System

Abstract

A system is provided.SOLUTION: A system comprising: means for causing a user to input meal information and storing the meal information in a database; means for analyzing the meal information stored in the database and calculating a generation amount of advanced glycation end products (AGEs); means for performing risk evaluation for each user based on the calculated AGE generation amount; and means for generating nutrition advice according to a health condition and a lifestyle of the user and providing the advice to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, there is a lack of appropriate nutritional advice regarding food cooking methods and combinations, and no guidelines are provided for aging care that suits individual lifestyles. Furthermore, there is no system in place to individually assess the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking and provide users with appropriate countermeasures. This poses a challenge: users are not receiving sufficient support for healthy aging. [Means for solving the problem]

[0005] The system according to the present invention comprises means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, and means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user.

[0006] This allows users to specifically understand the impact of their diet and cooking methods on their health, and to practice appropriate eating habits and nutritional balance. This system effectively supports users in achieving healthy aging.

[0007] A "user" is an individual who utilizes the system to input dietary information and receive risk assessments and nutritional advice.

[0008] "Dietary information" is data relating to the contents of a meal, specifically including the names of ingredients, cooking methods, portions, and intake times.

[0009] A "database" is an information system for storing and managing dietary information and health data input by users.

[0010] Advanced glycation end products (AGEs) are substances produced by the non-enzymatic binding of sugars with proteins or lipids. Their production is accelerated by high-temperature cooking, and they are the cause of aging and various diseases.

[0011] "Risk assessment" is a process of assessing the risk to the user's health based on the analyzed amount of AGE produced, and is performed on a three-level scale: high, medium, or low.

[0012] A "risk alert" is a warning message that notifies the user of the results of a risk assessment and calls for necessary countermeasures.

[0013] "Nutrition advice" refers to suggestions on optimal diet and nutritional balance provided by the AI ​​based on the user's health and lifestyle. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. It also provides optimal nutritional advice based on the user's health status and lifestyle, supporting the user in achieving healthy aging.

[0036] Program processing

[0037] The system of the present invention is implemented through a series of processes involving three parties: a server, a terminal, and a user.

[0038] Collection of dietary data

[0039] User: Using a dedicated app, the user enters information about their daily meals, including the names of ingredients, cooking methods, portions, and intake times.

[0040] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[0041] Server: Stores the received meal information in a database.

[0042] Data analysis

[0043] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[0044] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[0045] Providing risk alerts

[0046] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes a detailed risk description and a warning message.

[0047] Server: Sends the generated risk alerts to the user's device.

[0048] On the device: Display a risk alert in the user's app to notify the user.

[0049] Generate nutrition advice

[0050] Server: Based on the user's past health data and dietary information, the AI ​​checks their health condition and generates and proposes an appropriate nutritional balance and dietary plan.

[0051] Server: Provides specific advice such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients.

[0052] Nagetsu: Provides nutrition advice within the user's app, with specific recipes and actionable methods.

[0053] Providing wellness support

[0054] Device: The user puts the nutrition advice provided into practice and enters their results and progress into the app.

[0055] Server: Based on the feedback data, the database is updated to reflect the user's latest health status.

[0056] Server: Provides continuous advice based on updated data to support users in managing their health.

[0057] Specific examples

[0058] Example 1: Case of middle-aged male user A

[0059] 1. Collection of dietary data

[0060] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[0061] 2. Data Analysis

[0062] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[0063] 3. Providing risk alerts

[0064] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[0065] Device: An alert is displayed in the app and notifies User A.

[0066] 4. Generating nutrition advice

[0067] Server: The generative AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[0068] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[0069] 5. Providing wellness support

[0070] Device: User A practices the suggested recipe and enters the results into the app.

[0071] Server: Updates user A's health data based on feedback data and provides ongoing support.

[0072] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[0073] The processing flow will be explained below.

[0074] Step 1: Collect dietary data

[0075] User: Opens the dedicated app and enters meal information, including the names of ingredients, cooking methods, portions, and intake times.

[0076] Terminal: Processes the meal information entered by the user and converts it into a standard data format.

[0077] Terminal: Sends the converted meal information to the server.

[0078] Step 2: Save your data

[0079] Server: Receives the received meal information and stores it in a database.

[0080] Server: Adds metadata such as user ID, meal date and time, ingredient list, and cooking method to the saved meal information.

[0081] Step 3: Analyze the data

[0082] Server: Extracts the target user's meal information from the database and selects the necessary data using queries.

