanism for resizing received image data to a certain standard size and performing preprocessing such as noise removal and format conversion.

[1089] The "means for transmitting image data to a server" is a mechanism for transferring preprocessed image data to a server.

[1090] "Means for the server to analyze preprocessed image data" refers to a mechanism for receiving preprocessed image data on the server and analyzing it using an image recognition API.

[1091] The "means for generating information on nutrients and ingredients based on the image analysis results" is a mechanism for generating information on ingredients and nutrients extracted from the analyzed image data.

[1092] The "means for analyzing a user's long-term eating and drinking habits" is a mechanism for collecting a user's past dietary data and analyzing the user's long-term eating and drinking habits based on that data.

[1093] "Means for analyzing the user's emotional state in real time" refers to a mechanism for detecting and analyzing the user's emotions in real time from facial expressions, voice, etc.

[1094] The "means for generating dietary improvement suggestions based on the results of the analysis of the emotional state" is a mechanism for generating individual dietary improvement suggestions based on the results of the user's emotional analysis and long-term eating and drinking habits.

[1095] The "means for presenting the generated diet improvement suggestions to the user" is a mechanism for transmitting the diet improvement suggestions generated by the server to the terminal and visually displaying them on the user interface.

[1096] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system is implemented in the following steps.

[1097] Hardware and Software Configuration

[1098] User's device

[1099] The user's smartphone or tablet device is used to take and upload images and display dietary improvement suggestions. The following applications are installed on the device:

[1100] Camera application: Ability to take photos of meals

[1101] Image processing application: Functions for pre-processing captured images

[1102] server

[1103] The server is the central component that analyzes images, stores data, analyzes emotions, and generates improvement recommendations. The main software used includes:

[1104] Image Recognition API: Generative AI models (e.g., TensorFlow, OpenCV) for extracting ingredient and nutrient information from images

[1105] Database: A database (e.g., MySQL) to store analysis results and user eating habits and emotion data.

[1106] Emotion analysis engine: Software for analyzing emotions from a user's facial expressions and voice (e.g., Microsoft Azure Cognitive Services)

[1107] Data processing flow

[1108] Image preprocessing

[1109] Users take a photo of their meal using their smartphone's camera application or select it from their camera roll, and then the image is preprocessed using the application's image processing function, which involves resizing the image (to 512x512 pixels) and removing noise.

[1110] Image analysis

[1111] The preprocessed image data is sent to a server, which uses an image recognition API to analyze the image content. The analysis extracts information about ingredients and nutrients, which is then stored in a database.

[1112] Analysis of eating and drinking habits and emotional states

[1113] The server retrieves the user's past dietary data from the database and analyzes their long-term eating and drinking habits. It also uses an emotion analysis engine to analyze the user's emotional state in real time. The analysis results are recorded in the database.

[1114] Generating and presenting dietary improvement suggestions

[1115] The server comprehensively analyzes eating habits and emotional states to generate personalized dietary improvement recommendations. This generation process uses the following generative AI model:

[1116] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[1117] The server then sends the generated dietary improvement suggestions to the user's device, which then displays the suggestions on a user interface. For example, if the user is feeling stressed, the server can suggest a relaxing herbal tea.

[1118] In this way, the present invention provides a system that combines image recognition technology, data analysis technology, and emotion recognition technology to realize effective meal suggestions in physical stores.

[1119] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1120] Step 1: User takes or uploads an image

[1121] The user takes a picture of the meal using the smartphone's camera application or selects an image from the camera roll. The input image is in a common image format such as JPEG or PNG. The output is the selected or captured raw image data.

[1122] Step 2: The device preprocesses the image

[1123] The device preprocesses the image taken or selected by the user. Specifically, it resizes the image (e.g., to 512x512 pixels) and denoises it. This process uses libraries such as Pillow and OpenCV. The input is raw image data. The output is preprocessed, clean image data.

[1124] Step 3: Send the preprocessed image data to the server

[1125] The device sends the preprocessed image data to the server. This communication is performed using an HTTP POST request. The input is the preprocessed image data. The output is the status of completion of transmission to the server.

[1126] Step 4: The server analyzes the image data

[1127] The server analyzes the received image data, using an image recognition API (e.g., TensorFlow or OpenCV) to extract information about ingredients and nutrients from the image. The input is the preprocessed image data, and the output is a detailed list of ingredients and nutrients.

[1128] Step 5: Save your ingredient and nutrition data

[1129] The server stores the resulting food and nutrient data in a database. This data is managed individually for each user. The input is a detailed list of food ingredients and nutrients. The output is a data entry stored in the database.

[1130] Step 6: The server analyzes your past eating and drinking habits

[1131] The server retrieves the user's past eating and drinking data from the database and analyzes their long-term eating and drinking habits. The input is the past eating and drinking data in the database. The output is the analyzed long-term eating and drinking habits data.

[1132] Step 7: The server analyzes the emotional state in real time

[1133] The server uses an emotion analysis engine (e.g., Microsoft Azure Cognitive Services) to analyze the user's real-time emotional state. In this process, facial and voice data are input. The input is real-time facial and voice data. The output is analyzed emotional state data.

[1134] Step 8: Generate dietary recommendations based on your emotional state

[1135] The server generates personalized dietary recommendations based on long-term eating and drinking habits and real-time emotional state, using a generative AI model and prompts such as:

[1136] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[1137] The input is data on eating habits and emotional state, and the output is detailed dietary improvement recommendations.

[1138] Step 9: Present the improvement suggestions to the user

[1139] The server sends the generated dietary improvement suggestions to the terminal, which then visually displays the improvement suggestions on a user interface. The input is the generated dietary improvement suggestions. The output is the improvement suggestions displayed to the user.

[1140] In this way, through each processing step, the user can be provided with dietary improvement suggestions that take into account their emotional state.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] [Fourth embodiment]

[1145] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1146] 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.

[1147] 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).

[1148] 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.

[1149] 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.

[1150] 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).

[1151] 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.

[1152] 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.

[1153] 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.

[1154] 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.

[1155] 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.

[1156] 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.

[1157] 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."

