system

Abstract

To provide a health management system that automatically analyzes meal photos taken by users and calculates calories and suggests nutritional balance. [Solution] The system includes: a means for a user to take photos of their meals and save them in a photo folder; a means for the device to monitor the photo folder and detect new photos; a means for the device to upload new photos to a server; a means for the server to analyze the received photo data; a means for the server to calculate calories and nutrients based on the analysis results; a means for the server to save the calculation results in cumulative data for each user; a means for the server to generate health advice using a generation AI; a means for the server to send the advice to the device via push notification; and a means for the device to notify the user of the advice and display it within the app.

Description

[Technical Field]

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

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

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

[0004] Conventional health management apps require users to take photos of their meals, register them in the app, and manually enter the information. This manual input process is time-consuming for users, which can make it difficult for them to continue using the app. Furthermore, the need for specialized knowledge to calculate the nutritional balance and calories of meals makes it impractical for many users. Therefore, there is a need to solve these issues and realize a health management system that anyone can easily continue. [Means for solving the problem]

[0005] The present invention is a health management system that automatically analyzes food photos taken by a user, calculates calories, and suggests nutritional balance. The system of the present invention includes the following means:

[0006] A way for users to take photos of their meals and save them in a photo folder.

[0007] A way for your device to monitor your photo folders for new photos.

[0008] A means for a device to upload new photos to a server.

[0009] A means for analyzing the photo data received by the server.

[0010] A method by which the server calculates calories and nutrients based on the analysis results.

[0011] A means by which the server stores the results of calculations in per-user cumulative data.

[0012] A means for the server to generate health advice using generative AI.

[0013] A means for the server to send advice to the device via push notification.

[0014] A means for the device to notify the user of advice and display it within the app.

[0015] This allows users to effortlessly manage their diet and supports continuous health management.In addition, the advanced food ingredient identification technology using an image processing engine and personalized health advice using generative AI provide specific and appropriate nutritional management.

[0016] "User" refers to an individual who uses this system to manage their diet.

[0017] "Device" refers to an electronic device such as a smartphone or tablet owned by a user, on which a health management app is installed.

[0018] "Server" refers to a computer system for analyzing, storing, and processing data using generative AI models.

[0019] "Photo folder" refers to the storage area that stores image files saved on the device.

[0020] "Monitoring program" refers to software that runs on a device to detect changes in a photo folder.

[0021] "Uploading" refers to the process of sending data (in this case, food photos) from your device to a server.

[0022] "Image processing engine" refers to software that analyzes received photo data and identifies the ingredients and their amounts contained in the photo.

[0023] "Calculating calories and nutrients" refers to the process of calculating the energy content and nutritional components of food based on the ingredient information identified by the image processing engine.

[0024] "Cumulative data" refers to data that records and accumulates information about individual user's dietary habits and nutritional information.

[0025] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and generates appropriate health advice for users.

[0026] "Push notification" refers to a message transmission technology that sends advice and information from a server to a device in real time.

[0027] "Displayed within the app" refers to a state in which the user can view advice and information on the screen of the health management application on the device. [Brief explanation of the drawings]

[0028] [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

[0029] 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.

[0030] First, the terms used in the following description will be explained.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] [First embodiment]

[0037] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0038] 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.

[0039] 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).

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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."

[0049] This invention provides a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when a user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0050] System Overview

[0051] 1. User Action:

[0052] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[0053] 2. Device monitoring and notifications:

[0054] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[0055] 3. Upload to Cloud:

[0056] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[0057] 4. Parsing on the server:

[0058] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[0059] 5. Calorie and Nutritional Value Calculator:

[0060] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[0061] 6. Counting and Storage:

[0062] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[0063] 7. Generative AI Advice:

[0064] The server uses a generative AI model to generate specific health advice based on the user's cumulative data and their most recent dietary habits, including suggestions for dietary improvements and supplements.

[0065] 8. Notification and Display of Advice:

[0066] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0067] Specific examples

[0068] Example 1: Breakfast analysis and advice

[0069] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0070] Example 2: Lunch analysis and advice

[0071] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[0072] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user takes a photo of their meal and saves it to the photo folder on their smartphone. The user opens the camera app, takes a photo of the meal, and saves it to the photo folder naturally without any special operation.

[0076] Step 2:

[0077] Your device will run a background service to monitor your photo folder and detect new photos. The monitoring program will periodically scan your photo folder to check if any new photo files have been added.

[0078] Step 3:

[0079] When the device detects a new meal photo, it calls an API to upload the photo and user ID to the server. Here, the path to the photo file and the user ID information are sent to the server in the form of a POST request.

[0080] Step 4:

[0081] The server receives the HTTP request, saves the photo data in the analysis directory, and prepares to pass the photo data to the image processing engine as an image analysis job.

[0082] Step 5:

[0083] The server's image processing engine analyzes the photo to identify ingredients and their quantities. The image processing engine uses machine learning models to scan the photo and output a bounding box, name, and estimated quantity for each ingredient.

[0084] Step 6:

[0085] The server calculates calories and nutrients based on the output from the image processing engine, referencing the nutritional information for each ingredient stored in the database to calculate the total calories, protein, fat, carbohydrates, etc. of the identified ingredients.

[0086] Step 7:

[0087] The server stores the calculation results as cumulative data for each user. Each user's dietary history and nutritional information are recorded in a database and managed cumulatively.

[0088] Step 8:

[0089] The server generates health advice using a generative AI model based on the user's cumulative data and latest dietary information. The generative AI model takes the user's current situation into consideration and outputs specific advice and improvement suggestions in text format.

[0090] Step 9:

[0091] The server generates health advice and sends it to the device via push notifications, which are sent in real time via APNs or Firebase Cloud Messaging services.

[0092] Step 10:

[0093] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[0094] Example 1

[0095] 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."

[0096] Conventional health management systems require users to manually input their dietary information, which is cumbersome and time-consuming. Furthermore, there are limitations to the accuracy of nutritional balance and calorie calculation, making it difficult to provide individually optimized advice. The present invention aims to solve these problems and realize automated dietary management and highly accurate nutritional balance recommendations.

[0097] 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.

[0098] In this invention, the server includes a means for analyzing photos of meals taken by the user and identifying ingredients and their amounts, a means for calculating calories and nutrients based on the analysis results, and a means for generating individually optimized health advice using a generative AI model, thereby reducing the burden on the user and enabling highly accurate nutritional balance suggestions.

[0099] "User" refers to a person who uses the system to take photos of their meals and receive health management services.

[0100] "Device" refers to an electronic device such as a smartphone or tablet owned by a user.

[0101] The "photo folder" is a folder provided in the terminal, and refers to a location where photos taken by the user are automatically saved.

[0102] A "server" is a computer system installed on the cloud that analyzes received photo data, calculates calories, and generates advice using a generative AI model.

[0103] "Means for analyzing received photographic data" refers to software and / or hardware that performs the process of analyzing the photograph of the meal to identify ingredients and their quantities.

[0104] "Image processing engine" refers to algorithms and systems that use machine learning models to analyze food photos and identify ingredients.

[0105] "Means for calculating calories and nutrients" refers to software or databases for calculating the calories and nutrients of each ingredient based on analyzed ingredient information.

[0106] "Means for storing cumulative data" means a database or storage process for storing cumulative calorie and nutrient data for each user and tracking long-term eating patterns.

[0107] "Generative AI Model" refers to a machine learning model used to generate health advice based on received data.

[0108] "Means for generating health advice" refers to the process of using a generative AI model to create health improvements and suggestions based on the analysis results and the user's cumulative data.

[0109] "Means for sending push notifications" refers to communication technologies and protocols for notifying the user's device of advice generated by the server in real time.

[0110] "Means of notifying the device and displaying within the app" refers to the interface or software that displays advice on the user's device and allows detailed information to be viewed within the application.

[0111] "User identification information" refers to identification data for identifying an individual user, such as a user ID or account information.

[0112] "Means for obtaining ingredient information from a database" refers to the process of obtaining the necessary data from a database that stores calorie and nutrient information.

[0113] "Machine learning model" refers to the algorithms trained on the server to perform photo analysis and ingredient identification.

[0114] This invention is a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when the user takes a photo of the meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0115] System Overview

[0116] First, a user takes a photo of a meal using the camera app on their smartphone. The photo is automatically saved in the device's photo folder. An application running in the background is installed on the device, and this application monitors the photo folder in real time. When it detects that a new photo has been saved, it uploads the photo data to the server.

[0117] The server uses an image processing engine with a machine learning model to analyze the received photo data. It uses technologies such as TENSORFLOW (registered trademark) and OpenCV to identify ingredients and their quantities. Based on the analysis results, the server calculates the calories and nutrients for each ingredient. For this calculation, it references a database that stores nutritional information for ingredients (such as the USDA Nutrient Database).

[0118] The calculation results are stored in a database as the user's cumulative data, allowing the user to track their long-term eating patterns and nutritional balance. The server then uses a generative AI model (such as OpenAI's GPT-4) to generate health advice based on the user's cumulative data and their most recent dietary history. This advice is specific and may include suggestions for dietary improvements or supplements.

[0119] The generated advice is sent to the user's device via push notification from the server, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0120] Specific examples

[0121] Example 1: Breakfast analysis and advice

[0122] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0123] Example prompt:

[0124] Analyze a photo of your breakfast, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 200g of pancakes, 50g of bacon, and 200ml of orange juice.

[0125] Example 2: Lunch analysis and advice

[0126] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[0127] Example prompt:

[0128] Analyze a photo of your lunch, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 100g of salad, 150g of grilled chicken, and 300ml of smoothie.

[0129] In this way, the system is able to fully automate the user's dietary management and provide continuous, individually optimized health advice.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] A user opens the camera app on their smartphone and takes a photo of their meal. The photo is automatically saved to the device's photo folder. The input is a photo of the meal taken by the user, and the output is that the photo is saved to the device's photo folder.

[0133] Step 2:

[0134] An app installed on the device monitors the photo folder in the background to detect when a new photo has been saved. This monitoring is done using the Python watchdog library. The input is a save event to the photo folder, and the output is a detection signal that a new photo has been saved.

[0135] Step 3:

[0136] After the device detects a new photo, it sends the photo data and the user ID to the server. This is done using an HTTP request, specifically the requests library. The input is the new photo data and the user ID, and the output is that it is uploaded to the server.

[0137] Step 4:

[0138] The server passes the received photo data to an image processing engine to identify ingredients and their quantities. This analysis uses machine learning models (TensorFlow and OpenCV). The input is the received photo data, and the output is the identified ingredient information.

[0139] Step 5:

[0140] The server calculates the calories and nutrients for each ingredient based on the analysis results. The nutritional information for ingredients is obtained from a database (e.g., USDA Nutrient Database). The input is the analyzed ingredient information, and the output is the calculated calorie and nutrient information.

[0141] Step 6:

[0142] The server stores the calculation results in a database as cumulative data for each user, allowing you to track long-term eating patterns. The input is the calculated calories and nutrient information, and the output is the cumulative data.

[0143] Step 7:

[0144] The server uses a generative AI model (e.g., GPT-4) to generate health advice based on the user's accumulated data and latest dietary information. The input is the user's accumulated data and latest food information, and the output is the generated health advice. Example prompts to use:

[0145] A user's most recent meal consisted of 200g pancakes, 50g bacon, and 200ml orange juice. Please provide health advice based on this meal.

[0146] Step 8:

[0147] The server sends the generated advice to the device as a push notification using Firebase Cloud Messaging (FCM). The input is the generated health advice, and the output is the notification sent.

[0148] Step 9:

[0149] The device displays the received notification to the user and allows detailed advice to be viewed within the app. The input is the received notification and advice data, and the output is the display within the app.

[0150] Through these steps, the system is able to analyze photos of meals taken by users and provide calorie calculations and personalized health advice.

[0151] (Application example 1)

[0152] 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."

[0153] To manage one's health, it is important to understand the calorie and nutritional value of one's meals and receive appropriate guidance. However, doing this manually is extremely time-consuming. Furthermore, when eating at a restaurant, it is difficult to know the exact calorie and nutritional value from the menu. For this reason, there is a demand for a system that allows users to easily measure the calorie and nutritional value of their meals and receive health advice in real time.

[0154] 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.

[0155] In this invention, the server includes: means for a user to take photos of their meals and save them in a photo folder; means for a device to monitor the photo folder and detect new photos; means for the device to upload new photos to the server; means for the server to analyze the received photo data; means for the server to calculate calories and nutrients based on the analysis results; means for the server to store the calculation results in cumulative data for each user; means for the server to generate health advice using a generation AI; means for the server to send the advice to the device by push notification; means for the device to notify the user of the advice and display it within the app; and means for a user to take photos of restaurant menus and analyze the calories and nutritional value to support meal selection. This enables a user to simply take photos of their meals and receive analysis results of calories and nutritional value, providing real-time support for healthy meal selection.

[0156] "User" refers to a person who uses this system to take photos of their meals and receive health advice.

[0157] "Means for taking photos of meals" refers to the ability to take photos of meals using a device such as a smartphone or smart glasses and save the photos in the device's photo folder.

[0158] "Means for monitoring photo folders" refers to having the ability to periodically check a specific folder on the device and detect when new photos have been added.

[0159] "Means for uploading new photos to the server" refers to having a function for transferring new photos stored on the device to the server via the Internet.

[0160] "Means for analyzing photographic data" refers to the ability of the server to analyze the photographs it receives using image processing technology and identify the ingredients and their amounts in the photographs.

[0161] "Means for calculating calories and nutrients" refers to the ability to calculate the calories and nutrients of each ingredient based on the analyzed ingredient information.

[0162] "Means for saving cumulative data for each user" refers to the ability to link calculated calorie and nutrient data to individual user profiles and save them.

[0163] "Means for generating health advice using generative AI" refers to the ability of the generative AI model to create appropriate health advice based on cumulative data and the latest dietary information.

[0164] "Means for sending advice to a device via push notification" refers to having the ability to notify the device of generated health advice in real time.

[0165] "Means for notifying the user of the advice and displaying it within the app" refers to having the function of informing the user of the received advice and displaying detailed information within the application.

[0166] "Means for taking photos of restaurant menus and analyzing their calories and nutritional value" refers to a function that allows a user to take a photo of a restaurant menu and analyze the calories and nutritional value based on that photo.

[0167] The "image processing engine for identifying ingredients and their quantities" refers to algorithms or software that can identify specific ingredients from a photo and estimate their approximate weight and quantity.

[0168] A "generative AI model" is an artificial intelligence-based model that automatically generates health advice based on collected data.

[0169] A "prompt sentence" is a sentence that is input to a generative AI model to obtain an appropriate response.

[0170] The following system configuration and procedures are used to implement the present invention: The main components of the system include a device that allows a user to take photos of their meals, a terminal that monitors the photo folder, and a server that analyzes the photo data.

[0171] System Configuration

[0172] 1. Your device

[0173] Use your smartphone or smart glasses to take a photo of your meal and save the photo in the device's photo folder.

[0174] 2. Terminal

[0175] This applies to smartphones and smart glasses, and monitors photo folders to detect newly saved photos.

[0176] It also has the function of uploading new photos to the server.

[0177] 3. Server

[0178] The server receives the uploaded photo data and uses an image processing engine to identify the ingredients and their quantities.

[0179] It has data to calculate calories and nutritional value based on ingredient information.

[0180] It has the function of saving cumulative data for each user.

[0181] It uses a generative AI model to generate health advice based on your cumulative data and your most recent diet.

[0182] The generated advice is sent to the user's device via push notification.

[0183] Hardware and software used

[0184] Hardware:

[0185] Devices: Smartphones (e.g., iPhone (registered trademark), Android (registered trademark) smartphones), smart glasses (e.g., Google (registered trademark) Glass (registered trademark))

[0186] Server: High-performance cloud server (e.g., Amazon AWS (registered trademark), Microsoft (registered trademark) Azure (registered trademark))

[0187] software:

[0188] Terminal monitoring: Background service using Python and Java (registered trademark)

[0189] Image processing engine: Uses TensorFlow and OpenCV

[0190] Cloud storage and database management: Amazon S3 and MySQL®

[0191] Generative AI models: Machine learning models such as TensorFlow or GPT-3®

[0192] Specific examples

[0193] Example 1: Breakfast analysis and advice

[0194] A user uses their smartphone to take a photo of their breakfast (pancakes, bacon, and orange juice). Once the photo is saved, the device detects it and automatically uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on the analysis results, calories and nutrients are calculated, and advice is generated: "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch." This advice is sent via a push notification to the user's smartphone, and details can be viewed within the app.

[0195] Example 2: Restaurant meal selection support

[0196] A user takes a photo of a salad, grilled chicken, and smoothie at a restaurant using smart glasses. The device detects the new photo and uploads it to the server. The server analyzes the photo and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This generates advice such as, "This meal is well-balanced, so continue with this." This advice is displayed on the smart glasses' display, and the user can check it in real time.

[0197] Prompt Sentence Examples

[0198] Food photo: salad, grilled chicken, smoothie

[0199] Calories and nutritional value: 100g salad, 150g grilled chicken, 300ml smoothie

[0200] Advice: This diet is well balanced, so stick with it.

[0201] This system allows users to easily analyze the calories and nutritional value of their meals and provides real-time support for making healthy eating choices.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] A user takes a photo of their meal and saves it in the device's photo folder.

[0205] Input: Food photo

[0206] Output: Photo files saved in the device's photo folder

[0207] How it works: Users use their smartphone or smart glasses to take photos of their food at a restaurant or at home, and the photos are automatically saved to the device's photo folder.

[0208] Step 2:

[0209] Your device monitors your photo folder for new photos.

[0210] Input: A new photo saved in the Photos folder

[0211] Output: New photo detected notification

[0212] How it works: A monitoring program running on the device periodically checks the photo folder to detect newly saved photos.

[0213] Step 3:

[0214] The device uploads the new photo to the server.

[0215] Input: Newly detected photo file

[0216] Output: Photo data uploaded to the server

[0217] Specific operation: Retrieves new photo files from the photo folder and uploads them to the server via the Internet, along with the user ID.

[0218] Step 4:

[0219] The server analyzes the received photo data.

[0220] Input: Uploaded photo data

[0221] Output: Data about ingredients in the photo and their quantities

[0222] How it works: The server uses an image processing engine (e.g., TensorFlow or OpenCV) to identify ingredients from the photo and determine their approximate weight and quantity.

[0223] Step 5:

[0224] The server calculates calories and nutrients based on the analysis results.

[0225] Input: Identified food ingredient data

[0226] Output: Calorie and nutrient data for meals

[0227] Specific operation: The server references the nutritional information for each ingredient stored in the database and calculates calories and major nutrients (e.g., fat, protein, vitamins, etc.) based on the identified ingredient data.

[0228] Step 6:

[0229] The server stores the calculation results in cumulative data for each user.

