System

Abstract

A system is provided.SOLUTION: The system includes a photographing means for photographing a meal content, an image analysis means for analyzing a meal image photographed by the photographing means and specifying a food material and a dish name, a nutrient calculation means for calculating a nutrient of the food material and the dish specified by the image analysis means and specifying an insufficient nutrient based on health information of a user, and a proposal means for proposing a recipe for supplementing the specified insufficient nutrient.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, many individuals find it difficult to obtain a balanced intake of the nutrients they need. This is due to the lack of a means to accurately analyze the contents of their diet and the difficulty of creating recipes that supplement the nutrients that are lacking based on the analysis results. The purpose of this invention is to solve these problems and enable users to lead a balanced and healthy diet. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means:

[0006] A photographing means for photographing the meal contents;

[0007] an image analysis means for analyzing the food image captured by the photographing means and identifying ingredients and the name of the dish;

[0008] a nutrient calculation means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means and for identifying any nutrients that are lacking based on the user's health information;

[0009] a suggestion means for suggesting a recipe for supplementing the identified nutrient deficiency;

[0010] This is realized by a system including:

[0011] Furthermore, by including a means for suggesting appropriate recipes taking into consideration the user's age, sex, weight, blood pressure, daily activity level, and health data, as well as a means for taking a photo of leftover food after a meal, analyzing the leftover food with the image analysis means, and recalculating the nutritional components actually ingested, it becomes possible to suggest more accurate nutritional balances.

[0012] The "photography means for photographing meal contents" refers to a means including a camera for taking photos of meals, as well as related hardware and software.

[0013] "Image analysis means" refers to means including AI models and algorithms for analyzing photographed food images and identifying ingredients and names of dishes.

[0014] "Nutrient calculation means" refers to means including software and algorithms for calculating the nutritional content of ingredients and dishes identified by the image analysis means and for identifying nutrient deficiencies based on the user's health information.

[0015] The "suggestion means" is a means including a system and software for presenting recipes to a user to supplement the identified nutrient deficiencies.

[0016] "User's age, gender, weight, blood pressure, daily activity level, and health data" is a general term for data that indicates the user's basic physical information and health condition.

[0017] The "means for recalculating" is a means including software and algorithms for analyzing a photograph of the leftover food portion after a meal and recalculating the actual nutritional intake. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including the user's device, a server, and an AI model.

[0040] User Interface

[0041] User: First, the user launches the application on their device and takes a photo of their meal. The photo is then displayed once within the application, allowing the user to review the content.

[0042] Uploading an image

[0043] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[0044] Image analysis and nutrition calculations

[0045] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[0046] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[0047] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0048] Recipe Suggestions

[0049] Server: Selects recipes from the database to supplement missing nutrients, and creates new recipes using a recipe generation algorithm if necessary.

[0050] Server: Suggested recipes are customized for each user and sent to the user's device.

[0051] Displaying suggested recipes

[0052] On the device: Users can view the received recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipe.

[0053] Post-meal check-up and feedback

[0054] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[0055] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. This data is used for future recommendations.

[0056] Specific examples

[0057] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of it and upload it to the server via the app.

[0058] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis, calculates the nutritional components (protein, vitamins, minerals, etc.) of each, and evaluates the nutritional balance of the user's entire meal, determining that calcium is particularly lacking.

[0059] Server: To supplement calcium, suggest a recipe for "Komatsuna and Tofu Stir-fry" and send it to the user's device.

[0060] On the device: Users can view recipes and save them for their next cooking plan.

[0061] User: If there is any food left over after a meal, the user can take a photo of it again and upload it to the server, which will reflect the actual amount consumed.

[0062] In this way, by using this system, it is easy to create nutritionally balanced meals tailored to each individual user.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] User: Takes a photo of their meal using their device's camera. After taking the photo, the app displays a screen where they can review the photo.

[0066] Step 2:

[0067] Terminal: The user checks the photo and, if there are no problems, presses the "Upload" button. This action sends the taken photo and the user ID to the server.

[0068] Step 3:

[0069] Server: Stores the received food photos in a temporary storage area.

[0070] Step 4:

[0071] Server: Calls the AI ​​model for image analysis and provides the stored food photos as input.

[0072] Step 5:

[0073] AI model (on the server): Analyzes the image and identifies the ingredients, dish name, and quantity. The analysis results are generated as a data list.

[0074] Step 6:

[0075] Server: Saves the analysis result data list in a database for each user.

[0076] Step 7:

[0077] Server: Based on the analysis results, the nutritional components of each ingredient and dish are queried from the database and individual components are obtained.

[0078] Step 8:

[0079] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies any nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0080] Step 9:

[0081] Server: Searches the database for suitable recipes to supplement missing nutrients. If necessary, it runs the recipe generation algorithm to create new recipes.

[0082] Step 10:

[0083] Server: Formats the suggested recipes into a format suitable for the user and sends them to the user's device.

[0084] Step 11:

[0085] On your device: The received recipes are displayed for the user to review. The user can then review the suggested recipes and save them as their next meal.

[0086] Step 12:

[0087] User: If necessary, after the meal, if there is any leftover food, take a photo of it again and upload it to the server via the device.

[0088] Step 13:

[0089] Server: The received post-meal photo is provided to an image analysis AI model to analyze any leftover food.

[0090] Step 14:

[0091] AI model (on server): Detects leftover food and returns nutritional data for recalculation.

[0092] Step 15:

[0093] Server: Recalculates the actual nutritional intake and updates the user's nutritional intake history.

[0094] Step 16:

[0095] Server: The server accumulates the user's food history and preferences as learning data and updates the model parameters for future suggestions. This data is stored in a database and used for future recipe suggestions.

[0096] Example 1

[0097] 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."

[0098] Conventional dietary management systems require users to manually input meal contents and calculate nutrients, which is time-consuming and often lacks accuracy. Furthermore, there is a need for improved management of leftover food after meals and more accurate recipe suggestions that take individual health information into account. A system that solves these problems and allows for easier and more accurate dietary management is desired.

[0099] 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.

[0100] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the photographed meal image to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dishes and identifying nutrient deficiencies based on the user's health information, a proposal means for proposing recipes to compensate for the identified nutrient deficiencies, a transmission means for sending the recipes generated by the proposal means to the user's terminal, a reanalysis means for photographing leftover food after a meal and reanalyzing the leftover food with the image analysis means to recalculate the actual nutritional components ingested, and a learning model reflection means for utilizing the results of the reanalysis means for future proposals. This significantly reduces the user's workload and enables highly accurate nutritional management and appropriate recipe proposals based on individual health information.

[0101] The "photography means" is a device or application with a camera function that allows the user to take photos of the contents of a meal.

[0102] "Image analysis means" refers to software or algorithms that analyze photographed food images to identify ingredients and the name of the dish.

[0103] The "nutrient calculation means" is a means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means, and for identifying any nutrients that are lacking based on the user's health information.

[0104] A "suggestion tool" is software or an algorithm that suggests recipes to supplement identified nutrient deficiencies.

[0105] The "transmission means" is a device or application having a communication function for transmitting the recipe generated by the proposal means to the user's terminal.

[0106] The "reanalysis means" is a means for taking a photo of the leftover food after a meal, analyzing the leftover food again using the image analysis means, and recalculating the nutritional components actually ingested.

[0107] The "learning model reflection means" refers to a machine learning model or algorithm that is used for future proposals based on the results of the reanalysis means.

[0108] The system of this invention allows users to take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including a user device, a server, and an AI model.

[0109] First, the user launches the application on their device and takes a photo of their meal using the camera function of their smartphone or tablet. The photo is displayed once within the application, allowing the user to confirm the content. After confirming the photo, the user presses the "Upload" button, which sends the photo file and the user's ID information to the server.

[0110] The server saves the received photos in a dedicated directory and passes them to an image analysis AI model. This AI model (for example, a model built using TENSORFLOW (registered trademark) or PyTorch) analyzes the images and identifies the ingredients, dish names, and quantities. The analysis results are saved in an internal database (for example, MySQL (registered trademark) or PostgreSQL), and the nutritional content of each ingredient and dish is calculated.

[0111] Next, the server evaluates the nutritional balance of the entire meal based on the user's health information (age, gender, weight, blood pressure, daily activity level, etc.) and identifies any nutrient deficiencies. This evaluation can be performed using the Nutrient Analysis API.

[0112] The server then suggests recipes to supplement the identified nutrient deficiencies. It can query existing recipe databases to find recipes that match the user's criteria and select the recipe that best suits them. It can also generate new recipes as needed using a generative AI model. The recipe generation algorithm then takes into account the user's preferences and health status when creating a recipe.

[0113] The suggested recipes are individually customized and sent to the user's device. The recipe data is delivered via a push notification service, and the user can check the recipe on the application screen and save it as a cooking plan for the next time. They can also enter feedback or requests for changes.

[0114] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server via the app. The server then analyzes the image again and recalculates the actual nutrient intake. The recalculated data is stored in an internal database and will be reflected in future recommendations. This allows for more accurate recommendations based on the user's preferences and actual intake data.

[0115] As a concrete example, consider the case where a user has "grilled salmon" and "vegetable salad" for dinner. The user takes a photo of this and uploads it to the server via the app. The server uses image analysis to identify that it is "grilled salmon" and "vegetable salad" and calculates the nutritional content of each. If the server determines that the user's health data indicates a calcium deficiency, it will suggest a recipe for "komatsuna and tofu stir fry" and send it to the user's device. The user can check the recipe on their device and save it for their next cooking plan.

[0116] An example of a prompt is as follows:

[0117] text

[0118] A user uploads a photo of their dinner. Perform image analysis to identify the ingredients, dish name, and nutritional components of each, and generate a recipe that takes into account the user's health data and supplements any missing nutrients.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] The user takes a photo of their meal

[0122] User: Takes a photo of a meal using the camera function of a smartphone or tablet. The input is the image of the meal captured through the camera, and the output is a preview image displayed on the application screen.

[0123] Step 2:

[0124] Upload the image to the server

[0125] Device: The user presses the "Upload" button. The input is the captured photo file and the user's ID information, and the output is the data sent to the server as an HTTP request. Specifically, the device generates an HTTP POST request to send the captured image file to the server.

[0126] Step 3:

[0127] Save and analyze the image

[0128] Server: Saves the received photos in a dedicated directory. Then, inputs the saved image file into an AI model for image analysis. The input is the saved image file, and the output is a list of ingredients and dish names analyzed by the AI ​​model. Specifically, the server saves the image file to disk and passes the path of that file to the API of the AI ​​model.

[0129] Step 4:

[0130] Calculate nutritional information

[0131] Server: Calculates the nutritional content of each ingredient and dish based on the results of image analysis. The input is the data on ingredients, dish names, and quantities obtained as a result of the analysis, and the output is detailed data on each nutritional content. Specifically, the server compares this data with its internal database and obtains nutritional information for each ingredient.

[0132] Step 5:

[0133] Evaluate nutritional balance based on user health information

[0134] Server: Refers to the user's health information, such as age, gender, weight, blood pressure, and daily activity level, to identify nutrient deficiencies. The input is the user's health information and nutritional composition data, and the output is a list of nutrient deficiencies. Specifically, the server uses the Nutrient Analysis API to evaluate nutritional balance.

[0135] Step 6:

[0136] Suggest suitable recipes

[0137] Server: Searches the database for recipes to supplement nutrient deficiencies or generates new recipes using a generative AI model. The input is a list of nutrient deficiencies, and the output is suggested recipes. Specifically, the server queries the recipe database and extracts recipes that match the criteria.

[0138] Step 7:

[0139] Sending recipes to the user's device

[0140] Device: Receives the suggested recipe and displays it on the application screen. The input is the recipe data sent from the server, and the output is the recipe displayed on the device's application screen. Specifically, the device receives a push notification and displays the contents in the application.

[0141] Step 8:

[0142] Take a photo of your leftovers after eating and upload it again

[0143] User: If there is any leftover food after the meal, the user takes another photo of the meal and uploads it to the server through the app. The input is the newly taken photo after the meal, and the output is the photo file uploaded to the server.

[0144] Step 9:

[0145] Reanalyze leftovers and recalculate nutritional information

[0146] Server: Analyzes the post-meal photo again, identifies any leftover food, and recalculates the actual nutritional intake. The input is the re-taken photo and the analysis results, and the output is the revised nutritional intake data. Specifically, the server performs image analysis again and saves the results in a database.

[0147] Step 10:

[0148] Reflecting in the learning model

[0149] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. The input is the revised nutritional intake data, and the output is an updated learning model. Specifically, the server updates the model using a machine learning algorithm and uses it for future recommendations.

[0150] Through the above processing steps, the system provides users with highly accurate nutritional management and appropriate recipe suggestions.

[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] Conventional dietary management systems have the ability to photograph meals and evaluate their nutritional balance, but they lack the ability to suggest specific actions based on the evaluation results or provide practical measures for nutritional supplementation. In particular, they lack an appropriate means for users to easily put the suggested recipes into practice. Furthermore, they lack a system for accurately grasping post-meal intake and reflecting this in future recommendations.

[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 a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the identified ingredients and dish and identifying any nutrient deficiencies based on the user's health information, a suggestion means for suggesting recipes to compensate for the identified nutrient deficiencies, and a delivery means for delivering appropriate dishes based on the suggested recipes. This allows the user to easily take concrete actions to replenish the identified nutrients, and enables the next suggestion to accurately reflect the nutrition actually ingested.

[0156] "Photographing means" refers to a device or apparatus that allows the user to photograph the contents of their meal.

[0157] The "image analysis means" is a system or program for analyzing a photographed image of a meal and identifying the ingredients and the name of the dish.

[0158] The "nutrient calculation means" is a system or program that calculates the nutritional components of the ingredients and dishes identified by the image analysis means and identifies any nutrients that are lacking based on the user's health information.

[0159] The "suggestion means" is a system or program that suggests to the user recipes for supplementing the nutrient deficiencies identified by the nutrient calculation means.

[0160] "Delivery Method" means a system or service that delivers appropriate dishes to users based on the suggested recipes.

[0161] "User health information" refers to data such as the user's age, gender, weight, blood pressure, and daily activity level.

[0162] A "recipe" is a document or information that shows how to prepare or mix a dish to supplement missing nutrients.

[0163] The "after-meal photo" is an image of leftover food after a meal.

[0164] A "server" is a computer system for receiving and analyzing data sent by users.

[0165] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is comprised of an integrated platform that includes the user's device, a server, and an AI model.

[0166] First, the user launches the application on their device and takes a photo of their meal. The photo is displayed once within the application, and the user confirms the content. After that, the user presses the "Upload" button. This action sends the photo and the user's ID information to the server.

[0167] The server passes the received photos to an AI model for image analysis. The AI ​​model uses deep learning frameworks such as TensorFlow and Keras. This analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated. Based on this, the nutritional balance of the entire meal is evaluated.

[0168] The server then identifies nutrient deficiencies, taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data. Based on this information, the server selects recipes from its database to address these nutrient deficiencies, and creates new recipes if necessary using a recipe generation algorithm. The proposed recipes are customized for each user and sent to the user's device.

[0169] Users can review the received recipe on their device and save it as their next meal. They can also order meals based on the suggested recipe through a delivery method that will provide the appropriate dish. If there are any leftovers after the meal, the user can take another photo of the meal and upload it to the server. The actual nutrient intake is then recalculated based on the photo. This allows the user's dietary history and preferences to be reflected in the learning model. This data will be used for future suggestions.

[0170] As a concrete example, let's say a user is having "grilled salmon" and "vegetable salad" for dinner. They take a photo of this and upload it to the server via the app. The server then analyzes the image and identifies the dishes as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish (protein, vitamins, minerals, etc.) and evaluates the nutritional balance of the entire meal. For example, if the server determines that the user is lacking in calcium, it will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can then check this recipe, save it as part of their next cooking plan, or order it through a food delivery service.

[0171] An example of a prompt is:

[0172] "Just take a photo of the dinner you recently had and upload it to the app (NutriMeal). The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[0173] Examples include:

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1: Shoot and review

[0176] The user launches the application on their device and takes a photo of their meal. The photo is then displayed in the application, allowing the user to review the content.

[0177] Input: A meal photo taken by the user

[0178] Output: Confirmation photo displayed on the device

[0179] How it works: A user takes a photo of a meal and reviews it.

[0180] Step 2: Upload a photo

[0181] The user presses the "upload" button, and the captured photo and the user's ID information are sent to the server.

[0182] Input: Meal photos taken by the user, user ID information

[0183] Output: Photo and ID information uploaded to the server

[0184] Operation: The device sends the input photo and ID information to the server.

[0185] Step 3: Image analysis

[0186] The server passes the received photos to an AI model for image analysis, which identifies the ingredients, dish name, and quantity.

[0187] Input: Photo uploaded to the server

[0188] Output: Identified ingredients, dish name, and quantity

[0189] How it works: The AI ​​model analyzes the image and identifies ingredients and dishes.

[0190] Step 4: Nutritional assessment

[0191] The server calculates the nutritional content of the identified ingredients and dishes and identifies any nutrient deficiencies based on the user's health information.

[0192] Input: Identified ingredients and dish names, user health information

[0193] Output: Identification of nutrient deficiencies

[0194] Operation: The nutrient calculation tool calculates nutritional components and assesses nutritional deficiencies based on health information.

[0195] Step 5: Recipe suggestions

[0196] The server selects recipes from a database to supplement the identified nutrient deficiencies and generates new recipes as needed. The suggested recipes are customized for each user and sent to the device.

[0197] Input: Identification results of missing nutrients, recipe information from the database

[0198] Output: The customized recipe sent to the user's device

[0199] How it works: The server selects the appropriate recipe and sends the customized results to the device.

[0200] Step 6: View and save the recipe

[0201] Users can view the received recipes on their device, save them as their next meal, and order meals based on the suggested recipes through food delivery services.

[0202] Input: Recipe sent to terminal

[0203] Output: User-saved next cooking plan and ordering information

[0204] What it does: Displays a recipe on the device, allowing the user to review, save, and order.

[0205] Step 7: Post-meal review and feedback

[0206] After a meal, users take a photo of the leftover food and upload it to the server, which then analyzes the image again and recalculates the actual nutritional intake.

[0207] Input: A photo of leftover food taken after a meal

[0208] Output: Recalculated nutrient data

[0209] How it works: The server analyzes the post-meal photo and re-evaluates the actual intake.

[0210] Examples:

[0211] If a user eats "grilled salmon" and "vegetable salad" for dinner, they take a photo of it and upload it to the server via the app. The server then analyzes the image and identifies it as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish and evaluates their nutritional balance. For example, if it determines that the user is lacking in calcium, the server will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can check this recipe, save it in their next cooking plan, or order it through a food delivery service. If there is any leftover food after the meal, they can take another photo of it and upload it to the server, which will reflect their actual intake.