[0083] Server: Based on the meal information extracted by the generation AI, calculates the amount of AGE generated for each ingredient and cooking method. The calculation is performed according to the AGE generation amount calculation method.

[0084] Server: Based on the calculation results, calculate the user's total AGE intake.

[0085] Step 4: Risk assessment

[0086] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[0087] Server: Stores the results of the risk assessment in a database.

[0088] Step 5: Generate and send a risk alert

[0089] Server: If a high risk is determined, a risk alert is generated. The alert includes specific details of the risk and countermeasures.

[0090] Server: Sends the generated risk alerts to the user's device.

[0091] Device: The received risk alert is displayed in the app and notified to the user.

[0092] Step 6: Generate nutrition advice

[0093] Server: Checks the user's health status based on the user's past health data and dietary information.

[0094] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[0095] Server: Sends the generated nutrition advice to the user's device.

[0096] Step 7: Provide and implement nutrition advice

[0097] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[0098] User: Prepares and follows the advice.

[0099] Step 8: Gather feedback and update data

[0100] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[0101] Terminal: Sends the input feedback data to the server.

[0102] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[0103] Step 9: Ongoing Wellness Support

[0104] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[0105] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[0106] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[0107] In this way, the system provides personalized AGE risk management and nutrition advice to each user, effectively supporting them in achieving healthy aging.

[0108] Example 1

[0109] 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."

[0110] In today's busy lifestyles, it is difficult for users to fully understand the impact of their diet and cooking methods on their health and take appropriate measures. Furthermore, there are few systems that provide individualized healthy nutrition advice, particularly for managing the risk of advanced glycation end products (AGEs) accumulation caused by high-temperature cooking. Furthermore, there is a lack of methods for users to implement the advice they receive and receive ongoing feedback on the results to enable ongoing health management.

[0111] 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.

[0112] In this invention, the server includes means for having users input dietary information and storing the dietary information in a database, means for periodically retrieving the dietary information stored in the database by batch processing and calculating the amount of advanced glycation end products (AGEs) produced for each ingredient and cooking method, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, generating a risk alert for the user based on the results of the risk assessment, and transmitting the alert, means for generating nutritional advice tailored to the user's health condition and lifestyle based on the user's past health data and the input dietary information, and providing the advice to the user, and means for having the user input the results and progress of the nutritional advice put into practice by the user into the database and providing ongoing advice based on updated health data. This allows users to understand the impact of their diet on their health, receive appropriate risk management and personalized nutritional advice, and enable ongoing health management.

[0113] A "user" is an individual or entity that utilizes the system to input dietary information and follow the nutrition advice and risk alerts provided.

[0114] "Dietary information" refers to information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[0115] "Database" means an information management system for storing dietary information, health data, nutritional advice, and risk alerts entered by users.

[0116] "Batch processing" is a method of periodically retrieving data stored in a database and processing it all at once.

[0117] Advanced glycation end products (AGEs) are compounds produced when sugars and proteins in food react with each other. They are easily produced by high-temperature cooking and pose a risk to health.

[0118] "Risk assessment" is the process of assessing the health risk of a user based on the calculated amount of AGE production.

[0119] A "risk alert" is a message that warns the user about risks based on the results of risk assessment.

[0120] "Nutrition advice" is information that suggests optimal dietary and nutritional intake methods that are tailored to the user's health condition and lifestyle, based on the user's dietary information and health data.

[0121] A "prompt" is a sentence that is input to a generative AI model and is an instruction to generate advice or other output based on specific information.

[0122] A "generative AI model" is an artificial intelligence system that uses machine learning to analyze user data, calculate the amount of AGE production, and generate nutritional advice.

[0123] "Feedback data" refers to information entered into the app by users about the results and progress of the nutrition advice they have implemented.

[0124] This invention is a system that collects a user's dietary information, evaluates the risk of AGE accumulation due to high-temperature cooking, and provides optimal nutritional advice. This system is composed of three main components: a server, a terminal, and the user.

[0125] First, the user uses a dedicated application to input their daily dietary information. At this time, the user enters information such as "food name," "cooking method," "portion," and "time of intake" from the app's food record screen. For example, if the user has a fried egg (cooked at high temperature) and toast (fried) for breakfast, they enter that information into the app. This allows the user's dietary information to be collected.

[0126] Next, the device temporarily stores the meal information entered by the user locally and converts it into a standard data format (e.g., JSON). It then sends this to the server via an HTTP request. The server then stores the received meal information in a database. The database uses a common RDBMS (e.g., MySQL).