[1158] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[1159] Image upload and preprocessing

[1160] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[1161] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[1162] Image Recognition and Data Analysis

[1163] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[1164] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[1165] Analysis of eating and drinking habits

[1166] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. The server analyzes the user's eating and drinking patterns and nutritional intake trends, and identifies any nutrients that are clearly lacking or in excess based on data over a certain period of time (e.g., the past month). This is done by using a proprietary algorithm to perform a detailed analysis of the user's eating pattern trends.

[1167] Generate and present improvement proposals

[1168] The server generates specific dietary recommendations for the user based on the analysis of their eating habits. These recommendations are tailored to the user's individual eating habits and include short-term meal suggestions and long-term meal plans. For example, the server may recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[1169] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[1170] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[1171] Specific examples

[1172] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and discovers that they are lacking in protein. Based on this, the server suggests adding chicken to the next meal. The device then presents this suggestion to the user along with a specific recipe and encourages them to follow through.

[1173] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[1174] The processing flow will be explained below.

[1175] Step 1:

[1176] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[1177] Step 2:

[1178] The device processes the image received from the user, resizing it (e.g., to 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[1179] Step 3:

[1180] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[1181] Step 4:

[1182] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[1183] Step 5:

[1184] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[1185] Step 6:

[1186] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[1187] Step 7:

[1188] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[1189] Step 8:

[1190] The server collects the user's past meal data. Specifically, it retrieves all meal data for a specific period (e.g., the past month) from the database.

[1191] Step 9:

[1192] The server analyzes the user's eating habits, specifically analyzing daily nutrient balance, calorie intake, and food types to identify the user's eating patterns and identify any obvious nutrient deficiencies or excesses.

[1193] Step 10:

[1194] The server generates dietary improvement recommendations based on the analysis of eating and drinking habits, using an algorithm supervised by a nutritionist to create short-term meal suggestions and long-term meal plans.

[1195] Step 11:

[1196] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[1197] Step 12:

[1198] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[1199] Example 1

[1200] 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."

[1201] In recent years, health problems such as lifestyle-related diseases and obesity have been increasing, and approaches to prevent and improve these problems are needed. However, it is difficult to obtain a detailed understanding of each user's dietary content and eating habits and provide individualized improvement suggestions. Furthermore, users need specialized knowledge and time to record their own meals and properly manage their nutrition. The present invention aims to solve these problems and provide a system that allows users to easily analyze their own dietary content and obtain effective dietary improvement suggestions.

[1202] 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.

[1203] In this invention, the server includes means for collecting a user's past dietary data and analyzing their long-term eating and drinking habits, means for generating dietary improvement suggestions using a generative AI model based on the analysis results of the eating and drinking habits, and means for transmitting the generated dietary improvement suggestions to a terminal and visually presenting them to the user. This allows users to receive detailed nutritional analysis and visually receive individual improvement suggestions simply by uploading meal images.

[1204] A "user" is an entity that uses the system to analyze their own diet and receive dietary improvement suggestions.

[1205] "Terminal" refers to a device used by a user, such as a smartphone or tablet, that has functions such as receiving images, preprocessing, and sending data to a server.

[1206] The "server" is a central processing unit that receives data sent from the terminal, stores it in a database, analyzes images, and generates dietary improvement suggestions.

[1207] "Preprocessing" refers to the process of resizing the received image to a standard size, removing noise, and converting the format.

[1208] An "image recognition API" is an application programming interface for analyzing preprocessed image data and extracting information about ingredients and nutrients.

[1209] A "generative AI model" is an artificial intelligence model that generates individual dietary improvement suggestions based on the analysis of eating and drinking habits.

[1210] "Dietary improvement suggestions" refer to specific suggestions and recipes for optimizing nutritional balance based on the user's diet.

[1211] The "database" is a data storage location where the server saves and manages the image data and analysis results it receives, as well as the user's dietary history.

[1212] "User interface" refers to the screen and operating environment for visually presenting the generated dietary improvement suggestions to the user.

[1213] A "prompt sentence" is a natural language sentence that is input into a generative AI model based on data collected from the user.

[1214] The present invention is a system that allows users to upload photos of their meals, analyzes the photos to understand the meal contents, analyzes eating habits, and provides appropriate improvement suggestions. This system operates in cooperation with the user's terminal and a server, and a specific embodiment of the system is described below.

[1215] Image upload and preprocessing

[1216] Users open the application on their smartphones, tablets, or other devices and take or select from their camera roll an image of their meal to upload. The device then resizes the received image to a standard size (e.g., 512x512 pixels) and performs noise reduction. It also converts the image format from JPEG to PNG if necessary. This preprocessed image data is then sent to the server.

[1217] Image Recognition and Data Analysis

[1218] The server receives the image data sent from the device and stores it in a database. The stored image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API, which analyzes the image using a generative AI model. This image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[1219] The server receives the analysis results returned by the generative AI model and stores them in a database, which includes the ingredient list, the amount of each ingredient, calories, and detailed nutrition information.

[1220] Analysis of eating and drinking habits

[1221] The server also collects the user's past dietary data and uses a proprietary algorithm to analyze their long-term eating and drinking habits over a certain period of time (e.g., the past month), and can identify any obvious nutrient deficiencies or excesses.

[1222] Generate and present improvement proposals

[1223] The server generates specific dietary recommendations for the user based on the analysis of their eating and drinking habits. These recommendations are created using a generative AI model and are tailored to the individual user's eating habits. They include short-term meal suggestions and long-term meal plans. For example, they recommend foods to include in the next meal (e.g., eggs, fruits) and foods to avoid (e.g., high-fat foods).

[1224] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists). The device visually presents the improvement suggestions received from the server in a user interface, which is designed to be easy for users to understand.

[1225] Specific examples

[1226] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's eating habits and discovers, for example, that they are lacking in protein. Based on this analysis, the server suggests adding chicken to the next meal. The device then provides this suggestion to the user along with a specific recipe and encourages them to act. For example, a prompt might be, "Please add chicken to your next meal."

[1227] In this way, by combining image recognition technology and data analysis technology, the present invention can realize a system that analyzes each user's eating habits in detail and provides effective dietary improvement suggestions, allowing users to receive specific guidance to maintain and improve their health.