[0212] Prompt statement:

[0213] "Just take a photo of the dinner you recently had and upload it to the app. The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[0214] 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.

[0215] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to suggest more effective recipes. The system is comprised of an integrated platform that includes the user's device, a server, an AI model, and the emotion engine.

[0216] User Interface

[0217] User: First, the user launches the app on their device and takes a photo of their meal. The photo is then viewed once within the app, where the user can review it.

[0218] Uploading an image

[0219] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[0220] Image analysis and nutrition calculations

[0221] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[0222] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[0223] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0224] Emotion Recognition and Recipe Suggestion

[0225] Server: At the same time, the emotion engine recognizes emotions based on the facial image acquired from the user's camera and the user's input data.

[0226] Server: The emotional data recognized by the emotion engine is incorporated into recipe suggestions to supplement the identified nutrient deficiencies.

[0227] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a recipe generation algorithm.

[0228] Server: Suggested recipes are customized according to the user's emotional state and sent to the user's device.

[0229] Displaying suggested recipes

[0230] On the device: The user can review the received recipe on the device, save it as a recipe to make next, and enter feedback or requests for changes to the recipe.

[0231] Post-meal check-up and feedback

[0232] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[0233] Server: Based on the analysis results and actual intake data, the user's eating history and emotional data are reflected in the learning model. This data is used for future recommendations.

[0234] Specific examples

[0235] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of this meal and upload it to the server via the app.

[0236] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis and calculates the nutritional components (protein, vitamins, minerals, etc.) of each. Based on these results, evaluates the nutritional balance of the entire meal and identifies any nutrients that are lacking (such as calcium).

[0237] Server: At the same time, the emotion engine recognizes the user's emotional state (e.g., whether they are feeling stressed) from their facial expressions.

[0238] Server: Suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to relieve stress and sends it to the user's device.

[0239] On the device: Users can view recipes and save them for future cooking plans.

[0240] User: If desired, if there is any leftover food after a meal, take and upload a photo of it again, which will reflect the actual amount consumed.

[0241] In this way, by using this system, users can receive more appropriate meal suggestions based on their own nutritional balance and emotional state.

[0242] The processing flow will be explained below.

[0243] Step 1:

[0244] User: Takes a photo of their meal using their device's camera. After taking the photo, the photo is displayed in the app and the user can review the photo.

[0245] Step 2:

[0246] On the device: The user checks the photo and presses the "Upload" button. This action sends the captured photo and user ID information to the server.

[0247] Step 3:

[0248] Server: Temporarily stores the received food photos and prepares them for passing to the image analysis AI model.

[0249] Step 4:

[0250] Server: Calls the image analysis AI model and inputs the saved food photos to analyze them.

[0251] Step 5:

[0252] AI model (on the server): Analyzes food photos and identifies ingredients, dish names, and quantities. The analysis results are generated as a data list.

[0253] Step 6:

[0254] Server: Saves the analysis result data list in a database for each user. Next, proceeds to calculate nutritional components.

[0255] Step 7:

[0256] Server: Based on the analysis results, the server queries the database for the nutritional information of each ingredient and dish and obtains the information.

[0257] Step 8:

[0258] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0259] Step 9:

[0260] User: During this time, the device camera takes a picture of the user's face and recognizes their current emotional state.

[0261] Step 10:

[0262] Device: Sends the user's facial image to the server.

[0263] Step 11:

[0264] Server: Inputs the received facial image into the emotion engine to recognize the user's emotional state.

[0265] Step 12:

[0266] Emotion engine (on the server): Analyzes facial images to identify the user's emotional state (e.g., joy, stress, fatigue, etc.).

[0267] Step 13:

[0268] Server: Based on the emotional data identified by the emotion engine, the suggested recipes are adjusted according to the user's emotional state.

[0269] Step 14:

[0270] Server: Searches the database for suitable recipes based on missing nutrients and emotion data, and runs the recipe generation algorithm to create new recipes as needed.

[0271] Step 15:

[0272] Server: The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[0273] Step 16:

[0274] On the device: The received recipe is displayed to the user, who can then review the recipe and save it for their next cooking appointment.

[0275] Step 17:

[0276] User: If there is any food left over after the meal, take another photo after the meal and upload it to the server via the device.

[0277] Step 18:

[0278] Device: Send a photo of the leftovers and the user ID to the server.

[0279] Step 19:

[0280] Server: Provides newly received images to an image analysis AI model to analyze leftover food.

[0281] Step 20:

[0282] AI model (in the server): Detects leftover food and returns the analysis results to the server.

[0283] Step 21:

[0284] Server: Recalculates the actual nutritional intake and records the new nutritional balance data in the user's diet history.

[0285] Step 22:

[0286] Server: The user's eating history and emotional data are reflected in the learning model. This data is used to suggest recipes for future meals.

[0287] In this way, users can receive appropriate meal suggestions based on their nutritional balance and emotional state, enabling more precise and personalized dietary management.

[0288] Example 2

[0289] 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."

[0290] In modern society, it is extremely important to properly manage individual dietary content and personal health. However, many existing systems only analyze the nutritional balance of meals and are unable to provide personalized suggestions that take the user's emotional state into account. As a result, it is difficult for the suggested healthy recipes to increase the user's psychological satisfaction, making it difficult to maintain long-term health.

[0291] 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.

[0292] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dish identified by the image analysis means and identifying nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the emotional state of the user, and a suggestion means for suggesting recipes based on the emotional state and nutrient deficiencies identified by the emotion recognition means. This makes it possible to suggest individually optimized recipes that comprehensively consider the user's nutritional and emotional states.

[0293] "Photographing means" refers to the device and its functions used to photograph the contents of a meal.

[0294] "Image analysis means" refers to technology or equipment for analyzing photographed food images to identify ingredients and the name of the dish.

[0295] "Nutrient calculation means" refers to technology or equipment for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrients that are lacking based on the user's health information.

[0296] "Emotion recognition means" refers to techniques or devices for recognizing a user's emotional state, including analyzing facial expressions and evaluating user-input data.

[0297] "Recommendation means" refers to a technology or device for suggesting recipes based on identified nutrient deficiencies and emotional state.

[0298] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to provide an integrated platform for more effective recipe suggestions. This system includes a user device, a server, a generative AI model, and an emotion recognition engine.

[0299] Hardware and software used

[0300] Device: The user uses a smartphone or tablet, which includes a camera and internet connectivity.

[0301] Server: The center of data processing, performing various calculations and storing data. The server is installed with an AI model (e.g., TensorFlow), an emotion recognition engine (e.g., Affectiva), and a database (e.g., MongoDB).

[0302] Generative AI models: used to generate recipes. An example is GPT-4®.

[0303] System Operation

[0304] The user launches the application on their device and takes a photo of their meal. The photo is then viewed within the app, and when the user presses the "upload" button, the photo and the user's ID information are sent to the server.

[0305] The server passes the received photo to an AI model for image analysis (e.g., TensorFlow). The AI ​​model analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated.

[0306] Next, nutrient deficiencies are identified, taking into account the user's age, gender, weight, blood pressure, daily activity, and health data. At the same time, an emotion engine (e.g., Affectiva) recognizes emotions based on facial images captured from the user's camera. Emotional data is combined with the identified nutrient deficiencies to find suitable recipes, or create new recipes using a generative AI model (e.g., GPT-4) if necessary.

[0307] The suggested recipes are customized based on the user's emotional state, encoded, and sent to the user's device. The user can then review the recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipes.

[0308] If the user has leftover food after a meal, they can take a photo of it again and upload it to the server. Based on that photo, the actual nutrient intake is recalculated, and the results are reflected in future recipe suggestions.

[0309] Specific examples

[0310] For example, if a user has "grilled salmon" and "vegetable salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server will use image analysis to identify the dishes as "grilled salmon" and "vegetable salad" and calculate the nutritional content (protein, vitamins, minerals, etc.) of each. It will then evaluate the nutritional balance of the entire meal and identify any nutrients (such as calcium) that are lacking.

[0311] Next, the emotion engine recognizes the user's emotional state (e.g., stress) from their facial expressions, and suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to alleviate stress, and sends it to the user's device.

[0312] Users can review recipes, save them for their next cooking plan, and, if desired, take and upload a photo of any leftovers after a meal to reflect their actual intake.

[0313] By using this system, users can receive more appropriate meal suggestions based on their nutritional balance and emotional state.

[0314] Prompt Sentence Examples

[0315] Prompt: If the user had "grilled salmon" and "vegetable salad" for dinner but is feeling stressed, suggest a new recipe that contains magnesium.

[0316] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0317] Step 1:

[0318] User: The user launches the application on their smartphone or tablet. They launch the dedicated app, select camera mode, and take a photo of their current meal. The input is the meal photo, and the output is the confirmed photo data.

[0319] Step 2:

[0320] Device: When the user presses the "Upload" button, the photo of the meal taken and the user's ID information are sent from the device to the server. Here, the data travels via an Internet connection. The input is the photo data and the user ID, and the output is the data reception status on the server.

[0321] Step 3:

[0322] Server: The server inputs the received photo data into an AI model (TensorFlow) for image analysis. The AI ​​model analyzes the image and identifies the ingredients, dish name, and quantity. The input is the photo data, and the output is the identified ingredients, dish name, and quantity.

[0323] Specifically, the image analysis model scans the photo, compares it with an existing database to identify ingredients and the name of the dish, and then verifies whether the analysis is correct before proceeding to the next step.

[0324] Step 4:

[0325] Server: Stores the analysis results in a database and calculates the nutritional content of each ingredient and dish. A publicly available food nutrition database is used for the nutrition calculation. The input is the identified ingredient information, and the output is the calculated nutritional content data.

[0326] Specifically, the server uses a nutrition calculation algorithm to calculate the nutritional content (protein, vitamins, minerals, etc.) of each identified ingredient.

[0327] Step 5:

[0328] Server: Identifies nutrient deficiencies based on the user's age, gender, weight, blood pressure, daily activity level, and health data stored in a database. The input is the calculated nutritional composition data and the user's personal data, and the output is a list of nutrient deficiencies.

[0329] Specifically, it compares and analyzes individual health data with calculated nutritional components to identify nutrients that are lacking (e.g., calcium, magnesium, etc.).

[0330] Step 6:

[0331] Server: The emotion engine (Affectiva) recognizes emotions based on facial images acquired from the user's camera and emotion data entered by the user. The input is facial images and emotion input data, and the output is the recognized emotion data.

[0332] Specifically, the server passes facial images and text data to the emotion recognition engine, which then performs emotion analysis. The emotion engine then returns the recognized emotion to the server.

[0333] Step 7:

[0334] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a generative AI model (GPT-4). The input is nutrient deficiency data and emotion data, and the output is a suggested recipe.

[0335] Specifically, the server uses a database or generative AI model to search for or generate an appropriate recipe and output it as recipe data.

[0336] Step 8:

[0337] Device: The suggested recipes are customized according to the user's emotional state, encoded, and sent to the device. The input is the recipe data, and the output is the recipe information displayed on the user's device.

[0338] Specifically, the server encodes a recipe tailored to the user's emotional state and sends it to the device, which then decodes it and displays it to the user.

[0339] Step 9:

[0340] User: The user can review the received recipe and save it as the next dish to make. They can also enter feedback or requests for changes to the recipe. The input is the recipe data, and the output is the user's feedback data.

[0341] Specifically, users can view and check recipe information on their device, add it to their next cooking plan, and use the feedback function to enter comments about the suggested recipes.

[0342] Step 10:

[0343] User: If there is any food left after the meal, the user takes a photo of it again and uploads it to the server from their device. The input is the photo after the meal, and the output is the state of data reception to the server.

[0344] Step 11:

[0345] Server: Re-analyzes the re-received photos and re-calculates the actual nutritional intake. The input is the post-meal photo data, and the output is the recalculated nutritional information. This information is reflected in future recipe suggestions.

[0346] Specifically, the server performs image analysis again, recalculates the intake amount, and stores it in the database. This recalculated data is used to suggest the next recipe.

[0347] (Application example 2)

[0348] 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."

[0349] Conventional dietary management applications were able to analyze a user's dietary content and evaluate the nutrients in their meals, but they were unable to suggest recipes that took the user's emotional state into account. This made it difficult to increase user satisfaction and suggest meals that matched their mental state. Furthermore, the functionality to reassess the actual nutrients ingested based on leftover food after a meal was also insufficient. Therefore, there was a need for a system that could offer comprehensive dietary suggestions to users that took into account not only nutritional balance but also emotions.

[0350] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the ingredients and the dish identified by the image analysis means and identifying any nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the user's emotional information, and a suggestion means for suggesting recipes based on the identified nutrient deficiencies and emotional information. This enables more effective meal suggestions that take into account the user's emotional state as well as their nutritional balance.

[0351] "Meal content" refers to the types and amounts of ingredients and dishes consumed by the user.

[0352] "Photography method" refers to the device or method used by a user to photograph their meal.

[0353] "Image analysis means" refers to technology or equipment for analyzing food images acquired by the photographing means and identifying ingredients and the name of the dish.

[0354] "Nutrient calculation means" refers to a system or method for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrient deficiencies based on the results.

[0355] "Nutritional components" refers to the components such as proteins, lipids, carbohydrates, vitamins, and minerals contained in ingredients and dishes.

[0356] "Suggestion methods" refer to techniques and methods for suggesting recipes to supplement identified nutrient deficiencies.

[0357] "Emotion recognition means" refers to technology or devices that determine a user's emotional state at that time from their facial expressions and input data.

[0358] "Emotional information" refers to data that indicates a user's emotional state.

[0359] "Recipes" refer to cooking methods or dishes suggested based on specific nutrients or emotional states.

[0360] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. Furthermore, it combines an emotion engine that recognizes the user's emotional state to suggest more effective recipes.

[0361] User Interface

[0362] The user launches the application on their device and takes a photo of their meal. This application is for smartphones and includes a means for taking photos of the meal using the camera function. The photos are then viewed within the app, and after the user has confirmed the content, they press the "upload" button to send it to the server.

[0363] Image analysis and nutrition calculations

[0364] The server passes the received photos to an AI model for image analysis. This AI model uses TensorFlow and OpenCV to analyze the images and identify the ingredients and dish names. The analysis results are stored in a database, and a nutrient calculation tool is used to calculate the nutritional content of the ingredients and dishes, evaluating the nutritional balance of the entire meal. The user's age, gender, weight, blood pressure, daily activity level, and health data are identified to determine any nutrient deficiencies.

[0365] Emotion Recognition and Recipe Suggestion

[0366] The server uses an emotion recognition API to analyze the user's emotional state based on facial images captured from the user's camera and user input data. Based on the emotional information and nutrient deficiencies, the suggestion method searches for suitable recipes from the database and creates new recipes using a generative AI model if necessary. The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[0367] View and give feedback on suggested recipes

[0368] Users can review the received recipes on their device, save them for their next cooking plan, and even provide feedback or suggestions for changes to the recipes.

[0369] Post-meal check-up and feedback

[0370] If there are any leftovers after a meal, the user takes another photo of the meal and uploads it to the server. The server then uses image analysis to analyze the leftovers and recalculate the actual nutrient intake. Based on this result and the actual intake data, the user's eating history and emotional data are reflected in the learning model. This will be used to make suggestions for future meals.

[0371] Specific examples

[0372] For example, if a user has "pizza" and "salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server uses image analysis to identify the pizza and salad and calculate the nutritional components of each. As a result, the overall nutritional balance is evaluated and any nutrients that are lacking (e.g., vitamin D) are identified. At the same time, an emotion recognition engine recognizes the user's emotional state (e.g., stress). A recipe for "sauteed spinach and chicken," which contains food ingredients (e.g., magnesium) to alleviate stress, is suggested and sent to the user's device.

[0373] Prompt Sentence Examples

[0374] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[0375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0376] Step 1:

[0377] The user launches the smartphone application and takes a photo of the meal. This application provides a means to capture the meal contents through the smartphone's camera function. When the user presses the "upload" button, the taken photo and user ID are sent to the server. The input data are the meal image and user ID, and these data are sent as output to proceed to the next step.

[0378] Step 2:

[0379] The server passes the received photo data to an AI model for image analysis. The AI ​​model uses TensorFlow and OpenCV to analyze the image and identify ingredients and dish names. The input is food image data, and the output is a list of identified ingredients and dish names. Specifically, the AI ​​model preprocesses the food images, extracts features, and classifies the ingredients and dishes using a pre-trained model.

[0380] Step 3:

[0381] The server uses a nutrient calculation means to calculate nutritional components based on the analyzed ingredients and dish names. The input is a list of identified ingredients and dish names and the user's health information (age, gender, weight, blood pressure, activity level, etc.). The output is a list of nutrients that are lacking. Specifically, the server obtains nutritional information for each ingredient from the database and totals it to evaluate the overall nutritional balance and identify any nutrients that are lacking.

[0382] Step 4:

[0383] The server activates the emotion recognition means using facial images and input data acquired from the user's camera. The input is the facial image and input data, and the output is the recognized emotional information of the user. Specifically, the emotion recognition API is used to analyze the emotional state (stress, joy, fatigue, etc.) from the facial image.

[0384] Step 5:

[0385] The server uses a suggestion mechanism to suggest recipes based on the identified nutrient deficiencies and emotional information. The input is a list of nutrient deficiencies and emotional information, and the output is a list of suitable recipes. Specifically, it searches for relevant recipes in the database and creates new recipes using a generative AI model if necessary. Here, the generative AI model uses the following prompt sentence:

[0386] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[0387] Step 6:

[0388] The server sends the suggested recipes to the user's device. The input is a list of suitable recipes, and the output is the data describing the recipes. The user's device displays the received recipes, and the user can save them for their next cooking plan. They can also enter feedback or requests for changes to the recipes.

[0389] Step 7:

[0390] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server. The server then uses image analysis to analyze the leftover food and recalculate the actual nutritional intake. The input is the post-meal photo, and the output is a recalculated list of nutrients. This allows the user's eating history and emotional data to be reflected in the learning model and used to make suggestions for future meals.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] [Second embodiment]

[0395] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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).

[0401] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0406] 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."

[0407] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including the user's device, a server, and an AI model.

[0408] User Interface

[0409] User: First, the user launches the application on their device and takes a photo of their meal. The photo is then displayed once within the application, allowing the user to review the content.

[0410] Uploading an image

[0411] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[0412] Image analysis and nutrition calculations

[0413] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[0414] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[0415] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0416] Recipe Suggestions

[0417] Server: Selects recipes from the database to supplement missing nutrients, and creates new recipes using a recipe generation algorithm if necessary.

[0418] Server: Suggested recipes are customized for each user and sent to the user's device.