[0127] The server retrieves the dietary information stored in the database at regular intervals and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method. The generative AI model uses a machine learning model using, for example, PyTorch. This model can calculate the amount of AGE generated by a fried egg (cooked at high temperature) to be 100, and by toast (baked) to be 50. Based on these calculation results, the user's total AGE intake is calculated and a risk assessment is performed for each user.

[0128] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device via an HTTP request and displayed as a notification.

[0129] Furthermore, the server uses a generative AI model to suggest appropriate nutritional balance and dietary methods based on past health data and dietary information. For example, this includes advice on introducing low-temperature cooking techniques and how to select specific ingredients. The device receives this nutritional advice and displays it on the app's "Recommended Menu" screen. Specific recipe examples are also displayed.

[0130] The user puts the suggested nutrition advice into practice and enters their results and progress into the app, which generates user feedback data. The server receives this feedback data and updates it in a database. The server then continuously generates advice based on the updated data, supporting the user's health management.

[0131] As a concrete example, consider the case where middle-aged male User A eats steak and grilled vegetables for lunch. User A enters these meal details into the app. The server receives this and calculates that the AGE generation amount for steak (cooked at high temperature) is 200, and for grilled vegetables (cooked at high temperature) is 100. Based on the total AGE intake of 300, it is determined that the risk is high, and a risk alert is sent. Next, the server suggests to User A that they use low-temperature cooking for steak and steamed vegetables. User A puts the recipe into practice based on this advice and enters the results into the app.

[0132] An example of a specific prompt sentence to input to the generative AI model is as follows:

[0133] User's dietary information: steak (cooked at high temperature), grilled vegetables (cooked at high temperature)

[0134] Past health data: high blood pressure, prediabetes

[0135] User's lifestyle: Sedentary work, lack of exercise

[0136] Suggest specific nutritional advice to this user, such as low-temperature cooking techniques or choosing specific ingredients.

[0137] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1: Enter your meal information

[0140] User: Using a dedicated app, the user inputs the details of their daily meals. The input details include the names of ingredients, cooking methods, portions, and intake times. For example, for breakfast, the user inputs "fried eggs (cooked at high temperature), toast (fried)." This allows the user's dietary information to be collected. The input data is temporarily stored in a local database.

[0141] Step 2: Submit your meal information

[0142] Terminal: The terminal converts the meal information entered by the user into a standard data format (such as JSON format). This converted data is sent to the server via an HTTP request. The input is the meal information entered by the user, and the output is the meal information converted into JSON format.

[0143] Step 3: Save your meal information

[0144] Server: Saves the received meal information in a database (e.g., MySQL database). The input is meal information in JSON format, and the output is the meal information stored in the database. This saving process permanently saves the meal information in the database.

[0145] Step 4: Extracting meal information

[0146] Server: The server retrieves the meal information stored in the database at regular intervals using batch processing. For example, it retrieves the previous day's meal data every night at midnight. The input is the meal information stored in the database, and the output is the meal information extracted by batch processing.

[0147] Step 5: Calculate the amount of AGE produced

[0148] Server: The extracted meal information is input into a generative AI model (for example, a machine learning model using PyTorch) to calculate the amount of AGE generated based on each ingredient and cooking method. The input is the meal information, and the generative AI model processes the data. The output is the amount of AGE generated for each ingredient and cooking method. For example, the amount of AGE generated for fried eggs (cooked at high temperature) is calculated to be 100, and for toast (fried) it is calculated to be 50.

[0149] Step 6: Conduct a risk assessment

[0150] Server: Based on the calculated amount of AGE produced, calculates the user's total AGE intake and performs a risk assessment. The input is the amount of AGE produced for each ingredient and cooking method, and the output is the total AGE intake for each user and the risk assessment results. For example, a fried egg and toast combined results in an AGE intake of 150, which is determined to be a high risk level.

[0151] Step 7: Generate and send risk alerts

[0152] Server: If the risk assessment results in a high risk, it generates a risk alert. The risk alert contains a detailed risk explanation and a warning message. The generated risk alert is sent to the user's terminal via an HTTP request. The input is the risk assessment result, and the output is the risk alert message.

[0153] Step 8: View risk alerts

[0154] Device: The device stores the received risk alert locally and notifies the user using the app's notification function. The alert content is displayed on the app's notification screen. The input is the risk alert message, and the output is the notification displayed in the app.