[0230] Input: Calculated calories and nutrient data

[0231] Output: New meal data added to the cumulative data per user

[0232] Specific operation: The server associates the calculation results with individual user profiles and stores them in cumulative data.

[0233] Step 7:

[0234] The server generates health advice using generation AI.

[0235] Input: Accumulative data and latest meal data

[0236] Output: Generated health advice

[0237] Specific operation: Using a generative AI model (e.g., GPT-3), specific health advice is generated based on the user's cumulative data and latest dietary information.

[0238] Step 8:

[0239] The server sends the advice to the device via push notification.

[0240] Input: Generated health advice

[0241] Output: Sending advice via push notification

[0242] Specific operation: The generated advice is pushed from the server to the user's device in real time.

[0243] Step 9:

[0244] The device notifies the user of the advice and displays it within the app.

[0245] Input: Push notification from the server

[0246] Output: Detailed advice displayed in the app

[0247] Specific operation: The device notifies the user of notifications received and displays detailed advice within the application, allowing the user to check health advice in real time.

[0248] 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.

[0249] This invention combines a health management system that automatically analyzes photos of meals taken by the user to calculate calories and suggest nutritional balance, with an emotion engine that recognizes the user's emotions to provide more personalized health advice. The system begins when the user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0250] System Overview

[0251] 1. User Action:

[0252] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[0253] 2. Device monitoring and notifications:

[0254] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[0255] 3. Upload to Cloud:

[0256] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[0257] 4. Parsing on the server:

[0258] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[0259] 5. Calorie and Nutritional Value Calculator:

[0260] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[0261] 6. Counting and Storage:

[0262] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[0263] 7. Acquiring emotion data using the emotion engine:

[0264] The server runs an emotion engine that analyzes emotions from user input and voice data. The emotion engine uses natural language processing and voice analysis to accurately identify the user's emotional state. This emotion data is sent to the server and added to the user's cumulative data.

[0265] 8. Advice generation by generative AI:

[0266] The server uses a generative AI model to generate specific health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes suggestions for dietary improvements and supplements, as well as messages that take into account the user's emotional state.

[0267] 9. Notification and Display of Advice:

[0268] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0269] Specific examples

[0270] Example 1: Breakfast analysis and advice

[0271] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After saving the photo, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated, such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0272] Example 2: Lunch analysis and advice

[0273] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated such as, "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a motivational message such as "Keep it up" is added to the advice and sent via push notification.

[0274] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice. The introduction of an emotion engine makes it possible to provide more personalized advice that takes into account the user's emotional state.

[0275] The processing flow will be explained below.

[0276] Step 1:

[0277] The user takes a photo of the meal and saves it in the photo folder of their smartphone. The user does not need to perform any special operations; they simply take a photo of the meal using a regular camera app.

[0278] Step 2:

[0279] The app installed on your device monitors your photo folder for changes and detects new photos by periodically scanning the folder in the background.

[0280] Step 3:

[0281] When a device detects a new photo, it uploads the photo data and user ID to the server via an HTTP POST request to a specified endpoint on the server.

[0282] Step 4:

[0283] The server stores the received photo data in the analysis directory, which prepares an analysis job and passes it to the image processing engine.

[0284] Step 5:

[0285] The server's image processing engine analyzes the photo to identify ingredients and their quantities, using a machine learning model to scan the ingredients in the photo, draw bounding boxes, and detect the name and quantity of each ingredient.

[0286] Step 6:

[0287] The server calculates calories and nutrients based on the output from the image processing engine. It references the nutritional information of ingredients stored in a database to calculate the total calories and each nutrient (protein, fat, carbohydrates, etc.) of the detected ingredients.

[0288] Step 7:

[0289] The server stores the calculation results as cumulative data for each user. The user's dietary history and nutritional information are recorded in a database and managed cumulatively for long-term tracking.

[0290] Step 8:

[0291] The server receives user input and voice data, which the emotion engine analyzes to identify the user's emotional state. The emotion engine uses natural language processing and voice analysis technology to identify emotions with high accuracy.

[0292] Step 9:

[0293] The emotion data analyzed by the emotion engine is sent to the server and added to the user's cumulative data, allowing for the integrated management of the user's emotional information.

[0294] Step 10:

[0295] The server uses the generative AI model to generate health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes messages that take into account the user's emotional state.

[0296] Step 11:

[0297] The server generates health advice and sends it to the device via push notification. The notification is sent in real time, allowing the user to receive the advice immediately.

[0298] Step 12:

[0299] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[0300] Example 2

[0301] 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."

[0302] In recent years, the importance of health management has increased, and there is a demand for dietary records, calorie calculations, and consideration of nutritional balance. However, manually recording meals and calculating calories and nutrients is cumbersome and inaccurate. Furthermore, simply providing uniform health advice without considering the user's emotional state poses a challenge, making it difficult to provide effective and personalized support to users.

[0303] 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.

[0304] In this invention, the server includes means for analyzing photo data of meals, means for calculating calories and nutrients, means for acquiring user emotion data using an emotion engine that analyzes emotions, means for generating health advice using a generation AI, and means for sending the advice to a terminal by push notification. This makes it possible to automate the recording and analysis of meals and provide personalized health advice that takes into account the user's emotional state.

[0305] A "user" is a person who uses this system to take photos of their meals and manage their health.

[0306] A "terminal" is a device used by a user, such as a smartphone or tablet, that has the function of taking and saving photos.

[0307] A "photo folder" is a location within the device where new photos are saved.

[0308] A "server" is a central computing resource with data analysis, calculation, storage, and notification functions.

[0309] The "image processing engine" is software installed on the server that identifies ingredients and their quantities from a photo of a meal.

[0310] "Calories" is a unit that indicates the amount of energy contained in food.

[0311] "Nutrients" are components contained in food ingredients that are necessary for maintaining health, and include carbohydrates, lipids, proteins, vitamins, etc.

[0312] An "emotion engine" is software that analyzes user input data and voice data to identify the user's emotional state.

[0313] A "generative AI model" is an artificial intelligence technology that generates health advice based on a user's cumulative data, latest dietary habits, and emotional data.

[0314] "Push notification" is a communication technology in which a server sends information to a device in real time.

[0315] "Cumulative data" refers to the collection of each user's meal records, nutritional information, and emotional data.

[0316] "Health Advice" is advice provided based on the user's diet and emotional state using a generative AI model.

[0317] This invention realizes a system that allows a user to take a photo of their meal, calculates the calorie and nutritional balance based on the photo, and provides health advice that takes the user's emotions into consideration. A specific embodiment of the system is described below.

[0318] First, the user takes a photo of their meal using the camera on their smartphone or tablet. At this time, the photo is automatically saved to the device's photo folder. An app installed on the device monitors the photo folder and detects when a new photo has been saved. This app runs in the background, reducing the user's operational burden.

[0319] When the device detects a new photo, it uploads it to a dedicated server. The uploaded photo data also contains the user's ID, which allows for individual management. The server acquires the received photo data and passes it to an image processing engine. The image processing engine uses machine learning models such as TensorFlow and PyTorch. This engine identifies ingredients in the photo with high accuracy and determines the type and quantity of each ingredient.

[0320] The server calculates calories and various nutrients based on the analysis results. The nutritional information used here is based on information for representative ingredients pre-stored in a database. The calculation results are saved as cumulative data for each user and used to track long-term eating patterns and nutritional balance.

[0321] Furthermore, the server acquires the user's emotional data using an emotion engine. The emotion engine uses natural language processing and speech analysis technologies such as IBM Watson® and Google Cloud Natural Language API to analyze emotions from the user's input data and voice data. This identifies the user's emotional state as "stress," "joy," "sadness," etc. This emotional data is also added to the cumulative data.

[0322] The server then generates health advice using a generative AI model, such as OpenAI's GPT-4, which generates specific, personalized advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice includes suggestions for dietary improvements and supplements, as well as emotional messages. The server then sends the generated advice to the device via push notification.

[0323] The device will display the received notification to the user and allow them to view detailed advice within the app, allowing users to efficiently manage their daily diet and health.

[0324] Specific examples

[0325] Example 1: Breakfast analysis and advice

[0326] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated such as, "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice. The advice is sent to the user via push notification, which the user can open to view the details.

[0327] Example 2: Lunch analysis and advice

[0328] A user takes a photo of their lunch, which includes salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. Calories and nutrients (protein, vitamins, etc.) are calculated. As a result, advice is generated, such as "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a message such as "Keep up the good work" is added to the advice. The advice is sent via push notification, and the user can view details within the app.

[0329] Prompt Sentence Examples

[0330] Example prompt 1: Breakfast analysis and advice

[0331] A user takes a photo of pancakes, bacon, and orange juice for breakfast. The analysis results show 200g of pancakes, 50g of bacon, and 200ml of orange juice. The user is currently feeling stressed. Generate appropriate health advice.

[0332] Example prompt 2: Lunch analysis and advice

[0333] A user takes a photo of a salad, grilled chicken, and smoothie for lunch. The analysis results show 100g of salad, 150g of grilled chicken, and 300ml of smoothie. The user has a positive emotion. Generate appropriate health advice.

[0334]

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] Step 1:

[0337] A user takes a photo of a meal using the camera on their smartphone or tablet. The photo is automatically saved to the device's photo folder. This is the input, and the saved photo data is the output. The specific action is when the user opens the camera app and taps the button to take a photo.

[0338] Step 2:

[0339] An app installed on a device monitors a photo folder in the background. The app detects when a new photo has been saved and notifies the user. The input is the state of the photo folder, and the output is the saving of a new photo. Specifically, the device's file system event listener monitors changes in the folder and detects an event when a new photo is added.

[0340] Step 3:

[0341] The device uploads a new photo to a dedicated server. At this time, the photo data is assigned a user ID. The input is the new photo and the user ID, and the output is the photo data uploaded to the server. Specifically, the device app creates an HTTP request and sends the photo data to the server's upload API endpoint.

[0342] Step 4:

[0343] The server receives the received photo data and passes it to an image processing engine. The image processing engine uses an application (for example, TensorFlow or PyTorch). The input is the photo data, and the output is the analyzed ingredients and their quantities. Specifically, the data is processed by an image processing algorithm that detects the outlines of the ingredients in the photo, and a machine learning model that estimates the type and quantity of the ingredients.

[0344] Step 5:

[0345] The server calculates calories and nutrients based on the analyzed ingredient information. The input is ingredient information, and the output is calorie and nutrient data. Specifically, the server retrieves nutritional information for each ingredient from the database and uses it to calculate calories and nutrients.

[0346] Step 6:

[0347] The server saves the calculation results in the cumulative data for each user. The input is calorie and nutrient data, and the output is the updated cumulative data. The specific operation is to add new data to the user's cumulative data stored in the server's database and update it.

[0348] Step 7:

[0349] The server receives input data and voice data from the user and runs the emotion engine. The input is the user's input data and voice data, and the output is analyzed emotion data. Specifically, the server passes the data to the emotion engine and identifies the emotional state through natural language processing and voice analysis.

[0350] Step 8:

[0351] The server uses a generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The inputs are cumulative data, dietary details, and emotional data, and the output is the generated health advice. Specifically, the server inputs this data into the generative AI model and processes it to generate appropriate health advice and messages.

[0352] Step 9:

[0353] The server sends the generated advice to the device via push notification. The input is the health advice, and the output is the notification to the device. Specifically, the server creates a notification message and sends it to the device via a push notification service (e.g., Apple Push Notification Service or Firebase Cloud Messaging).

[0354] Step 10:

[0355] The device displays the received notification to the user. When the notification is tapped, detailed advice can be viewed within the app. The input is the push notification, and the output is advice that the user can view. Specifically, the device's notification system displays the notification, and when the user taps it, the details screen within the app opens.

[0356] (Application example 2)

[0357] 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."

[0358] Conventional health management systems only calculate the calories of meals and analyze nutritional balance, making it difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, when using food delivery services, there is a problem in that meal options cannot be optimized to match the user's health condition and emotions. This can lead to a decline in the user's overall health management and satisfaction.

[0359] 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 received photo data, means for calculating calories and nutrients, means for saving the calculation results in cumulative data for each user, means for generating health advice using a generation AI, means including an emotion recognition engine, and means for providing personalized dietary advice based on the user's emotional state in a food delivery service that takes a photo of a menu selected by the user and analyzes the calories and nutritional balance. This makes it possible to provide personalized health advice that takes the user's emotions into consideration, enabling optimal menu selection and health management when using a food delivery service.

[0360] In this invention, the term "user" refers to a person who uses the system to take food photos and receive health management advice.

[0361] A "terminal" refers to an electronic device that allows a user to take photos of their meals, monitor a photo folder, detect new photos, and upload them to a server.

[0362] "Server" refers to the computer system that is responsible for a series of processes, including receiving and analyzing photo data uploaded from the device, calculating calories and nutrients, storing the calculation results, and generating health advice using generative AI.

[0363] "Photo folder" refers to the storage location within the device where photos taken by the user are stored.

[0364] A "monitoring program that runs in the background" refers to software that automatically monitors photo folders without user interaction and detects when new photos are saved.

[0365] "Analysis" refers to image processing that identifies ingredients and their amounts based on the photo data received by the server.

[0366] "Calculating calories and nutrients" refers to the process of calculating the calories and nutritional balance of each ingredient based on the analysis results.

[0367] "Cumulative Data" refers to information that stores calorie and nutrient data calculated for each user over time and is used to track the user's eating patterns and nutritional balance.

[0368] "Generative AI" refers to an artificial intelligence model that generates personalized health advice based on a user's cumulative data, recent dietary habits, emotional data, etc.

[0369] "Push notification" refers to a notification message that is automatically sent from a server to a user's device.

[0370] An "emotion recognition engine" refers to artificial intelligence software that analyzes user input and voice data to identify emotional states.

[0371] "Food delivery service" refers to a service that allows users to order food online and have the food delivered to a specified location.

[0372] "Personalized advice" means health advice that is optimized for a particular user, taking into account the user's emotional state and cumulative data.

[0373] This invention combines an emotion recognition engine with a health management system that allows users to take photos of their meals, automatically analyzes the photos, calculates calories, and suggests nutritional balance, providing personalized health advice. This system also supports optimal menu selection and health management based on the user's emotional state when using a food delivery service.

[0374] System Configuration

[0375] The system consists of a user's device, a backend server, an image processing engine, a generative AI model, an emotion recognition engine, and more.

[0376] Hardware and Software Use

[0377] Smartphone: The user takes a photo of the meal and runs the app.

[0378] Server: Responsible for analyzing photos and generating advice using AI.

[0379] TensorFlow: Used as an image processing engine to identify ingredients.

[0380] Azure Cognitive Services: Used as an emotion recognition engine to analyze user emotions.

[0381] System Operation Overview

[0382] 1. User Action:

[0383] Users take a photo of the food delivery menu using their smartphone camera, and the photo is automatically saved in a photo folder.

[0384] 2. Photo folder monitoring:

[0385] A background program running on the device monitors the photo folder and detects when new photos are saved.

[0386] 3. Upload to the server:

[0387] The device uploads the newly saved photo to the server, along with any user input (text or voice input).

[0388] 4. Photo Analysis:

[0389] The server analyzes the received photo data using TensorFlow to identify the ingredients and their quantities.

[0390] 5. Calorie and Nutrition Counts:

[0391] Based on the analyzed ingredient information, the calories and nutrients of each ingredient are calculated.

[0392] 6. Emotion recognition:

[0393] The server uses Azure Cognitive Services to analyze emotions from user input data.

[0394] 7. Advice generation using generative AI models:

[0395] The server uses a generative AI model to generate health advice based on the user's cumulative data, recent dietary history, and emotional data.

[0396] 8. Push Notifications:

[0397] The generated advice is sent to the device via a push notification, and the user can open the notification to view the detailed advice within the app.

[0398] Specific examples

[0399] Example 1: A user takes a photo of a fried chicken bento they ordered via food delivery for lunch and types, "I'm tired from work today." The device detects the new photo and uploads it to the server. The server analyzes the photo, identifies the fried chicken and various side dishes, and their portions, and calculates the calories and nutrients. At the same time, it uses Azure Cognitive Services to analyze emotions and detects that the user is "tired." As a result, personalized advice is generated and sent via push notification, such as, "This meal was high in fat, so choose a vegetable-based menu for your next meal. High-fat meals on a tired day can cause stress, so choose a lighter meal next time."

[0400] Example 2: A user takes a photo of pancakes, bacon, and orange juice for breakfast and saves the photo in a folder. The device detects the photo and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch" is generated. If the emotion recognition engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification.

[0401] Example prompt sentence:

[0402] "A user orders a fried chicken bento for lunch and types a photo of it along with the comment, 'I'm tired from work today.' Give them personalized advice based on their diet and their emotions."

[0403] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0404] Step 1:

[0405] A user takes a photo of a food delivery menu using the camera on their smartphone. The photo is automatically saved in a photo folder. In this example, the input is a "photo of the menu" and the output is the "image data saved in the photo folder."

[0406] Step 2:

[0407] A background program on the device monitors the photo folder and detects when new photos are saved. The input is the "photo folder status" and the output is "new photo detection notification." Specifically, the program periodically checks the folder and catches the information when a new photo is saved.

[0408] Step 3:

[0409] The device uploads the newly saved photo data to the server. At this time, it also sends the user's input data (text and voice input). The input is "new photo data and user input data," and the output is "data uploaded to the server." Specifically, the device sends the data to the server using an HTTP POST request.

[0410] Step 4:

[0411] The server analyzes the received photo data using an image processing engine (TensorFlow) to identify the ingredients and their quantities. The input is "photo data" and the output is "ingredient information (type and quantity)." Specifically, the server inputs the image data into the TensorFlow model and obtains the type of ingredient and its quantity as the model's output.

[0412] Step 5:

[0413] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information. The input is "ingredient information" and the output is "calculated calorie and nutrient data." Specifically, the server obtains the calorie and nutrient information for each ingredient from the database within the server and performs calculations based on that information.

[0414] Step 6:

[0415] The server uses Azure Cognitive Services to analyze emotions from user input data (text or voice). The input is "user input data" and the output is "emotion data." Specifically, the server sends an API request to Azure Cognitive Services and receives the emotion analysis results.

[0416] Step 7:

[0417] The server uses the generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The input is "cumulative data, dietary details, and emotional data," and the output is "generated health advice." Specifically, the server inputs this data into the generative AI model and outputs the optimal advice.

[0418] Step 8:

[0419] The generated advice is sent from the server to the device as a push notification. The input is the "generated health advice" and the output is the "notification sent to the device." Specifically, the server uses the push notification service to send the notification to the app.

[0420] Step 9:

[0421] The device displays the received notification to the user and allows them to view detailed advice within the app. The input is the "content of the push notification" and the output is the "advice displayed to the user." Specifically, clicking the notification launches the app and displays the advice.

[0422] 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.

[0423] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0424] 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.

[0425] [Second embodiment]

[0426] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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).