[0419] Displaying suggested recipes

[0420] On the device: Users can view the received recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipe.

[0421] Post-meal check-up and feedback

[0422] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[0423] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. This data is used for future recommendations.

[0424] Specific examples

[0425] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of it and upload it to the server via the app.

[0426] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis, calculates the nutritional components (protein, vitamins, minerals, etc.) of each, and evaluates the nutritional balance of the user's entire meal, determining that calcium is particularly lacking.

[0427] Server: To supplement calcium, suggest a recipe for "Komatsuna and Tofu Stir-fry" and send it to the user's device.

[0428] On the device: Users can view recipes and save them for their next cooking plan.

[0429] User: If there is any food left over after a meal, the user can take a photo of it again and upload it to the server, which will reflect the actual amount consumed.

[0430] In this way, by using this system, it is easy to create nutritionally balanced meals tailored to each individual user.

[0431] The processing flow will be explained below.

[0432] Step 1:

[0433] User: Takes a photo of their meal using their device's camera. After taking the photo, the app displays a screen where they can review the photo.

[0434] Step 2:

[0435] Terminal: The user checks the photo and, if there are no problems, presses the "Upload" button. This action sends the taken photo and the user ID to the server.

[0436] Step 3:

[0437] Server: Stores the received food photos in a temporary storage area.

[0438] Step 4:

[0439] Server: Calls the AI ​​model for image analysis and provides the stored food photos as input.

[0440] Step 5:

[0441] AI model (on the server): Analyzes the image and identifies the ingredients, dish name, and quantity. The analysis results are generated as a data list.

[0442] Step 6:

[0443] Server: Saves the analysis result data list in a database for each user.

[0444] Step 7:

[0445] Server: Based on the analysis results, the nutritional components of each ingredient and dish are queried from the database and individual components are obtained.

[0446] Step 8:

[0447] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies any nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0448] Step 9:

[0449] Server: Searches the database for suitable recipes to supplement missing nutrients. If necessary, it runs the recipe generation algorithm to create new recipes.

[0450] Step 10:

[0451] Server: Formats the suggested recipes into a format suitable for the user and sends them to the user's device.

[0452] Step 11:

[0453] On your device: The received recipes are displayed for the user to review. The user can then review the suggested recipes and save them as their next meal.

[0454] Step 12:

[0455] User: If necessary, after the meal, if there is any leftover food, take a photo of it again and upload it to the server via the device.

[0456] Step 13:

[0457] Server: The received post-meal photo is provided to an image analysis AI model to analyze any leftover food.

[0458] Step 14:

[0459] AI model (on server): Detects leftover food and returns nutritional data for recalculation.

[0460] Step 15:

[0461] Server: Recalculates the actual nutritional intake and updates the user's nutritional intake history.

[0462] Step 16:

[0463] Server: The server accumulates the user's food history and preferences as learning data and updates the model parameters for future suggestions. This data is stored in a database and used for future recipe suggestions.

[0464] Example 1

[0465] 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."

[0466] Conventional dietary management systems require users to manually input meal contents and calculate nutrients, which is time-consuming and often lacks accuracy. Furthermore, there is a need for improved management of leftover food after meals and more accurate recipe suggestions that take individual health information into account. A system that solves these problems and allows for easier and more accurate dietary management is desired.

[0467] 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.

[0468] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the photographed meal image to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dishes and identifying nutrient deficiencies based on the user's health information, a proposal means for proposing recipes to compensate for the identified nutrient deficiencies, a transmission means for sending the recipes generated by the proposal means to the user's terminal, a reanalysis means for photographing leftover food after a meal and reanalyzing the leftover food with the image analysis means to recalculate the actual nutritional components ingested, and a learning model reflection means for utilizing the results of the reanalysis means for future proposals. This significantly reduces the user's workload and enables highly accurate nutritional management and appropriate recipe proposals based on individual health information.

[0469] The "photography means" is a device or application with a camera function that allows the user to take photos of the contents of a meal.

[0470] "Image analysis means" refers to software or algorithms that analyze photographed food images to identify ingredients and the name of the dish.

[0471] The "nutrient calculation means" is a means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means, and for identifying any nutrients that are lacking based on the user's health information.

[0472] A "suggestion tool" is software or an algorithm that suggests recipes to supplement identified nutrient deficiencies.

[0473] The "transmission means" is a device or application having a communication function for transmitting the recipe generated by the proposal means to the user's terminal.

[0474] The "reanalysis means" is a means for taking a photo of the leftover food after a meal, analyzing the leftover food again using the image analysis means, and recalculating the nutritional components actually ingested.

[0475] The "learning model reflection means" refers to a machine learning model or algorithm that is used for future proposals based on the results of the reanalysis means.

[0476] The system of this invention allows users to take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including a user device, a server, and an AI model.

[0477] First, the user launches the application on their device and takes a photo of their meal using the camera function of their smartphone or tablet. The photo is displayed once within the application, allowing the user to confirm the content. After confirming the photo, the user presses the "Upload" button, which sends the photo file and the user's ID information to the server.

[0478] The server stores the received photos in a dedicated directory and passes them to an image analysis AI model. This AI model (for example, a model built using TensorFlow or PyTorch) analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in an internal database (for example, MySQL or PostgreSQL), and the nutritional content of each ingredient and dish is calculated.

[0479] Next, the server evaluates the nutritional balance of the entire meal based on the user's health information (age, gender, weight, blood pressure, daily activity level, etc.) and identifies any nutrient deficiencies. This evaluation can be performed using the Nutrient Analysis API.

[0480] The server then suggests recipes to supplement the identified nutrient deficiencies. It can query existing recipe databases to find recipes that match the user's criteria and select the recipe that best suits them. It can also generate new recipes as needed using a generative AI model. The recipe generation algorithm then takes into account the user's preferences and health status when creating a recipe.

[0481] The suggested recipes are individually customized and sent to the user's device. The recipe data is delivered via a push notification service, and the user can check the recipe on the application screen and save it as a cooking plan for the next time. They can also enter feedback or requests for changes.

[0482] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server via the app. The server then analyzes the image again and recalculates the actual nutrient intake. The recalculated data is stored in an internal database and will be reflected in future recommendations. This allows for more accurate recommendations based on the user's preferences and actual intake data.

[0483] As a concrete example, consider the case where a user has "grilled salmon" and "vegetable salad" for dinner. The user takes a photo of this and uploads it to the server via the app. The server uses image analysis to identify that it is "grilled salmon" and "vegetable salad" and calculates the nutritional content of each. If the server determines that the user's health data indicates a calcium deficiency, it will suggest a recipe for "komatsuna and tofu stir fry" and send it to the user's device. The user can check the recipe on their device and save it for their next cooking plan.

[0484] An example of a prompt is as follows:

[0485] text

[0486] A user uploads a photo of their dinner. Perform image analysis to identify the ingredients, dish name, and nutritional components of each, and generate a recipe that takes into account the user's health data and supplements any missing nutrients.

[0487] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0488] Step 1:

[0489] The user takes a photo of their meal

[0490] User: Takes a photo of a meal using the camera function of a smartphone or tablet. The input is the image of the meal captured through the camera, and the output is a preview image displayed on the application screen.

[0491] Step 2:

[0492] Upload the image to the server

[0493] Device: The user presses the "Upload" button. The input is the captured photo file and the user's ID information, and the output is the data sent to the server as an HTTP request. Specifically, the device generates an HTTP POST request to send the captured image file to the server.

[0494] Step 3:

[0495] Save and analyze the image

[0496] Server: Saves the received photos in a dedicated directory. Then, inputs the saved image file into an AI model for image analysis. The input is the saved image file, and the output is a list of ingredients and dish names analyzed by the AI ​​model. Specifically, the server saves the image file to disk and passes the path of that file to the API of the AI ​​model.

[0497] Step 4:

[0498] Calculate nutritional information

[0499] Server: Calculates the nutritional content of each ingredient and dish based on the results of image analysis. The input is the data on ingredients, dish names, and quantities obtained as a result of the analysis, and the output is detailed data on each nutritional content. Specifically, the server compares this data with its internal database and obtains nutritional information for each ingredient.

[0500] Step 5:

[0501] Evaluate nutritional balance based on user health information

[0502] Server: Refers to the user's health information, such as age, gender, weight, blood pressure, and daily activity level, to identify nutrient deficiencies. The input is the user's health information and nutritional composition data, and the output is a list of nutrient deficiencies. Specifically, the server uses the Nutrient Analysis API to evaluate nutritional balance.

[0503] Step 6:

[0504] Suggest suitable recipes

[0505] Server: Searches the database for recipes to supplement nutrient deficiencies or generates new recipes using a generative AI model. The input is a list of nutrient deficiencies, and the output is suggested recipes. Specifically, the server queries the recipe database and extracts recipes that match the criteria.

[0506] Step 7:

[0507] Sending recipes to the user's device

[0508] Device: Receives the suggested recipe and displays it on the application screen. The input is the recipe data sent from the server, and the output is the recipe displayed on the device's application screen. Specifically, the device receives a push notification and displays the contents in the application.

[0509] Step 8:

[0510] Take a photo of your leftovers after eating and upload it again

[0511] User: If there is any leftover food after the meal, the user takes another photo of the meal and uploads it to the server through the app. The input is the newly taken photo after the meal, and the output is the photo file uploaded to the server.

[0512] Step 9:

[0513] Reanalyze leftovers and recalculate nutritional information

[0514] Server: Analyzes the post-meal photo again, identifies any leftover food, and recalculates the actual nutritional intake. The input is the re-taken photo and the analysis results, and the output is the revised nutritional intake data. Specifically, the server performs image analysis again and saves the results in a database.

[0515] Step 10:

[0516] Reflecting in the learning model

[0517] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. The input is the revised nutritional intake data, and the output is an updated learning model. Specifically, the server updates the model using a machine learning algorithm and uses it for future recommendations.

[0518] Through the above processing steps, the system provides users with highly accurate nutritional management and appropriate recipe suggestions.

[0519] (Application example 1)

[0520] 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."

[0521] Conventional dietary management systems have the ability to photograph meals and evaluate their nutritional balance, but they lack the ability to suggest specific actions based on the evaluation results or provide practical measures for nutritional supplementation. In particular, they lack an appropriate means for users to easily put the suggested recipes into practice. Furthermore, they lack a system for accurately grasping post-meal intake and reflecting this in future recommendations.

[0522] 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.

[0523] In this invention, the server includes a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the identified ingredients and dish and identifying any nutrient deficiencies based on the user's health information, a suggestion means for suggesting recipes to compensate for the identified nutrient deficiencies, and a delivery means for delivering appropriate dishes based on the suggested recipes. This allows the user to easily take concrete actions to replenish the identified nutrients, and enables the next suggestion to accurately reflect the nutrition actually ingested.

[0524] "Photographing means" refers to a device or apparatus that allows the user to photograph the contents of their meal.

[0525] The "image analysis means" is a system or program for analyzing a photographed image of a meal and identifying the ingredients and the name of the dish.

[0526] The "nutrient calculation means" is a system or program that calculates the nutritional components of the ingredients and dishes identified by the image analysis means and identifies any nutrients that are lacking based on the user's health information.

[0527] The "suggestion means" is a system or program that suggests to the user recipes for supplementing the nutrient deficiencies identified by the nutrient calculation means.

[0528] "Delivery Method" means a system or service that delivers appropriate dishes to users based on the suggested recipes.

[0529] "User health information" refers to data such as the user's age, gender, weight, blood pressure, and daily activity level.

[0530] A "recipe" is a document or information that shows how to prepare or mix a dish to supplement missing nutrients.

[0531] The "after-meal photo" is an image of leftover food after a meal.

[0532] A "server" is a computer system for receiving and analyzing data sent by users.

[0533] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is comprised of an integrated platform that includes the user's device, a server, and an AI model.

[0534] First, the user launches the application on their device and takes a photo of their meal. The photo is displayed once within the application, and the user confirms the content. After that, the user presses the "Upload" button. This action sends the photo and the user's ID information to the server.

[0535] The server passes the received photos to an AI model for image analysis. The AI ​​model uses deep learning frameworks such as TensorFlow and Keras. This analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated. Based on this, the nutritional balance of the entire meal is evaluated.

[0536] The server then identifies nutrient deficiencies, taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data. Based on this information, the server selects recipes from its database to address these nutrient deficiencies, and creates new recipes if necessary using a recipe generation algorithm. The proposed recipes are customized for each user and sent to the user's device.

[0537] Users can review the received recipe on their device and save it as their next meal. They can also order meals based on the suggested recipe through a delivery method that will provide the appropriate dish. If there are any leftovers after the meal, the user can take another photo of the meal and upload it to the server. The actual nutrient intake is then recalculated based on the photo. This allows the user's dietary history and preferences to be reflected in the learning model. This data will be used for future suggestions.

[0538] As a concrete example, let's say a user is having "grilled salmon" and "vegetable salad" for dinner. They take a photo of this and upload it to the server via the app. The server then analyzes the image and identifies the dishes as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish (protein, vitamins, minerals, etc.) and evaluates the nutritional balance of the entire meal. For example, if the server determines that the user is lacking in calcium, it will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can then check this recipe, save it as part of their next cooking plan, or order it through a food delivery service.

[0539] An example of a prompt is:

[0540] "Just take a photo of the dinner you recently had and upload it to the app (NutriMeal). The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[0541] Examples include:

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

[0543] Step 1: Shoot and review

[0544] The user launches the application on their device and takes a photo of their meal. The photo is then displayed in the application, allowing the user to review the content.

[0545] Input: A meal photo taken by the user

[0546] Output: Confirmation photo displayed on the device

[0547] How it works: A user takes a photo of a meal and reviews it.

[0548] Step 2: Upload a photo

[0549] The user presses the "upload" button, and the captured photo and the user's ID information are sent to the server.

[0550] Input: Meal photos taken by the user, user ID information

[0551] Output: Photo and ID information uploaded to the server

[0552] Operation: The device sends the input photo and ID information to the server.

[0553] Step 3: Image analysis

[0554] The server passes the received photos to an AI model for image analysis, which identifies the ingredients, dish name, and quantity.

[0555] Input: Photo uploaded to the server

[0556] Output: Identified ingredients, dish name, and quantity

[0557] How it works: The AI ​​model analyzes the image and identifies ingredients and dishes.

[0558] Step 4: Nutritional assessment

[0559] The server calculates the nutritional content of the identified ingredients and dishes and identifies any nutrient deficiencies based on the user's health information.

[0560] Input: Identified ingredients and dish names, user health information

[0561] Output: Identification of nutrient deficiencies

[0562] Operation: The nutrient calculation tool calculates nutritional components and assesses nutritional deficiencies based on health information.

[0563] Step 5: Recipe suggestions

[0564] The server selects recipes from a database to supplement the identified nutrient deficiencies and generates new recipes as needed. The suggested recipes are customized for each user and sent to the device.

[0565] Input: Identification results of missing nutrients, recipe information from the database

[0566] Output: The customized recipe sent to the user's device

[0567] How it works: The server selects the appropriate recipe and sends the customized results to the device.

[0568] Step 6: View and save the recipe

[0569] Users can view the received recipes on their device, save them as their next meal, and order meals based on the suggested recipes through food delivery services.

[0570] Input: Recipe sent to terminal

[0571] Output: User-saved next cooking plan and ordering information

[0572] What it does: Displays a recipe on the device, allowing the user to review, save, and order.

[0573] Step 7: Post-meal review and feedback

[0574] After a meal, users take a photo of the leftover food and upload it to the server, which then analyzes the image again and recalculates the actual nutritional intake.

[0575] Input: A photo of leftover food taken after a meal

[0576] Output: Recalculated nutrient data

[0577] How it works: The server analyzes the post-meal photo and re-evaluates the actual intake.

[0578] Examples:

[0579] If a user eats "grilled salmon" and "vegetable salad" for dinner, they take a photo of it and upload it to the server via the app. The server then analyzes the image and identifies it as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish and evaluates their nutritional balance. For example, if it determines that the user is lacking in calcium, the server will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can check this recipe, save it in their next cooking plan, or order it through a food delivery service. If there is any leftover food after the meal, they can take another photo of it and upload it to the server, which will reflect their actual intake.

[0580] Prompt statement:

[0581] "Just take a photo of the dinner you recently had and upload it to the app. The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[0582] 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.

[0583] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to suggest more effective recipes. The system is comprised of an integrated platform that includes the user's device, a server, an AI model, and the emotion engine.

[0584] User Interface

[0585] User: First, the user launches the app on their device and takes a photo of their meal. The photo is then viewed once within the app, where the user can review it.

[0586] Uploading an image

[0587] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[0588] Image analysis and nutrition calculations

[0589] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[0590] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[0591] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0592] Emotion Recognition and Recipe Suggestion

[0593] Server: At the same time, the emotion engine recognizes emotions based on the facial image acquired from the user's camera and the user's input data.

[0594] Server: The emotional data recognized by the emotion engine is incorporated into recipe suggestions to supplement the identified nutrient deficiencies.

[0595] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a recipe generation algorithm.

[0596] Server: Suggested recipes are customized according to the user's emotional state and sent to the user's device.

[0597] Displaying suggested recipes

[0598] On the device: The user can review the received recipe on the device, save it as a recipe to make next, and enter feedback or requests for changes to the recipe.

[0599] Post-meal check-up and feedback

[0600] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[0601] Server: Based on the analysis results and actual intake data, the user's eating history and emotional data are reflected in the learning model. This data is used for future recommendations.

[0602] Specific examples

[0603] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of this meal and upload it to the server via the app.

[0604] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis and calculates the nutritional components (protein, vitamins, minerals, etc.) of each. Based on these results, evaluates the nutritional balance of the entire meal and identifies any nutrients that are lacking (such as calcium).

[0605] Server: At the same time, the emotion engine recognizes the user's emotional state (e.g., whether they are feeling stressed) from their facial expressions.

[0606] Server: Suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to relieve stress and sends it to the user's device.

[0607] On the device: Users can view recipes and save them for future cooking plans.

[0608] User: If desired, if there is any leftover food after a meal, take and upload a photo of it again, which will reflect the actual amount consumed.

[0609] In this way, by using this system, users can receive more appropriate meal suggestions based on their own nutritional balance and emotional state.

[0610] The processing flow will be explained below.

[0611] Step 1:

[0612] User: Takes a photo of their meal using their device's camera. After taking the photo, the photo is displayed in the app and the user can review the photo.

[0613] Step 2:

[0614] On the device: The user checks the photo and presses the "Upload" button. This action sends the captured photo and user ID information to the server.

[0615] Step 3:

[0616] Server: Temporarily stores the received food photos and prepares them for passing to the image analysis AI model.