[1228] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1229] Step 1:

[1230] Users open the app on their smartphone or tablet and take a picture of their meal or select one from their camera roll and upload it. The input is the image taken or selected by the user, and the output is the uploaded image file. Specifically, the image file is selected or taken by operating the app's buttons, and is prepared to be sent to the server.

[1231] Step 2:

[1232] The device preprocesses the images received from the user by resizing them to a standard size (e.g., 512x512 pixels) and removing noise. It also converts the image format from JPEG to PNG if necessary. The input is the uploaded image, and the output is a preprocessed image file. Specifically, it uses an image processing library to change the resolution, apply a noise filter, and convert the format.

[1233] Step 3:

[1234] The terminal sends the preprocessed image data to the server. The input is the preprocessed image file, and the output is the image data sent to the server. Specifically, the terminal sends the image data to the server using an HTTP request.

[1235] Step 4:

[1236] The server receives image data sent from the terminal and stores it in a database. The input is the image data sent from the terminal, and the output is the image information stored in the database. Specifically, the reception listener on the server side receives the image data and writes it to the database.

[1237] Step 5:

[1238] The server sends a request to the image recognition API and analyzes the preprocessed image data. The input is the image data stored in the database, and the output is the analysis results. Specifically, the image recognition API is called and processing is performed to extract information about ingredients and components in the image.

[1239] Step 6:

[1240] The server saves the analysis results in a database. The input is the analysis results returned from the image recognition API, and the output is the analysis information saved in the database. Specifically, it analyzes the data structure of the analysis results and writes them to the database in an appropriate format.

[1241] Step 7:

[1242] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits using a proprietary algorithm. The input is the user's past dietary data stored in the database, and the output is the analysis results of their eating and drinking habits. Specifically, the server uses a data analysis library to aggregate past dietary data and analyze nutrient intake trends.

[1243] Step 8:

[1244] The server uses a generative AI model to generate dietary improvement suggestions based on the analysis results of eating and drinking habits. The input is the analysis results of eating and drinking habits, and the output is the generated dietary improvement suggestions. Specifically, the server inputs the eating and drinking habit data into the generative AI model, creates a prompt sentence and supplies it to the model, which then generates specific dietary improvement suggestions.

[1245] Step 9:

[1246] The server sends the generated dietary improvement suggestions to the terminal. The input is the generated dietary improvement suggestions, and the output is the dietary improvement suggestions sent to the terminal. Specifically, the server sends the generated text and data to the terminal via an HTTP request.

[1247] Step 10:

[1248] The device visually presents the improvement suggestions received from the server on a user interface. The input is the dietary improvement suggestions sent from the server, and the output is the suggestions displayed on the user interface. Specifically, the data received within the application is visually formatted and displayed in a format that is easy for the user to understand.

[1249] (Application example 1)

[1250] 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."

[1251] In modern society, with the development of the restaurant industry, many people are increasingly relying on eating out. However, when eating out, it can be difficult to accurately understand the nutritional balance and health effects of the meal. In particular, people who prioritize health management have limited means of verifying whether the meal they eat at a restaurant is in line with their nutritional goals. This has led to a need for an effective system to support dietary choices and health management.

[1252] 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.

[1253] In this invention, the server includes means for receiving images taken or uploaded by a user, means for preprocessing the received images, means for transmitting the preprocessed image data to the server, means for the server to analyze the preprocessed image data, means for generating nutrient and ingredient information based on the image analysis results, means for analyzing the user's long-term eating and drinking habits, means for generating dietary improvement suggestions based on the analysis results of the eating and drinking habits, means for presenting the generated dietary improvement suggestions to the user, means for taking images of dishes using smart glasses and transmitting them to the server, and means for the server to suggest alternative menu items to the user based on the analysis results, thereby enabling users to easily understand nutritional information for meals even when eating out and supporting healthy meal selection.

[1254] "User" refers to a person who uses the system.

[1255] "Photographing" refers to the act of acquiring an image using a camera device.

[1256] "Upload" refers to the act of sending data from a local device to a server.

[1257] "Image" refers to visual information acquired using a digital camera, smartphone, etc.

[1258] "Means of receiving" refers to the technical mechanism for obtaining data from outside.

[1259] "Preprocessing" refers to the processing of image data to convert it into a format suitable for analysis.

[1260] "Preprocessing means" refers to functions that perform processing on image data, such as noise removal and resizing.

[1261] "Preprocessed image data" refers to image data that has been subjected to appropriate processing before analysis.

[1262] "Server" refers to a computer system for processing and storing data.

[1263] "Transmission mechanism" refers to the technical mechanisms by which data is sent to other systems or devices.

[1264] "Means of analysis" refers to the technical capabilities to extract useful information from data.

[1265] "Nutrients" refer to the energy and components contained in food ingredients.

[1266] "Ingredients" refers to the raw materials that make up a dish.

[1267] "Means of generating information" refers to the technical mechanisms that create new information from the results of data analysis.

[1268] "Eating habits" refers to the eating patterns and tendencies that a user has chosen in the past.

[1269] "Means of analysis" refers to the technical function of finding patterns and characteristics in data.

[1270] "Means for generating dietary improvement suggestions" refers to the function of creating appropriate dietary suggestions based on the analysis results.

[1271] "Means of presentation" refers to the technical mechanisms by which information is visually displayed to the user.

[1272] "Smart glasses" refers to wearable devices with image capture capabilities.

[1273] "Menu Alternatives" refer to other meal choices that meet the user's health goals.

[1274] "Means of suggestion" refers to the technical functionality that presents options to the user.

[1275] The present invention provides a system for assisting users in making healthy food choices when eating out. Specific embodiments of the system are described below.

[1276] 1. Image Reception and Preprocessing

[1277] A user uses smart glasses to take an image of the food they want to choose at a restaurant. The smart glasses capture the image and store the data locally. The application on the smart glasses has a function to preprocess the image. Specifically, it resizes the image to 512x512 pixels and performs noise reduction using the OpenCV library. This preprocessed image data is then sent to the server.