[0432] 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. 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0437] 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."

[0438] This invention provides a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when a user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0439] System Overview

[0440] 1. User Action:

[0441] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[0442] 2. Device monitoring and notifications:

[0443] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[0444] 3. Upload to Cloud:

[0445] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[0446] 4. Parsing on the server:

[0447] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[0448] 5. Calorie and Nutritional Value Calculator:

[0449] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[0450] 6. Counting and Storage:

[0451] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[0452] 7. Generative AI Advice:

[0453] The server uses a generative AI model to generate specific health advice based on the user's cumulative data and their most recent dietary habits, including suggestions for dietary improvements and supplements.

[0454] 8. Notification and Display of Advice:

[0455] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0456] Specific examples

[0457] Example 1: Breakfast analysis and advice

[0458] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0459] Example 2: Lunch analysis and advice

[0460] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[0461] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice.

[0462] The processing flow will be explained below.

[0463] Step 1:

[0464] The user takes a photo of their meal and saves it to the photo folder on their smartphone. The user opens the camera app, takes a photo of the meal, and saves it to the photo folder naturally without any special operation.

[0465] Step 2:

[0466] Your device will run a background service to monitor your photo folder and detect new photos. The monitoring program will periodically scan your photo folder to check if any new photo files have been added.

[0467] Step 3:

[0468] When the device detects a new meal photo, it calls an API to upload the photo and user ID to the server. Here, the path to the photo file and the user ID information are sent to the server in the form of a POST request.

[0469] Step 4:

[0470] The server receives the HTTP request, saves the photo data in the analysis directory, and prepares to pass the photo data to the image processing engine as an image analysis job.

[0471] Step 5:

[0472] The server's image processing engine analyzes the photo to identify ingredients and their quantities. The image processing engine uses machine learning models to scan the photo and output a bounding box, name, and estimated quantity for each ingredient.

[0473] Step 6:

[0474] The server calculates calories and nutrients based on the output from the image processing engine, referencing the nutritional information for each ingredient stored in the database to calculate the total calories, protein, fat, carbohydrates, etc. of the identified ingredients.

[0475] Step 7:

[0476] The server stores the calculation results as cumulative data for each user. Each user's dietary history and nutritional information are recorded in a database and managed cumulatively.

[0477] Step 8:

[0478] The server generates health advice using a generative AI model based on the user's cumulative data and latest dietary information. The generative AI model takes the user's current situation into consideration and outputs specific advice and improvement suggestions in text format.

[0479] Step 9:

[0480] The server generates health advice and sends it to the device via push notifications, which are sent in real time via APNs or Firebase Cloud Messaging services.

[0481] Step 10:

[0482] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[0483] Example 1

[0484] 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."

[0485] Conventional health management systems require users to manually input their dietary information, which is cumbersome and time-consuming. Furthermore, there are limitations to the accuracy of nutritional balance and calorie calculation, making it difficult to provide individually optimized advice. The present invention aims to solve these problems and realize automated dietary management and highly accurate nutritional balance recommendations.

[0486] 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.

[0487] In this invention, the server includes a means for analyzing photos of meals taken by the user and identifying ingredients and their amounts, a means for calculating calories and nutrients based on the analysis results, and a means for generating individually optimized health advice using a generative AI model, thereby reducing the burden on the user and enabling highly accurate nutritional balance suggestions.

[0488] "User" refers to a person who uses the system to take photos of their meals and receive health management services.

[0489] "Device" refers to an electronic device such as a smartphone or tablet owned by a user.

[0490] The "photo folder" is a folder provided in the terminal, and refers to a location where photos taken by the user are automatically saved.

[0491] A "server" is a computer system installed on the cloud that analyzes received photo data, calculates calories, and generates advice using a generative AI model.

[0492] "Means for analyzing received photographic data" refers to software and / or hardware that performs the process of analyzing the photograph of the meal to identify ingredients and their quantities.

[0493] "Image processing engine" refers to algorithms and systems that use machine learning models to analyze food photos and identify ingredients.

[0494] "Means for calculating calories and nutrients" refers to software or databases for calculating the calories and nutrients of each ingredient based on analyzed ingredient information.

[0495] "Means for storing cumulative data" means a database or storage process for storing cumulative calorie and nutrient data for each user and tracking long-term eating patterns.

[0496] "Generative AI Model" refers to a machine learning model used to generate health advice based on received data.

[0497] "Means for generating health advice" refers to the process of using a generative AI model to create health improvements and suggestions based on the analysis results and the user's cumulative data.

[0498] "Means for sending push notifications" refers to communication technologies and protocols for notifying the user's device of advice generated by the server in real time.

[0499] "Means of notifying the device and displaying within the app" refers to the interface or software that displays advice on the user's device and allows detailed information to be viewed within the application.

[0500] "User identification information" refers to identification data for identifying an individual user, such as a user ID or account information.

[0501] "Means for obtaining ingredient information from a database" refers to the process of obtaining the necessary data from a database that stores calorie and nutrient information.

[0502] "Machine learning model" refers to the algorithms trained on the server to perform photo analysis and ingredient identification.

[0503] This invention is a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when the user takes a photo of the meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0504] System Overview

[0505] First, a user takes a photo of a meal using the camera app on their smartphone. The photo is automatically saved in the device's photo folder. An application running in the background is installed on the device, and this application monitors the photo folder in real time. When it detects that a new photo has been saved, it uploads the photo data to the server.

[0506] The server uses an image processing engine with a machine learning model to analyze the received photo data. Here, it uses technologies such as TensorFlow and OpenCV to identify ingredients and their quantities. Based on the analysis results, the server calculates the calories and nutrients for each ingredient. For calculations, it references a database that stores nutritional information for ingredients (such as the USDA Nutrient Database).

[0507] The calculation results are stored in a database as the user's cumulative data, allowing the user to track their long-term eating patterns and nutritional balance. The server then uses a generative AI model (such as OpenAI's GPT-4) to generate health advice based on the user's cumulative data and their most recent dietary history. This advice is specific and may include suggestions for dietary improvements or supplements.

[0508] The generated advice is sent to the user's device via push notification from the server, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0509] Specific examples

[0510] Example 1: Breakfast analysis and advice

[0511] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0512] Example prompt:

[0513] Analyze a photo of your breakfast, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 200g of pancakes, 50g of bacon, and 200ml of orange juice.

[0514] Example 2: Lunch analysis and advice

[0515] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[0516] Example prompt:

[0517] Analyze a photo of your lunch, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 100g of salad, 150g of grilled chicken, and 300ml of smoothie.

[0518] In this way, the system is able to fully automate the user's dietary management and provide continuous, individually optimized health advice.

[0519] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0520] Step 1:

[0521] A user opens the camera app on their smartphone and takes a photo of their meal. The photo is automatically saved to the device's photo folder. The input is a photo of the meal taken by the user, and the output is that the photo is saved to the device's photo folder.

[0522] Step 2:

[0523] An app installed on the device monitors the photo folder in the background to detect when a new photo has been saved. This monitoring is done using the Python watchdog library. The input is a save event to the photo folder, and the output is a detection signal that a new photo has been saved.

[0524] Step 3:

[0525] After the device detects a new photo, it sends the photo data and the user ID to the server. This is done using an HTTP request, specifically the requests library. The input is the new photo data and the user ID, and the output is that it is uploaded to the server.

[0526] Step 4:

[0527] The server passes the received photo data to an image processing engine to identify ingredients and their quantities. This analysis uses machine learning models (TensorFlow and OpenCV). The input is the received photo data, and the output is the identified ingredient information.

[0528] Step 5:

[0529] The server calculates the calories and nutrients for each ingredient based on the analysis results. The nutritional information for ingredients is obtained from a database (e.g., USDA Nutrient Database). The input is the analyzed ingredient information, and the output is the calculated calorie and nutrient information.

[0530] Step 6:

[0531] The server stores the calculation results in a database as cumulative data for each user, allowing you to track long-term eating patterns. The input is the calculated calories and nutrient information, and the output is the cumulative data.

[0532] Step 7:

[0533] The server uses a generative AI model (e.g., GPT-4) to generate health advice based on the user's accumulated data and latest dietary information. The input is the user's accumulated data and latest food information, and the output is the generated health advice. Example prompts to use:

[0534] A user's most recent meal consisted of 200g pancakes, 50g bacon, and 200ml orange juice. Please provide health advice based on this meal.

[0535] Step 8:

[0536] The server sends the generated advice to the device as a push notification using Firebase Cloud Messaging (FCM). The input is the generated health advice, and the output is the notification sent.

[0537] Step 9:

[0538] The device displays the received notification to the user and allows detailed advice to be viewed within the app. The input is the received notification and advice data, and the output is the display within the app.

[0539] Through these steps, the system is able to analyze photos of meals taken by users and provide calorie calculations and personalized health advice.

[0540] (Application example 1)

[0541] 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."

[0542] To manage one's health, it is important to understand the calorie and nutritional value of one's meals and receive appropriate guidance. However, doing this manually is extremely time-consuming. Furthermore, when eating at a restaurant, it is difficult to know the exact calorie and nutritional value from the menu. For this reason, there is a demand for a system that allows users to easily measure the calorie and nutritional value of their meals and receive health advice in real time.

[0543] 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.

[0544] In this invention, the server includes: means for a user to take photos of their meals and save them in a photo folder; means for a device to monitor the photo folder and detect new photos; means for the device to upload new photos to the server; means for the server to analyze the received photo data; means for the server to calculate calories and nutrients based on the analysis results; means for the server to store the calculation results in cumulative data for each user; means for the server to generate health advice using a generation AI; means for the server to send the advice to the device by push notification; means for the device to notify the user of the advice and display it within the app; and means for a user to take photos of restaurant menus and analyze the calories and nutritional value to support meal selection. This enables a user to simply take photos of their meals and receive analysis results of calories and nutritional value, providing real-time support for healthy meal selection.

[0545] "User" refers to a person who uses this system to take photos of their meals and receive health advice.

[0546] "Means for taking photos of meals" refers to the ability to take photos of meals using a device such as a smartphone or smart glasses and save the photos in the device's photo folder.

[0547] "Means for monitoring photo folders" refers to having the ability to periodically check a specific folder on the device and detect when new photos have been added.

[0548] "Means for uploading new photos to the server" refers to having a function for transferring new photos stored on the device to the server via the Internet.

[0549] "Means for analyzing photographic data" refers to the ability of the server to analyze the photographs it receives using image processing technology and identify the ingredients and their amounts in the photographs.

[0550] "Means for calculating calories and nutrients" refers to the ability to calculate the calories and nutrients of each ingredient based on the analyzed ingredient information.

[0551] "Means for saving cumulative data for each user" refers to the ability to link calculated calorie and nutrient data to individual user profiles and save them.

[0552] "Means for generating health advice using generative AI" refers to the ability of the generative AI model to create appropriate health advice based on cumulative data and the latest dietary information.

[0553] "Means for sending advice to a device via push notification" refers to having the ability to notify the device of generated health advice in real time.

[0554] "Means for notifying the user of the advice and displaying it within the app" refers to having the function of informing the user of the received advice and displaying detailed information within the application.

[0555] "Means for taking photos of restaurant menus and analyzing their calories and nutritional value" refers to a function that allows a user to take a photo of a restaurant menu and analyze the calories and nutritional value based on that photo.

[0556] The "image processing engine for identifying ingredients and their quantities" refers to algorithms or software that can identify specific ingredients from a photo and estimate their approximate weight and quantity.

[0557] A "generative AI model" is an artificial intelligence-based model that automatically generates health advice based on collected data.

[0558] A "prompt sentence" is a sentence that is input to a generative AI model to obtain an appropriate response.

[0559] The following system configuration and procedures are used to implement the present invention: The main components of the system include a device that allows a user to take photos of their meals, a terminal that monitors the photo folder, and a server that analyzes the photo data.

[0560] System Configuration

[0561] 1. Your device

[0562] Use your smartphone or smart glasses to take a photo of your meal and save the photo in the device's photo folder.

[0563] 2. Terminal

[0564] This applies to smartphones and smart glasses, and monitors photo folders to detect newly saved photos.

[0565] It also has the function of uploading new photos to the server.

[0566] 3. Server

[0567] The server receives the uploaded photo data and uses an image processing engine to identify the ingredients and their quantities.

[0568] It has data to calculate calories and nutritional value based on ingredient information.

[0569] It has the function of saving cumulative data for each user.

[0570] It uses a generative AI model to generate health advice based on your cumulative data and your most recent diet.

[0571] The generated advice is sent to the user's device via push notification.

[0572] Hardware and software used

[0573] Hardware:

[0574] Devices: Smartphones (e.g., iPhone, Android smartphones), smart glasses (e.g., Google Glass)

[0575] Server: High-performance cloud server (e.g., Amazon AWS, Microsoft Azure)

[0576] software:

[0577] Device monitoring: background services using Python and Java

[0578] Image processing engine: Uses TensorFlow and OpenCV

[0579] Cloud storage and database management: Amazon S3 and MySQL

[0580] Generative AI models: Machine learning models such as TensorFlow or GPT-3

[0581] Specific examples

[0582] Example 1: Breakfast analysis and advice

[0583] A user uses their smartphone to take a photo of their breakfast (pancakes, bacon, and orange juice). Once the photo is saved, the device detects it and automatically uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on the analysis results, calories and nutrients are calculated, and advice is generated: "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch." This advice is sent via a push notification to the user's smartphone, and details can be viewed within the app.

[0584] Example 2: Restaurant meal selection support

[0585] A user takes a photo of a salad, grilled chicken, and smoothie at a restaurant using smart glasses. The device detects the new photo and uploads it to the server. The server analyzes the photo and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This generates advice such as, "This meal is well-balanced, so continue with this." This advice is displayed on the smart glasses' display, and the user can check it in real time.

[0586] Prompt Sentence Examples

[0587] Food photo: salad, grilled chicken, smoothie

[0588] Calories and nutritional value: 100g salad, 150g grilled chicken, 300ml smoothie

[0589] Advice: This diet is well balanced, so stick with it.

[0590] This system allows users to easily analyze the calories and nutritional value of their meals and provides real-time support for making healthy eating choices.

[0591] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0592] Step 1:

[0593] A user takes a photo of their meal and saves it in the device's photo folder.

[0594] Input: Food photo

[0595] Output: Photo files saved in the device's photo folder

[0596] How it works: Users use their smartphone or smart glasses to take photos of their food at a restaurant or at home, and the photos are automatically saved to the device's photo folder.

[0597] Step 2:

[0598] Your device monitors your photo folder for new photos.

[0599] Input: A new photo saved in the Photos folder

[0600] Output: New photo detected notification

[0601] How it works: A monitoring program running on the device periodically checks the photo folder to detect newly saved photos.

[0602] Step 3:

[0603] The device uploads the new photo to the server.

[0604] Input: Newly detected photo file

[0605] Output: Photo data uploaded to the server

[0606] Specific operation: Retrieves new photo files from the photo folder and uploads them to the server via the Internet, along with the user ID.

[0607] Step 4:

[0608] The server analyzes the received photo data.

[0609] Input: Uploaded photo data

[0610] Output: Data about ingredients in the photo and their quantities

[0611] How it works: The server uses an image processing engine (e.g., TensorFlow or OpenCV) to identify ingredients from the photo and determine their approximate weight and quantity.

[0612] Step 5:

[0613] The server calculates calories and nutrients based on the analysis results.

[0614] Input: Identified food ingredient data

[0615] Output: Calorie and nutrient data for meals

[0616] Specific operation: The server references the nutritional information for each ingredient stored in the database and calculates calories and major nutrients (e.g., fat, protein, vitamins, etc.) based on the identified ingredient data.

[0617] Step 6:

[0618] The server stores the calculation results in cumulative data for each user.

[0619] Input: Calculated calories and nutrient data

[0620] Output: New meal data added to the cumulative data per user

[0621] Specific operation: The server associates the calculation results with individual user profiles and stores them in cumulative data.

[0622] Step 7:

[0623] The server generates health advice using generation AI.

[0624] Input: Accumulative data and latest meal data

[0625] Output: Generated health advice

[0626] Specific operation: Using a generative AI model (e.g., GPT-3), specific health advice is generated based on the user's cumulative data and latest dietary information.

[0627] Step 8:

[0628] The server sends the advice to the device via push notification.

[0629] Input: Generated health advice

[0630] Output: Sending advice via push notification

[0631] Specific operation: The generated advice is pushed from the server to the user's device in real time.

[0632] Step 9:

[0633] The device notifies the user of the advice and displays it within the app.

[0634] Input: Push notification from the server

[0635] Output: Detailed advice displayed in the app

[0636] Specific operation: The device notifies the user of notifications received and displays detailed advice within the application, allowing the user to check health advice in real time.

[0637] 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.

[0638] This invention combines a health management system that automatically analyzes photos of meals taken by the user to calculate calories and suggest nutritional balance, with an emotion engine that recognizes the user's emotions to provide more personalized health advice. The system begins when the user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0639] System Overview

[0640] 1. User Action:

[0641] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[0642] 2. Device monitoring and notifications:

[0643] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[0644] 3. Upload to Cloud:

[0645] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[0646] 4. Parsing on the server:

[0647] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[0648] 5. Calorie and Nutritional Value Calculator:

[0649] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[0650] 6. Counting and Storage:

[0651] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[0652] 7. Acquiring emotion data using the emotion engine:

[0653] The server runs an emotion engine that analyzes emotions from user input and voice data. The emotion engine uses natural language processing and voice analysis to accurately identify the user's emotional state. This emotion data is sent to the server and added to the user's cumulative data.

[0654] 8. Advice generation by generative AI:

[0655] The server uses a generative AI model to generate specific health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes suggestions for dietary improvements and supplements, as well as messages that take into account the user's emotional state.

[0656] 9. Notification and Display of Advice:

[0657] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0658] Specific examples

[0659] Example 1: Breakfast analysis and advice

[0660] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After saving the photo, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated, such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0661] Example 2: Lunch analysis and advice

[0662] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated such as, "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a motivational message such as "Keep it up" is added to the advice and sent via push notification.

[0663] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice. The introduction of an emotion engine makes it possible to provide more personalized advice that takes into account the user's emotional state.

[0664] The processing flow will be explained below.

[0665] Step 1:

[0666] The user takes a photo of the meal and saves it in the photo folder of their smartphone. The user does not need to perform any special operations; they simply take a photo of the meal using a regular camera app.

[0667] Step 2:

[0668] The app installed on your device monitors your photo folder for changes and detects new photos by periodically scanning the folder in the background.

[0669] Step 3:

[0670] When a device detects a new photo, it uploads the photo data and user ID to the server via an HTTP POST request to a specified endpoint on the server.

[0671] Step 4:

[0672] The server stores the received photo data in the analysis directory, which prepares an analysis job and passes it to the image processing engine.