[0617] Step 4:

[0618] Server: Calls the image analysis AI model and inputs the saved food photos to analyze them.

[0619] Step 5:

[0620] AI model (on the server): Analyzes food photos and identifies ingredients, dish names, and quantities. The analysis results are generated as a data list.

[0621] Step 6:

[0622] Server: Saves the analysis result data list in a database for each user. Next, proceeds to calculate nutritional components.

[0623] Step 7:

[0624] Server: Based on the analysis results, the server queries the database for the nutritional information of each ingredient and dish and obtains the information.

[0625] Step 8:

[0626] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0627] Step 9:

[0628] User: During this time, the device camera takes a picture of the user's face and recognizes their current emotional state.

[0629] Step 10:

[0630] Device: Sends the user's facial image to the server.

[0631] Step 11:

[0632] Server: Inputs the received facial image into the emotion engine to recognize the user's emotional state.

[0633] Step 12:

[0634] Emotion engine (on the server): Analyzes facial images to identify the user's emotional state (e.g., joy, stress, fatigue, etc.).

[0635] Step 13:

[0636] Server: Based on the emotional data identified by the emotion engine, the suggested recipes are adjusted according to the user's emotional state.

[0637] Step 14:

[0638] Server: Searches the database for suitable recipes based on missing nutrients and emotion data, and runs the recipe generation algorithm to create new recipes as needed.

[0639] Step 15:

[0640] Server: The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[0641] Step 16:

[0642] On the device: The received recipe is displayed to the user, who can then review the recipe and save it for their next cooking appointment.

[0643] Step 17:

[0644] User: If there is any food left over after the meal, take another photo after the meal and upload it to the server via the device.

[0645] Step 18:

[0646] Device: Send a photo of the leftovers and the user ID to the server.

[0647] Step 19:

[0648] Server: Provides newly received images to an image analysis AI model to analyze leftover food.

[0649] Step 20:

[0650] AI model (in the server): Detects leftover food and returns the analysis results to the server.

[0651] Step 21:

[0652] Server: Recalculates the actual nutritional intake and records the new nutritional balance data in the user's diet history.

[0653] Step 22:

[0654] Server: The user's eating history and emotional data are reflected in the learning model. This data is used to suggest recipes for future meals.

[0655] In this way, users can receive appropriate meal suggestions based on their nutritional balance and emotional state, enabling more precise and personalized dietary management.

[0656] Example 2

[0657] 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."

[0658] In modern society, it is extremely important to properly manage individual dietary content and personal health. However, many existing systems only analyze the nutritional balance of meals and are unable to provide personalized suggestions that take the user's emotional state into account. As a result, it is difficult for the suggested healthy recipes to increase the user's psychological satisfaction, making it difficult to maintain long-term health.

[0659] 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.

[0660] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dish identified by the image analysis means and identifying nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the emotional state of the user, and a suggestion means for suggesting recipes based on the emotional state and nutrient deficiencies identified by the emotion recognition means. This makes it possible to suggest individually optimized recipes that comprehensively consider the user's nutritional and emotional states.

[0661] "Photographing means" refers to the device and its functions used to photograph the contents of a meal.

[0662] "Image analysis means" refers to technology or equipment for analyzing photographed food images to identify ingredients and the name of the dish.

[0663] "Nutrient calculation means" refers to technology or equipment for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrients that are lacking based on the user's health information.

[0664] "Emotion recognition means" refers to techniques or devices for recognizing a user's emotional state, including analyzing facial expressions and evaluating user-input data.

[0665] "Recommendation means" refers to a technology or device for suggesting recipes based on identified nutrient deficiencies and emotional state.

[0666] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to provide an integrated platform for more effective recipe suggestions. This system includes a user device, a server, a generative AI model, and an emotion recognition engine.

[0667] Hardware and software used

[0668] Device: The user uses a smartphone or tablet, which includes a camera and internet connectivity.

[0669] Server: The center of data processing, performing various calculations and storing data. The server is installed with an AI model (e.g., TensorFlow), an emotion recognition engine (e.g., Affectiva), and a database (e.g., MongoDB).

[0670] Generative AI models: used to generate recipes. An example is GPT-4.

[0671] System Operation

[0672] The user launches the application on their device and takes a photo of their meal. The photo is then viewed within the app, and when the user presses the "upload" button, the photo and the user's ID information are sent to the server.

[0673] The server passes the received photo to an AI model for image analysis (e.g., TensorFlow). The AI ​​model analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated.

[0674] Next, nutrient deficiencies are identified, taking into account the user's age, gender, weight, blood pressure, daily activity, and health data. At the same time, an emotion engine (e.g., Affectiva) recognizes emotions based on facial images captured from the user's camera. Emotional data is combined with the identified nutrient deficiencies to find suitable recipes, or create new recipes using a generative AI model (e.g., GPT-4) if necessary.

[0675] The suggested recipes are customized based on the user's emotional state, encoded, and sent to the user's device. The user can then review the recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipes.

[0676] If the user has leftover food after a meal, they can take a photo of it again and upload it to the server. Based on that photo, the actual nutrient intake is recalculated, and the results are reflected in future recipe suggestions.

[0677] Specific examples

[0678] For example, if a user has "grilled salmon" and "vegetable salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server will use image analysis to identify the dishes as "grilled salmon" and "vegetable salad" and calculate the nutritional content (protein, vitamins, minerals, etc.) of each. It will then evaluate the nutritional balance of the entire meal and identify any nutrients (such as calcium) that are lacking.

[0679] Next, the emotion engine recognizes the user's emotional state (e.g., stress) from their facial expressions, and suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to alleviate stress, and sends it to the user's device.

[0680] Users can review recipes, save them for their next cooking plan, and, if desired, take and upload a photo of any leftovers after a meal to reflect their actual intake.

[0681] By using this system, users can receive more appropriate meal suggestions based on their nutritional balance and emotional state.

[0682] Prompt Sentence Examples

[0683] Prompt: If the user had "grilled salmon" and "vegetable salad" for dinner but is feeling stressed, suggest a new recipe that contains magnesium.

[0684] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0685] Step 1:

[0686] User: The user launches the application on their smartphone or tablet. They launch the dedicated app, select camera mode, and take a photo of their current meal. The input is the meal photo, and the output is the confirmed photo data.

[0687] Step 2:

[0688] Device: When the user presses the "Upload" button, the photo of the meal taken and the user's ID information are sent from the device to the server. Here, the data travels via an Internet connection. The input is the photo data and the user ID, and the output is the data reception status on the server.

[0689] Step 3:

[0690] Server: The server inputs the received photo data into an AI model (TensorFlow) for image analysis. The AI ​​model analyzes the image and identifies the ingredients, dish name, and quantity. The input is the photo data, and the output is the identified ingredients, dish name, and quantity.

[0691] Specifically, the image analysis model scans the photo, compares it with an existing database to identify ingredients and the name of the dish, and then verifies whether the analysis is correct before proceeding to the next step.

[0692] Step 4:

[0693] Server: Stores the analysis results in a database and calculates the nutritional content of each ingredient and dish. A publicly available food nutrition database is used for the nutrition calculation. The input is the identified ingredient information, and the output is the calculated nutritional content data.

[0694] Specifically, the server uses a nutrition calculation algorithm to calculate the nutritional content (protein, vitamins, minerals, etc.) of each identified ingredient.

[0695] Step 5:

[0696] Server: Identifies nutrient deficiencies based on the user's age, gender, weight, blood pressure, daily activity level, and health data stored in a database. The input is the calculated nutritional composition data and the user's personal data, and the output is a list of nutrient deficiencies.

[0697] Specifically, it compares and analyzes individual health data with calculated nutritional components to identify nutrients that are lacking (e.g., calcium, magnesium, etc.).

[0698] Step 6:

[0699] Server: The emotion engine (Affectiva) recognizes emotions based on facial images acquired from the user's camera and emotion data entered by the user. The input is facial images and emotion input data, and the output is the recognized emotion data.

[0700] Specifically, the server passes facial images and text data to the emotion recognition engine, which then performs emotion analysis. The emotion engine then returns the recognized emotion to the server.

[0701] Step 7:

[0702] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a generative AI model (GPT-4). The input is nutrient deficiency data and emotion data, and the output is a suggested recipe.

[0703] Specifically, the server uses a database or generative AI model to search for or generate an appropriate recipe and output it as recipe data.

[0704] Step 8:

[0705] Device: The suggested recipes are customized according to the user's emotional state, encoded, and sent to the device. The input is the recipe data, and the output is the recipe information displayed on the user's device.

[0706] Specifically, the server encodes a recipe tailored to the user's emotional state and sends it to the device, which then decodes it and displays it to the user.

[0707] Step 9:

[0708] User: The user can review the received recipe and save it as the next dish to make. They can also enter feedback or requests for changes to the recipe. The input is the recipe data, and the output is the user's feedback data.

[0709] Specifically, users can view and check recipe information on their device, add it to their next cooking plan, and use the feedback function to enter comments about the suggested recipes.

[0710] Step 10:

[0711] User: If there is any food left after the meal, the user takes a photo of it again and uploads it to the server from their device. The input is the photo after the meal, and the output is the state of data reception to the server.

[0712] Step 11:

[0713] Server: Re-analyzes the re-received photos and re-calculates the actual nutritional intake. The input is the post-meal photo data, and the output is the recalculated nutritional information. This information is reflected in future recipe suggestions.

[0714] Specifically, the server performs image analysis again, recalculates the intake amount, and stores it in the database. This recalculated data is used to suggest the next recipe.

[0715] (Application example 2)

[0716] 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."

[0717] Conventional dietary management applications were able to analyze a user's dietary content and evaluate the nutrients in their meals, but they were unable to suggest recipes that took the user's emotional state into account. This made it difficult to increase user satisfaction and suggest meals that matched their mental state. Furthermore, the functionality to reassess the actual nutrients ingested based on leftover food after a meal was also insufficient. Therefore, there was a need for a system that could offer comprehensive dietary suggestions to users that took into account not only nutritional balance but also emotions.

[0718] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the ingredients and the dish identified by the image analysis means and identifying any nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the user's emotional information, and a suggestion means for suggesting recipes based on the identified nutrient deficiencies and emotional information. This enables more effective meal suggestions that take into account the user's emotional state as well as their nutritional balance.

[0719] "Meal content" refers to the types and amounts of ingredients and dishes consumed by the user.

[0720] "Photography method" refers to the device or method used by a user to photograph their meal.

[0721] "Image analysis means" refers to technology or equipment for analyzing food images acquired by the photographing means and identifying ingredients and the name of the dish.

[0722] "Nutrient calculation means" refers to a system or method for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrient deficiencies based on the results.

[0723] "Nutritional components" refers to the components such as proteins, lipids, carbohydrates, vitamins, and minerals contained in ingredients and dishes.

[0724] "Suggestion methods" refer to techniques and methods for suggesting recipes to supplement identified nutrient deficiencies.

[0725] "Emotion recognition means" refers to technology or devices that determine a user's emotional state at that time from their facial expressions and input data.

[0726] "Emotional information" refers to data that indicates a user's emotional state.

[0727] "Recipes" refer to cooking methods or dishes suggested based on specific nutrients or emotional states.

[0728] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. Furthermore, it combines an emotion engine that recognizes the user's emotional state to suggest more effective recipes.

[0729] User Interface

[0730] The user launches the application on their device and takes a photo of their meal. This application is for smartphones and includes a means for taking photos of the meal using the camera function. The photos are then viewed within the app, and after the user has confirmed the content, they press the "upload" button to send it to the server.

[0731] Image analysis and nutrition calculations

[0732] The server passes the received photos to an AI model for image analysis. This AI model uses TensorFlow and OpenCV to analyze the images and identify the ingredients and dish names. The analysis results are stored in a database, and a nutrient calculation tool is used to calculate the nutritional content of the ingredients and dishes, evaluating the nutritional balance of the entire meal. The user's age, gender, weight, blood pressure, daily activity level, and health data are identified to determine any nutrient deficiencies.

[0733] Emotion Recognition and Recipe Suggestion

[0734] The server uses an emotion recognition API to analyze the user's emotional state based on facial images captured from the user's camera and user input data. Based on the emotional information and nutrient deficiencies, the suggestion method searches for suitable recipes from the database and creates new recipes using a generative AI model if necessary. The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[0735] View and give feedback on suggested recipes

[0736] Users can review the received recipes on their device, save them for their next cooking plan, and even provide feedback or suggestions for changes to the recipes.

[0737] Post-meal check-up and feedback

[0738] If there are any leftovers after a meal, the user takes another photo of the meal and uploads it to the server. The server then uses image analysis to analyze the leftovers and recalculate the actual nutrient intake. Based on this result and the actual intake data, the user's eating history and emotional data are reflected in the learning model. This will be used to make suggestions for future meals.

[0739] Specific examples

[0740] For example, if a user has "pizza" and "salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server uses image analysis to identify the pizza and salad and calculate the nutritional components of each. As a result, the overall nutritional balance is evaluated and any nutrients that are lacking (e.g., vitamin D) are identified. At the same time, an emotion recognition engine recognizes the user's emotional state (e.g., stress). A recipe for "sauteed spinach and chicken," which contains food ingredients (e.g., magnesium) to alleviate stress, is suggested and sent to the user's device.

[0741] Prompt Sentence Examples

[0742] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[0743] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0744] Step 1:

[0745] The user launches the smartphone application and takes a photo of the meal. This application provides a means to capture the meal contents through the smartphone's camera function. When the user presses the "upload" button, the taken photo and user ID are sent to the server. The input data are the meal image and user ID, and these data are sent as output to proceed to the next step.

[0746] Step 2:

[0747] The server passes the received photo data to an AI model for image analysis. The AI ​​model uses TensorFlow and OpenCV to analyze the image and identify ingredients and dish names. The input is food image data, and the output is a list of identified ingredients and dish names. Specifically, the AI ​​model preprocesses the food images, extracts features, and classifies the ingredients and dishes using a pre-trained model.

[0748] Step 3:

[0749] The server uses a nutrient calculation means to calculate nutritional components based on the analyzed ingredients and dish names. The input is a list of identified ingredients and dish names and the user's health information (age, gender, weight, blood pressure, activity level, etc.). The output is a list of nutrients that are lacking. Specifically, the server obtains nutritional information for each ingredient from the database and totals it to evaluate the overall nutritional balance and identify any nutrients that are lacking.

[0750] Step 4:

[0751] The server activates the emotion recognition means using facial images and input data acquired from the user's camera. The input is the facial image and input data, and the output is the recognized emotional information of the user. Specifically, the emotion recognition API is used to analyze the emotional state (stress, joy, fatigue, etc.) from the facial image.

[0752] Step 5:

[0753] The server uses a suggestion mechanism to suggest recipes based on the identified nutrient deficiencies and emotional information. The input is a list of nutrient deficiencies and emotional information, and the output is a list of suitable recipes. Specifically, it searches for relevant recipes in the database and creates new recipes using a generative AI model if necessary. Here, the generative AI model uses the following prompt sentence:

[0754] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[0755] Step 6:

[0756] The server sends the suggested recipes to the user's device. The input is a list of suitable recipes, and the output is the data describing the recipes. The user's device displays the received recipes, and the user can save them for their next cooking plan. They can also enter feedback or requests for changes to the recipes.

[0757] Step 7:

[0758] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server. The server then uses image analysis to analyze the leftover food and recalculate the actual nutritional intake. The input is the post-meal photo, and the output is a recalculated list of nutrients. This allows the user's eating history and emotional data to be reflected in the learning model and used to make suggestions for future meals.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] [Third embodiment]

[0763] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0764] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0765] 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).

[0766] 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.

[0767] 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.

[0768] 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).

[0769] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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."

[0775] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including the user's device, a server, and an AI model.

[0776] User Interface

[0777] User: First, the user launches the application on their device and takes a photo of their meal. The photo is then displayed once within the application, allowing the user to review the content.

[0778] Uploading an image

[0779] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[0780] Image analysis and nutrition calculations

[0781] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[0782] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[0783] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0784] Recipe Suggestions

[0785] Server: Selects recipes from the database to supplement missing nutrients, and creates new recipes using a recipe generation algorithm if necessary.

[0786] Server: Suggested recipes are customized for each user and sent to the user's device.

[0787] Displaying suggested recipes

[0788] On the device: Users can view the received recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipe.

[0789] Post-meal check-up and feedback

[0790] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[0791] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. This data is used for future recommendations.

[0792] Specific examples

[0793] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of it and upload it to the server via the app.

[0794] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis, calculates the nutritional components (protein, vitamins, minerals, etc.) of each, and evaluates the nutritional balance of the user's entire meal, determining that calcium is particularly lacking.

[0795] Server: To supplement calcium, suggest a recipe for "Komatsuna and Tofu Stir-fry" and send it to the user's device.

[0796] On the device: Users can view recipes and save them for their next cooking plan.

[0797] User: If there is any food left over after a meal, the user can take a photo of it again and upload it to the server, which will reflect the actual amount consumed.

[0798] In this way, by using this system, it is easy to create nutritionally balanced meals tailored to each individual user.

[0799] The processing flow will be explained below.

[0800] Step 1:

[0801] User: Takes a photo of their meal using their device's camera. After taking the photo, the app displays a screen where they can review the photo.

[0802] Step 2:

[0803] Terminal: The user checks the photo and, if there are no problems, presses the "Upload" button. This action sends the taken photo and the user ID to the server.

[0804] Step 3:

[0805] Server: Stores the received food photos in a temporary storage area.

[0806] Step 4:

[0807] Server: Calls the AI ​​model for image analysis and provides the stored food photos as input.

[0808] Step 5:

[0809] AI model (on the server): Analyzes the image and identifies the ingredients, dish name, and quantity. The analysis results are generated as a data list.

[0810] Step 6:

[0811] Server: Saves the analysis result data list in a database for each user.

[0812] Step 7:

[0813] Server: Based on the analysis results, the nutritional components of each ingredient and dish are queried from the database and individual components are obtained.

[0814] Step 8:

[0815] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies any nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0816] Step 9:

[0817] Server: Searches the database for suitable recipes to supplement missing nutrients. If necessary, it runs the recipe generation algorithm to create new recipes.

[0818] Step 10:

[0819] Server: Formats the suggested recipes into a format suitable for the user and sends them to the user's device.

[0820] Step 11:

[0821] On your device: The received recipes are displayed for the user to review. The user can then review the suggested recipes and save them as their next meal.

[0822] Step 12:

[0823] User: If necessary, after the meal, if there is any leftover food, take a photo of it again and upload it to the server via the device.

[0824] Step 13:

[0825] Server: The received post-meal photo is provided to an image analysis AI model to analyze any leftover food.

[0826] Step 14:

[0827] AI model (on server): Detects leftover food and returns nutritional data for recalculation.