[1278] 2. Image analysis and data generation

[1279] The server receives and analyzes the preprocessed image data sent from the device. The server then uses a generative AI model to analyze the image. This generative AI model extracts the ingredients and nutritional information contained in the dish from the image. The analysis results include a list of ingredients and detailed information about each nutrient (protein, fat, calories, etc.).

[1280] 3. Analysis of eating habits and generation of dietary improvement suggestions

[1281] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess. Based on the results of this analysis, the server generates specific dietary recommendations for the user. For example, it suggests ingredients to add to the user's next meal or alternative menu items.

[1282] 4. Proposal for improvement

[1283] The server sends the generated dietary suggestions to the smart glasses and visually presents them to the user through the smart glasses' user interface, allowing the user to understand the nutritional information of their own meals and alternative menus that meet their health goals in real time.

[1284] Examples and prompts

[1285] For example, if a user orders a steak at a restaurant, they can take a picture of the steak with the smart glasses. The app will analyze the image and display the steak's nutritional information (protein, fat, calories, etc.) and suggest alternative dishes like salads or vegetable soups based on the user's nutritional goals.

[1286] Prompt Sentence Examples

[1287] "I'm planning to have steak for lunch today. Could you please provide me with nutritional information for this dish and suggest alternatives to make it more nutritious?"

[1288] Thus, by leveraging image capture using smart glasses and generative AI models, the system of the present invention helps users make healthy food choices even when dining out.

[1289] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1290] Step 1: Image capture and pre-processing

[1291] A user uses smart glasses to take an image of the dish they are selecting at a restaurant. The smart glasses then use their image capture function to capture the image data of the dish and store it on their local device. The image is then preprocessed. Specifically, the image is resized (to 512x512 pixels) and noise is removed. This generates preprocessed image data suitable for analysis.

[1292] Input: Raw food image data

[1293] Data processing: resizing, noise removal

[1294] Output: Preprocessed image data

[1295] Step 2: Sending preprocessed image data

[1296] The device (smart glasses) sends the preprocessed image data to the server, where it is encoded in an appropriate format (e.g., PNG format) and uploaded to the server via the network.

[1297] Input: Preprocessed image data

[1298] Data processing: Encoding image data

[1299] Output: Image data sent to the server

[1300] Step 3: Image analysis

[1301] The server receives the image data sent from the device and performs image analysis using a generative AI model. This generative AI model (e.g., YOLO or ResNet) extracts the ingredients and nutritional information contained in the dish from the image. The analysis results are output as an ingredient list and detailed information on each nutrient.

[1302] Input: Preprocessed image data

[1303] Data Computing: Image Analysis with Generative AI Models

[1304] Output: Ingredient list, nutritional information

[1305] Step 4: Analyze eating and drinking habits

[1306] The server retrieves the user's past dietary data from a database and analyzes their long-term eating and drinking habits. Using a proprietary algorithm, the server analyzes the user's nutritional intake trends and identifies nutrients that may be lacking or in excess.

[1307] Input: User's past meal data

[1308] Data Computing: Algorithms for Analyzing Eating and Drinking Habits

[1309] Output: Nutritional intake trends and problems

[1310] Step 5: Generate dietary improvement suggestions

[1311] Based on the analysis of the eating and drinking habits, the server generates specific dietary recommendations for the user, including suggestions for alternative menu items to supplement necessary nutrients. The recommendations are customized for each user.

[1312] Input: Nutritional intake trends, problems

[1313] Data Computing: Diet Improvement Algorithms

[1314] Output: Specific dietary improvement suggestions

[1315] Step 6: Propose improvements

[1316] The server transmits the generated dietary suggestions to the smart glasses, which visually display the suggestions to the user in real time through a user interface, allowing the user to make healthy eating choices on the spot.

[1317] Input: Specific dietary improvement suggestions

[1318] Data processing: Display on the user interface

[1319] Output: Visually presented improvement suggestions to the user

[1320] This series of steps helps users make healthy food choices even when eating out.

[1321] 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.

[1322] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system operates in cooperation with the user's terminal, a server, and an emotion engine, and a specific embodiment thereof is described below.

[1323] Image upload and preprocessing

[1324] Users upload images of their meals to the app using their smartphones, tablets, or other devices, either by selecting an image from their camera roll or by taking a photo of their meal in real time using their camera.

[1325] The device does not accept the image received from the user as is, but performs certain preprocessing. Specifically, the image is resized to a standard size (e.g., 512x512 pixels), noise is removed, and the image format is converted as needed (e.g., from JPEG to PNG). This preprocessed image data is then sent to the server.

[1326] Image Recognition and Data Analysis

[1327] The server receives the image data sent from the device and stores it in a database. The saved image data is kept in a format suitable for analysis. The server then sends a request to an image recognition API to analyze the image. This generative AI image recognition API identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[1328] The server receives the analysis results returned by the generative AI and stores them in a database, which includes a list of ingredients, their amounts, calories, and detailed nutritional information.

[1329] Analysis of eating and drinking habits and emotional states

[1330] The server also collects the user's past dietary data and analyzes their long-term eating and drinking habits. It also uses an emotion engine to recognize the user's emotional state in real time. The emotion engine detects emotions from the user's facial expressions and voice, and records the results in a database.

[1331] The server combines the collected emotion data with data on eating and drinking habits and analyzes them, for example, to analyze how a particular meal affects the user's emotions and determine the state of the user when they ate a particular meal.

[1332] Generate and present improvement proposals

[1333] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[1334] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[1335] The terminal visually presents the improvement proposals received from the server to the user. The improvement proposals are displayed on a user interface that is designed to be easily understood and implemented by the user.

[1336] Specific examples

[1337] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the salad's ingredients (lettuce, tomato, cheese, etc.) and the nutrients they contain. Based on the analysis results, the server analyzes the user's long-term eating habits and their emotional state while eating the salad. Based on this, the server can suggest relaxing foods to add to the user's next meal, taking into account the emotional impact of a particular meal.

[1338] In this way, by combining image recognition technology, data analysis technology, and emotion recognition technology, the present invention can realize a system that analyzes the eating habits and emotional state of each individual user in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[1339] The processing flow will be explained below.