[0673] Step 5:

[0674] The server's image processing engine analyzes the photo to identify ingredients and their quantities, using a machine learning model to scan the ingredients in the photo, draw bounding boxes, and detect the name and quantity of each ingredient.

[0675] Step 6:

[0676] The server calculates calories and nutrients based on the output from the image processing engine. It references the nutritional information of ingredients stored in a database to calculate the total calories and each nutrient (protein, fat, carbohydrates, etc.) of the detected ingredients.

[0677] Step 7:

[0678] The server stores the calculation results as cumulative data for each user. The user's dietary history and nutritional information are recorded in a database and managed cumulatively for long-term tracking.

[0679] Step 8:

[0680] The server receives user input and voice data, which the emotion engine analyzes to identify the user's emotional state. The emotion engine uses natural language processing and voice analysis technology to identify emotions with high accuracy.

[0681] Step 9:

[0682] The emotion data analyzed by the emotion engine is sent to the server and added to the user's cumulative data, allowing for the integrated management of the user's emotional information.

[0683] Step 10:

[0684] The server uses the generative AI model to generate health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes messages that take into account the user's emotional state.

[0685] Step 11:

[0686] The server generates health advice and sends it to the device via push notification. The notification is sent in real time, allowing the user to receive the advice immediately.

[0687] Step 12:

[0688] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[0689] Example 2

[0690] 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."

[0691] In recent years, the importance of health management has increased, and there is a demand for dietary records, calorie calculations, and consideration of nutritional balance. However, manually recording meals and calculating calories and nutrients is cumbersome and inaccurate. Furthermore, simply providing uniform health advice without considering the user's emotional state poses a challenge, making it difficult to provide effective and personalized support to users.

[0692] 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.

[0693] In this invention, the server includes means for analyzing photo data of meals, means for calculating calories and nutrients, means for acquiring user emotion data using an emotion engine that analyzes emotions, means for generating health advice using a generation AI, and means for sending the advice to a terminal by push notification. This makes it possible to automate the recording and analysis of meals and provide personalized health advice that takes into account the user's emotional state.

[0694] A "user" is a person who uses this system to take photos of their meals and manage their health.

[0695] A "terminal" is a device used by a user, such as a smartphone or tablet, that has the function of taking and saving photos.

[0696] A "photo folder" is a location within the device where new photos are saved.

[0697] A "server" is a central computing resource with data analysis, calculation, storage, and notification functions.

[0698] The "image processing engine" is software installed on the server that identifies ingredients and their quantities from a photo of a meal.

[0699] "Calories" is a unit that indicates the amount of energy contained in food.

[0700] "Nutrients" are components contained in food ingredients that are necessary for maintaining health, and include carbohydrates, lipids, proteins, vitamins, etc.

[0701] An "emotion engine" is software that analyzes user input data and voice data to identify the user's emotional state.

[0702] A "generative AI model" is an artificial intelligence technology that generates health advice based on a user's cumulative data, latest dietary habits, and emotional data.

[0703] "Push notification" is a communication technology in which a server sends information to a device in real time.

[0704] "Cumulative data" refers to the collection of each user's meal records, nutritional information, and emotional data.

[0705] "Health Advice" is advice provided based on the user's diet and emotional state using a generative AI model.

[0706] This invention realizes a system that allows a user to take a photo of their meal, calculates the calorie and nutritional balance based on the photo, and provides health advice that takes the user's emotions into consideration. A specific embodiment of the system is described below.

[0707] First, the user takes a photo of their meal using the camera on their smartphone or tablet. At this time, the photo is automatically saved to the device's photo folder. An app installed on the device monitors the photo folder and detects when a new photo has been saved. This app runs in the background, reducing the user's operational burden.

[0708] When the device detects a new photo, it uploads it to a dedicated server. The uploaded photo data also contains the user's ID, which allows for individual management. The server acquires the received photo data and passes it to an image processing engine. The image processing engine uses machine learning models such as TensorFlow and PyTorch. This engine identifies ingredients in the photo with high accuracy and determines the type and quantity of each ingredient.

[0709] The server calculates calories and various nutrients based on the analysis results. The nutritional information used here is based on information for representative ingredients pre-stored in a database. The calculation results are saved as cumulative data for each user and used to track long-term eating patterns and nutritional balance.

[0710] The server then uses an emotion engine to obtain the user's emotional data. The emotion engine uses natural language processing and speech analysis technologies, such as IBM Watson and Google Cloud Natural Language API, to analyze emotions from the user's input data and voice data. This allows the user's emotional state to be identified as "stress," "joy," "sadness," etc. This emotional data is also added to the cumulative data.

[0711] The server then generates health advice using a generative AI model, such as OpenAI's GPT-4, which generates specific, personalized advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice includes suggestions for dietary improvements and supplements, as well as emotional messages. The server then sends the generated advice to the device via push notification.

[0712] The device will display the received notification to the user and allow them to view detailed advice within the app, allowing users to efficiently manage their daily diet and health.

[0713] Specific examples

[0714] Example 1: Breakfast analysis and advice

[0715] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated such as, "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice. The advice is sent to the user via push notification, which the user can open to view the details.

[0716] Example 2: Lunch analysis and advice

[0717] A user takes a photo of their lunch, which includes salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. Calories and nutrients (protein, vitamins, etc.) are calculated. As a result, advice is generated, such as "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a message such as "Keep up the good work" is added to the advice. The advice is sent via push notification, and the user can view details within the app.

[0718] Prompt Sentence Examples

[0719] Example prompt 1: Breakfast analysis and advice

[0720] A user takes a photo of pancakes, bacon, and orange juice for breakfast. The analysis results show 200g of pancakes, 50g of bacon, and 200ml of orange juice. The user is currently feeling stressed. Generate appropriate health advice.

[0721] Example prompt 2: Lunch analysis and advice

[0722] A user takes a photo of a salad, grilled chicken, and smoothie for lunch. The analysis results show 100g of salad, 150g of grilled chicken, and 300ml of smoothie. The user has a positive emotion. Generate appropriate health advice.

[0723]

[0724] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0725] Step 1:

[0726] A user takes a photo of a meal using the camera on their smartphone or tablet. The photo is automatically saved to the device's photo folder. This is the input, and the saved photo data is the output. The specific action is when the user opens the camera app and taps the button to take a photo.

[0727] Step 2:

[0728] An app installed on a device monitors a photo folder in the background. The app detects when a new photo has been saved and notifies the user. The input is the state of the photo folder, and the output is the saving of a new photo. Specifically, the device's file system event listener monitors changes in the folder and detects an event when a new photo is added.

[0729] Step 3:

[0730] The device uploads a new photo to a dedicated server. At this time, the photo data is assigned a user ID. The input is the new photo and the user ID, and the output is the photo data uploaded to the server. Specifically, the device app creates an HTTP request and sends the photo data to the server's upload API endpoint.

[0731] Step 4:

[0732] The server receives the received photo data and passes it to an image processing engine. The image processing engine uses an application (for example, TensorFlow or PyTorch). The input is the photo data, and the output is the analyzed ingredients and their quantities. Specifically, the data is processed by an image processing algorithm that detects the outlines of the ingredients in the photo, and a machine learning model that estimates the type and quantity of the ingredients.

[0733] Step 5:

[0734] The server calculates calories and nutrients based on the analyzed ingredient information. The input is ingredient information, and the output is calorie and nutrient data. Specifically, the server retrieves nutritional information for each ingredient from the database and uses it to calculate calories and nutrients.

[0735] Step 6:

[0736] The server saves the calculation results in the cumulative data for each user. The input is calorie and nutrient data, and the output is the updated cumulative data. The specific operation is to add new data to the user's cumulative data stored in the server's database and update it.

[0737] Step 7:

[0738] The server receives input data and voice data from the user and runs the emotion engine. The input is the user's input data and voice data, and the output is analyzed emotion data. Specifically, the server passes the data to the emotion engine and identifies the emotional state through natural language processing and voice analysis.

[0739] Step 8:

[0740] The server uses a generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The inputs are cumulative data, dietary details, and emotional data, and the output is the generated health advice. Specifically, the server inputs this data into the generative AI model and processes it to generate appropriate health advice and messages.

[0741] Step 9:

[0742] The server sends the generated advice to the device via push notification. The input is the health advice, and the output is the notification to the device. Specifically, the server creates a notification message and sends it to the device via a push notification service (e.g., Apple Push Notification Service or Firebase Cloud Messaging).

[0743] Step 10:

[0744] The device displays the received notification to the user. When the notification is tapped, detailed advice can be viewed within the app. The input is the push notification, and the output is advice that the user can view. Specifically, the device's notification system displays the notification, and when the user taps it, the details screen within the app opens.

[0745] (Application example 2)

[0746] 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."

[0747] Conventional health management systems only calculate the calories of meals and analyze nutritional balance, making it difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, when using food delivery services, there is a problem in that meal options cannot be optimized to match the user's health condition and emotions. This can lead to a decline in the user's overall health management and satisfaction.

[0748] 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 received photo data, means for calculating calories and nutrients, means for saving the calculation results in cumulative data for each user, means for generating health advice using a generation AI, means including an emotion recognition engine, and means for providing personalized dietary advice based on the user's emotional state in a food delivery service that takes a photo of a menu selected by the user and analyzes the calories and nutritional balance. This makes it possible to provide personalized health advice that takes the user's emotions into consideration, enabling optimal menu selection and health management when using a food delivery service.

[0749] In this invention, the term "user" refers to a person who uses the system to take food photos and receive health management advice.

[0750] A "terminal" refers to an electronic device that allows a user to take photos of their meals, monitor a photo folder, detect new photos, and upload them to a server.

[0751] "Server" refers to the computer system that is responsible for a series of processes, including receiving and analyzing photo data uploaded from the device, calculating calories and nutrients, storing the calculation results, and generating health advice using generative AI.

[0752] "Photo folder" refers to the storage location within the device where photos taken by the user are stored.

[0753] A "monitoring program that runs in the background" refers to software that automatically monitors photo folders without user interaction and detects when new photos are saved.

[0754] "Analysis" refers to image processing that identifies ingredients and their amounts based on the photo data received by the server.

[0755] "Calculating calories and nutrients" refers to the process of calculating the calories and nutritional balance of each ingredient based on the analysis results.

[0756] "Cumulative Data" refers to information that stores calorie and nutrient data calculated for each user over time and is used to track the user's eating patterns and nutritional balance.

[0757] "Generative AI" refers to an artificial intelligence model that generates personalized health advice based on a user's cumulative data, recent dietary habits, emotional data, etc.

[0758] "Push notification" refers to a notification message that is automatically sent from a server to a user's device.

[0759] An "emotion recognition engine" refers to artificial intelligence software that analyzes user input and voice data to identify emotional states.

[0760] "Food delivery service" refers to a service that allows users to order food online and have the food delivered to a specified location.

[0761] "Personalized advice" means health advice that is optimized for a particular user, taking into account the user's emotional state and cumulative data.

[0762] This invention combines an emotion recognition engine with a health management system that allows users to take photos of their meals, automatically analyzes the photos, calculates calories, and suggests nutritional balance, providing personalized health advice. This system also supports optimal menu selection and health management based on the user's emotional state when using a food delivery service.

[0763] System Configuration

[0764] The system consists of a user's device, a backend server, an image processing engine, a generative AI model, an emotion recognition engine, and more.

[0765] Hardware and Software Use

[0766] Smartphone: The user takes a photo of the meal and runs the app.

[0767] Server: Responsible for analyzing photos and generating advice using AI.

[0768] TensorFlow: Used as an image processing engine to identify ingredients.

[0769] Azure Cognitive Services: Used as an emotion recognition engine to analyze user emotions.

[0770] System Operation Overview

[0771] 1. User Action:

[0772] Users take a photo of the food delivery menu using their smartphone camera, and the photo is automatically saved in a photo folder.

[0773] 2. Photo folder monitoring:

[0774] A background program running on the device monitors the photo folder and detects when new photos are saved.

[0775] 3. Upload to the server:

[0776] The device uploads the newly saved photo to the server, along with any user input (text or voice input).

[0777] 4. Photo Analysis:

[0778] The server analyzes the received photo data using TensorFlow to identify the ingredients and their quantities.

[0779] 5. Calorie and Nutrition Counts:

[0780] Based on the analyzed ingredient information, the calories and nutrients of each ingredient are calculated.

[0781] 6. Emotion recognition:

[0782] The server uses Azure Cognitive Services to analyze emotions from user input data.

[0783] 7. Advice generation using generative AI models:

[0784] The server uses a generative AI model to generate health advice based on the user's cumulative data, recent dietary history, and emotional data.

[0785] 8. Push Notifications:

[0786] The generated advice is sent to the device via a push notification, and the user can open the notification to view the detailed advice within the app.

[0787] Specific examples

[0788] Example 1: A user takes a photo of a fried chicken bento they ordered via food delivery for lunch and types, "I'm tired from work today." The device detects the new photo and uploads it to the server. The server analyzes the photo, identifies the fried chicken and various side dishes, and their portions, and calculates the calories and nutrients. At the same time, it uses Azure Cognitive Services to analyze emotions and detects that the user is "tired." As a result, personalized advice is generated and sent via push notification, such as, "This meal was high in fat, so choose a vegetable-based menu for your next meal. High-fat meals on a tired day can cause stress, so choose a lighter meal next time."

[0789] Example 2: A user takes a photo of pancakes, bacon, and orange juice for breakfast and saves the photo in a folder. The device detects the photo and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch" is generated. If the emotion recognition engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification.

[0790] Example prompt sentence:

[0791] "A user orders a fried chicken bento for lunch and types a photo of it along with the comment, 'I'm tired from work today.' Give them personalized advice based on their diet and their emotions."

[0792] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0793] Step 1:

[0794] A user takes a photo of a food delivery menu using the camera on their smartphone. The photo is automatically saved in a photo folder. In this example, the input is a "photo of the menu" and the output is the "image data saved in the photo folder."

[0795] Step 2:

[0796] A background program on the device monitors the photo folder and detects when new photos are saved. The input is the "photo folder status" and the output is "new photo detection notification." Specifically, the program periodically checks the folder and catches the information when a new photo is saved.

[0797] Step 3:

[0798] The device uploads the newly saved photo data to the server. At this time, it also sends the user's input data (text and voice input). The input is "new photo data and user input data," and the output is "data uploaded to the server." Specifically, the device sends the data to the server using an HTTP POST request.

[0799] Step 4:

[0800] The server analyzes the received photo data using an image processing engine (TensorFlow) to identify the ingredients and their quantities. The input is "photo data" and the output is "ingredient information (type and quantity)." Specifically, the server inputs the image data into the TensorFlow model and obtains the type of ingredient and its quantity as the model's output.

[0801] Step 5:

[0802] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information. The input is "ingredient information" and the output is "calculated calorie and nutrient data." Specifically, the server obtains the calorie and nutrient information for each ingredient from the database within the server and performs calculations based on that information.

[0803] Step 6:

[0804] The server uses Azure Cognitive Services to analyze emotions from user input data (text or voice). The input is "user input data" and the output is "emotion data." Specifically, the server sends an API request to Azure Cognitive Services and receives the emotion analysis results.

[0805] Step 7:

[0806] The server uses the generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The input is "cumulative data, dietary details, and emotional data," and the output is "generated health advice." Specifically, the server inputs this data into the generative AI model and outputs the optimal advice.

[0807] Step 8:

[0808] The generated advice is sent from the server to the device as a push notification. The input is the "generated health advice" and the output is the "notification sent to the device." Specifically, the server uses the push notification service to send the notification to the app.

[0809] Step 9:

[0810] The device displays the received notification to the user and allows them to view detailed advice within the app. The input is the "content of the push notification" and the output is the "advice displayed to the user." Specifically, clicking the notification launches the app and displays the advice.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] [Third embodiment]

[0815] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0816] 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.

[0817] 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).

[0818] 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.

[0819] 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.

[0820] 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).

[0821] 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. 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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."

[0827] This invention provides a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when a user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0828] System Overview

[0829] 1. User Action:

[0830] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[0831] 2. Device monitoring and notifications:

[0832] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[0833] 3. Upload to Cloud:

[0834] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[0835] 4. Parsing on the server:

[0836] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[0837] 5. Calorie and Nutritional Value Calculator:

[0838] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[0839] 6. Counting and Storage:

[0840] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[0841] 7. Generative AI Advice:

[0842] The server uses a generative AI model to generate specific health advice based on the user's cumulative data and their most recent dietary habits, including suggestions for dietary improvements and supplements.

[0843] 8. Notification and Display of Advice:

[0844] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0845] Specific examples

[0846] Example 1: Breakfast analysis and advice

[0847] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0848] Example 2: Lunch analysis and advice

[0849] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[0850] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice.

[0851] The processing flow will be explained below.

[0852] Step 1:

[0853] The user takes a photo of their meal and saves it to the photo folder on their smartphone. The user opens the camera app, takes a photo of the meal, and saves it to the photo folder naturally without any special operation.

[0854] Step 2:

[0855] Your device will run a background service to monitor your photo folder and detect new photos. The monitoring program will periodically scan your photo folder to check if any new photo files have been added.

[0856] Step 3:

[0857] When the device detects a new meal photo, it calls an API to upload the photo and user ID to the server. Here, the path to the photo file and the user ID information are sent to the server in the form of a POST request.

[0858] Step 4:

[0859] The server receives the HTTP request, saves the photo data in the analysis directory, and prepares to pass the photo data to the image processing engine as an image analysis job.

[0860] Step 5:

[0861] The server's image processing engine analyzes the photo to identify ingredients and their quantities. The image processing engine uses machine learning models to scan the photo and output a bounding box, name, and estimated quantity for each ingredient.

[0862] Step 6:

[0863] The server calculates calories and nutrients based on the output from the image processing engine, referencing the nutritional information for each ingredient stored in the database to calculate the total calories, protein, fat, carbohydrates, etc. of the identified ingredients.

[0864] Step 7:

[0865] The server stores the calculation results as cumulative data for each user. Each user's dietary history and nutritional information are recorded in a database and managed cumulatively.

[0866] Step 8:

[0867] The server generates health advice using a generative AI model based on the user's cumulative data and latest dietary information. The generative AI model takes the user's current situation into consideration and outputs specific advice and improvement suggestions in text format.

[0868] Step 9:

[0869] The server generates health advice and sends it to the device via push notifications, which are sent in real time via APNs or Firebase Cloud Messaging services.

[0870] Step 10:

[0871] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[0872] Example 1

[0873] 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."

[0874] Conventional health management systems require users to manually input their dietary information, which is cumbersome and time-consuming. Furthermore, there are limitations to the accuracy of nutritional balance and calorie calculation, making it difficult to provide individually optimized advice. The present invention aims to solve these problems and realize automated dietary management and highly accurate nutritional balance recommendations.

[0875] 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.