[0828] Step 15:

[0829] Server: Recalculates the actual nutritional intake and updates the user's nutritional intake history.

[0830] Step 16:

[0831] Server: The server accumulates the user's food history and preferences as learning data and updates the model parameters for future suggestions. This data is stored in a database and used for future recipe suggestions.

[0832] Example 1

[0833] 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."

[0834] Conventional dietary management systems require users to manually input meal contents and calculate nutrients, which is time-consuming and often lacks accuracy. Furthermore, there is a need for improved management of leftover food after meals and more accurate recipe suggestions that take individual health information into account. A system that solves these problems and allows for easier and more accurate dietary management is desired.

[0835] 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.

[0836] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the photographed meal image to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dishes and identifying nutrient deficiencies based on the user's health information, a proposal means for proposing recipes to compensate for the identified nutrient deficiencies, a transmission means for sending the recipes generated by the proposal means to the user's terminal, a reanalysis means for photographing leftover food after a meal and reanalyzing the leftover food with the image analysis means to recalculate the actual nutritional components ingested, and a learning model reflection means for utilizing the results of the reanalysis means for future proposals. This significantly reduces the user's workload and enables highly accurate nutritional management and appropriate recipe proposals based on individual health information.

[0837] The "photography means" is a device or application with a camera function that allows the user to take photos of the contents of a meal.

[0838] "Image analysis means" refers to software or algorithms that analyze photographed food images to identify ingredients and the name of the dish.

[0839] The "nutrient calculation means" is a means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means, and for identifying any nutrients that are lacking based on the user's health information.

[0840] A "suggestion tool" is software or an algorithm that suggests recipes to supplement identified nutrient deficiencies.

[0841] The "transmission means" is a device or application having a communication function for transmitting the recipe generated by the proposal means to the user's terminal.

[0842] The "reanalysis means" is a means for taking a photo of the leftover food after a meal, analyzing the leftover food again using the image analysis means, and recalculating the nutritional components actually ingested.

[0843] The "learning model reflection means" refers to a machine learning model or algorithm that is used for future proposals based on the results of the reanalysis means.

[0844] The system of this invention allows users to take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including a user device, a server, and an AI model.

[0845] First, the user launches the application on their device and takes a photo of their meal using the camera function of their smartphone or tablet. The photo is displayed once within the application, allowing the user to confirm the content. After confirming the photo, the user presses the "Upload" button, which sends the photo file and the user's ID information to the server.

[0846] The server stores the received photos in a dedicated directory and passes them to an image analysis AI model. This AI model (for example, a model built using TensorFlow or PyTorch) analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in an internal database (for example, MySQL or PostgreSQL), and the nutritional content of each ingredient and dish is calculated.

[0847] Next, the server evaluates the nutritional balance of the entire meal based on the user's health information (age, gender, weight, blood pressure, daily activity level, etc.) and identifies any nutrient deficiencies. This evaluation can be performed using the Nutrient Analysis API.

[0848] The server then suggests recipes to supplement the identified nutrient deficiencies. It can query existing recipe databases to find recipes that match the user's criteria and select the recipe that best suits them. It can also generate new recipes as needed using a generative AI model. The recipe generation algorithm then takes into account the user's preferences and health status when creating a recipe.

[0849] The suggested recipes are individually customized and sent to the user's device. The recipe data is delivered via a push notification service, and the user can check the recipe on the application screen and save it as a cooking plan for the next time. They can also enter feedback or requests for changes.

[0850] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server via the app. The server then analyzes the image again and recalculates the actual nutrient intake. The recalculated data is stored in an internal database and will be reflected in future recommendations. This allows for more accurate recommendations based on the user's preferences and actual intake data.

[0851] As a concrete example, consider the case where a user has "grilled salmon" and "vegetable salad" for dinner. The user takes a photo of this and uploads it to the server via the app. The server uses image analysis to identify that it is "grilled salmon" and "vegetable salad" and calculates the nutritional content of each. If the server determines that the user's health data indicates a calcium deficiency, it will suggest a recipe for "komatsuna and tofu stir fry" and send it to the user's device. The user can check the recipe on their device and save it for their next cooking plan.

[0852] An example of a prompt is as follows:

[0853] text

[0854] A user uploads a photo of their dinner. Perform image analysis to identify the ingredients, dish name, and nutritional components of each, and generate a recipe that takes into account the user's health data and supplements any missing nutrients.

[0855] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0856] Step 1:

[0857] The user takes a photo of their meal

[0858] User: Takes a photo of a meal using the camera function of a smartphone or tablet. The input is the image of the meal captured through the camera, and the output is a preview image displayed on the application screen.

[0859] Step 2:

[0860] Upload the image to the server

[0861] Device: The user presses the "Upload" button. The input is the captured photo file and the user's ID information, and the output is the data sent to the server as an HTTP request. Specifically, the device generates an HTTP POST request to send the captured image file to the server.

[0862] Step 3:

[0863] Save and analyze the image

[0864] Server: Saves the received photos in a dedicated directory. Then, inputs the saved image file into an AI model for image analysis. The input is the saved image file, and the output is a list of ingredients and dish names analyzed by the AI ​​model. Specifically, the server saves the image file to disk and passes the path of that file to the API of the AI ​​model.

[0865] Step 4:

[0866] Calculate nutritional information

[0867] Server: Calculates the nutritional content of each ingredient and dish based on the results of image analysis. The input is the data on ingredients, dish names, and quantities obtained as a result of the analysis, and the output is detailed data on each nutritional content. Specifically, the server compares this data with its internal database and obtains nutritional information for each ingredient.

[0868] Step 5:

[0869] Evaluate nutritional balance based on user health information

[0870] Server: Refers to the user's health information, such as age, gender, weight, blood pressure, and daily activity level, to identify nutrient deficiencies. The input is the user's health information and nutritional composition data, and the output is a list of nutrient deficiencies. Specifically, the server uses the Nutrient Analysis API to evaluate nutritional balance.

[0871] Step 6:

[0872] Suggest suitable recipes

[0873] Server: Searches the database for recipes to supplement nutrient deficiencies or generates new recipes using a generative AI model. The input is a list of nutrient deficiencies, and the output is suggested recipes. Specifically, the server queries the recipe database and extracts recipes that match the criteria.

[0874] Step 7:

[0875] Sending recipes to the user's device

[0876] Device: Receives the suggested recipe and displays it on the application screen. The input is the recipe data sent from the server, and the output is the recipe displayed on the device's application screen. Specifically, the device receives a push notification and displays the contents in the application.

[0877] Step 8:

[0878] Take a photo of your leftovers after eating and upload it again

[0879] User: If there is any leftover food after the meal, the user takes another photo of the meal and uploads it to the server through the app. The input is the newly taken photo after the meal, and the output is the photo file uploaded to the server.

[0880] Step 9:

[0881] Reanalyze leftovers and recalculate nutritional information

[0882] Server: Analyzes the post-meal photo again, identifies any leftover food, and recalculates the actual nutritional intake. The input is the re-taken photo and the analysis results, and the output is the revised nutritional intake data. Specifically, the server performs image analysis again and saves the results in a database.

[0883] Step 10:

[0884] Reflecting in the learning model

[0885] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. The input is the revised nutritional intake data, and the output is an updated learning model. Specifically, the server updates the model using a machine learning algorithm and uses it for future recommendations.

[0886] Through the above processing steps, the system provides users with highly accurate nutritional management and appropriate recipe suggestions.

[0887] (Application example 1)

[0888] 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."

[0889] Conventional dietary management systems have the ability to photograph meals and evaluate their nutritional balance, but they lack the ability to suggest specific actions based on the evaluation results or provide practical measures for nutritional supplementation. In particular, they lack an appropriate means for users to easily put the suggested recipes into practice. Furthermore, they lack a system for accurately grasping post-meal intake and reflecting this in future recommendations.

[0890] 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.

[0891] In this invention, the server includes a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the identified ingredients and dish and identifying any nutrient deficiencies based on the user's health information, a suggestion means for suggesting recipes to compensate for the identified nutrient deficiencies, and a delivery means for delivering appropriate dishes based on the suggested recipes. This allows the user to easily take concrete actions to replenish the identified nutrients, and enables the next suggestion to accurately reflect the nutrition actually ingested.

[0892] "Photographing means" refers to a device or apparatus that allows the user to photograph the contents of their meal.

[0893] The "image analysis means" is a system or program for analyzing a photographed image of a meal and identifying the ingredients and the name of the dish.

[0894] The "nutrient calculation means" is a system or program that calculates the nutritional components of the ingredients and dishes identified by the image analysis means and identifies any nutrients that are lacking based on the user's health information.

[0895] The "suggestion means" is a system or program that suggests to the user recipes for supplementing the nutrient deficiencies identified by the nutrient calculation means.

[0896] "Delivery Method" means a system or service that delivers appropriate dishes to users based on the suggested recipes.

[0897] "User health information" refers to data such as the user's age, gender, weight, blood pressure, and daily activity level.

[0898] A "recipe" is a document or information that shows how to prepare or mix a dish to supplement missing nutrients.

[0899] The "after-meal photo" is an image of leftover food after a meal.

[0900] A "server" is a computer system for receiving and analyzing data sent by users.

[0901] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is comprised of an integrated platform that includes the user's device, a server, and an AI model.

[0902] First, the user launches the application on their device and takes a photo of their meal. The photo is displayed once within the application, and the user confirms the content. After that, the user presses the "Upload" button. This action sends the photo and the user's ID information to the server.

[0903] The server passes the received photos to an AI model for image analysis. The AI ​​model uses deep learning frameworks such as TensorFlow and Keras. This analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated. Based on this, the nutritional balance of the entire meal is evaluated.

[0904] The server then identifies nutrient deficiencies, taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data. Based on this information, the server selects recipes from its database to address these nutrient deficiencies, and creates new recipes if necessary using a recipe generation algorithm. The proposed recipes are customized for each user and sent to the user's device.

[0905] Users can review the received recipe on their device and save it as their next meal. They can also order meals based on the suggested recipe through a delivery method that will provide the appropriate dish. If there are any leftovers after the meal, the user can take another photo of the meal and upload it to the server. The actual nutrient intake is then recalculated based on the photo. This allows the user's dietary history and preferences to be reflected in the learning model. This data will be used for future suggestions.

[0906] As a concrete example, let's say a user is having "grilled salmon" and "vegetable salad" for dinner. They take a photo of this and upload it to the server via the app. The server then analyzes the image and identifies the dishes as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish (protein, vitamins, minerals, etc.) and evaluates the nutritional balance of the entire meal. For example, if the server determines that the user is lacking in calcium, it will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can then check this recipe, save it as part of their next cooking plan, or order it through a food delivery service.

[0907] An example of a prompt is:

[0908] "Just take a photo of the dinner you recently had and upload it to the app (NutriMeal). The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[0909] Examples include:

[0910] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0911] Step 1: Shoot and review

[0912] The user launches the application on their device and takes a photo of their meal. The photo is then displayed in the application, allowing the user to review the content.

[0913] Input: A meal photo taken by the user

[0914] Output: Confirmation photo displayed on the device

[0915] How it works: A user takes a photo of a meal and reviews it.

[0916] Step 2: Upload a photo

[0917] The user presses the "upload" button, and the captured photo and the user's ID information are sent to the server.

[0918] Input: Meal photos taken by the user, user ID information

[0919] Output: Photo and ID information uploaded to the server

[0920] Operation: The device sends the input photo and ID information to the server.

[0921] Step 3: Image analysis

[0922] The server passes the received photos to an AI model for image analysis, which identifies the ingredients, dish name, and quantity.

[0923] Input: Photo uploaded to the server

[0924] Output: Identified ingredients, dish name, and quantity

[0925] How it works: The AI ​​model analyzes the image and identifies ingredients and dishes.

[0926] Step 4: Nutritional assessment

[0927] The server calculates the nutritional content of the identified ingredients and dishes and identifies any nutrient deficiencies based on the user's health information.

[0928] Input: Identified ingredients and dish names, user health information

[0929] Output: Identification of nutrient deficiencies

[0930] Operation: The nutrient calculation tool calculates nutritional components and assesses nutritional deficiencies based on health information.

[0931] Step 5: Recipe suggestions

[0932] The server selects recipes from a database to supplement the identified nutrient deficiencies and generates new recipes as needed. The suggested recipes are customized for each user and sent to the device.

[0933] Input: Identification results of missing nutrients, recipe information from the database

[0934] Output: The customized recipe sent to the user's device

[0935] How it works: The server selects the appropriate recipe and sends the customized results to the device.

[0936] Step 6: View and save the recipe

[0937] Users can view the received recipes on their device, save them as their next meal, and order meals based on the suggested recipes through food delivery services.

[0938] Input: Recipe sent to terminal

[0939] Output: User-saved next cooking plan and ordering information

[0940] What it does: Displays a recipe on the device, allowing the user to review, save, and order.

[0941] Step 7: Post-meal review and feedback

[0942] After a meal, users take a photo of the leftover food and upload it to the server, which then analyzes the image again and recalculates the actual nutritional intake.

[0943] Input: A photo of leftover food taken after a meal

[0944] Output: Recalculated nutrient data

[0945] How it works: The server analyzes the post-meal photo and re-evaluates the actual intake.

[0946] Examples:

[0947] If a user eats "grilled salmon" and "vegetable salad" for dinner, they take a photo of it and upload it to the server via the app. The server then analyzes the image and identifies it as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish and evaluates their nutritional balance. For example, if it determines that the user is lacking in calcium, the server will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can check this recipe, save it in their next cooking plan, or order it through a food delivery service. If there is any leftover food after the meal, they can take another photo of it and upload it to the server, which will reflect their actual intake.

[0948] Prompt statement:

[0949] "Just take a photo of the dinner you recently had and upload it to the app. The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[0950] 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.

[0951] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to suggest more effective recipes. The system is comprised of an integrated platform that includes the user's device, a server, an AI model, and the emotion engine.

[0952] User Interface

[0953] User: First, the user launches the app on their device and takes a photo of their meal. The photo is then viewed once within the app, where the user can review it.

[0954] Uploading an image

[0955] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[0956] Image analysis and nutrition calculations

[0957] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[0958] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[0959] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0960] Emotion Recognition and Recipe Suggestion

[0961] Server: At the same time, the emotion engine recognizes emotions based on the facial image acquired from the user's camera and the user's input data.

[0962] Server: The emotional data recognized by the emotion engine is incorporated into recipe suggestions to supplement the identified nutrient deficiencies.

[0963] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a recipe generation algorithm.

[0964] Server: Suggested recipes are customized according to the user's emotional state and sent to the user's device.

[0965] Displaying suggested recipes

[0966] On the device: The user can review the received recipe on the device, save it as a recipe to make next, and enter feedback or requests for changes to the recipe.

[0967] Post-meal check-up and feedback

[0968] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[0969] Server: Based on the analysis results and actual intake data, the user's eating history and emotional data are reflected in the learning model. This data is used for future recommendations.

[0970] Specific examples

[0971] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of this meal and upload it to the server via the app.

[0972] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis and calculates the nutritional components (protein, vitamins, minerals, etc.) of each. Based on these results, evaluates the nutritional balance of the entire meal and identifies any nutrients that are lacking (such as calcium).

[0973] Server: At the same time, the emotion engine recognizes the user's emotional state (e.g., whether they are feeling stressed) from their facial expressions.

[0974] Server: Suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to relieve stress and sends it to the user's device.

[0975] On the device: Users can view recipes and save them for future cooking plans.

[0976] User: If desired, if there is any leftover food after a meal, take and upload a photo of it again, which will reflect the actual amount consumed.

[0977] In this way, by using this system, users can receive more appropriate meal suggestions based on their own nutritional balance and emotional state.

[0978] The processing flow will be explained below.

[0979] Step 1:

[0980] User: Takes a photo of their meal using their device's camera. After taking the photo, the photo is displayed in the app and the user can review the photo.

[0981] Step 2:

[0982] On the device: The user checks the photo and presses the "Upload" button. This action sends the captured photo and user ID information to the server.

[0983] Step 3:

[0984] Server: Temporarily stores the received food photos and prepares them for passing to the image analysis AI model.

[0985] Step 4:

[0986] Server: Calls the image analysis AI model and inputs the saved food photos to analyze them.

[0987] Step 5:

[0988] AI model (on the server): Analyzes food photos and identifies ingredients, dish names, and quantities. The analysis results are generated as a data list.

[0989] Step 6:

[0990] Server: Saves the analysis result data list in a database for each user. Next, proceeds to calculate nutritional components.

[0991] Step 7:

[0992] Server: Based on the analysis results, the server queries the database for the nutritional information of each ingredient and dish and obtains the information.

[0993] Step 8:

[0994] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[0995] Step 9:

[0996] User: During this time, the device camera takes a picture of the user's face and recognizes their current emotional state.

[0997] Step 10:

[0998] Device: Sends the user's facial image to the server.

[0999] Step 11:

[1000] Server: Inputs the received facial image into the emotion engine to recognize the user's emotional state.

[1001] Step 12:

[1002] Emotion engine (on the server): Analyzes facial images to identify the user's emotional state (e.g., joy, stress, fatigue, etc.).

[1003] Step 13:

[1004] Server: Based on the emotional data identified by the emotion engine, the suggested recipes are adjusted according to the user's emotional state.

[1005] Step 14:

[1006] Server: Searches the database for suitable recipes based on missing nutrients and emotion data, and runs the recipe generation algorithm to create new recipes as needed.

[1007] Step 15:

[1008] Server: The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[1009] Step 16:

[1010] On the device: The received recipe is displayed to the user, who can then review the recipe and save it for their next cooking appointment.

[1011] Step 17:

[1012] User: If there is any food left over after the meal, take another photo after the meal and upload it to the server via the device.

[1013] Step 18:

[1014] Device: Send a photo of the leftovers and the user ID to the server.

[1015] Step 19:

[1016] Server: Provides newly received images to an image analysis AI model to analyze leftover food.

[1017] Step 20:

[1018] AI model (in the server): Detects leftover food and returns the analysis results to the server.

[1019] Step 21:

[1020] Server: Recalculates the actual nutritional intake and records the new nutritional balance data in the user's diet history.

[1021] Step 22:

[1022] Server: The user's eating history and emotional data are reflected in the learning model. This data is used to suggest recipes for future meals.

[1023] In this way, users can receive appropriate meal suggestions based on their nutritional balance and emotional state, enabling more precise and personalized dietary management.

[1024] Example 2

[1025] 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."

[1026] In modern society, it is extremely important to properly manage individual dietary content and personal health. However, many existing systems only analyze the nutritional balance of meals and are unable to provide personalized suggestions that take the user's emotional state into account. As a result, it is difficult for the suggested healthy recipes to increase the user's psychological satisfaction, making it difficult to maintain long-term health.