[1340] Step 1:

[1341] Users upload images of their meals to the app by tapping the "Upload Image" button within the app and selecting an image from their camera roll or taking a photo of their meal in real time using their camera.

[1342] Step 2:

[1343] The device preprocesses the image received from the user by resizing it to a standard size (e.g., 512x512 pixels), removing noise, and converting the image format from JPEG to PNG if necessary.

[1344] Step 3:

[1345] The device sends the preprocessed image data to the server using an HTTP request, adding metadata (e.g., user ID, timestamp) to the image data.

[1346] Step 4:

[1347] The server stores the received image data, specifically, the image data and metadata in a database so that they can be linked to analysis results later.

[1348] Step 5:

[1349] The server sends the image data to the generative AI's image recognition API, which sends an analysis request to identify ingredients and dish names.

[1350] Step 6:

[1351] The generative AI analyzes the image and returns results, specifically extracting a list of ingredients and dish names, as well as the amount, calories, and nutritional information for each ingredient.

[1352] Step 7:

[1353] The server receives the analysis results and saves them as analysis data in a database, linking them to each user.

[1354] Step 8:

[1355] The server uses an emotion engine to recognize the user's emotional state. Specifically, it acquires emotion data from the user's facial expressions and voice and records the results in a database.

[1356] Step 9:

[1357] The server collects the user's past meal data and emotion data. It retrieves all meal data and emotion data for a specific period (e.g., the past month) from the database.

[1358] Step 10:

[1359] The server analyzes the trends in eating habits and emotional state. Specifically, it analyzes daily nutrient balance, calorie intake, food types, and emotional state to identify the user's eating patterns and emotional trends. It identifies obvious nutrient deficiencies or excesses, as well as factors that cause emotional fluctuations.

[1360] Step 11:

[1361] The server generates dietary improvement suggestions based on the analysis of the user's eating habits and emotional state. Specifically, it makes dietary suggestions that address the user's emotional state, such as stress or fatigue. Using an algorithm supervised by a nutritionist, it creates short-term dietary suggestions and long-term meal plans.

[1362] Step 12:

[1363] The server sends the generated improvement suggestions to the device, including details of the meal suggestions (e.g., specific recipes and food lists).

[1364] Step 13:

[1365] The terminal displays the received improvement proposal to the user. Specifically, the contents of the improvement proposal are displayed on the user interface, providing a visually easy-to-understand presentation.

[1366] Example 2

[1367] 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."

[1368] In today's world, healthy eating habits are becoming increasingly important, but it is difficult for users to obtain appropriate dietary improvement suggestions based on their own eating habits and emotional state. Conventional systems have had difficulty analyzing a user's eating habits and emotional state in detail and providing dietary improvement suggestions tailored to individual needs. In particular, few systems provide improvement suggestions that take into account the relationship between dietary content and emotional state. As a result, users are unable to receive optimal dietary suggestions tailored to their emotional state. The present invention aims to provide a system that analyzes a user's eating habits and emotional state in detail and provides specific and effective dietary improvement suggestions tailored to the needs of each individual user.

[1369] 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.

[1370] In this invention, the server includes a means for generating information on nutrients and ingredients based on the image analysis results, a means for analyzing the user's long-term eating habits, and a means for analyzing the user's emotional state, which allows for detailed analysis of the user's eating habits and emotional state and the generation of dietary improvement proposals tailored to each individual user.

[1371] A "user" is someone who uses the system to upload photos of their meals and receive suggestions for improving their meals.

[1372] A "terminal" is a device such as a smartphone or tablet that a user uses to take or upload images.

[1373] A "server" is a computer system that receives image data sent from a user's terminal and analyzes and stores the image data.

[1374] "Image data" is data based on photos of meals taken or uploaded by users.

[1375] "Preprocessing" refers to the process of converting image data into a format suitable for analysis, and specifically includes resizing, noise removal, and format conversion.

[1376] "Image analysis" is the process of analyzing pre-processed image data to identify its contents, such as ingredients, nutrients, and calories.

[1377] "Nutrient and ingredient information" refers to information such as the ingredients contained in a meal, their amounts, and calories, as identified through image analysis.

[1378] "Dietary habits" refers to the history of meals a user has eaten in the past and their patterns.

[1379] The "emotional state" is the psychological state of the user that is detected from the user's facial expression, voice, and the like.

[1380] "Improvement suggestions" are specific dietary suggestions provided to the user based on the results of image analysis, as well as the analysis of eating habits and emotional state.

[1381] A "user interface" is a display means for visually presenting information to a user on a terminal.

[1382] The present invention is a system that analyzes food images taken or uploaded by a user and provides dietary improvement suggestions based on the user's eating habits and emotional state. Specifically, the system operates by linking the user's terminal, a server, and an emotion engine. Specific embodiments of the system are described below.

[1383] Image upload and preprocessing

[1384] Users upload photos of their meals to the app using their smartphones, tablets, or other devices. They can either select an image from their camera roll or take a photo of their meal in real time using their camera. The app guides users through the process.

[1385] The device preprocesses the images received from the user. This includes resizing the image (e.g., resizing to 512x512 pixels), removing noise, and converting the image format (e.g., converting from JPEG to PNG). An open-source image processing library (e.g., OpenCV) is used for preprocessing. The preprocessed images are then sent to the server.

[1386] Image Recognition and Data Analysis

[1387] The server receives the preprocessed image data sent from the device and stores it in a database. The database uses a storage management system (e.g., MySQL). The server then calls an image recognition API (e.g., Google Vision API) to analyze the image. The image recognition API of this generative AI model identifies the ingredients and dish names contained in the image, as well as the amount and calories of each ingredient.

[1388] The analysis results are stored in a database as a list of ingredients, nutrient amounts, calories, and other details, which can then be used for further data analysis and to generate dietary improvement recommendations.

[1389] Analysis of eating and drinking habits and emotional states

[1390] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits. The past dietary data is retrieved from a database and analyzed using statistical analysis tools (e.g., Python and the pandas library). The server also has the ability to recognize the user's emotional state in real time using an emotion engine (e.g., Affectiva). The emotion engine detects emotions from the user's facial expressions and voice and records the results in a database.