[0876] In this invention, the server includes a means for analyzing photos of meals taken by the user and identifying ingredients and their amounts, a means for calculating calories and nutrients based on the analysis results, and a means for generating individually optimized health advice using a generative AI model, thereby reducing the burden on the user and enabling highly accurate nutritional balance suggestions.

[0877] "User" refers to a person who uses the system to take photos of their meals and receive health management services.

[0878] "Device" refers to an electronic device such as a smartphone or tablet owned by a user.

[0879] The "photo folder" is a folder provided in the terminal, and refers to a location where photos taken by the user are automatically saved.

[0880] A "server" is a computer system installed on the cloud that analyzes received photo data, calculates calories, and generates advice using a generative AI model.

[0881] "Means for analyzing received photographic data" refers to software and / or hardware that performs the process of analyzing the photograph of the meal to identify ingredients and their quantities.

[0882] "Image processing engine" refers to algorithms and systems that use machine learning models to analyze food photos and identify ingredients.

[0883] "Means for calculating calories and nutrients" refers to software or databases for calculating the calories and nutrients of each ingredient based on analyzed ingredient information.

[0884] "Means for storing cumulative data" means a database or storage process for storing cumulative calorie and nutrient data for each user and tracking long-term eating patterns.

[0885] "Generative AI Model" refers to a machine learning model used to generate health advice based on received data.

[0886] "Means for generating health advice" refers to the process of using a generative AI model to create health improvements and suggestions based on the analysis results and the user's cumulative data.

[0887] "Means for sending push notifications" refers to communication technologies and protocols for notifying the user's device of advice generated by the server in real time.

[0888] "Means of notifying the device and displaying within the app" refers to the interface or software that displays advice on the user's device and allows detailed information to be viewed within the application.

[0889] "User identification information" refers to identification data for identifying an individual user, such as a user ID or account information.

[0890] "Means for obtaining ingredient information from a database" refers to the process of obtaining the necessary data from a database that stores calorie and nutrient information.

[0891] "Machine learning model" refers to the algorithms trained on the server to perform photo analysis and ingredient identification.

[0892] This invention is a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when the user takes a photo of the meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[0893] System Overview

[0894] First, a user takes a photo of a meal using the camera app on their smartphone. The photo is automatically saved in the device's photo folder. An application running in the background is installed on the device, and this application monitors the photo folder in real time. When it detects that a new photo has been saved, it uploads the photo data to the server.

[0895] The server uses an image processing engine with a machine learning model to analyze the received photo data. Here, it uses technologies such as TensorFlow and OpenCV to identify ingredients and their quantities. Based on the analysis results, the server calculates the calories and nutrients for each ingredient. For calculations, it references a database that stores nutritional information for ingredients (such as the USDA Nutrient Database).

[0896] The calculation results are stored in a database as the user's cumulative data, allowing the user to track their long-term eating patterns and nutritional balance. The server then uses a generative AI model (such as OpenAI's GPT-4) to generate health advice based on the user's cumulative data and their most recent dietary history. This advice is specific and may include suggestions for dietary improvements or supplements.

[0897] The generated advice is sent to the user's device via push notification from the server, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[0898] Specific examples

[0899] Example 1: Breakfast analysis and advice

[0900] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[0901] Example prompt:

[0902] Analyze a photo of your breakfast, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 200g of pancakes, 50g of bacon, and 200ml of orange juice.

[0903] Example 2: Lunch analysis and advice

[0904] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[0905] Example prompt:

[0906] Analyze a photo of your lunch, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 100g of salad, 150g of grilled chicken, and 300ml of smoothie.

[0907] In this way, the system is able to fully automate the user's dietary management and provide continuous, individually optimized health advice.

[0908] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0909] Step 1:

[0910] A user opens the camera app on their smartphone and takes a photo of their meal. The photo is automatically saved to the device's photo folder. The input is a photo of the meal taken by the user, and the output is that the photo is saved to the device's photo folder.

[0911] Step 2:

[0912] An app installed on the device monitors the photo folder in the background to detect when a new photo has been saved. This monitoring is done using the Python watchdog library. The input is a save event to the photo folder, and the output is a detection signal that a new photo has been saved.

[0913] Step 3:

[0914] After the device detects a new photo, it sends the photo data and the user ID to the server. This is done using an HTTP request, specifically the requests library. The input is the new photo data and the user ID, and the output is that it is uploaded to the server.

[0915] Step 4:

[0916] The server passes the received photo data to an image processing engine to identify ingredients and their quantities. This analysis uses machine learning models (TensorFlow and OpenCV). The input is the received photo data, and the output is the identified ingredient information.

[0917] Step 5:

[0918] The server calculates the calories and nutrients for each ingredient based on the analysis results. The nutritional information for ingredients is obtained from a database (e.g., USDA Nutrient Database). The input is the analyzed ingredient information, and the output is the calculated calorie and nutrient information.

[0919] Step 6:

[0920] The server stores the calculation results in a database as cumulative data for each user, allowing you to track long-term eating patterns. The input is the calculated calories and nutrient information, and the output is the cumulative data.

[0921] Step 7:

[0922] The server uses a generative AI model (e.g., GPT-4) to generate health advice based on the user's accumulated data and latest dietary information. The input is the user's accumulated data and latest food information, and the output is the generated health advice. Example prompts to use:

[0923] A user's most recent meal consisted of 200g pancakes, 50g bacon, and 200ml orange juice. Please provide health advice based on this meal.

[0924] Step 8:

[0925] The server sends the generated advice to the device as a push notification using Firebase Cloud Messaging (FCM). The input is the generated health advice, and the output is the notification sent.

[0926] Step 9:

[0927] The device displays the received notification to the user and allows detailed advice to be viewed within the app. The input is the received notification and advice data, and the output is the display within the app.

[0928] Through these steps, the system is able to analyze photos of meals taken by users and provide calorie calculations and personalized health advice.

[0929] (Application example 1)

[0930] 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."

[0931] To manage one's health, it is important to understand the calorie and nutritional value of one's meals and receive appropriate guidance. However, doing this manually is extremely time-consuming. Furthermore, when eating at a restaurant, it is difficult to know the exact calorie and nutritional value from the menu. For this reason, there is a demand for a system that allows users to easily measure the calorie and nutritional value of their meals and receive health advice in real time.

[0932] 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.

[0933] In this invention, the server includes: means for a user to take photos of their meals and save them in a photo folder; means for a device to monitor the photo folder and detect new photos; means for the device to upload new photos to the server; means for the server to analyze the received photo data; means for the server to calculate calories and nutrients based on the analysis results; means for the server to store the calculation results in cumulative data for each user; means for the server to generate health advice using a generation AI; means for the server to send the advice to the device by push notification; means for the device to notify the user of the advice and display it within the app; and means for a user to take photos of restaurant menus and analyze the calories and nutritional value to support meal selection. This enables a user to simply take photos of their meals and receive analysis results of calories and nutritional value, providing real-time support for healthy meal selection.

[0934] "User" refers to a person who uses this system to take photos of their meals and receive health advice.

[0935] "Means for taking photos of meals" refers to the ability to take photos of meals using a device such as a smartphone or smart glasses and save the photos in the device's photo folder.

[0936] "Means for monitoring photo folders" refers to having the ability to periodically check a specific folder on the device and detect when new photos have been added.

[0937] "Means for uploading new photos to the server" refers to having a function for transferring new photos stored on the device to the server via the Internet.

[0938] "Means for analyzing photographic data" refers to the ability of the server to analyze the photographs it receives using image processing technology and identify the ingredients and their amounts in the photographs.

[0939] "Means for calculating calories and nutrients" refers to the ability to calculate the calories and nutrients of each ingredient based on the analyzed ingredient information.

[0940] "Means for saving cumulative data for each user" refers to the ability to link calculated calorie and nutrient data to individual user profiles and save them.

[0941] "Means for generating health advice using generative AI" refers to the ability of the generative AI model to create appropriate health advice based on cumulative data and the latest dietary information.

[0942] "Means for sending advice to a device via push notification" refers to having the ability to notify the device of generated health advice in real time.

[0943] "Means for notifying the user of the advice and displaying it within the app" refers to having the function of informing the user of the received advice and displaying detailed information within the application.

[0944] "Means for taking photos of restaurant menus and analyzing their calories and nutritional value" refers to a function that allows a user to take a photo of a restaurant menu and analyze the calories and nutritional value based on that photo.

[0945] The "image processing engine for identifying ingredients and their quantities" refers to algorithms or software that can identify specific ingredients from a photo and estimate their approximate weight and quantity.

[0946] A "generative AI model" is an artificial intelligence-based model that automatically generates health advice based on collected data.

[0947] A "prompt sentence" is a sentence that is input to a generative AI model to obtain an appropriate response.

[0948] The following system configuration and procedures are used to implement the present invention: The main components of the system include a device that allows a user to take photos of their meals, a terminal that monitors the photo folder, and a server that analyzes the photo data.

[0949] System Configuration

[0950] 1. Your device

[0951] Use your smartphone or smart glasses to take a photo of your meal and save the photo in the device's photo folder.

[0952] 2. Terminal

[0953] This applies to smartphones and smart glasses, and monitors photo folders to detect newly saved photos.

[0954] It also has the function of uploading new photos to the server.

[0955] 3. Server

[0956] The server receives the uploaded photo data and uses an image processing engine to identify the ingredients and their quantities.

[0957] It has data to calculate calories and nutritional value based on ingredient information.

[0958] It has the function of saving cumulative data for each user.

[0959] It uses a generative AI model to generate health advice based on your cumulative data and your most recent diet.

[0960] The generated advice is sent to the user's device via push notification.

[0961] Hardware and software used

[0962] Hardware:

[0963] Devices: Smartphones (e.g., iPhone, Android smartphones), smart glasses (e.g., Google Glass)

[0964] Server: High-performance cloud server (e.g., Amazon AWS, Microsoft Azure)

[0965] software:

[0966] Device monitoring: background services using Python and Java

[0967] Image processing engine: Uses TensorFlow and OpenCV

[0968] Cloud storage and database management: Amazon S3 and MySQL

[0969] Generative AI models: Machine learning models such as TensorFlow or GPT-3

[0970] Specific examples

[0971] Example 1: Breakfast analysis and advice

[0972] A user uses their smartphone to take a photo of their breakfast (pancakes, bacon, and orange juice). Once the photo is saved, the device detects it and automatically uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on the analysis results, calories and nutrients are calculated, and advice is generated: "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch." This advice is sent via a push notification to the user's smartphone, and details can be viewed within the app.

[0973] Example 2: Restaurant meal selection support

[0974] A user takes a photo of a salad, grilled chicken, and smoothie at a restaurant using smart glasses. The device detects the new photo and uploads it to the server. The server analyzes the photo and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This generates advice such as, "This meal is well-balanced, so continue with this." This advice is displayed on the smart glasses' display, and the user can check it in real time.

[0975] Prompt Sentence Examples

[0976] Food photo: salad, grilled chicken, smoothie

[0977] Calories and nutritional value: 100g salad, 150g grilled chicken, 300ml smoothie

[0978] Advice: This diet is well balanced, so stick with it.

[0979] This system allows users to easily analyze the calories and nutritional value of their meals and provides real-time support for making healthy eating choices.

[0980] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0981] Step 1:

[0982] A user takes a photo of their meal and saves it in the device's photo folder.

[0983] Input: Food photo

[0984] Output: Photo files saved in the device's photo folder

[0985] How it works: Users use their smartphone or smart glasses to take photos of their food at a restaurant or at home, and the photos are automatically saved to the device's photo folder.

[0986] Step 2:

[0987] Your device monitors your photo folder for new photos.

[0988] Input: A new photo saved in the Photos folder

[0989] Output: New photo detected notification

[0990] How it works: A monitoring program running on the device periodically checks the photo folder to detect newly saved photos.

[0991] Step 3:

[0992] The device uploads the new photo to the server.

[0993] Input: Newly detected photo file

[0994] Output: Photo data uploaded to the server

[0995] Specific operation: Retrieves new photo files from the photo folder and uploads them to the server via the Internet, along with the user ID.

[0996] Step 4:

[0997] The server analyzes the received photo data.

[0998] Input: Uploaded photo data

[0999] Output: Data about ingredients in the photo and their quantities

[1000] How it works: The server uses an image processing engine (e.g., TensorFlow or OpenCV) to identify ingredients from the photo and determine their approximate weight and quantity.

[1001] Step 5:

[1002] The server calculates calories and nutrients based on the analysis results.

[1003] Input: Identified food ingredient data

[1004] Output: Calorie and nutrient data for meals

[1005] Specific operation: The server references the nutritional information for each ingredient stored in the database and calculates calories and major nutrients (e.g., fat, protein, vitamins, etc.) based on the identified ingredient data.

[1006] Step 6:

[1007] The server stores the calculation results in cumulative data for each user.

[1008] Input: Calculated calories and nutrient data

[1009] Output: New meal data added to the cumulative data per user

[1010] Specific operation: The server associates the calculation results with individual user profiles and stores them in cumulative data.

[1011] Step 7:

[1012] The server generates health advice using generation AI.

[1013] Input: Accumulative data and latest meal data

[1014] Output: Generated health advice

[1015] Specific operation: Using a generative AI model (e.g., GPT-3), specific health advice is generated based on the user's cumulative data and latest dietary information.

[1016] Step 8:

[1017] The server sends the advice to the device via push notification.

[1018] Input: Generated health advice

[1019] Output: Sending advice via push notification

[1020] Specific operation: The generated advice is pushed from the server to the user's device in real time.

[1021] Step 9:

[1022] The device notifies the user of the advice and displays it within the app.

[1023] Input: Push notification from the server

[1024] Output: Detailed advice displayed in the app

[1025] Specific operation: The device notifies the user of notifications received and displays detailed advice within the application, allowing the user to check health advice in real time.

[1026] 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.

[1027] This invention combines a health management system that automatically analyzes photos of meals taken by the user to calculate calories and suggest nutritional balance, with an emotion engine that recognizes the user's emotions to provide more personalized health advice. The system begins when the user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[1028] System Overview

[1029] 1. User Action:

[1030] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[1031] 2. Device monitoring and notifications:

[1032] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[1033] 3. Upload to Cloud:

[1034] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[1035] 4. Parsing on the server:

[1036] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[1037] 5. Calorie and Nutritional Value Calculator:

[1038] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[1039] 6. Counting and Storage:

[1040] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[1041] 7. Acquiring emotion data using the emotion engine:

[1042] The server runs an emotion engine that analyzes emotions from user input and voice data. The emotion engine uses natural language processing and voice analysis to accurately identify the user's emotional state. This emotion data is sent to the server and added to the user's cumulative data.

[1043] 8. Advice generation by generative AI:

[1044] The server uses a generative AI model to generate specific health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes suggestions for dietary improvements and supplements, as well as messages that take into account the user's emotional state.

[1045] 9. Notification and Display of Advice:

[1046] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[1047] Specific examples

[1048] Example 1: Breakfast analysis and advice

[1049] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After saving the photo, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated, such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[1050] Example 2: Lunch analysis and advice

[1051] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated such as, "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a motivational message such as "Keep it up" is added to the advice and sent via push notification.

[1052] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice. The introduction of an emotion engine makes it possible to provide more personalized advice that takes into account the user's emotional state.

[1053] The processing flow will be explained below.

[1054] Step 1:

[1055] The user takes a photo of the meal and saves it in the photo folder of their smartphone. The user does not need to perform any special operations; they simply take a photo of the meal using a regular camera app.

[1056] Step 2:

[1057] The app installed on your device monitors your photo folder for changes and detects new photos by periodically scanning the folder in the background.

[1058] Step 3:

[1059] When a device detects a new photo, it uploads the photo data and user ID to the server via an HTTP POST request to a specified endpoint on the server.

[1060] Step 4:

[1061] The server stores the received photo data in the analysis directory, which prepares an analysis job and passes it to the image processing engine.

[1062] Step 5:

[1063] The server's image processing engine analyzes the photo to identify ingredients and their quantities, using a machine learning model to scan the ingredients in the photo, draw bounding boxes, and detect the name and quantity of each ingredient.

[1064] Step 6:

[1065] The server calculates calories and nutrients based on the output from the image processing engine. It references the nutritional information of ingredients stored in a database to calculate the total calories and each nutrient (protein, fat, carbohydrates, etc.) of the detected ingredients.

[1066] Step 7:

[1067] The server stores the calculation results as cumulative data for each user. The user's dietary history and nutritional information are recorded in a database and managed cumulatively for long-term tracking.

[1068] Step 8:

[1069] The server receives user input and voice data, which the emotion engine analyzes to identify the user's emotional state. The emotion engine uses natural language processing and voice analysis technology to identify emotions with high accuracy.

[1070] Step 9:

[1071] The emotion data analyzed by the emotion engine is sent to the server and added to the user's cumulative data, allowing for the integrated management of the user's emotional information.

[1072] Step 10:

[1073] The server uses the generative AI model to generate health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes messages that take into account the user's emotional state.

[1074] Step 11:

[1075] The server generates health advice and sends it to the device via push notification. The notification is sent in real time, allowing the user to receive the advice immediately.

[1076] Step 12:

[1077] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[1078] Example 2

[1079] 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."

[1080] In recent years, the importance of health management has increased, and there is a demand for dietary records, calorie calculations, and consideration of nutritional balance. However, manually recording meals and calculating calories and nutrients is cumbersome and inaccurate. Furthermore, simply providing uniform health advice without considering the user's emotional state poses a challenge, making it difficult to provide effective and personalized support to users.

[1081] 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.

[1082] In this invention, the server includes means for analyzing photo data of meals, means for calculating calories and nutrients, means for acquiring user emotion data using an emotion engine that analyzes emotions, means for generating health advice using a generation AI, and means for sending the advice to a terminal by push notification. This makes it possible to automate the recording and analysis of meals and provide personalized health advice that takes into account the user's emotional state.

[1083] A "user" is a person who uses this system to take photos of their meals and manage their health.

[1084] A "terminal" is a device used by a user, such as a smartphone or tablet, that has the function of taking and saving photos.

[1085] A "photo folder" is a location within the device where new photos are saved.

[1086] A "server" is a central computing resource with data analysis, calculation, storage, and notification functions.

[1087] The "image processing engine" is software installed on the server that identifies ingredients and their quantities from a photo of a meal.

[1088] "Calories" is a unit that indicates the amount of energy contained in food.

[1089] "Nutrients" are components contained in food ingredients that are necessary for maintaining health, and include carbohydrates, lipids, proteins, vitamins, etc.

[1090] An "emotion engine" is software that analyzes user input data and voice data to identify the user's emotional state.

[1091] A "generative AI model" is an artificial intelligence technology that generates health advice based on a user's cumulative data, latest dietary habits, and emotional data.

[1092] "Push notification" is a communication technology in which a server sends information to a device in real time.

[1093] "Cumulative data" refers to the collection of each user's meal records, nutritional information, and emotional data.

[1094] "Health Advice" is advice provided based on the user's diet and emotional state using a generative AI model.