[1027] 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.

[1028] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dish identified by the image analysis means and identifying nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the emotional state of the user, and a suggestion means for suggesting recipes based on the emotional state and nutrient deficiencies identified by the emotion recognition means. This makes it possible to suggest individually optimized recipes that comprehensively consider the user's nutritional and emotional states.

[1029] "Photographing means" refers to the device and its functions used to photograph the contents of a meal.

[1030] "Image analysis means" refers to technology or equipment for analyzing photographed food images to identify ingredients and the name of the dish.

[1031] "Nutrient calculation means" refers to technology or equipment for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrients that are lacking based on the user's health information.

[1032] "Emotion recognition means" refers to techniques or devices for recognizing a user's emotional state, including analyzing facial expressions and evaluating user-input data.

[1033] "Recommendation means" refers to a technology or device for suggesting recipes based on identified nutrient deficiencies and emotional state.

[1034] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to provide an integrated platform for more effective recipe suggestions. This system includes a user device, a server, a generative AI model, and an emotion recognition engine.

[1035] Hardware and software used

[1036] Device: The user uses a smartphone or tablet, which includes a camera and internet connectivity.

[1037] Server: The center of data processing, performing various calculations and storing data. The server is installed with an AI model (e.g., TensorFlow), an emotion recognition engine (e.g., Affectiva), and a database (e.g., MongoDB).

[1038] Generative AI models: used to generate recipes. An example is GPT-4.

[1039] System Operation

[1040] The user launches the application on their device and takes a photo of their meal. The photo is then viewed within the app, and when the user presses the "upload" button, the photo and the user's ID information are sent to the server.

[1041] The server passes the received photo to an AI model for image analysis (e.g., TensorFlow). The AI ​​model analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated.

[1042] Next, nutrient deficiencies are identified, taking into account the user's age, gender, weight, blood pressure, daily activity, and health data. At the same time, an emotion engine (e.g., Affectiva) recognizes emotions based on facial images captured from the user's camera. Emotional data is combined with the identified nutrient deficiencies to find suitable recipes, or create new recipes using a generative AI model (e.g., GPT-4) if necessary.

[1043] The suggested recipes are customized based on the user's emotional state, encoded, and sent to the user's device. The user can then review the recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipes.

[1044] If the user has leftover food after a meal, they can take a photo of it again and upload it to the server. Based on that photo, the actual nutrient intake is recalculated, and the results are reflected in future recipe suggestions.

[1045] Specific examples

[1046] For example, if a user has "grilled salmon" and "vegetable salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server will use image analysis to identify the dishes as "grilled salmon" and "vegetable salad" and calculate the nutritional content (protein, vitamins, minerals, etc.) of each. It will then evaluate the nutritional balance of the entire meal and identify any nutrients (such as calcium) that are lacking.

[1047] Next, the emotion engine recognizes the user's emotional state (e.g., stress) from their facial expressions, and suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to alleviate stress, and sends it to the user's device.

[1048] Users can review recipes, save them for their next cooking plan, and, if desired, take and upload a photo of any leftovers after a meal to reflect their actual intake.

[1049] By using this system, users can receive more appropriate meal suggestions based on their nutritional balance and emotional state.

[1050] Prompt Sentence Examples

[1051] Prompt: If the user had "grilled salmon" and "vegetable salad" for dinner but is feeling stressed, suggest a new recipe that contains magnesium.

[1052] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1053] Step 1:

[1054] User: The user launches the application on their smartphone or tablet. They launch the dedicated app, select camera mode, and take a photo of their current meal. The input is the meal photo, and the output is the confirmed photo data.

[1055] Step 2:

[1056] Device: When the user presses the "Upload" button, the photo of the meal taken and the user's ID information are sent from the device to the server. Here, the data travels via an Internet connection. The input is the photo data and the user ID, and the output is the data reception status on the server.

[1057] Step 3:

[1058] Server: The server inputs the received photo data into an AI model (TensorFlow) for image analysis. The AI ​​model analyzes the image and identifies the ingredients, dish name, and quantity. The input is the photo data, and the output is the identified ingredients, dish name, and quantity.

[1059] Specifically, the image analysis model scans the photo, compares it with an existing database to identify ingredients and the name of the dish, and then verifies whether the analysis is correct before proceeding to the next step.

[1060] Step 4:

[1061] Server: Stores the analysis results in a database and calculates the nutritional content of each ingredient and dish. A publicly available food nutrition database is used for the nutrition calculation. The input is the identified ingredient information, and the output is the calculated nutritional content data.

[1062] Specifically, the server uses a nutrition calculation algorithm to calculate the nutritional content (protein, vitamins, minerals, etc.) of each identified ingredient.

[1063] Step 5:

[1064] Server: Identifies nutrient deficiencies based on the user's age, gender, weight, blood pressure, daily activity level, and health data stored in a database. The input is the calculated nutritional composition data and the user's personal data, and the output is a list of nutrient deficiencies.

[1065] Specifically, it compares and analyzes individual health data with calculated nutritional components to identify nutrients that are lacking (e.g., calcium, magnesium, etc.).

[1066] Step 6:

[1067] Server: The emotion engine (Affectiva) recognizes emotions based on facial images acquired from the user's camera and emotion data entered by the user. The input is facial images and emotion input data, and the output is the recognized emotion data.

[1068] Specifically, the server passes facial images and text data to the emotion recognition engine, which then performs emotion analysis. The emotion engine then returns the recognized emotion to the server.

[1069] Step 7:

[1070] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a generative AI model (GPT-4). The input is nutrient deficiency data and emotion data, and the output is a suggested recipe.

[1071] Specifically, the server uses a database or generative AI model to search for or generate an appropriate recipe and output it as recipe data.

[1072] Step 8:

[1073] Device: The suggested recipes are customized according to the user's emotional state, encoded, and sent to the device. The input is the recipe data, and the output is the recipe information displayed on the user's device.

[1074] Specifically, the server encodes a recipe tailored to the user's emotional state and sends it to the device, which then decodes it and displays it to the user.

[1075] Step 9:

[1076] User: The user can review the received recipe and save it as the next dish to make. They can also enter feedback or requests for changes to the recipe. The input is the recipe data, and the output is the user's feedback data.

[1077] Specifically, users can view and check recipe information on their device, add it to their next cooking plan, and use the feedback function to enter comments about the suggested recipes.

[1078] Step 10:

[1079] User: If there is any food left after the meal, the user takes a photo of it again and uploads it to the server from their device. The input is the photo after the meal, and the output is the state of data reception to the server.

[1080] Step 11:

[1081] Server: Re-analyzes the re-received photos and re-calculates the actual nutritional intake. The input is the post-meal photo data, and the output is the recalculated nutritional information. This information is reflected in future recipe suggestions.

[1082] Specifically, the server performs image analysis again, recalculates the intake amount, and stores it in the database. This recalculated data is used to suggest the next recipe.

[1083] (Application example 2)

[1084] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1085] Conventional dietary management applications were able to analyze a user's dietary content and evaluate the nutrients in their meals, but they were unable to suggest recipes that took the user's emotional state into account. This made it difficult to increase user satisfaction and suggest meals that matched their mental state. Furthermore, the functionality to reassess the actual nutrients ingested based on leftover food after a meal was also insufficient. Therefore, there was a need for a system that could offer comprehensive dietary suggestions to users that took into account not only nutritional balance but also emotions.

[1086] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the ingredients and the dish identified by the image analysis means and identifying any nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the user's emotional information, and a suggestion means for suggesting recipes based on the identified nutrient deficiencies and emotional information. This enables more effective meal suggestions that take into account the user's emotional state as well as their nutritional balance.

[1087] "Meal content" refers to the types and amounts of ingredients and dishes consumed by the user.

[1088] "Photography method" refers to the device or method used by a user to photograph their meal.

[1089] "Image analysis means" refers to technology or equipment for analyzing food images acquired by the photographing means and identifying ingredients and the name of the dish.

[1090] "Nutrient calculation means" refers to a system or method for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrient deficiencies based on the results.

[1091] "Nutritional components" refers to the components such as proteins, lipids, carbohydrates, vitamins, and minerals contained in ingredients and dishes.

[1092] "Suggestion methods" refer to techniques and methods for suggesting recipes to supplement identified nutrient deficiencies.

[1093] "Emotion recognition means" refers to technology or devices that determine a user's emotional state at that time from their facial expressions and input data.

[1094] "Emotional information" refers to data that indicates a user's emotional state.

[1095] "Recipes" refer to cooking methods or dishes suggested based on specific nutrients or emotional states.

[1096] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. Furthermore, it combines an emotion engine that recognizes the user's emotional state to suggest more effective recipes.

[1097] User Interface

[1098] The user launches the application on their device and takes a photo of their meal. This application is for smartphones and includes a means for taking photos of the meal using the camera function. The photos are then viewed within the app, and after the user has confirmed the content, they press the "upload" button to send it to the server.

[1099] Image analysis and nutrition calculations

[1100] The server passes the received photos to an AI model for image analysis. This AI model uses TensorFlow and OpenCV to analyze the images and identify the ingredients and dish names. The analysis results are stored in a database, and a nutrient calculation tool is used to calculate the nutritional content of the ingredients and dishes, evaluating the nutritional balance of the entire meal. The user's age, gender, weight, blood pressure, daily activity level, and health data are identified to determine any nutrient deficiencies.

[1101] Emotion Recognition and Recipe Suggestion

[1102] The server uses an emotion recognition API to analyze the user's emotional state based on facial images captured from the user's camera and user input data. Based on the emotional information and nutrient deficiencies, the suggestion method searches for suitable recipes from the database and creates new recipes using a generative AI model if necessary. The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[1103] View and give feedback on suggested recipes

[1104] Users can review the received recipes on their device, save them for their next cooking plan, and even provide feedback or suggestions for changes to the recipes.

[1105] Post-meal check-up and feedback

[1106] If there are any leftovers after a meal, the user takes another photo of the meal and uploads it to the server. The server then uses image analysis to analyze the leftovers and recalculate the actual nutrient intake. Based on this result and the actual intake data, the user's eating history and emotional data are reflected in the learning model. This will be used to make suggestions for future meals.

[1107] Specific examples

[1108] For example, if a user has "pizza" and "salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server uses image analysis to identify the pizza and salad and calculate the nutritional components of each. As a result, the overall nutritional balance is evaluated and any nutrients that are lacking (e.g., vitamin D) are identified. At the same time, an emotion recognition engine recognizes the user's emotional state (e.g., stress). A recipe for "sauteed spinach and chicken," which contains food ingredients (e.g., magnesium) to alleviate stress, is suggested and sent to the user's device.

[1109] Prompt Sentence Examples

[1110] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[1111] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1112] Step 1:

[1113] The user launches the smartphone application and takes a photo of the meal. This application provides a means to capture the meal contents through the smartphone's camera function. When the user presses the "upload" button, the taken photo and user ID are sent to the server. The input data are the meal image and user ID, and these data are sent as output to proceed to the next step.

[1114] Step 2:

[1115] The server passes the received photo data to an AI model for image analysis. The AI ​​model uses TensorFlow and OpenCV to analyze the image and identify ingredients and dish names. The input is food image data, and the output is a list of identified ingredients and dish names. Specifically, the AI ​​model preprocesses the food images, extracts features, and classifies the ingredients and dishes using a pre-trained model.

[1116] Step 3:

[1117] The server uses a nutrient calculation means to calculate nutritional components based on the analyzed ingredients and dish names. The input is a list of identified ingredients and dish names and the user's health information (age, gender, weight, blood pressure, activity level, etc.). The output is a list of nutrients that are lacking. Specifically, the server obtains nutritional information for each ingredient from the database and totals it to evaluate the overall nutritional balance and identify any nutrients that are lacking.

[1118] Step 4:

[1119] The server activates the emotion recognition means using facial images and input data acquired from the user's camera. The input is the facial image and input data, and the output is the recognized emotional information of the user. Specifically, the emotion recognition API is used to analyze the emotional state (stress, joy, fatigue, etc.) from the facial image.

[1120] Step 5:

[1121] The server uses a suggestion mechanism to suggest recipes based on the identified nutrient deficiencies and emotional information. The input is a list of nutrient deficiencies and emotional information, and the output is a list of suitable recipes. Specifically, it searches for relevant recipes in the database and creates new recipes using a generative AI model if necessary. Here, the generative AI model uses the following prompt sentence:

[1122] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[1123] Step 6:

[1124] The server sends the suggested recipes to the user's device. The input is a list of suitable recipes, and the output is the data describing the recipes. The user's device displays the received recipes, and the user can save them for their next cooking plan. They can also enter feedback or requests for changes to the recipes.

[1125] Step 7:

[1126] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server. The server then uses image analysis to analyze the leftover food and recalculate the actual nutritional intake. The input is the post-meal photo, and the output is a recalculated list of nutrients. This allows the user's eating history and emotional data to be reflected in the learning model and used to make suggestions for future meals.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] [Fourth embodiment]

[1131] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1132] 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.

[1133] 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).

[1134] 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.

[1135] 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.

[1136] 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).

[1137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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."

[1144] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including the user's device, a server, and an AI model.

[1145] User Interface

[1146] User: First, the user launches the application on their device and takes a photo of their meal. The photo is then displayed once within the application, allowing the user to review the content.

[1147] Uploading an image

[1148] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[1149] Image analysis and nutrition calculations

[1150] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[1151] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[1152] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[1153] Recipe Suggestions

[1154] Server: Selects recipes from the database to supplement missing nutrients, and creates new recipes using a recipe generation algorithm if necessary.

[1155] Server: Suggested recipes are customized for each user and sent to the user's device.

[1156] Displaying suggested recipes

[1157] On the device: Users can view the received recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipe.

[1158] Post-meal check-up and feedback

[1159] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[1160] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. This data is used for future recommendations.

[1161] Specific examples

[1162] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of it and upload it to the server via the app.

[1163] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis, calculates the nutritional components (protein, vitamins, minerals, etc.) of each, and evaluates the nutritional balance of the user's entire meal, determining that calcium is particularly lacking.

[1164] Server: To supplement calcium, suggest a recipe for "Komatsuna and Tofu Stir-fry" and send it to the user's device.

[1165] On the device: Users can view recipes and save them for their next cooking plan.

[1166] User: If there is any food left over after a meal, the user can take a photo of it again and upload it to the server, which will reflect the actual amount consumed.

[1167] In this way, by using this system, it is easy to create nutritionally balanced meals tailored to each individual user.

[1168] The processing flow will be explained below.

[1169] Step 1:

[1170] User: Takes a photo of their meal using their device's camera. After taking the photo, the app displays a screen where they can review the photo.

[1171] Step 2:

[1172] Terminal: The user checks the photo and, if there are no problems, presses the "Upload" button. This action sends the taken photo and the user ID to the server.

[1173] Step 3:

[1174] Server: Stores the received food photos in a temporary storage area.

[1175] Step 4:

[1176] Server: Calls the AI ​​model for image analysis and provides the stored food photos as input.

[1177] Step 5:

[1178] AI model (on the server): Analyzes the image and identifies the ingredients, dish name, and quantity. The analysis results are generated as a data list.

[1179] Step 6:

[1180] Server: Saves the analysis result data list in a database for each user.

[1181] Step 7:

[1182] Server: Based on the analysis results, the nutritional components of each ingredient and dish are queried from the database and individual components are obtained.

[1183] Step 8:

[1184] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies any nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[1185] Step 9:

[1186] Server: Searches the database for suitable recipes to supplement missing nutrients. If necessary, it runs the recipe generation algorithm to create new recipes.

[1187] Step 10:

[1188] Server: Formats the suggested recipes into a format suitable for the user and sends them to the user's device.

[1189] Step 11:

[1190] On your device: The received recipes are displayed for the user to review. The user can then review the suggested recipes and save them as their next meal.

[1191] Step 12:

[1192] User: If necessary, after the meal, if there is any leftover food, take a photo of it again and upload it to the server via the device.

[1193] Step 13:

[1194] Server: The received post-meal photo is provided to an image analysis AI model to analyze any leftover food.

[1195] Step 14:

[1196] AI model (on server): Detects leftover food and returns nutritional data for recalculation.

[1197] Step 15:

[1198] Server: Recalculates the actual nutritional intake and updates the user's nutritional intake history.

[1199] Step 16:

[1200] Server: The server accumulates the user's food history and preferences as learning data and updates the model parameters for future suggestions. This data is stored in a database and used for future recipe suggestions.

[1201] Example 1

[1202] 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."

[1203] Conventional dietary management systems require users to manually input meal contents and calculate nutrients, which is time-consuming and often lacks accuracy. Furthermore, there is a need for improved management of leftover food after meals and more accurate recipe suggestions that take individual health information into account. A system that solves these problems and allows for easier and more accurate dietary management is desired.

[1204] 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.

[1205] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the photographed meal image to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dishes and identifying nutrient deficiencies based on the user's health information, a proposal means for proposing recipes to compensate for the identified nutrient deficiencies, a transmission means for sending the recipes generated by the proposal means to the user's terminal, a reanalysis means for photographing leftover food after a meal and reanalyzing the leftover food with the image analysis means to recalculate the actual nutritional components ingested, and a learning model reflection means for utilizing the results of the reanalysis means for future proposals. This significantly reduces the user's workload and enables highly accurate nutritional management and appropriate recipe proposals based on individual health information.

[1206] The "photography means" is a device or application with a camera function that allows the user to take photos of the contents of a meal.

[1207] "Image analysis means" refers to software or algorithms that analyze photographed food images to identify ingredients and the name of the dish.

[1208] The "nutrient calculation means" is a means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means, and for identifying any nutrients that are lacking based on the user's health information.

[1209] A "suggestion tool" is software or an algorithm that suggests recipes to supplement identified nutrient deficiencies.

[1210] The "transmission means" is a device or application having a communication function for transmitting the recipe generated by the proposal means to the user's terminal.

[1211] The "reanalysis means" is a means for taking a photo of the leftover food after a meal, analyzing the leftover food again using the image analysis means, and recalculating the nutritional components actually ingested.

[1212] The "learning model reflection means" refers to a machine learning model or algorithm that is used for future proposals based on the results of the reanalysis means.

[1213] The system of this invention allows users to take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is composed of an integrated platform including a user device, a server, and an AI model.

[1214] First, the user launches the application on their device and takes a photo of their meal using the camera function of their smartphone or tablet. The photo is displayed once within the application, allowing the user to confirm the content. After confirming the photo, the user presses the "Upload" button, which sends the photo file and the user's ID information to the server.