[1391] The server combines and analyzes the collected emotional data with data on eating and drinking habits, allowing it to understand the emotional impact of a particular meal on the user and the state of mind in which the user ate a particular meal.

[1392] Generate and present improvement proposals

[1393] The server generates specific dietary recommendations for each user based on the analysis of their eating habits and emotional state. These recommendations are tailored to each user's individual eating habits and emotional state and include short-term meal suggestions and long-term meal plans. For example, a user experiencing stress may be recommended foods with a relaxing effect, while a user experiencing fatigue may be recommended foods that replenish energy.

[1394] The improvement proposal also includes details of the meal suggestion (for example, a specific recipe or a list of foods). An example of a prompt generated using a generative AI model is as follows:

[1395] "Analyze a salad image uploaded by a user, identify the ingredients and the amounts of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide next meal suggestions that take into account the user's emotional state."

[1396] The server sends the generated improvement proposals to the terminal, which visually displays them on a user interface that is designed to be easy for the user to understand and put into practice.

[1397] Specific examples

[1398] For example, if a user uploads an image of a salad for lunch, the device preprocesses the image and sends it to the server. The server uses an image recognition API to identify the ingredients (lettuce, tomato, cheese, etc.) and their nutrients. Based on the analysis results, the server analyzes the user's long-term eating habits and emotional state. This allows the server to consider the emotional impact of a particular meal and suggest relaxing foods to add to the user's next meal.

[1399] In this way, the present invention combines image recognition technology, data analysis technology, and emotion recognition technology to realize a system that analyzes a user's eating habits and emotional state in detail and provides effective dietary improvement suggestions, allowing the user to receive specific dietary advice that takes into account their own health and psychological state.

[1400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1401] Step 1:

[1402] Users upload photos of their meals using an app on their smartphone or tablet.

[1403] Input: An image of a meal taken or selected by the user.

[1404] How it works: The user uses the camera to take a photo in real time or selects an image from the camera roll.

[1405] Output: Image files of the selected or photographed meal.

[1406] Step 2:

[1407] The terminal pre-processes the received image.

[1408] Input: Raw image files uploaded by the user.

[1409] What it does: The device resizes the image to 512x512 pixels, denoises it, and optionally converts it from JPEG to PNG format using an image processing library such as OpenCV.

[1410] Output: Preprocessed image files.

[1411] Step 3:

[1412] The terminal transmits the preprocessed image to the server.

[1413] Input: Preprocessed image files.

[1414] Operation: The terminal uploads preprocessed image data to the server via the network.

[1415] Output: Preprocessed image data sent to the server.

[1416] Step 4:

[1417] The server receives the pre-processed image data and stores it in a database.

[1418] Input: Preprocessed image data sent from the device.

[1419] Operation: The server stores the received image data in a database using a storage management system such as MySQL.

[1420] Output: Image data stored in a database.

[1421] Step 5:

[1422] The server uses an image recognition API to analyze the meal contents.

[1423] Input: Preprocessed image data stored in a database.

[1424] How it works: The server calls an image recognition API, such as the Google Vision API, to analyze the stored image and identify the ingredients, dish name, amount of each ingredient, and calories.

[1425] Output: A list of ingredients, their amounts, and calorie analysis results.

[1426] Step 6:

[1427] The server stores the analysis results in a database.

[1428] Input: Analysis results obtained from the image recognition API.

[1429] How it works: The server stores the results of the analysis in a database, which is done by writing data using SQL queries.

[1430] Output: A list of ingredients stored in a database, along with their amounts and calorie information.

[1431] Step 7:

[1432] The server collects the user's past dietary data and analyzes their long-term eating and drinking habits.

[1433] Input: Historical dietary data stored in a database.

[1434] How it works: The server collects historical dietary data and uses statistical analysis tools (e.g., Python's pandas library) to analyze long-term eating and drinking habits.

[1435] Output: Analysis results about the user's eating and drinking habits.

[1436] Step 8:

[1437] The server uses an emotion engine to analyze the user's emotional state.

[1438] Input: User's facial and voice data.

[1439] How it works: The server uses an emotion engine such as Affectiva to detect the user's emotional state from their facial expressions and voice, and records the results in a database.

[1440] Output: Analysis results about the user's emotional state.

[1441] Step 9:

[1442] The server generates dietary improvement suggestions based on the analysis of eating habits and emotional state.

[1443] Input: Analysis of eating and drinking habits and emotional state.

[1444] How it works: The server integrates this data and uses a generative AI model to generate specific, personalized dietary recommendations. Prompts include: "Analyze a salad image uploaded by the user, identify its ingredients and the amount of each ingredient, and calculate the nutritional value of the meal. Based on the results, provide the next meal suggestion, taking into account the user's emotional state."

[1445] Output: Improvement proposal generation results.

[1446] Step 10:

[1447] The server transmits the generated improvement plan to the terminal.

[1448] Input: The data of the generated improvement proposal.

[1449] Operation: The server transfers data using a network protocol to send the generated improvement proposal to the terminal.

[1450] Output: Improvement suggestion data sent to the device.

[1451] Step 11:

[1452] The terminal presents improvement proposals to the user.

[1453] Input: Improvement proposal data sent from the server.

[1454] Operation: The device visually displays the received improvement suggestions in the user interface, making it easier for the user to understand the suggestions.

[1455] Output: Suggested improvements displayed in the user interface.

[1456] Through the above processing steps, the system of the present invention can analyze the user's eating habits and emotional state, generate dietary improvement suggestions based on the analysis, and provide them to the user.

[1457] (Application example 2)

[1458] 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."

[1459] While conventional dietary analysis systems can suggest meals based on a user's eating habits, they are unable to make suggestions that take into account the user's emotional state. Furthermore, systems designed for use in brick-and-mortar establishments such as restaurants and cafes have not yet become widespread. This has made it difficult to effectively support the improvement of a user's health and psychological state.