[1095] This invention realizes a system that allows a user to take a photo of their meal, calculates the calorie and nutritional balance based on the photo, and provides health advice that takes the user's emotions into consideration. A specific embodiment of the system is described below.

[1096] First, the user takes a photo of their meal using the camera on their smartphone or tablet. At this time, the photo is automatically saved to the device's photo folder. An app installed on the device monitors the photo folder and detects when a new photo has been saved. This app runs in the background, reducing the user's operational burden.

[1097] When the device detects a new photo, it uploads it to a dedicated server. The uploaded photo data also contains the user's ID, which allows for individual management. The server acquires the received photo data and passes it to an image processing engine. The image processing engine uses machine learning models such as TensorFlow and PyTorch. This engine identifies ingredients in the photo with high accuracy and determines the type and quantity of each ingredient.

[1098] The server calculates calories and various nutrients based on the analysis results. The nutritional information used here is based on information for representative ingredients pre-stored in a database. The calculation results are saved as cumulative data for each user and used to track long-term eating patterns and nutritional balance.

[1099] The server then uses an emotion engine to obtain the user's emotional data. The emotion engine uses natural language processing and speech analysis technologies, such as IBM Watson and Google Cloud Natural Language API, to analyze emotions from the user's input data and voice data. This allows the user's emotional state to be identified as "stress," "joy," "sadness," etc. This emotional data is also added to the cumulative data.

[1100] The server then generates health advice using a generative AI model, such as OpenAI's GPT-4, which generates specific, personalized advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice includes suggestions for dietary improvements and supplements, as well as emotional messages. The server then sends the generated advice to the device via push notification.

[1101] The device will display the received notification to the user and allow them to view detailed advice within the app, allowing users to efficiently manage their daily diet and health.

[1102] Specific examples

[1103] Example 1: Breakfast analysis and advice

[1104] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated such as, "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice. The advice is sent to the user via push notification, which the user can open to view the details.

[1105] Example 2: Lunch analysis and advice

[1106] A user takes a photo of their lunch, which includes salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. Calories and nutrients (protein, vitamins, etc.) are calculated. As a result, advice is generated, such as "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a message such as "Keep up the good work" is added to the advice. The advice is sent via push notification, and the user can view details within the app.

[1107] Prompt Sentence Examples

[1108] Example prompt 1: Breakfast analysis and advice

[1109] A user takes a photo of pancakes, bacon, and orange juice for breakfast. The analysis results show 200g of pancakes, 50g of bacon, and 200ml of orange juice. The user is currently feeling stressed. Generate appropriate health advice.

[1110] Example prompt 2: Lunch analysis and advice

[1111] A user takes a photo of a salad, grilled chicken, and smoothie for lunch. The analysis results show 100g of salad, 150g of grilled chicken, and 300ml of smoothie. The user has a positive emotion. Generate appropriate health advice.

[1112]

[1113] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1114] Step 1:

[1115] A user takes a photo of a meal using the camera on their smartphone or tablet. The photo is automatically saved to the device's photo folder. This is the input, and the saved photo data is the output. The specific action is when the user opens the camera app and taps the button to take a photo.

[1116] Step 2:

[1117] An app installed on a device monitors a photo folder in the background. The app detects when a new photo has been saved and notifies the user. The input is the state of the photo folder, and the output is the saving of a new photo. Specifically, the device's file system event listener monitors changes in the folder and detects an event when a new photo is added.

[1118] Step 3:

[1119] The device uploads a new photo to a dedicated server. At this time, the photo data is assigned a user ID. The input is the new photo and the user ID, and the output is the photo data uploaded to the server. Specifically, the device app creates an HTTP request and sends the photo data to the server's upload API endpoint.

[1120] Step 4:

[1121] The server receives the received photo data and passes it to an image processing engine. The image processing engine uses an application (for example, TensorFlow or PyTorch). The input is the photo data, and the output is the analyzed ingredients and their quantities. Specifically, the data is processed by an image processing algorithm that detects the outlines of the ingredients in the photo, and a machine learning model that estimates the type and quantity of the ingredients.

[1122] Step 5:

[1123] The server calculates calories and nutrients based on the analyzed ingredient information. The input is ingredient information, and the output is calorie and nutrient data. Specifically, the server retrieves nutritional information for each ingredient from the database and uses it to calculate calories and nutrients.

[1124] Step 6:

[1125] The server saves the calculation results in the cumulative data for each user. The input is calorie and nutrient data, and the output is the updated cumulative data. The specific operation is to add new data to the user's cumulative data stored in the server's database and update it.

[1126] Step 7:

[1127] The server receives input data and voice data from the user and runs the emotion engine. The input is the user's input data and voice data, and the output is analyzed emotion data. Specifically, the server passes the data to the emotion engine and identifies the emotional state through natural language processing and voice analysis.

[1128] Step 8:

[1129] The server uses a generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The inputs are cumulative data, dietary details, and emotional data, and the output is the generated health advice. Specifically, the server inputs this data into the generative AI model and processes it to generate appropriate health advice and messages.

[1130] Step 9:

[1131] The server sends the generated advice to the device via push notification. The input is the health advice, and the output is the notification to the device. Specifically, the server creates a notification message and sends it to the device via a push notification service (e.g., Apple Push Notification Service or Firebase Cloud Messaging).

[1132] Step 10:

[1133] The device displays the received notification to the user. When the notification is tapped, detailed advice can be viewed within the app. The input is the push notification, and the output is advice that the user can view. Specifically, the device's notification system displays the notification, and when the user taps it, the details screen within the app opens.

[1134] (Application example 2)

[1135] 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."

[1136] Conventional health management systems only calculate the calories of meals and analyze nutritional balance, making it difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, when using food delivery services, there is a problem in that meal options cannot be optimized to match the user's health condition and emotions. This can lead to a decline in the user's overall health management and satisfaction.

[1137] 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 received photo data, means for calculating calories and nutrients, means for saving the calculation results in cumulative data for each user, means for generating health advice using a generation AI, means including an emotion recognition engine, and means for providing personalized dietary advice based on the user's emotional state in a food delivery service that takes a photo of a menu selected by the user and analyzes the calories and nutritional balance. This makes it possible to provide personalized health advice that takes the user's emotions into consideration, enabling optimal menu selection and health management when using a food delivery service.

[1138] In this invention, the term "user" refers to a person who uses the system to take food photos and receive health management advice.

[1139] A "terminal" refers to an electronic device that allows a user to take photos of their meals, monitor a photo folder, detect new photos, and upload them to a server.

[1140] "Server" refers to the computer system that is responsible for a series of processes, including receiving and analyzing photo data uploaded from the device, calculating calories and nutrients, storing the calculation results, and generating health advice using generative AI.

[1141] "Photo folder" refers to the storage location within the device where photos taken by the user are stored.

[1142] A "monitoring program that runs in the background" refers to software that automatically monitors photo folders without user interaction and detects when new photos are saved.

[1143] "Analysis" refers to image processing that identifies ingredients and their amounts based on the photo data received by the server.

[1144] "Calculating calories and nutrients" refers to the process of calculating the calories and nutritional balance of each ingredient based on the analysis results.

[1145] "Cumulative Data" refers to information that stores calorie and nutrient data calculated for each user over time and is used to track the user's eating patterns and nutritional balance.

[1146] "Generative AI" refers to an artificial intelligence model that generates personalized health advice based on a user's cumulative data, recent dietary habits, emotional data, etc.

[1147] "Push notification" refers to a notification message that is automatically sent from a server to a user's device.

[1148] An "emotion recognition engine" refers to artificial intelligence software that analyzes user input and voice data to identify emotional states.

[1149] "Food delivery service" refers to a service that allows users to order food online and have the food delivered to a specified location.

[1150] "Personalized advice" means health advice that is optimized for a particular user, taking into account the user's emotional state and cumulative data.

[1151] This invention combines an emotion recognition engine with a health management system that allows users to take photos of their meals, automatically analyzes the photos, calculates calories, and suggests nutritional balance, providing personalized health advice. This system also supports optimal menu selection and health management based on the user's emotional state when using a food delivery service.

[1152] System Configuration

[1153] The system consists of a user's device, a backend server, an image processing engine, a generative AI model, an emotion recognition engine, and more.

[1154] Hardware and Software Use

[1155] Smartphone: The user takes a photo of the meal and runs the app.

[1156] Server: Responsible for analyzing photos and generating advice using AI.

[1157] TensorFlow: Used as an image processing engine to identify ingredients.

[1158] Azure Cognitive Services: Used as an emotion recognition engine to analyze user emotions.

[1159] System Operation Overview

[1160] 1. User Action:

[1161] Users take a photo of the food delivery menu using their smartphone camera, and the photo is automatically saved in a photo folder.

[1162] 2. Photo folder monitoring:

[1163] A background program running on the device monitors the photo folder and detects when new photos are saved.

[1164] 3. Upload to the server:

[1165] The device uploads the newly saved photo to the server, along with any user input (text or voice input).

[1166] 4. Photo Analysis:

[1167] The server analyzes the received photo data using TensorFlow to identify the ingredients and their quantities.

[1168] 5. Calorie and Nutrition Counts:

[1169] Based on the analyzed ingredient information, the calories and nutrients of each ingredient are calculated.

[1170] 6. Emotion recognition:

[1171] The server uses Azure Cognitive Services to analyze emotions from user input data.

[1172] 7. Advice generation using generative AI models:

[1173] The server uses a generative AI model to generate health advice based on the user's cumulative data, recent dietary history, and emotional data.

[1174] 8. Push Notifications:

[1175] The generated advice is sent to the device via a push notification, and the user can open the notification to view the detailed advice within the app.

[1176] Specific examples

[1177] Example 1: A user takes a photo of a fried chicken bento they ordered via food delivery for lunch and types, "I'm tired from work today." The device detects the new photo and uploads it to the server. The server analyzes the photo, identifies the fried chicken and various side dishes, and their portions, and calculates the calories and nutrients. At the same time, it uses Azure Cognitive Services to analyze emotions and detects that the user is "tired." As a result, personalized advice is generated and sent via push notification, such as, "This meal was high in fat, so choose a vegetable-based menu for your next meal. High-fat meals on a tired day can cause stress, so choose a lighter meal next time."

[1178] Example 2: A user takes a photo of pancakes, bacon, and orange juice for breakfast and saves the photo in a folder. The device detects the photo and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch" is generated. If the emotion recognition engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification.

[1179] Example prompt sentence:

[1180] "A user orders a fried chicken bento for lunch and types a photo of it along with the comment, 'I'm tired from work today.' Give them personalized advice based on their diet and their emotions."

[1181] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1182] Step 1:

[1183] A user takes a photo of a food delivery menu using the camera on their smartphone. The photo is automatically saved in a photo folder. In this example, the input is a "photo of the menu" and the output is the "image data saved in the photo folder."

[1184] Step 2:

[1185] A background program on the device monitors the photo folder and detects when new photos are saved. The input is the "photo folder status" and the output is "new photo detection notification." Specifically, the program periodically checks the folder and catches the information when a new photo is saved.

[1186] Step 3:

[1187] The device uploads the newly saved photo data to the server. At this time, it also sends the user's input data (text and voice input). The input is "new photo data and user input data," and the output is "data uploaded to the server." Specifically, the device sends the data to the server using an HTTP POST request.

[1188] Step 4:

[1189] The server analyzes the received photo data using an image processing engine (TensorFlow) to identify the ingredients and their quantities. The input is "photo data" and the output is "ingredient information (type and quantity)." Specifically, the server inputs the image data into the TensorFlow model and obtains the type of ingredient and its quantity as the model's output.

[1190] Step 5:

[1191] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information. The input is "ingredient information" and the output is "calculated calorie and nutrient data." Specifically, the server obtains the calorie and nutrient information for each ingredient from the database within the server and performs calculations based on that information.

[1192] Step 6:

[1193] The server uses Azure Cognitive Services to analyze emotions from user input data (text or voice). The input is "user input data" and the output is "emotion data." Specifically, the server sends an API request to Azure Cognitive Services and receives the emotion analysis results.

[1194] Step 7:

[1195] The server uses the generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The input is "cumulative data, dietary details, and emotional data," and the output is "generated health advice." Specifically, the server inputs this data into the generative AI model and outputs the optimal advice.

[1196] Step 8:

[1197] The generated advice is sent from the server to the device as a push notification. The input is the "generated health advice" and the output is the "notification sent to the device." Specifically, the server uses the push notification service to send the notification to the app.

[1198] Step 9:

[1199] The device displays the received notification to the user and allows them to view detailed advice within the app. The input is the "content of the push notification" and the output is the "advice displayed to the user." Specifically, clicking the notification launches the app and displays the advice.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] [Fourth embodiment]

[1204] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1205] 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.

[1206] 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).

[1207] 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.

[1208] 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.

[1209] 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).

[1210] 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. 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.

[1211] 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.

[1212] 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.

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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."

[1217] This invention provides a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when a user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[1218] System Overview

[1219] 1. User Action:

[1220] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[1221] 2. Device monitoring and notifications:

[1222] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[1223] 3. Upload to Cloud:

[1224] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[1225] 4. Parsing on the server:

[1226] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[1227] 5. Calorie and Nutritional Value Calculator:

[1228] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[1229] 6. Counting and Storage:

[1230] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[1231] 7. Generative AI Advice:

[1232] The server uses a generative AI model to generate specific health advice based on the user's cumulative data and their most recent dietary habits, including suggestions for dietary improvements and supplements.

[1233] 8. Notification and Display of Advice:

[1234] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[1235] Specific examples

[1236] Example 1: Breakfast analysis and advice

[1237] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[1238] Example 2: Lunch analysis and advice

[1239] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[1240] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice.

[1241] The processing flow will be explained below.

[1242] Step 1:

[1243] The user takes a photo of their meal and saves it to the photo folder on their smartphone. The user opens the camera app, takes a photo of the meal, and saves it to the photo folder naturally without any special operation.

[1244] Step 2:

[1245] Your device will run a background service to monitor your photo folder and detect new photos. The monitoring program will periodically scan your photo folder to check if any new photo files have been added.

[1246] Step 3:

[1247] When the device detects a new meal photo, it calls an API to upload the photo and user ID to the server. Here, the path to the photo file and the user ID information are sent to the server in the form of a POST request.

[1248] Step 4:

[1249] The server receives the HTTP request, saves the photo data in the analysis directory, and prepares to pass the photo data to the image processing engine as an image analysis job.

[1250] Step 5:

[1251] The server's image processing engine analyzes the photo to identify ingredients and their quantities. The image processing engine uses machine learning models to scan the photo and output a bounding box, name, and estimated quantity for each ingredient.

[1252] Step 6:

[1253] The server calculates calories and nutrients based on the output from the image processing engine, referencing the nutritional information for each ingredient stored in the database to calculate the total calories, protein, fat, carbohydrates, etc. of the identified ingredients.

[1254] Step 7:

[1255] The server stores the calculation results as cumulative data for each user. Each user's dietary history and nutritional information are recorded in a database and managed cumulatively.

[1256] Step 8:

[1257] The server generates health advice using a generative AI model based on the user's cumulative data and latest dietary information. The generative AI model takes the user's current situation into consideration and outputs specific advice and improvement suggestions in text format.

[1258] Step 9:

[1259] The server generates health advice and sends it to the device via push notifications, which are sent in real time via APNs or Firebase Cloud Messaging services.

[1260] Step 10:

[1261] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[1262] Example 1

[1263] 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."

[1264] Conventional health management systems require users to manually input their dietary information, which is cumbersome and time-consuming. Furthermore, there are limitations to the accuracy of nutritional balance and calorie calculation, making it difficult to provide individually optimized advice. The present invention aims to solve these problems and realize automated dietary management and highly accurate nutritional balance recommendations.

[1265] 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.

[1266] In this invention, the server includes a means for analyzing photos of meals taken by the user and identifying ingredients and their amounts, a means for calculating calories and nutrients based on the analysis results, and a means for generating individually optimized health advice using a generative AI model, thereby reducing the burden on the user and enabling highly accurate nutritional balance suggestions.

[1267] "User" refers to a person who uses the system to take photos of their meals and receive health management services.

[1268] "Device" refers to an electronic device such as a smartphone or tablet owned by a user.

[1269] The "photo folder" is a folder provided in the terminal, and refers to a location where photos taken by the user are automatically saved.

[1270] A "server" is a computer system installed on the cloud that analyzes received photo data, calculates calories, and generates advice using a generative AI model.

[1271] "Means for analyzing received photographic data" refers to software and / or hardware that performs the process of analyzing the photograph of the meal to identify ingredients and their quantities.

[1272] "Image processing engine" refers to algorithms and systems that use machine learning models to analyze food photos and identify ingredients.

[1273] "Means for calculating calories and nutrients" refers to software or databases for calculating the calories and nutrients of each ingredient based on analyzed ingredient information.

[1274] "Means for storing cumulative data" means a database or storage process for storing cumulative calorie and nutrient data for each user and tracking long-term eating patterns.

[1275] "Generative AI Model" refers to a machine learning model used to generate health advice based on received data.

[1276] "Means for generating health advice" refers to the process of using a generative AI model to create health improvements and suggestions based on the analysis results and the user's cumulative data.

[1277] "Means for sending push notifications" refers to communication technologies and protocols for notifying the user's device of advice generated by the server in real time.

[1278] "Means of notifying the device and displaying within the app" refers to the interface or software that displays advice on the user's device and allows detailed information to be viewed within the application.

[1279] "User identification information" refers to identification data for identifying an individual user, such as a user ID or account information.

[1280] "Means for obtaining ingredient information from a database" refers to the process of obtaining the necessary data from a database that stores calorie and nutrient information.

[1281] "Machine learning model" refers to the algorithms trained on the server to perform photo analysis and ingredient identification.

[1282] This invention is a health management system that automatically analyzes photos of meals taken by users, calculates calories, and suggests nutritional balance. The system starts when the user takes a photo of the meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[1283] System Overview

[1284] First, a user takes a photo of a meal using the camera app on their smartphone. The photo is automatically saved in the device's photo folder. An application running in the background is installed on the device, and this application monitors the photo folder in real time. When it detects that a new photo has been saved, it uploads the photo data to the server.

[1285] The server uses an image processing engine with a machine learning model to analyze the received photo data. Here, it uses technologies such as TensorFlow and OpenCV to identify ingredients and their quantities. Based on the analysis results, the server calculates the calories and nutrients for each ingredient. For calculations, it references a database that stores nutritional information for ingredients (such as the USDA Nutrient Database).

[1286] The calculation results are stored in a database as the user's cumulative data, allowing the user to track their long-term eating patterns and nutritional balance. The server then uses a generative AI model (such as OpenAI's GPT-4) to generate health advice based on the user's cumulative data and their most recent dietary history. This advice is specific and may include suggestions for dietary improvements or supplements.