[1215] The server stores the received photos in a dedicated directory and passes them to an image analysis AI model. This AI model (for example, a model built using TensorFlow or PyTorch) analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in an internal database (for example, MySQL or PostgreSQL), and the nutritional content of each ingredient and dish is calculated.

[1216] Next, the server evaluates the nutritional balance of the entire meal based on the user's health information (age, gender, weight, blood pressure, daily activity level, etc.) and identifies any nutrient deficiencies. This evaluation can be performed using the Nutrient Analysis API.

[1217] The server then suggests recipes to supplement the identified nutrient deficiencies. It can query existing recipe databases to find recipes that match the user's criteria and select the recipe that best suits them. It can also generate new recipes as needed using a generative AI model. The recipe generation algorithm then takes into account the user's preferences and health status when creating a recipe.

[1218] The suggested recipes are individually customized and sent to the user's device. The recipe data is delivered via a push notification service, and the user can check the recipe on the application screen and save it as a cooking plan for the next time. They can also enter feedback or requests for changes.

[1219] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server via the app. The server then analyzes the image again and recalculates the actual nutrient intake. The recalculated data is stored in an internal database and will be reflected in future recommendations. This allows for more accurate recommendations based on the user's preferences and actual intake data.

[1220] As a concrete example, consider the case where a user has "grilled salmon" and "vegetable salad" for dinner. The user takes a photo of this and uploads it to the server via the app. The server uses image analysis to identify that it is "grilled salmon" and "vegetable salad" and calculates the nutritional content of each. If the server determines that the user's health data indicates a calcium deficiency, it will suggest a recipe for "komatsuna and tofu stir fry" and send it to the user's device. The user can check the recipe on their device and save it for their next cooking plan.

[1221] An example of a prompt is as follows:

[1222] text

[1223] A user uploads a photo of their dinner. Perform image analysis to identify the ingredients, dish name, and nutritional components of each, and generate a recipe that takes into account the user's health data and supplements any missing nutrients.

[1224] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1225] Step 1:

[1226] The user takes a photo of their meal

[1227] User: Takes a photo of a meal using the camera function of a smartphone or tablet. The input is the image of the meal captured through the camera, and the output is a preview image displayed on the application screen.

[1228] Step 2:

[1229] Upload the image to the server

[1230] Device: The user presses the "Upload" button. The input is the captured photo file and the user's ID information, and the output is the data sent to the server as an HTTP request. Specifically, the device generates an HTTP POST request to send the captured image file to the server.

[1231] Step 3:

[1232] Save and analyze the image

[1233] Server: Saves the received photos in a dedicated directory. Then, inputs the saved image file into an AI model for image analysis. The input is the saved image file, and the output is a list of ingredients and dish names analyzed by the AI ​​model. Specifically, the server saves the image file to disk and passes the path of that file to the API of the AI ​​model.

[1234] Step 4:

[1235] Calculate nutritional information

[1236] Server: Calculates the nutritional content of each ingredient and dish based on the results of image analysis. The input is the data on ingredients, dish names, and quantities obtained as a result of the analysis, and the output is detailed data on each nutritional content. Specifically, the server compares this data with its internal database and obtains nutritional information for each ingredient.

[1237] Step 5:

[1238] Evaluate nutritional balance based on user health information

[1239] Server: Refers to the user's health information, such as age, gender, weight, blood pressure, and daily activity level, to identify nutrient deficiencies. The input is the user's health information and nutritional composition data, and the output is a list of nutrient deficiencies. Specifically, the server uses the Nutrient Analysis API to evaluate nutritional balance.

[1240] Step 6:

[1241] Suggest suitable recipes

[1242] Server: Searches the database for recipes to supplement nutrient deficiencies or generates new recipes using a generative AI model. The input is a list of nutrient deficiencies, and the output is suggested recipes. Specifically, the server queries the recipe database and extracts recipes that match the criteria.

[1243] Step 7:

[1244] Sending recipes to the user's device

[1245] Device: Receives the suggested recipe and displays it on the application screen. The input is the recipe data sent from the server, and the output is the recipe displayed on the device's application screen. Specifically, the device receives a push notification and displays the contents in the application.

[1246] Step 8:

[1247] Take a photo of your leftovers after eating and upload it again

[1248] User: If there is any leftover food after the meal, the user takes another photo of the meal and uploads it to the server through the app. The input is the newly taken photo after the meal, and the output is the photo file uploaded to the server.

[1249] Step 9:

[1250] Reanalyze leftovers and recalculate nutritional information

[1251] Server: Analyzes the post-meal photo again, identifies any leftover food, and recalculates the actual nutritional intake. The input is the re-taken photo and the analysis results, and the output is the revised nutritional intake data. Specifically, the server performs image analysis again and saves the results in a database.

[1252] Step 10:

[1253] Reflecting in the learning model

[1254] Server: Based on the analysis results and actual intake data, the user's dietary history and preferences are reflected in the learning model. The input is the revised nutritional intake data, and the output is an updated learning model. Specifically, the server updates the model using a machine learning algorithm and uses it for future recommendations.

[1255] Through the above processing steps, the system provides users with highly accurate nutritional management and appropriate recipe suggestions.

[1256] (Application example 1)

[1257] 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."

[1258] Conventional dietary management systems have the ability to photograph meals and evaluate their nutritional balance, but they lack the ability to suggest specific actions based on the evaluation results or provide practical measures for nutritional supplementation. In particular, they lack an appropriate means for users to easily put the suggested recipes into practice. Furthermore, they lack a system for accurately grasping post-meal intake and reflecting this in future recommendations.

[1259] 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.

[1260] In this invention, the server includes a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the identified ingredients and dish and identifying any nutrient deficiencies based on the user's health information, a suggestion means for suggesting recipes to compensate for the identified nutrient deficiencies, and a delivery means for delivering appropriate dishes based on the suggested recipes. This allows the user to easily take concrete actions to replenish the identified nutrients, and enables the next suggestion to accurately reflect the nutrition actually ingested.

[1261] "Photographing means" refers to a device or apparatus that allows the user to photograph the contents of their meal.

[1262] The "image analysis means" is a system or program for analyzing a photographed image of a meal and identifying the ingredients and the name of the dish.

[1263] The "nutrient calculation means" is a system or program that calculates the nutritional components of the ingredients and dishes identified by the image analysis means and identifies any nutrients that are lacking based on the user's health information.

[1264] The "suggestion means" is a system or program that suggests to the user recipes for supplementing the nutrient deficiencies identified by the nutrient calculation means.

[1265] "Delivery Method" means a system or service that delivers appropriate dishes to users based on the suggested recipes.

[1266] "User health information" refers to data such as the user's age, gender, weight, blood pressure, and daily activity level.

[1267] A "recipe" is a document or information that shows how to prepare or mix a dish to supplement missing nutrients.

[1268] The "after-meal photo" is an image of leftover food after a meal.

[1269] A "server" is a computer system for receiving and analyzing data sent by users.

[1270] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. The system is comprised of an integrated platform that includes the user's device, a server, and an AI model.

[1271] First, the user launches the application on their device and takes a photo of their meal. The photo is displayed once within the application, and the user confirms the content. After that, the user presses the "Upload" button. This action sends the photo and the user's ID information to the server.

[1272] The server passes the received photos to an AI model for image analysis. The AI ​​model uses deep learning frameworks such as TensorFlow and Keras. This analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated. Based on this, the nutritional balance of the entire meal is evaluated.

[1273] The server then identifies nutrient deficiencies, taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data. Based on this information, the server selects recipes from its database to address these nutrient deficiencies, and creates new recipes if necessary using a recipe generation algorithm. The proposed recipes are customized for each user and sent to the user's device.

[1274] Users can review the received recipe on their device and save it as their next meal. They can also order meals based on the suggested recipe through a delivery method that will provide the appropriate dish. If there are any leftovers after the meal, the user can take another photo of the meal and upload it to the server. The actual nutrient intake is then recalculated based on the photo. This allows the user's dietary history and preferences to be reflected in the learning model. This data will be used for future suggestions.

[1275] As a concrete example, let's say a user is having "grilled salmon" and "vegetable salad" for dinner. They take a photo of this and upload it to the server via the app. The server then analyzes the image and identifies the dishes as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish (protein, vitamins, minerals, etc.) and evaluates the nutritional balance of the entire meal. For example, if the server determines that the user is lacking in calcium, it will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can then check this recipe, save it as part of their next cooking plan, or order it through a food delivery service.

[1276] An example of a prompt is:

[1277] "Just take a photo of the dinner you recently had and upload it to the app (NutriMeal). The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[1278] Examples include:

[1279] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1280] Step 1: Shoot and review

[1281] The user launches the application on their device and takes a photo of their meal. The photo is then displayed in the application, allowing the user to review the content.

[1282] Input: A meal photo taken by the user

[1283] Output: Confirmation photo displayed on the device

[1284] How it works: A user takes a photo of a meal and reviews it.

[1285] Step 2: Upload a photo

[1286] The user presses the "upload" button, and the captured photo and the user's ID information are sent to the server.

[1287] Input: Meal photos taken by the user, user ID information

[1288] Output: Photo and ID information uploaded to the server

[1289] Operation: The device sends the input photo and ID information to the server.

[1290] Step 3: Image analysis

[1291] The server passes the received photos to an AI model for image analysis, which identifies the ingredients, dish name, and quantity.

[1292] Input: Photo uploaded to the server

[1293] Output: Identified ingredients, dish name, and quantity

[1294] How it works: The AI ​​model analyzes the image and identifies ingredients and dishes.

[1295] Step 4: Nutritional assessment

[1296] The server calculates the nutritional content of the identified ingredients and dishes and identifies any nutrient deficiencies based on the user's health information.

[1297] Input: Identified ingredients and dish names, user health information

[1298] Output: Identification of nutrient deficiencies

[1299] Operation: The nutrient calculation tool calculates nutritional components and assesses nutritional deficiencies based on health information.

[1300] Step 5: Recipe suggestions

[1301] The server selects recipes from a database to supplement the identified nutrient deficiencies and generates new recipes as needed. The suggested recipes are customized for each user and sent to the device.

[1302] Input: Identification results of missing nutrients, recipe information from the database

[1303] Output: The customized recipe sent to the user's device

[1304] How it works: The server selects the appropriate recipe and sends the customized results to the device.

[1305] Step 6: View and save the recipe

[1306] Users can view the received recipes on their device, save them as their next meal, and order meals based on the suggested recipes through food delivery services.

[1307] Input: Recipe sent to terminal

[1308] Output: User-saved next cooking plan and ordering information

[1309] What it does: Displays a recipe on the device, allowing the user to review, save, and order.

[1310] Step 7: Post-meal review and feedback

[1311] After a meal, users take a photo of the leftover food and upload it to the server, which then analyzes the image again and recalculates the actual nutritional intake.

[1312] Input: A photo of leftover food taken after a meal

[1313] Output: Recalculated nutrient data

[1314] How it works: The server analyzes the post-meal photo and re-evaluates the actual intake.

[1315] Examples:

[1316] If a user eats "grilled salmon" and "vegetable salad" for dinner, they take a photo of it and upload it to the server via the app. The server then analyzes the image and identifies it as "grilled salmon" and "vegetable salad." The server then calculates the nutritional components of each dish and evaluates their nutritional balance. For example, if it determines that the user is lacking in calcium, the server will suggest a recipe for "komatsuna and tofu stir-fry" to supplement the calcium and send it to the user's device. The user can check this recipe, save it in their next cooking plan, or order it through a food delivery service. If there is any leftover food after the meal, they can take another photo of it and upload it to the server, which will reflect their actual intake.

[1317] Prompt statement:

[1318] "Just take a photo of the dinner you recently had and upload it to the app. The AI ​​will analyze the photo and suggest recipes that will help you fill in any missing nutrients based on your health status. You can then order that recipe via food delivery."

[1319] 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.

[1320] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to suggest more effective recipes. The system is comprised of an integrated platform that includes the user's device, a server, an AI model, and the emotion engine.

[1321] User Interface

[1322] User: First, the user launches the app on their device and takes a photo of their meal. The photo is then viewed once within the app, where the user can review it.

[1323] Uploading an image

[1324] On the device: After the meal photo is confirmed, the user presses the "Upload" button, which sends the captured photo and the user's ID information to the server.

[1325] Image analysis and nutrition calculations

[1326] Server: The received photo is passed to an AI model for image analysis, which analyzes the image and identifies the ingredients, dish name, and quantity.

[1327] Server: The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated, allowing the nutritional balance of the entire meal to be evaluated.

[1328] Server: Identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[1329] Emotion Recognition and Recipe Suggestion

[1330] Server: At the same time, the emotion engine recognizes emotions based on the facial image acquired from the user's camera and the user's input data.

[1331] Server: The emotional data recognized by the emotion engine is incorporated into recipe suggestions to supplement the identified nutrient deficiencies.

[1332] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a recipe generation algorithm.

[1333] Server: Suggested recipes are customized according to the user's emotional state and sent to the user's device.

[1334] Displaying suggested recipes

[1335] On the device: The user can review the received recipe on the device, save it as a recipe to make next, and enter feedback or requests for changes to the recipe.

[1336] Post-meal check-up and feedback

[1337] User: If there is any food left over after a meal, the user takes another photo of the meal and uploads it to the server. The actual nutrient intake is then recalculated based on that photo.

[1338] Server: Based on the analysis results and actual intake data, the user's eating history and emotional data are reflected in the learning model. This data is used for future recommendations.

[1339] Specific examples

[1340] For example, if a user has a dinner of grilled salmon and vegetable salad, they can take a photo of this meal and upload it to the server via the app.

[1341] Server: Identifies "grilled salmon" and "vegetable salad" through image analysis and calculates the nutritional components (protein, vitamins, minerals, etc.) of each. Based on these results, evaluates the nutritional balance of the entire meal and identifies any nutrients that are lacking (such as calcium).

[1342] Server: At the same time, the emotion engine recognizes the user's emotional state (e.g., whether they are feeling stressed) from their facial expressions.

[1343] Server: Suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to relieve stress and sends it to the user's device.

[1344] On the device: Users can view recipes and save them for future cooking plans.

[1345] User: If desired, if there is any leftover food after a meal, take and upload a photo of it again, which will reflect the actual amount consumed.

[1346] In this way, by using this system, users can receive more appropriate meal suggestions based on their own nutritional balance and emotional state.

[1347] The processing flow will be explained below.

[1348] Step 1:

[1349] User: Takes a photo of their meal using their device's camera. After taking the photo, the photo is displayed in the app and the user can review the photo.

[1350] Step 2:

[1351] On the device: The user checks the photo and presses the "Upload" button. This action sends the captured photo and user ID information to the server.

[1352] Step 3:

[1353] Server: Temporarily stores the received food photos and prepares them for passing to the image analysis AI model.

[1354] Step 4:

[1355] Server: Calls the image analysis AI model and inputs the saved food photos to analyze them.

[1356] Step 5:

[1357] AI model (on the server): Analyzes food photos and identifies ingredients, dish names, and quantities. The analysis results are generated as a data list.

[1358] Step 6:

[1359] Server: Saves the analysis result data list in a database for each user. Next, proceeds to calculate nutritional components.

[1360] Step 7:

[1361] Server: Based on the analysis results, the server queries the database for the nutritional information of each ingredient and dish and obtains the information.

[1362] Step 8:

[1363] Server: Calculates the nutritional balance of the entire meal using the acquired nutritional information. It identifies nutrient deficiencies by taking into account the user's age, gender, weight, blood pressure, daily activity level, and health data.

[1364] Step 9:

[1365] User: During this time, the device camera takes a picture of the user's face and recognizes their current emotional state.

[1366] Step 10:

[1367] Device: Sends the user's facial image to the server.

[1368] Step 11:

[1369] Server: Inputs the received facial image into the emotion engine to recognize the user's emotional state.

[1370] Step 12:

[1371] Emotion engine (on the server): Analyzes facial images to identify the user's emotional state (e.g., joy, stress, fatigue, etc.).

[1372] Step 13:

[1373] Server: Based on the emotional data identified by the emotion engine, the suggested recipes are adjusted according to the user's emotional state.

[1374] Step 14:

[1375] Server: Searches the database for suitable recipes based on missing nutrients and emotion data, and runs the recipe generation algorithm to create new recipes as needed.

[1376] Step 15:

[1377] Server: The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[1378] Step 16:

[1379] On the device: The received recipe is displayed to the user, who can then review the recipe and save it for their next cooking appointment.

[1380] Step 17:

[1381] User: If there is any food left over after the meal, take another photo after the meal and upload it to the server via the device.

[1382] Step 18:

[1383] Device: Send a photo of the leftovers and the user ID to the server.

[1384] Step 19:

[1385] Server: Provides newly received images to an image analysis AI model to analyze leftover food.

[1386] Step 20:

[1387] AI model (in the server): Detects leftover food and returns the analysis results to the server.

[1388] Step 21:

[1389] Server: Recalculates the actual nutritional intake and records the new nutritional balance data in the user's diet history.

[1390] Step 22:

[1391] Server: The user's eating history and emotional data are reflected in the learning model. This data is used to suggest recipes for future meals.

[1392] In this way, users can receive appropriate meal suggestions based on their nutritional balance and emotional state, enabling more precise and personalized dietary management.

[1393] Example 2

[1394] 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."

[1395] In modern society, it is extremely important to properly manage individual dietary content and personal health. However, many existing systems only analyze the nutritional balance of meals and are unable to provide personalized suggestions that take the user's emotional state into account. As a result, it is difficult for the suggested healthy recipes to increase the user's psychological satisfaction, making it difficult to maintain long-term health.

[1396] 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.

[1397] In this invention, the server includes a photographing means for photographing meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and dish names, a nutrient calculation means for calculating the nutritional components of the ingredients and dish identified by the image analysis means and identifying nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the emotional state of the user, and a suggestion means for suggesting recipes based on the emotional state and nutrient deficiencies identified by the emotion recognition means. This makes it possible to suggest individually optimized recipes that comprehensively consider the user's nutritional and emotional states.

[1398] "Photographing means" refers to the device and its functions used to photograph the contents of a meal.

[1399] "Image analysis means" refers to technology or equipment for analyzing photographed food images to identify ingredients and the name of the dish.

[1400] "Nutrient calculation means" refers to technology or equipment for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrients that are lacking based on the user's health information.

[1401] "Emotion recognition means" refers to techniques or devices for recognizing a user's emotional state, including analyzing facial expressions and evaluating user-input data.

[1402] "Recommendation means" refers to a technology or device for suggesting recipes based on identified nutrient deficiencies and emotional state.

[1403] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes that supplement missing nutrients. It also combines an emotion engine that recognizes the user's emotions to provide an integrated platform for more effective recipe suggestions. This system includes a user device, a server, a generative AI model, and an emotion recognition engine.