[1460] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state in real time, means for generating diet improvement suggestions based on the analysis results of the emotional state, and means for presenting the generated diet improvement suggestions to the user. This makes it possible to make diet suggestions that take the user's emotional state into consideration.

[1461] "Means for receiving images" refers to a mechanism by which the terminal receives image data taken or uploaded by the user.

[1462] The "means for preprocessing images" is a mechanism for resizing received image data to a certain standard size and performing preprocessing such as noise removal and format conversion.

[1463] The "means for transmitting image data to a server" is a mechanism for transferring preprocessed image data to a server.

[1464] "Means for the server to analyze preprocessed image data" refers to a mechanism for receiving preprocessed image data on the server and analyzing it using an image recognition API.

[1465] The "means for generating information on nutrients and ingredients based on the image analysis results" is a mechanism for generating information on ingredients and nutrients extracted from the analyzed image data.

[1466] The "means for analyzing a user's long-term eating and drinking habits" is a mechanism for collecting a user's past dietary data and analyzing the user's long-term eating and drinking habits based on that data.

[1467] "Means for analyzing the user's emotional state in real time" refers to a mechanism for detecting and analyzing the user's emotions in real time from facial expressions, voice, etc.

[1468] The "means for generating dietary improvement suggestions based on the results of the analysis of the emotional state" is a mechanism for generating individual dietary improvement suggestions based on the results of the user's emotional analysis and long-term eating and drinking habits.

[1469] The "means for presenting the generated diet improvement suggestions to the user" is a mechanism for transmitting the diet improvement suggestions generated by the server to the terminal and visually displaying them on the user interface.

[1470] The present invention is a system that uploads images of a user's meals, analyzes the images to understand the meal contents, and further analyzes the user's eating habits and emotional state to provide appropriate improvement suggestions. This system is implemented in the following steps.

[1471] Hardware and Software Configuration

[1472] User's device

[1473] The user's smartphone or tablet device is used to take and upload images and display dietary improvement suggestions. The following applications are installed on the device:

[1474] Camera application: Ability to take photos of meals

[1475] Image processing application: Functions for pre-processing captured images

[1476] server

[1477] The server is the central component that analyzes images, stores data, analyzes emotions, and generates improvement recommendations. The main software used includes:

[1478] Image Recognition API: Generative AI models (e.g., TensorFlow, OpenCV) for extracting ingredient and nutrient information from images

[1479] Database: A database (e.g., MySQL) to store analysis results and user eating habits and emotion data.

[1480] Emotion analysis engine: Software for analyzing emotions from a user's facial expressions and voice (e.g., Microsoft Azure Cognitive Services)

[1481] Data processing flow

[1482] Image preprocessing

[1483] Users take a photo of their meal using their smartphone's camera application or select it from their camera roll, and then the image is preprocessed using the application's image processing function, which involves resizing the image (to 512x512 pixels) and removing noise.

[1484] Image analysis

[1485] The preprocessed image data is sent to a server, which uses an image recognition API to analyze the image content. The analysis extracts information about ingredients and nutrients, which is then stored in a database.

[1486] Analysis of eating and drinking habits and emotional states

[1487] The server retrieves the user's past dietary data from the database and analyzes their long-term eating and drinking habits. It also uses an emotion analysis engine to analyze the user's emotional state in real time. The analysis results are recorded in the database.

[1488] Generating and presenting dietary improvement suggestions

[1489] The server comprehensively analyzes eating habits and emotional states to generate personalized dietary improvement recommendations. This generation process uses the following generative AI model:

[1490] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[1491] The server then sends the generated dietary improvement suggestions to the user's device, which then displays the suggestions on a user interface. For example, if the user is feeling stressed, the server can suggest a relaxing herbal tea.

[1492] In this way, the present invention provides a system that combines image recognition technology, data analysis technology, and emotion recognition technology to realize effective meal suggestions in physical stores.

[1493] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1494] Step 1: User takes or uploads an image

[1495] The user takes a picture of the meal using the smartphone's camera application or selects an image from the camera roll. The input image is in a common image format such as JPEG or PNG. The output is the selected or captured raw image data.

[1496] Step 2: The device preprocesses the image

[1497] The device preprocesses the image taken or selected by the user. Specifically, it resizes the image (e.g., to 512x512 pixels) and denoises it. This process uses libraries such as Pillow and OpenCV. The input is raw image data. The output is preprocessed, clean image data.

[1498] Step 3: Send the preprocessed image data to the server

[1499] The device sends the preprocessed image data to the server. This communication is performed using an HTTP POST request. The input is the preprocessed image data. The output is the status of completion of transmission to the server.

[1500] Step 4: The server analyzes the image data

[1501] The server analyzes the received image data, using an image recognition API (e.g., TensorFlow or OpenCV) to extract information about ingredients and nutrients from the image. The input is the preprocessed image data, and the output is a detailed list of ingredients and nutrients.

[1502] Step 5: Save your ingredient and nutrition data

[1503] The server stores the resulting food and nutrient data in a database. This data is managed individually for each user. The input is a detailed list of food ingredients and nutrients. The output is a data entry stored in the database.

[1504] Step 6: The server analyzes your past eating and drinking habits

[1505] The server retrieves the user's past eating and drinking data from the database and analyzes their long-term eating and drinking habits. The input is the past eating and drinking data in the database. The output is the analyzed long-term eating and drinking habits data.

[1506] Step 7: The server analyzes the emotional state in real time

[1507] The server uses an emotion analysis engine (e.g., Microsoft Azure Cognitive Services) to analyze the user's real-time emotional state. In this process, facial and voice data are input. The input is real-time facial and voice data. The output is analyzed emotional state data.

[1508] Step 8: Generate dietary recommendations based on your emotional state

[1509] The server generates personalized dietary recommendations based on long-term eating and drinking habits and real-time emotional state, using a generative AI model and prompts such as:

[1510] Example prompt: "Analyze a user-uploaded image of a salad and identify its ingredients and nutrients. Also, suggest foods that have a relaxing effect if the user is under stress."

[1511] The input is data on eating habits and emotional state, and the output is detailed dietary improvement recommendations.