[1287] The generated advice is sent to the user's device via push notification from the server, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[1288] Specific examples

[1289] Example 1: Breakfast analysis and advice

[1290] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch" is generated and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[1291] Example prompt:

[1292] Analyze a photo of your breakfast, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 200g of pancakes, 50g of bacon, and 200ml of orange juice.

[1293] Example 2: Lunch analysis and advice

[1294] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated and sent via push notification, such as, "This lunch is well-balanced, so keep it up. We also recommend a low-fat menu for dinner."

[1295] Example prompt:

[1296] Analyze a photo of your lunch, calculate the calories and nutrients of each ingredient, and provide health advice. The photo includes 100g of salad, 150g of grilled chicken, and 300ml of smoothie.

[1297] In this way, the system is able to fully automate the user's dietary management and provide continuous, individually optimized health advice.

[1298] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1299] Step 1:

[1300] A user opens the camera app on their smartphone and takes a photo of their meal. The photo is automatically saved to the device's photo folder. The input is a photo of the meal taken by the user, and the output is that the photo is saved to the device's photo folder.

[1301] Step 2:

[1302] An app installed on the device monitors the photo folder in the background to detect when a new photo has been saved. This monitoring is done using the Python watchdog library. The input is a save event to the photo folder, and the output is a detection signal that a new photo has been saved.

[1303] Step 3:

[1304] After the device detects a new photo, it sends the photo data and the user ID to the server. This is done using an HTTP request, specifically the requests library. The input is the new photo data and the user ID, and the output is that it is uploaded to the server.

[1305] Step 4:

[1306] The server passes the received photo data to an image processing engine to identify ingredients and their quantities. This analysis uses machine learning models (TensorFlow and OpenCV). The input is the received photo data, and the output is the identified ingredient information.

[1307] Step 5:

[1308] The server calculates the calories and nutrients for each ingredient based on the analysis results. The nutritional information for ingredients is obtained from a database (e.g., USDA Nutrient Database). The input is the analyzed ingredient information, and the output is the calculated calorie and nutrient information.

[1309] Step 6:

[1310] The server stores the calculation results in a database as cumulative data for each user, allowing you to track long-term eating patterns. The input is the calculated calories and nutrient information, and the output is the cumulative data.

[1311] Step 7:

[1312] The server uses a generative AI model (e.g., GPT-4) to generate health advice based on the user's accumulated data and latest dietary information. The input is the user's accumulated data and latest food information, and the output is the generated health advice. Example prompts to use:

[1313] A user's most recent meal consisted of 200g pancakes, 50g bacon, and 200ml orange juice. Please provide health advice based on this meal.

[1314] Step 8:

[1315] The server sends the generated advice to the device as a push notification using Firebase Cloud Messaging (FCM). The input is the generated health advice, and the output is the notification sent.

[1316] Step 9:

[1317] The device displays the received notification to the user and allows detailed advice to be viewed within the app. The input is the received notification and advice data, and the output is the display within the app.

[1318] Through these steps, the system is able to analyze photos of meals taken by users and provide calorie calculations and personalized health advice.

[1319] (Application example 1)

[1320] 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."

[1321] To manage one's health, it is important to understand the calorie and nutritional value of one's meals and receive appropriate guidance. However, doing this manually is extremely time-consuming. Furthermore, when eating at a restaurant, it is difficult to know the exact calorie and nutritional value from the menu. For this reason, there is a demand for a system that allows users to easily measure the calorie and nutritional value of their meals and receive health advice in real time.

[1322] 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.

[1323] In this invention, the server includes: means for a user to take photos of their meals and save them in a photo folder; means for a device to monitor the photo folder and detect new photos; means for the device to upload new photos to the server; means for the server to analyze the received photo data; means for the server to calculate calories and nutrients based on the analysis results; means for the server to store the calculation results in cumulative data for each user; means for the server to generate health advice using a generation AI; means for the server to send the advice to the device by push notification; means for the device to notify the user of the advice and display it within the app; and means for a user to take photos of restaurant menus and analyze the calories and nutritional value to support meal selection. This enables a user to simply take photos of their meals and receive analysis results of calories and nutritional value, providing real-time support for healthy meal selection.

[1324] "User" refers to a person who uses this system to take photos of their meals and receive health advice.

[1325] "Means for taking photos of meals" refers to the ability to take photos of meals using a device such as a smartphone or smart glasses and save the photos in the device's photo folder.

[1326] "Means for monitoring photo folders" refers to having the ability to periodically check a specific folder on the device and detect when new photos have been added.

[1327] "Means for uploading new photos to the server" refers to having a function for transferring new photos stored on the device to the server via the Internet.

[1328] "Means for analyzing photographic data" refers to the ability of the server to analyze the photographs it receives using image processing technology and identify the ingredients and their amounts in the photographs.

[1329] "Means for calculating calories and nutrients" refers to the ability to calculate the calories and nutrients of each ingredient based on the analyzed ingredient information.

[1330] "Means for saving cumulative data for each user" refers to the ability to link calculated calorie and nutrient data to individual user profiles and save them.

[1331] "Means for generating health advice using generative AI" refers to the ability of the generative AI model to create appropriate health advice based on cumulative data and the latest dietary information.

[1332] "Means for sending advice to a device via push notification" refers to having the ability to notify the device of generated health advice in real time.

[1333] "Means for notifying the user of the advice and displaying it within the app" refers to having the function of informing the user of the received advice and displaying detailed information within the application.

[1334] "Means for taking photos of restaurant menus and analyzing their calories and nutritional value" refers to a function that allows a user to take a photo of a restaurant menu and analyze the calories and nutritional value based on that photo.

[1335] The "image processing engine for identifying ingredients and their quantities" refers to algorithms or software that can identify specific ingredients from a photo and estimate their approximate weight and quantity.

[1336] A "generative AI model" is an artificial intelligence-based model that automatically generates health advice based on collected data.

[1337] A "prompt sentence" is a sentence that is input to a generative AI model to obtain an appropriate response.

[1338] The following system configuration and procedures are used to implement the present invention: The main components of the system include a device that allows a user to take photos of their meals, a terminal that monitors the photo folder, and a server that analyzes the photo data.

[1339] System Configuration

[1340] 1. Your device

[1341] Use your smartphone or smart glasses to take a photo of your meal and save the photo in the device's photo folder.

[1342] 2. Terminal

[1343] This applies to smartphones and smart glasses, and monitors photo folders to detect newly saved photos.

[1344] It also has the function of uploading new photos to the server.

[1345] 3. Server

[1346] The server receives the uploaded photo data and uses an image processing engine to identify the ingredients and their quantities.

[1347] It has data to calculate calories and nutritional value based on ingredient information.

[1348] It has the function of saving cumulative data for each user.

[1349] It uses a generative AI model to generate health advice based on your cumulative data and your most recent diet.

[1350] The generated advice is sent to the user's device via push notification.

[1351] Hardware and software used

[1352] Hardware:

[1353] Devices: Smartphones (e.g., iPhone, Android smartphones), smart glasses (e.g., Google Glass)

[1354] Server: High-performance cloud server (e.g., Amazon AWS, Microsoft Azure)

[1355] software:

[1356] Device monitoring: background services using Python and Java

[1357] Image processing engine: Uses TensorFlow and OpenCV

[1358] Cloud storage and database management: Amazon S3 and MySQL

[1359] Generative AI models: Machine learning models such as TensorFlow or GPT-3

[1360] Specific examples

[1361] Example 1: Breakfast analysis and advice

[1362] A user uses their smartphone to take a photo of their breakfast (pancakes, bacon, and orange juice). Once the photo is saved, the device detects it and automatically uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on the analysis results, calories and nutrients are calculated, and advice is generated: "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch." This advice is sent via a push notification to the user's smartphone, and details can be viewed within the app.

[1363] Example 2: Restaurant meal selection support

[1364] A user takes a photo of a salad, grilled chicken, and smoothie at a restaurant using smart glasses. The device detects the new photo and uploads it to the server. The server analyzes the photo and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This generates advice such as, "This meal is well-balanced, so continue with this." This advice is displayed on the smart glasses' display, and the user can check it in real time.

[1365] Prompt Sentence Examples

[1366] Food photo: salad, grilled chicken, smoothie

[1367] Calories and nutritional value: 100g salad, 150g grilled chicken, 300ml smoothie

[1368] Advice: This diet is well balanced, so stick with it.

[1369] This system allows users to easily analyze the calories and nutritional value of their meals and provides real-time support for making healthy eating choices.

[1370] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1371] Step 1:

[1372] A user takes a photo of their meal and saves it in the device's photo folder.

[1373] Input: Food photo

[1374] Output: Photo files saved in the device's photo folder

[1375] How it works: Users use their smartphone or smart glasses to take photos of their food at a restaurant or at home, and the photos are automatically saved to the device's photo folder.

[1376] Step 2:

[1377] Your device monitors your photo folder for new photos.

[1378] Input: A new photo saved in the Photos folder

[1379] Output: New photo detected notification

[1380] How it works: A monitoring program running on the device periodically checks the photo folder to detect newly saved photos.

[1381] Step 3:

[1382] The device uploads the new photo to the server.

[1383] Input: Newly detected photo file

[1384] Output: Photo data uploaded to the server

[1385] Specific operation: Retrieves new photo files from the photo folder and uploads them to the server via the Internet, along with the user ID.

[1386] Step 4:

[1387] The server analyzes the received photo data.

[1388] Input: Uploaded photo data

[1389] Output: Data about ingredients in the photo and their quantities

[1390] How it works: The server uses an image processing engine (e.g., TensorFlow or OpenCV) to identify ingredients from the photo and determine their approximate weight and quantity.

[1391] Step 5:

[1392] The server calculates calories and nutrients based on the analysis results.

[1393] Input: Identified food ingredient data

[1394] Output: Calorie and nutrient data for meals

[1395] Specific operation: The server references the nutritional information for each ingredient stored in the database and calculates calories and major nutrients (e.g., fat, protein, vitamins, etc.) based on the identified ingredient data.

[1396] Step 6:

[1397] The server stores the calculation results in cumulative data for each user.

[1398] Input: Calculated calories and nutrient data

[1399] Output: New meal data added to the cumulative data per user

[1400] Specific operation: The server associates the calculation results with individual user profiles and stores them in cumulative data.

[1401] Step 7:

[1402] The server generates health advice using generation AI.

[1403] Input: Accumulative data and latest meal data

[1404] Output: Generated health advice

[1405] Specific operation: Using a generative AI model (e.g., GPT-3), specific health advice is generated based on the user's cumulative data and latest dietary information.

[1406] Step 8:

[1407] The server sends the advice to the device via push notification.

[1408] Input: Generated health advice

[1409] Output: Sending advice via push notification

[1410] Specific operation: The generated advice is pushed from the server to the user's device in real time.

[1411] Step 9:

[1412] The device notifies the user of the advice and displays it within the app.

[1413] Input: Push notification from the server

[1414] Output: Detailed advice displayed in the app

[1415] Specific operation: The device notifies the user of notifications received and displays detailed advice within the application, allowing the user to check health advice in real time.

[1416] 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.

[1417] This invention combines a health management system that automatically analyzes photos of meals taken by the user to calculate calories and suggest nutritional balance, with an emotion engine that recognizes the user's emotions to provide more personalized health advice. The system begins when the user takes a photo of their meal and saves it in a photo folder on their device, and then automatically performs a series of subsequent processes.

[1418] System Overview

[1419] 1. User Action:

[1420] Users can take photos of their meals and the photos are automatically saved in a photo folder without any special action required by the user.

[1421] 2. Device monitoring and notifications:

[1422] The app installed on the device monitors the photo folder and detects when new photos are saved. This monitoring program runs in the background, reducing the burden on the user.

[1423] 3. Upload to Cloud:

[1424] The device uploads the new meal photo to the server. At this time, the photo data also includes the user ID and is managed as individual data.

[1425] 4. Parsing on the server:

[1426] The server then passes the received photo data to an image processing engine to identify the ingredients and their quantities, which then uses machine learning models to analyze the photo and identify the ingredients with high accuracy.

[1427] 5. Calorie and Nutritional Value Calculator:

[1428] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information, using the nutritional information for each ingredient stored in the database.

[1429] 6. Counting and Storage:

[1430] The server stores the calculated calorie and nutrient data for each user, allowing users to track their long-term eating patterns and nutritional balance.

[1431] 7. Acquiring emotion data using the emotion engine:

[1432] The server runs an emotion engine that analyzes emotions from user input and voice data. The emotion engine uses natural language processing and voice analysis to accurately identify the user's emotional state. This emotion data is sent to the server and added to the user's cumulative data.

[1433] 8. Advice generation by generative AI:

[1434] The server uses a generative AI model to generate specific health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes suggestions for dietary improvements and supplements, as well as messages that take into account the user's emotional state.

[1435] 9. Notification and Display of Advice:

[1436] The server sends the generated advice to the device via push notification, and the device displays the received notification to the user, allowing them to view detailed advice within the app.

[1437] Specific examples

[1438] Example 1: Breakfast analysis and advice

[1439] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After saving the photo, the device detects it and uploads it to the server. The server analyzes the photo and detects 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (e.g., carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated, such as "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification. The user can open the notification and view detailed advice within the app.

[1440] Example 2: Lunch analysis and advice

[1441] A user takes a photo of their lunch of salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. This allows the server to calculate the protein content of the grilled chicken and the vitamin content of the smoothie. As a result, advice is generated such as, "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a motivational message such as "Keep it up" is added to the advice and sent via push notification.

[1442] In this way, the system fully automates the user's dietary management and provides continuous, individually optimized health advice. The introduction of an emotion engine makes it possible to provide more personalized advice that takes into account the user's emotional state.

[1443] The processing flow will be explained below.

[1444] Step 1:

[1445] The user takes a photo of the meal and saves it in the photo folder of their smartphone. The user does not need to perform any special operations; they simply take a photo of the meal using a regular camera app.

[1446] Step 2:

[1447] The app installed on your device monitors your photo folder for changes and detects new photos by periodically scanning the folder in the background.

[1448] Step 3:

[1449] When a device detects a new photo, it uploads the photo data and user ID to the server via an HTTP POST request to a specified endpoint on the server.

[1450] Step 4:

[1451] The server stores the received photo data in the analysis directory, which prepares an analysis job and passes it to the image processing engine.

[1452] Step 5:

[1453] The server's image processing engine analyzes the photo to identify ingredients and their quantities, using a machine learning model to scan the ingredients in the photo, draw bounding boxes, and detect the name and quantity of each ingredient.

[1454] Step 6:

[1455] The server calculates calories and nutrients based on the output from the image processing engine. It references the nutritional information of ingredients stored in a database to calculate the total calories and each nutrient (protein, fat, carbohydrates, etc.) of the detected ingredients.

[1456] Step 7:

[1457] The server stores the calculation results as cumulative data for each user. The user's dietary history and nutritional information are recorded in a database and managed cumulatively for long-term tracking.

[1458] Step 8:

[1459] The server receives user input and voice data, which the emotion engine analyzes to identify the user's emotional state. The emotion engine uses natural language processing and voice analysis technology to identify emotions with high accuracy.

[1460] Step 9:

[1461] The emotion data analyzed by the emotion engine is sent to the server and added to the user's cumulative data, allowing for the integrated management of the user's emotional information.

[1462] Step 10:

[1463] The server uses the generative AI model to generate health advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice is specific and includes messages that take into account the user's emotional state.

[1464] Step 11:

[1465] The server generates health advice and sends it to the device via push notification. The notification is sent in real time, allowing the user to receive the advice immediately.

[1466] Step 12:

[1467] The device will display a push notification to the user, allowing them to view detailed advice within the app. Users can tap the notification to open the app and view detailed nutritional information and specific improvement suggestions.

[1468] Example 2

[1469] 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."

[1470] In recent years, the importance of health management has increased, and there is a demand for dietary records, calorie calculations, and consideration of nutritional balance. However, manually recording meals and calculating calories and nutrients is cumbersome and inaccurate. Furthermore, simply providing uniform health advice without considering the user's emotional state poses a challenge, making it difficult to provide effective and personalized support to users.

[1471] 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.

[1472] In this invention, the server includes means for analyzing photo data of meals, means for calculating calories and nutrients, means for acquiring user emotion data using an emotion engine that analyzes emotions, means for generating health advice using a generation AI, and means for sending the advice to a terminal by push notification. This makes it possible to automate the recording and analysis of meals and provide personalized health advice that takes into account the user's emotional state.

[1473] A "user" is a person who uses this system to take photos of their meals and manage their health.

[1474] A "terminal" is a device used by a user, such as a smartphone or tablet, that has the function of taking and saving photos.

[1475] A "photo folder" is a location within the device where new photos are saved.

[1476] A "server" is a central computing resource with data analysis, calculation, storage, and notification functions.

[1477] The "image processing engine" is software installed on the server that identifies ingredients and their quantities from a photo of a meal.

[1478] "Calories" is a unit that indicates the amount of energy contained in food.

[1479] "Nutrients" are components contained in food ingredients that are necessary for maintaining health, and include carbohydrates, lipids, proteins, vitamins, etc.

[1480] An "emotion engine" is software that analyzes user input data and voice data to identify the user's emotional state.

[1481] A "generative AI model" is an artificial intelligence technology that generates health advice based on a user's cumulative data, latest dietary habits, and emotional data.

[1482] "Push notification" is a communication technology in which a server sends information to a device in real time.

[1483] "Cumulative data" refers to the collection of each user's meal records, nutritional information, and emotional data.

[1484] "Health Advice" is advice provided based on the user's diet and emotional state using a generative AI model.

[1485] This invention realizes a system that allows a user to take a photo of their meal, calculates the calorie and nutritional balance based on the photo, and provides health advice that takes the user's emotions into consideration. A specific embodiment of the system is described below.

[1486] First, the user takes a photo of their meal using the camera on their smartphone or tablet. At this time, the photo is automatically saved to the device's photo folder. An app installed on the device monitors the photo folder and detects when a new photo has been saved. This app runs in the background, reducing the user's operational burden.

[1487] When the device detects a new photo, it uploads it to a dedicated server. The uploaded photo data also contains the user's ID, which allows for individual management. The server acquires the received photo data and passes it to an image processing engine. The image processing engine uses machine learning models such as TensorFlow and PyTorch. This engine identifies ingredients in the photo with high accuracy and determines the type and quantity of each ingredient.

[1488] The server calculates calories and various nutrients based on the analysis results. The nutritional information used here is based on information for representative ingredients pre-stored in a database. The calculation results are saved as cumulative data for each user and used to track long-term eating patterns and nutritional balance.

[1489] The server then uses an emotion engine to obtain the user's emotional data. The emotion engine uses natural language processing and speech analysis technologies, such as IBM Watson and Google Cloud Natural Language API, to analyze emotions from the user's input data and voice data. This allows the user's emotional state to be identified as "stress," "joy," "sadness," etc. This emotional data is also added to the cumulative data.