[1404] Hardware and software used

[1405] Device: The user uses a smartphone or tablet, which includes a camera and internet connectivity.

[1406] Server: The center of data processing, performing various calculations and storing data. The server is installed with an AI model (e.g., TensorFlow), an emotion recognition engine (e.g., Affectiva), and a database (e.g., MongoDB).

[1407] Generative AI models: used to generate recipes. An example is GPT-4.

[1408] System Operation

[1409] The user launches the application on their device and takes a photo of their meal. The photo is then viewed within the app, and when the user presses the "upload" button, the photo and the user's ID information are sent to the server.

[1410] The server passes the received photo to an AI model for image analysis (e.g., TensorFlow). The AI ​​model analyzes the image and identifies the ingredients, dish names, and quantities. The analysis results are stored in a database, and the nutritional content of each ingredient and dish is calculated.

[1411] Next, nutrient deficiencies are identified, taking into account the user's age, gender, weight, blood pressure, daily activity, and health data. At the same time, an emotion engine (e.g., Affectiva) recognizes emotions based on facial images captured from the user's camera. Emotional data is combined with the identified nutrient deficiencies to find suitable recipes, or create new recipes using a generative AI model (e.g., GPT-4) if necessary.

[1412] The suggested recipes are customized based on the user's emotional state, encoded, and sent to the user's device. The user can then review the recipes on their device, save them as their next meal, and provide feedback or suggestions for changes to the recipes.

[1413] If the user has leftover food after a meal, they can take a photo of it again and upload it to the server. Based on that photo, the actual nutrient intake is recalculated, and the results are reflected in future recipe suggestions.

[1414] Specific examples

[1415] For example, if a user has "grilled salmon" and "vegetable salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server will use image analysis to identify the dishes as "grilled salmon" and "vegetable salad" and calculate the nutritional content (protein, vitamins, minerals, etc.) of each. It will then evaluate the nutritional balance of the entire meal and identify any nutrients (such as calcium) that are lacking.

[1416] Next, the emotion engine recognizes the user's emotional state (e.g., stress) from their facial expressions, and suggests a recipe for "Komatsuna and Tofu Stir-fry" that contains food ingredients (e.g., magnesium) to alleviate stress, and sends it to the user's device.

[1417] Users can review recipes, save them for their next cooking plan, and, if desired, take and upload a photo of any leftovers after a meal to reflect their actual intake.

[1418] By using this system, users can receive more appropriate meal suggestions based on their nutritional balance and emotional state.

[1419] Prompt Sentence Examples

[1420] Prompt: If the user had "grilled salmon" and "vegetable salad" for dinner but is feeling stressed, suggest a new recipe that contains magnesium.

[1421] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1422] Step 1:

[1423] User: The user launches the application on their smartphone or tablet. They launch the dedicated app, select camera mode, and take a photo of their current meal. The input is the meal photo, and the output is the confirmed photo data.

[1424] Step 2:

[1425] Device: When the user presses the "Upload" button, the photo of the meal taken and the user's ID information are sent from the device to the server. Here, the data travels via an Internet connection. The input is the photo data and the user ID, and the output is the data reception status on the server.

[1426] Step 3:

[1427] Server: The server inputs the received photo data into an AI model (TensorFlow) for image analysis. The AI ​​model analyzes the image and identifies the ingredients, dish name, and quantity. The input is the photo data, and the output is the identified ingredients, dish name, and quantity.

[1428] Specifically, the image analysis model scans the photo, compares it with an existing database to identify ingredients and the name of the dish, and then verifies whether the analysis is correct before proceeding to the next step.

[1429] Step 4:

[1430] Server: Stores the analysis results in a database and calculates the nutritional content of each ingredient and dish. A publicly available food nutrition database is used for the nutrition calculation. The input is the identified ingredient information, and the output is the calculated nutritional content data.

[1431] Specifically, the server uses a nutrition calculation algorithm to calculate the nutritional content (protein, vitamins, minerals, etc.) of each identified ingredient.

[1432] Step 5:

[1433] Server: Identifies nutrient deficiencies based on the user's age, gender, weight, blood pressure, daily activity level, and health data stored in a database. The input is the calculated nutritional composition data and the user's personal data, and the output is a list of nutrient deficiencies.

[1434] Specifically, it compares and analyzes individual health data with calculated nutritional components to identify nutrients that are lacking (e.g., calcium, magnesium, etc.).

[1435] Step 6:

[1436] Server: The emotion engine (Affectiva) recognizes emotions based on facial images acquired from the user's camera and emotion data entered by the user. The input is facial images and emotion input data, and the output is the recognized emotion data.

[1437] Specifically, the server passes facial images and text data to the emotion recognition engine, which then performs emotion analysis. The emotion engine then returns the recognized emotion to the server.

[1438] Step 7:

[1439] Server: Searches the database for suitable recipes based on emotion data and nutrient deficiencies. If necessary, creates new recipes using a generative AI model (GPT-4). The input is nutrient deficiency data and emotion data, and the output is a suggested recipe.

[1440] Specifically, the server uses a database or generative AI model to search for or generate an appropriate recipe and output it as recipe data.

[1441] Step 8:

[1442] Device: The suggested recipes are customized according to the user's emotional state, encoded, and sent to the device. The input is the recipe data, and the output is the recipe information displayed on the user's device.

[1443] Specifically, the server encodes a recipe tailored to the user's emotional state and sends it to the device, which then decodes it and displays it to the user.

[1444] Step 9:

[1445] User: The user can review the received recipe and save it as the next dish to make. They can also enter feedback or requests for changes to the recipe. The input is the recipe data, and the output is the user's feedback data.

[1446] Specifically, users can view and check recipe information on their device, add it to their next cooking plan, and use the feedback function to enter comments about the suggested recipes.

[1447] Step 10:

[1448] User: If there is any food left after the meal, the user takes a photo of it again and uploads it to the server from their device. The input is the photo after the meal, and the output is the state of data reception to the server.

[1449] Step 11:

[1450] Server: Re-analyzes the re-received photos and re-calculates the actual nutritional intake. The input is the post-meal photo data, and the output is the recalculated nutritional information. This information is reflected in future recipe suggestions.

[1451] Specifically, the server performs image analysis again, recalculates the intake amount, and stores it in the database. This recalculated data is used to suggest the next recipe.

[1452] (Application example 2)

[1453] 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."

[1454] Conventional dietary management applications were able to analyze a user's dietary content and evaluate the nutrients in their meals, but they were unable to suggest recipes that took the user's emotional state into account. This made it difficult to increase user satisfaction and suggest meals that matched their mental state. Furthermore, the functionality to reassess the actual nutrients ingested based on leftover food after a meal was also insufficient. Therefore, there was a need for a system that could offer comprehensive dietary suggestions to users that took into account not only nutritional balance but also emotions.

[1455] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a photographing means for photographing the meal contents, an image analysis means for analyzing the meal image photographed by the photographing means to identify ingredients and the name of the dish, a nutrient calculation means for calculating the nutritional components of the ingredients and the dish identified by the image analysis means and identifying any nutrient deficiencies based on the user's health information, an emotion recognition means for recognizing the user's emotional information, and a suggestion means for suggesting recipes based on the identified nutrient deficiencies and emotional information. This enables more effective meal suggestions that take into account the user's emotional state as well as their nutritional balance.

[1456] "Meal content" refers to the types and amounts of ingredients and dishes consumed by the user.

[1457] "Photography method" refers to the device or method used by a user to photograph their meal.

[1458] "Image analysis means" refers to technology or equipment for analyzing food images acquired by the photographing means and identifying ingredients and the name of the dish.

[1459] "Nutrient calculation means" refers to a system or method for calculating the nutritional components of ingredients and dishes identified by the image analysis means and identifying any nutrient deficiencies based on the results.

[1460] "Nutritional components" refers to the components such as proteins, lipids, carbohydrates, vitamins, and minerals contained in ingredients and dishes.

[1461] "Suggestion methods" refer to techniques and methods for suggesting recipes to supplement identified nutrient deficiencies.

[1462] "Emotion recognition means" refers to technology or devices that determine a user's emotional state at that time from their facial expressions and input data.

[1463] "Emotional information" refers to data that indicates a user's emotional state.

[1464] "Recipes" refer to cooking methods or dishes suggested based on specific nutrients or emotional states.

[1465] This system allows users to easily take photos of their meals, analyzes the images, and suggests recipes to supplement missing nutrients. Furthermore, it combines an emotion engine that recognizes the user's emotional state to suggest more effective recipes.

[1466] User Interface

[1467] The user launches the application on their device and takes a photo of their meal. This application is for smartphones and includes a means for taking photos of the meal using the camera function. The photos are then viewed within the app, and after the user has confirmed the content, they press the "upload" button to send it to the server.

[1468] Image analysis and nutrition calculations

[1469] The server passes the received photos to an AI model for image analysis. This AI model uses TensorFlow and OpenCV to analyze the images and identify the ingredients and dish names. The analysis results are stored in a database, and a nutrient calculation tool is used to calculate the nutritional content of the ingredients and dishes, evaluating the nutritional balance of the entire meal. The user's age, gender, weight, blood pressure, daily activity level, and health data are identified to determine any nutrient deficiencies.

[1470] Emotion Recognition and Recipe Suggestion

[1471] The server uses an emotion recognition API to analyze the user's emotional state based on facial images captured from the user's camera and user input data. Based on the emotional information and nutrient deficiencies, the suggestion method searches for suitable recipes from the database and creates new recipes using a generative AI model if necessary. The suggested recipes are customized according to the user's emotional state and sent to the user's device.

[1472] View and give feedback on suggested recipes

[1473] Users can review the received recipes on their device, save them for their next cooking plan, and even provide feedback or suggestions for changes to the recipes.

[1474] Post-meal check-up and feedback

[1475] If there are any leftovers after a meal, the user takes another photo of the meal and uploads it to the server. The server then uses image analysis to analyze the leftovers and recalculate the actual nutrient intake. Based on this result and the actual intake data, the user's eating history and emotional data are reflected in the learning model. This will be used to make suggestions for future meals.

[1476] Specific examples

[1477] For example, if a user has "pizza" and "salad" for dinner, they can take a photo of the meal and upload it to the server via the app. The server uses image analysis to identify the pizza and salad and calculate the nutritional components of each. As a result, the overall nutritional balance is evaluated and any nutrients that are lacking (e.g., vitamin D) are identified. At the same time, an emotion recognition engine recognizes the user's emotional state (e.g., stress). A recipe for "sauteed spinach and chicken," which contains food ingredients (e.g., magnesium) to alleviate stress, is suggested and sent to the user's device.

[1478] Prompt Sentence Examples

[1479] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[1480] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1481] Step 1:

[1482] The user launches the smartphone application and takes a photo of the meal. This application provides a means to capture the meal contents through the smartphone's camera function. When the user presses the "upload" button, the taken photo and user ID are sent to the server. The input data are the meal image and user ID, and these data are sent as output to proceed to the next step.

[1483] Step 2:

[1484] The server passes the received photo data to an AI model for image analysis. The AI ​​model uses TensorFlow and OpenCV to analyze the image and identify ingredients and dish names. The input is food image data, and the output is a list of identified ingredients and dish names. Specifically, the AI ​​model preprocesses the food images, extracts features, and classifies the ingredients and dishes using a pre-trained model.

[1485] Step 3:

[1486] The server uses a nutrient calculation means to calculate nutritional components based on the analyzed ingredients and dish names. The input is a list of identified ingredients and dish names and the user's health information (age, gender, weight, blood pressure, activity level, etc.). The output is a list of nutrients that are lacking. Specifically, the server obtains nutritional information for each ingredient from the database and totals it to evaluate the overall nutritional balance and identify any nutrients that are lacking.

[1487] Step 4:

[1488] The server activates the emotion recognition means using facial images and input data acquired from the user's camera. The input is the facial image and input data, and the output is the recognized emotional information of the user. Specifically, the emotion recognition API is used to analyze the emotional state (stress, joy, fatigue, etc.) from the facial image.

[1489] Step 5:

[1490] The server uses a suggestion mechanism to suggest recipes based on the identified nutrient deficiencies and emotional information. The input is a list of nutrient deficiencies and emotional information, and the output is a list of suitable recipes. Specifically, it searches for relevant recipes in the database and creates new recipes using a generative AI model if necessary. Here, the generative AI model uses the following prompt sentence:

[1491] Analyze the images of meal photos uploaded by users to identify each ingredient and its quantity. Then, evaluate the nutritional value of each ingredient and identify any nutrient deficiencies. At the same time, use an emotion recognition engine to identify the user's emotional state from the camera image. Based on the nutrient deficiencies and the user's emotional state, suggest recipes.

[1492] Step 6:

[1493] The server sends the suggested recipes to the user's device. The input is a list of suitable recipes, and the output is the data describing the recipes. The user's device displays the received recipes, and the user can save them for their next cooking plan. They can also enter feedback or requests for changes to the recipes.

[1494] Step 7:

[1495] If the user has leftover food after a meal, they can take another photo of the meal and upload it to the server. The server then uses image analysis to analyze the leftover food and recalculate the actual nutritional intake. The input is the post-meal photo, and the output is a recalculated list of nutrients. This allows the user's eating history and emotional data to be reflected in the learning model and used to make suggestions for future meals.

[1496] 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.

[1497] 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.

[1498] 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 robot 414.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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).

[1503] 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.

[1504] 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."

[1505] 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.

[1506] 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).

[1507] 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.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] The following is further disclosed regarding the above embodiment.

[1518] (Claim 1)

[1519] A photographing means for photographing the meal contents;

[1520] an image analysis means for analyzing the food image captured by the photographing means and identifying ingredients and the name of the dish;

[1521] a nutrient calculation means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means and for identifying any nutrients that are lacking based on the user's health information;

[1522] a suggestion means for suggesting a recipe for supplementing the identified nutrient deficiency;

[1523] A system including:

[1524] (Claim 2)

[1525] The system of claim 1 , further comprising suggestion means for suggesting suitable recipes taking into consideration the user's age, sex, weight, blood pressure, daily activity level, and health data.

[1526] (Claim 3)

[1527] 10. The system of claim 1, further comprising means for taking a photograph of the leftover food after a meal and analyzing the leftover food portion with said image analysis means to recalculate the actual nutritional intake.

[1528] "Example 1"

[1529] (Claim 1)

[1530] A photographing means for photographing the meal contents;

[1531] an image analysis means for analyzing the food image captured by the photographing means and identifying ingredients and the name of the dish;

[1532] a nutrient calculation means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means and for identifying any nutrients that are lacking based on the user's health information;

[1533] a suggestion means for suggesting a recipe for supplementing the identified nutrient deficiency;

[1534] a transmitting means for transmitting the recipe generated by the suggesting means to a user's terminal;

[1535] a reanalysis means for taking a photograph of the leftover food after eating and re-analyzing the leftover food using the image analysis means to recalculate the nutritional components actually ingested;

[1536] A learning model reflection means for utilizing the results of the reanalysis means in subsequent proposals

[1537] A system including:

[1538] (Claim 2)

[1539] 10. The system of claim 1, further comprising means for suggesting suitable recipes taking into consideration the user's age, sex, weight, blood pressure, daily activity level, and health data.

[1540] (Claim 3)

[1541] 10. The system of claim 1, further comprising uploading means for uploading the meal images and leftover images to the server.

[1542] "Application Example 1"

[1543] (Claim 1)

[1544] A photographing means for photographing the meal contents;

[1545] an image analysis means for analyzing the food image captured by the photographing means and identifying ingredients and the name of the dish;

[1546] a nutrient calculation means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means and for identifying any nutrients that are lacking based on the user's health information;

[1547] a suggestion means for suggesting a recipe for supplementing the identified nutrient deficiency;

[1548] a delivery means for delivering a suitable dish based on the suggested recipe;

[1549] A system including:

[1550] (Claim 2)

[1551] The system of claim 1 , further comprising suggestion means for suggesting suitable recipes taking into consideration the user's age, sex, weight, blood pressure, daily activity level, and health data.

[1552] (Claim 3)

[1553] 10. The system of claim 1, further comprising means for taking a photograph of the leftover food after a meal and analyzing the leftover food portion with said image analysis means to recalculate the actual nutritional intake.

[1554] "Example 2: Combining Emotion Engines"

[1555] (Claim 1)

[1556] A photographing means for photographing the meal contents;

[1557] an image analysis means for analyzing the food image captured by the photographing means and identifying ingredients and the name of the dish;

[1558] a nutrient calculation means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means and for identifying any nutrients that are lacking based on the user's health information;

[1559] emotion recognition means for recognizing an emotional state of the user;

[1560] a suggestion means for suggesting a recipe based on the emotional state and nutrient deficiencies identified by the emotion recognition means;

[1561] A system including:

[1562] (Claim 2)

[1563] The system of claim 1 , further comprising suggestion means for suggesting suitable recipes taking into consideration the user's age, sex, weight, blood pressure, daily activity level, and health data.

[1564] (Claim 3)

[1565] 10. The system of claim 1, further comprising means for taking a photograph of the leftover food after a meal and analyzing the leftover food portion with said image analysis means to recalculate the actual nutritional intake.

[1566] "Application example 2 when combining emotion engines"

[1567] (Claim 1)

[1568] A photographing means for photographing the meal contents;

[1569] an image analysis means for analyzing the food image captured by the photographing means and identifying ingredients and the name of the dish;

[1570] a nutrient calculation means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means and for identifying any nutrients that are lacking based on the user's health information;

[1571] emotion recognition means for recognizing emotion information of a user;

[1572] a suggestion means for suggesting a recipe based on the identified nutrient deficiency and emotional information;

[1573] A system including:

[1574] (Claim 2)

[1575] The system of claim 1 , further comprising suggestion means for suggesting suitable recipes taking into consideration the user's age, sex, weight, blood pressure, daily activity level, and health data.

[1576] (Claim 3)

[1577] 10. The system of claim 1, further comprising means for taking a photograph of the leftover food after a meal and analyzing the leftover food portion with said image analysis means to recalculate the actual nutritional intake. [Explanation of symbols]

[1578] 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 photographing means for photographing the meal contents; an image analysis means for analyzing the food image captured by the photographing means and identifying ingredients and the name of the dish; a nutrient calculation means for calculating the nutritional components of the ingredients and dishes identified by the image analysis means and for identifying any nutrients that are lacking based on the user's health information; a suggestion means for suggesting a recipe for supplementing the identified nutrient deficiency; A system including:

2. The system according to claim 1 , further comprising suggestion means for suggesting suitable recipes taking into consideration the user's age, sex, weight, blood pressure, daily activity level, and health data.

3. 2. The system of claim 1, further comprising means for taking a photograph of the leftover food after a meal and analyzing the leftover food portion with said image analysis means to recalculate the nutritional components actually ingested.

Images