[1512] Step 9: Present the improvement suggestions to the user

[1513] The server sends the generated dietary improvement suggestions to the terminal, which then visually displays the improvement suggestions on a user interface. The input is the generated dietary improvement suggestions. The output is the improvement suggestions displayed to the user.

[1514] In this way, through each processing step, the user can be provided with dietary improvement suggestions that take into account their emotional state.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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.

[1520] 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.

[1521] 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).

[1522] 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.

[1523] 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."

[1524] 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.

[1525] 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).

[1526] 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.

[1527] 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.

[1528] 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.

[1529] 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.

[1530] 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.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] 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.

[1536] The following is further disclosed regarding the above embodiment.

[1537] (Claim 1)

[1538] means for receiving images taken or uploaded by a user;

[1539] means for pre-processing the received image;

[1540] means for transmitting the preprocessed image data to a server;

[1541] means for the server to analyze the preprocessed image data;

[1542] A means for generating information on nutrients and ingredients based on the image analysis results;

[1543] a means for analyzing a user's eating and drinking habits over time;

[1544] A means for generating dietary improvement suggestions based on the analysis results of eating and drinking habits;

[1545] means for presenting the generated dietary improvement suggestions to a user;

[1546] A system including:

[1547] (Claim 2)

[1548] 10. The system of claim 1, further comprising: providing the user with detailed information about the generated dietary improvement suggestions.

[1549] (Claim 3)

[1550] 10. The system of claim 1, wherein the dietary improvement suggestions are visually displayed in a user interface.

[1551] "Example 1"

[1552] (Claim 1)

[1553] means for receiving images taken or uploaded by a user;

[1554] pre-processing means for resizing, denoising and format converting the received image;

[1555] means for transmitting the preprocessed image data to a server;

[1556] A means for the server to store the image data in a database;

[1557] A means for the server to analyze the preprocessed image data using an image recognition API;

[1558] A means for generating information on nutrients and ingredients based on the image analysis results;

[1559] a means for collecting a user's past dietary data and analyzing long-term eating and drinking habits;

[1560] A means for generating dietary improvement suggestions using a generative AI model based on the analysis results of eating and drinking habits;

[1561] means for transmitting the generated dietary improvement suggestions to a terminal and visually presenting the suggestions to the user;

[1562] A system including:

[1563] (Claim 2)

[1564] 2. The system according to claim 1, wherein detailed information about the generated dietary improvement plan is presented to the user as a specific recipe.

[1565] (Claim 3)

[1566] 10. The system of claim 1, wherein the meal suggestion details are generated using prompt sentences and visually displayed in a user interface.

[1567] "Application Example 1"

[1568] (Claim 1)

[1569] means for receiving images taken or uploaded by a user;

[1570] means for pre-processing the received image;

[1571] means for transmitting the preprocessed image data to a server;

[1572] means for the server to analyze the preprocessed image data;

[1573] A means for generating information on nutrients and ingredients based on the image analysis results;

[1574] a means for analyzing a user's eating and drinking habits over time;

[1575] A means for generating dietary improvement suggestions based on the analysis results of eating and drinking habits;

[1576] means for presenting the generated dietary improvement suggestions to a user;

[1577] A means for taking an image of a dish using smart glasses and transmitting the image to a server;

[1578] The server proposes an alternative menu to the user based on the analysis results.

[1579] A system including:

[1580] (Claim 2)

[1581] 10. The system of claim 1, further comprising: providing the user with detailed information about the generated dietary improvement suggestions.

[1582] (Claim 3)

[1583] 10. The system of claim 1, wherein the dietary improvement suggestions are visually displayed on a user interface of the smart glasses.

[1584] "Example 2: Combining Emotion Engines"

[1585] (Claim 1)

[1586] means for receiving images taken or uploaded by a user;

[1587] means for pre-processing the received image;

[1588] means for transmitting the preprocessed image data to a server;

[1589] means for the server to analyze the preprocessed image data;

[1590] A means for generating information on nutrients and ingredients based on the image analysis results;

[1591] a means for analyzing a user's eating and drinking habits over time;

[1592] means for analyzing the emotional state of a user;

[1593] means for generating dietary improvement recommendations based on the analysis of eating habits and emotional states;

[1594] means for presenting the generated dietary improvement suggestions to a user;

[1595] A system including:

[1596] (Claim 2)

[1597] 10. The system of claim 1, further comprising: providing the user with detailed information about the generated dietary improvement suggestions.

[1598] (Claim 3)

[1599] 10. The system of claim 1, wherein the dietary improvement suggestions are visually displayed in a user interface.

[1600] "Application example 2 when combining emotion engines"

[1601] (Claim 1)

[1602] means for receiving images taken or uploaded by a user;

[1603] means for pre-processing the received image;

[1604] means for transmitting the preprocessed image data to a server;

[1605] means for the server to analyze the preprocessed image data;

[1606] A means for generating information on nutrients and ingredients based on the image analysis results;

[1607] a means for analyzing a user's eating and drinking habits over time;

[1608] means for analyzing the user's emotional state in real time;

[1609] A means for generating dietary improvement suggestions based on the analysis results of the emotional state;

[1610] means for presenting the generated dietary improvement suggestions to a user;

[1611] A system including:

[1612] (Claim 2)

[1613] 10. The system of claim 1, further comprising: providing the user with detailed information about the generated dietary improvement suggestions.

[1614] (Claim 3)

[1615] 10. The system of claim 1, wherein the dietary improvement suggestions are visually displayed in a user interface. [Explanation of symbols]

[1616] 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. means for receiving images taken or uploaded by a user; means for pre-processing the received image; means for transmitting the preprocessed image data to a server; means for the server to analyze the preprocessed image data; A means for generating information on nutrients and ingredients based on the image analysis results; a means for analyzing a user's eating and drinking habits over time; A means for generating dietary improvement suggestions based on the analysis results of eating and drinking habits; means for presenting the generated dietary improvement suggestions to a user; A system including:

2. The system of claim 1 , further comprising: providing the user with detailed information about the generated dietary improvement suggestions.

3. The system of claim 1 , wherein the dietary improvement suggestions are visually displayed in a user interface.

Images