[1490] The server then generates health advice using a generative AI model, such as OpenAI's GPT-4, which generates specific, personalized advice based on the user's cumulative data, recent dietary habits, and emotional data. The advice includes suggestions for dietary improvements and supplements, as well as emotional messages. The server then sends the generated advice to the device via push notification.

[1491] The device will display the received notification to the user and allow them to view detailed advice within the app, allowing users to efficiently manage their daily diet and health.

[1492] Specific examples

[1493] Example 1: Breakfast analysis and advice

[1494] A user takes a photo of pancakes, bacon, and orange juice for breakfast. After the photo is saved, the device detects it and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients (carbohydrates, fat, vitamin C, etc.) are calculated. As a result, advice is generated such as, "Pancakes for breakfast are high in calories, so choose a healthy vegetable-based menu for lunch." If the emotion engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice. The advice is sent to the user via push notification, which the user can open to view the details.

[1495] Example 2: Lunch analysis and advice

[1496] A user takes a photo of their lunch, which includes salad, grilled chicken, and a smoothie. The device detects the new photo and uploads it to the server. The server analyzes it and identifies 100g of salad, 150g of grilled chicken, and 300ml of smoothie. Calories and nutrients (protein, vitamins, etc.) are calculated. As a result, advice is generated, such as "This lunch is balanced, so keep it up. Also, we recommend a low-fat menu for dinner." At the same time, if the emotion engine recognizes "positive emotions," a message such as "Keep up the good work" is added to the advice. The advice is sent via push notification, and the user can view details within the app.

[1497] Prompt Sentence Examples

[1498] Example prompt 1: Breakfast analysis and advice

[1499] A user takes a photo of pancakes, bacon, and orange juice for breakfast. The analysis results show 200g of pancakes, 50g of bacon, and 200ml of orange juice. The user is currently feeling stressed. Generate appropriate health advice.

[1500] Example prompt 2: Lunch analysis and advice

[1501] A user takes a photo of a salad, grilled chicken, and smoothie for lunch. The analysis results show 100g of salad, 150g of grilled chicken, and 300ml of smoothie. The user has a positive emotion. Generate appropriate health advice.

[1502]

[1503] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1504] Step 1:

[1505] A user takes a photo of a meal using the camera on their smartphone or tablet. The photo is automatically saved to the device's photo folder. This is the input, and the saved photo data is the output. The specific action is when the user opens the camera app and taps the button to take a photo.

[1506] Step 2:

[1507] An app installed on a device monitors a photo folder in the background. The app detects when a new photo has been saved and notifies the user. The input is the state of the photo folder, and the output is the saving of a new photo. Specifically, the device's file system event listener monitors changes in the folder and detects an event when a new photo is added.

[1508] Step 3:

[1509] The device uploads a new photo to a dedicated server. At this time, the photo data is assigned a user ID. The input is the new photo and the user ID, and the output is the photo data uploaded to the server. Specifically, the device app creates an HTTP request and sends the photo data to the server's upload API endpoint.

[1510] Step 4:

[1511] The server receives the received photo data and passes it to an image processing engine. The image processing engine uses an application (for example, TensorFlow or PyTorch). The input is the photo data, and the output is the analyzed ingredients and their quantities. Specifically, the data is processed by an image processing algorithm that detects the outlines of the ingredients in the photo, and a machine learning model that estimates the type and quantity of the ingredients.

[1512] Step 5:

[1513] The server calculates calories and nutrients based on the analyzed ingredient information. The input is ingredient information, and the output is calorie and nutrient data. Specifically, the server retrieves nutritional information for each ingredient from the database and uses it to calculate calories and nutrients.

[1514] Step 6:

[1515] The server saves the calculation results in the cumulative data for each user. The input is calorie and nutrient data, and the output is the updated cumulative data. The specific operation is to add new data to the user's cumulative data stored in the server's database and update it.

[1516] Step 7:

[1517] The server receives input data and voice data from the user and runs the emotion engine. The input is the user's input data and voice data, and the output is analyzed emotion data. Specifically, the server passes the data to the emotion engine and identifies the emotional state through natural language processing and voice analysis.

[1518] Step 8:

[1519] The server uses a generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The inputs are cumulative data, dietary details, and emotional data, and the output is the generated health advice. Specifically, the server inputs this data into the generative AI model and processes it to generate appropriate health advice and messages.

[1520] Step 9:

[1521] The server sends the generated advice to the device via push notification. The input is the health advice, and the output is the notification to the device. Specifically, the server creates a notification message and sends it to the device via a push notification service (e.g., Apple Push Notification Service or Firebase Cloud Messaging).

[1522] Step 10:

[1523] The device displays the received notification to the user. When the notification is tapped, detailed advice can be viewed within the app. The input is the push notification, and the output is advice that the user can view. Specifically, the device's notification system displays the notification, and when the user taps it, the details screen within the app opens.

[1524] (Application example 2)

[1525] 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."

[1526] Conventional health management systems only calculate the calories of meals and analyze nutritional balance, making it difficult to provide personalized advice that takes into account the user's emotional state. Furthermore, when using food delivery services, there is a problem in that meal options cannot be optimized to match the user's health condition and emotions. This can lead to a decline in the user's overall health management and satisfaction.

[1527] 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 received photo data, means for calculating calories and nutrients, means for saving the calculation results in cumulative data for each user, means for generating health advice using a generation AI, means including an emotion recognition engine, and means for providing personalized dietary advice based on the user's emotional state in a food delivery service that takes a photo of a menu selected by the user and analyzes the calories and nutritional balance. This makes it possible to provide personalized health advice that takes the user's emotions into consideration, enabling optimal menu selection and health management when using a food delivery service.

[1528] In this invention, the term "user" refers to a person who uses the system to take food photos and receive health management advice.

[1529] A "terminal" refers to an electronic device that allows a user to take photos of their meals, monitor a photo folder, detect new photos, and upload them to a server.

[1530] "Server" refers to the computer system that is responsible for a series of processes, including receiving and analyzing photo data uploaded from the device, calculating calories and nutrients, storing the calculation results, and generating health advice using generative AI.

[1531] "Photo folder" refers to the storage location within the device where photos taken by the user are stored.

[1532] A "monitoring program that runs in the background" refers to software that automatically monitors photo folders without user interaction and detects when new photos are saved.

[1533] "Analysis" refers to image processing that identifies ingredients and their amounts based on the photo data received by the server.

[1534] "Calculating calories and nutrients" refers to the process of calculating the calories and nutritional balance of each ingredient based on the analysis results.

[1535] "Cumulative Data" refers to information that stores calorie and nutrient data calculated for each user over time and is used to track the user's eating patterns and nutritional balance.

[1536] "Generative AI" refers to an artificial intelligence model that generates personalized health advice based on a user's cumulative data, recent dietary habits, emotional data, etc.

[1537] "Push notification" refers to a notification message that is automatically sent from a server to a user's device.

[1538] An "emotion recognition engine" refers to artificial intelligence software that analyzes user input and voice data to identify emotional states.

[1539] "Food delivery service" refers to a service that allows users to order food online and have the food delivered to a specified location.

[1540] "Personalized advice" means health advice that is optimized for a particular user, taking into account the user's emotional state and cumulative data.

[1541] This invention combines an emotion recognition engine with a health management system that allows users to take photos of their meals, automatically analyzes the photos, calculates calories, and suggests nutritional balance, providing personalized health advice. This system also supports optimal menu selection and health management based on the user's emotional state when using a food delivery service.

[1542] System Configuration

[1543] The system consists of a user's device, a backend server, an image processing engine, a generative AI model, an emotion recognition engine, and more.

[1544] Hardware and Software Use

[1545] Smartphone: The user takes a photo of the meal and runs the app.

[1546] Server: Responsible for analyzing photos and generating advice using AI.

[1547] TensorFlow: Used as an image processing engine to identify ingredients.

[1548] Azure Cognitive Services: Used as an emotion recognition engine to analyze user emotions.

[1549] System Operation Overview

[1550] 1. User Action:

[1551] Users take a photo of the food delivery menu using their smartphone camera, and the photo is automatically saved in a photo folder.

[1552] 2. Photo folder monitoring:

[1553] A background program running on the device monitors the photo folder and detects when new photos are saved.

[1554] 3. Upload to the server:

[1555] The device uploads the newly saved photo to the server, along with any user input (text or voice input).

[1556] 4. Photo Analysis:

[1557] The server analyzes the received photo data using TensorFlow to identify the ingredients and their quantities.

[1558] 5. Calorie and Nutrition Counts:

[1559] Based on the analyzed ingredient information, the calories and nutrients of each ingredient are calculated.

[1560] 6. Emotion recognition:

[1561] The server uses Azure Cognitive Services to analyze emotions from user input data.

[1562] 7. Advice generation using generative AI models:

[1563] The server uses a generative AI model to generate health advice based on the user's cumulative data, recent dietary history, and emotional data.

[1564] 8. Push Notifications:

[1565] The generated advice is sent to the device via a push notification, and the user can open the notification to view the detailed advice within the app.

[1566] Specific examples

[1567] Example 1: A user takes a photo of a fried chicken bento they ordered via food delivery for lunch and types, "I'm tired from work today." The device detects the new photo and uploads it to the server. The server analyzes the photo, identifies the fried chicken and various side dishes, and their portions, and calculates the calories and nutrients. At the same time, it uses Azure Cognitive Services to analyze emotions and detects that the user is "tired." As a result, personalized advice is generated and sent via push notification, such as, "This meal was high in fat, so choose a vegetable-based menu for your next meal. High-fat meals on a tired day can cause stress, so choose a lighter meal next time."

[1568] Example 2: A user takes a photo of pancakes, bacon, and orange juice for breakfast and saves the photo in a folder. The device detects the photo and uploads it to the server. The server analyzes the photo and identifies 200g of pancakes, 50g of bacon, and 200ml of orange juice. Based on this, calories and various nutrients are calculated. As a result, advice such as "Pancakes for breakfast are high in calories, so choose a healthy, vegetable-based menu for lunch" is generated. If the emotion recognition engine recognizes the user's emotion as "feeling stressed," a message such as "Moderate exercise is effective in reducing stress" is added to the advice and sent to the user via push notification.

[1569] Example prompt sentence:

[1570] "A user orders a fried chicken bento for lunch and types a photo of it along with the comment, 'I'm tired from work today.' Give them personalized advice based on their diet and their emotions."

[1571] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1572] Step 1:

[1573] A user takes a photo of a food delivery menu using the camera on their smartphone. The photo is automatically saved in a photo folder. In this example, the input is a "photo of the menu" and the output is the "image data saved in the photo folder."

[1574] Step 2:

[1575] A background program on the device monitors the photo folder and detects when new photos are saved. The input is the "photo folder status" and the output is "new photo detection notification." Specifically, the program periodically checks the folder and catches the information when a new photo is saved.

[1576] Step 3:

[1577] The device uploads the newly saved photo data to the server. At this time, it also sends the user's input data (text and voice input). The input is "new photo data and user input data," and the output is "data uploaded to the server." Specifically, the device sends the data to the server using an HTTP POST request.

[1578] Step 4:

[1579] The server analyzes the received photo data using an image processing engine (TensorFlow) to identify the ingredients and their quantities. The input is "photo data" and the output is "ingredient information (type and quantity)." Specifically, the server inputs the image data into the TensorFlow model and obtains the type of ingredient and its quantity as the model's output.

[1580] Step 5:

[1581] The server calculates the calories and nutrients of each ingredient based on the analyzed ingredient information. The input is "ingredient information" and the output is "calculated calorie and nutrient data." Specifically, the server obtains the calorie and nutrient information for each ingredient from the database within the server and performs calculations based on that information.

[1582] Step 6:

[1583] The server uses Azure Cognitive Services to analyze emotions from user input data (text or voice). The input is "user input data" and the output is "emotion data." Specifically, the server sends an API request to Azure Cognitive Services and receives the emotion analysis results.

[1584] Step 7:

[1585] The server uses the generative AI model to generate health advice based on the user's cumulative data, latest dietary details, and emotional data. The input is "cumulative data, dietary details, and emotional data," and the output is "generated health advice." Specifically, the server inputs this data into the generative AI model and outputs the optimal advice.

[1586] Step 8:

[1587] The generated advice is sent from the server to the device as a push notification. The input is the "generated health advice" and the output is the "notification sent to the device." Specifically, the server uses the push notification service to send the notification to the app.

[1588] Step 9:

[1589] The device displays the received notification to the user and allows them to view detailed advice within the app. The input is the "content of the push notification" and the output is the "advice displayed to the user." Specifically, clicking the notification launches the app and displays the advice.

[1590] 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.

[1591] 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.

[1592] 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.

[1593] 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.

[1594] 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.

[1595] 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.

[1596] 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).

[1597] 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.

[1598] 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."

[1599] 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.

[1600] 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).

[1601] 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.

[1602] 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.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] The following is further disclosed regarding the above embodiment.

[1612] (Claim 1)

[1613] a means for a user to take a photo of the meal and save it in a photo folder;

[1614] a means for the device to monitor the photo folder for new photos;

[1615] A means for the device to upload new photos to the server;

[1616] A means for analyzing the photographic data received by the server;

[1617] A means for the server to calculate calories and nutrients based on the analysis results,

[1618] A means for the server to store the calculation results in cumulative data for each user;

[1619] A means for the server to generate health advice using the generation AI;

[1620] A means for the server to send advice to the device by push notification;

[1621] A means for the device to notify the user of the advice and display it within the app;

[1622] A system including:

[1623] (Claim 2)

[1624] 10. The system of claim 1, wherein the server includes an image processing engine that identifies ingredients and their amounts from a meal photograph.

[1625] (Claim 3)

[1626] The system of claim 1, wherein the generative AI model combines a user's cumulative data with their most recent dietary information to generate health advice.

[1627] "Example 1"

[1628] (Claim 1)

[1629] a means for a user to take a photo of the meal and save it in a photo folder;

[1630] a means for the device to monitor the photo folder for new photos;

[1631] A means for the device to upload new photos to the server;

[1632] A means for analyzing the photographic data received by the server;

[1633] A means for the server to calculate calories and nutrients based on the analysis results,

[1634] A means for the server to store the calculation results in cumulative data for each user;

[1635] A means for the server to generate health advice using the generative AI model;

[1636] A means for the server to send advice to the device by push notification;

[1637] A means for the device to notify the user of the advice and display it within the app;

[1638] means for transmitting the photo data and user identification information to a server when a meal photo is detected;

[1639] A means for retrieving food information from a database and calculating calories and nutrients;

[1640] a means for performing image processing using a machine learning model;

[1641] A system including:

[1642] (Claim 2)

[1643] 10. The system of claim 1, wherein the server includes an image processing engine that identifies ingredients and their amounts from a meal photograph.

[1644] (Claim 3)

[1645] The system of claim 1, wherein the generative AI model combines a user's cumulative data with their most recent dietary information to generate health advice.

[1646] "Application Example 1"

[1647] (Claim 1)

[1648] a means for a user to take a photo of the meal and save it in a photo folder;

[1649] a means for the device to monitor the photo folder for new photos;

[1650] A means for the device to upload new photos to the server;

[1651] A means for analyzing the photographic data received by the server;

[1652] A means for the server to calculate calories and nutrients based on the analysis results,

[1653] A means for the server to store the calculation results in cumulative data for each user;

[1654] A means for the server to generate health advice using the generation AI;

[1655] A means for the server to send advice to the device by push notification;

[1656] A means for the device to notify the user of the advice and display it within the app;

[1657] A way for users to take photos of restaurant menus and analyze the calories and nutritional value to help them make meal choices;

[1658] A system including:

[1659] (Claim 2)

[1660] 10. The system of claim 1, wherein the server includes an image processing engine that identifies ingredients and their amounts from a meal photograph.

[1661] (Claim 3)

[1662] The system of claim 1, wherein the generative AI model combines a user's cumulative data with their most recent dietary information to generate health advice.

[1663] "Example 2: Combining Emotion Engines"

[1664] (Claim 1)

[1665] a means for a user to take a photo of the meal and save it in a photo folder;

[1666] a means for the device to monitor the photo folder for new photos;

[1667] A means for the device to upload new photos to the server;

[1668] A means for analyzing the photographic data received by the server;

[1669] A means for the server to calculate calories and nutrients based on the analysis results,

[1670] A means for the server to store the calculation results in cumulative data for each user;

[1671] A means for the server to acquire user emotion data using an emotion engine that analyzes emotions;

[1672] A means for the server to generate health advice using the generation AI;

[1673] A means for the server to send advice to the device by push notification;

[1674] A means for the device to notify the user of the advice and display it within the app;

[1675] A system including:

[1676] (Claim 2)

[1677] 10. The system of claim 1, wherein the server includes an image processing engine that identifies ingredients and their amounts from a meal photograph.

[1678] (Claim 3)

[1679] 10. The system of claim 1, wherein the generative AI model generates health advice based on the user's cumulative data, recent dietary history, and emotional data.

[1680] "Application example 2 when combining emotion engines"

[1681] (Claim 1)

[1682] a means for a user to take a photo of the meal and save it in a photo folder;

[1683] a means for the device to monitor the photo folder for new photos;

[1684] A means for the device to upload new photos to the server;

[1685] A means for analyzing the photographic data received by the server;

[1686] A means for the server to calculate calories and nutrients based on the analysis results,

[1687] A means for the server to store the calculation results in cumulative data for each user;

[1688] A means for the server to generate health advice using the generation AI;

[1689] A means for the server to send advice to the device by push notification;

[1690] A means for the device to notify the user of the advice and display it within the app;

[1691] means including an emotion recognition engine for analyzing the emotion of a user;

[1692] A food delivery service that takes a photo of a menu item selected by a user and analyzes the calories and nutritional balance of the menu item, and provides personalized dietary advice based on the user's emotional state.

[1693] A system including:

[1694] (Claim 2)

[1695] 10. The system of claim 1, wherein the server includes an image processing engine that identifies ingredients and their amounts from a meal photograph.

[1696] (Claim 3)

[1697] 10. The system of claim 1, wherein the generative AI model combines a user's cumulative data, recent dietary history, and emotional data to generate health advice. [Explanation of symbols]

[1698] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to take a photo of the meal and save it in a photo folder; a means for the device to monitor the photo folder for new photos; A means for the device to upload new photos to the server; A means for analyzing the photographic data received by the server; A means for the server to calculate calories and nutrients based on the analysis results, A means for the server to store the calculation results in cumulative data for each user; A means for the server to generate health advice using the generation AI; A means for the server to send advice to the device by push notification; A means for the device to notify the user of the advice and display it within the app; A system including:

2. The system of claim 1 , wherein the server includes an image processing engine for identifying ingredients and their amounts from a meal photograph.

3. The system of claim 1, wherein the generative AI model combines the user's cumulative data and their most recent dietary information to generate health advice.

Images