[0155] Step 9: Generate and send nutrition advice

[0156] Server: The generative AI model proposes appropriate nutritional balance and dietary methods based on past health data and dietary information. Specifically, this includes introducing low-temperature cooking techniques and selecting specific ingredients. The server generates this nutritional advice and sends it to the device in JSON format. The input is past health data and dietary information, and the output is nutritional advice.

[0157] Step 10: View nutrition advice

[0158] Device: The device displays the received nutrition advice on the app's "Recommended Menu" screen. Specific recipe examples are also displayed. The input is the nutrition advice, and the output is the nutrition advice display within the app.

[0159] Step 11: Enter feedback data

[0160] User: The user puts the provided nutrition advice into practice and enters their results and progress into the app. The input data is temporarily stored in a local database. For example, the user might enter, "I tried making steamed vegetables and slow-cooked chicken."

[0161] Step 12: Submit and store feedback data

[0162] Terminal: The feedback data entered by the user is converted into a standard data format and sent to the server via an HTTP request. The server stores the received feedback data in a database. The input is the feedback data entered by the user, and the output is the feedback data stored in the database.

[0163] Step 13: Generating Ongoing Advice

[0164] Server: Based on the updated feedback data, the server continuously generates new nutrition advice using a generative AI model to analyze the user's health status and provide the next optimal advice. The input is the feedback data, and the output is the next nutrition advice.

[0165] In this way, the system provides personalized AGE risk management and nutrition advice for each user, supporting healthy aging.

[0166] (Application example 1)

[0167] 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."

[0168] In modern society, it is difficult to consistently consume a nutritionally balanced diet, and the risk of ingesting advanced glycation end products (AGEs) caused by high-temperature cooking is a particular concern. As a result, various health risks increase, so effective means are needed for users to manage their own diet and reduce these risks. It is also important to assess health risks in real time and provide personalized nutritional advice through food delivery services that users use on a daily basis. Current systems are unable to adequately resolve these issues.

[0169] 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.

[0170] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for automatically acquiring dietary information from the user's past order history, means for evaluating the amount of AGEs produced in real time when the user uses a food delivery service and displaying a risk alert, and means for providing customized recipe examples based on specific health advice. This allows users to have their health risks appropriately assessed and receive personalized nutritional advice even when using food delivery services.

[0171] A "user" is someone who uses this system to input dietary information and manage their health.

[0172] "Dietary information" refers to detailed information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[0173] A "database" is a data storage system for storing a user's dietary information, health data, and analysis results.

[0174] Advanced glycation end products (AGEs) are substances produced by high-temperature cooking and other processes, and their accumulation in the body can pose various health risks.

[0175] "Risk assessment" is the process of calculating the health risk to the user based on the amount of AGEs produced calculated based on dietary information.

[0176] "Risk Alerts" are notifications sent to users that include warnings about foods or cooking methods that are assessed as high risk.

[0177] "Nutrition advice" is information that suggests specific dietary methods and recipes for maintaining an appropriate nutritional balance based on the user's health condition and lifestyle.

[0178] "Order history" is a record of meals that a user has ordered in the past using a food delivery service.

[0179] "Real-time evaluation" is a process in which the amount of AGE production is instantly evaluated based on the meal selection made at the time a user uses a food delivery service.

[0180] "Customized recipes" are cooking methods and menus suggested based on specific health advice and tailored to the user's health condition and lifestyle.

[0181] This invention is a system that collects and analyzes a user's dietary information, evaluates the risk of accumulating advanced glycation end products (AGEs), and provides optimal nutritional advice. Specific embodiments of this system are described below.

[0182] System configuration

[0183] The system consists of three main components:

[0184] 1. User's device (terminal): This is assumed to be a smartphone or tablet with an application for entering meal information installed.

[0185] 2. Backend server: Built on the cloud, it stores and analyzes users' dietary and health data.

[0186] 3. Generative AI model: Using OpenAI GPT-4, the system calculates the amount of AGE production and provides personalized nutritional advice based on user data.

[0187] Program processing details

[0188] Collection of dietary data

[0189] Users use a dedicated app to input their daily meal plans. The app automatically captures specific information such as ingredients, cooking methods, portions, and consumption times. When users use food delivery services, meal information is automatically retrieved from their past order history.

[0190] Data analysis

[0191] The device converts the input dietary information into a standard data format and sends it to a backend server. The server extracts the dietary information stored in the database and uses a generative AI model to calculate the amount of AGEs generated based on each ingredient and cooking method. Based on the calculated data, the user's total AGE intake is calculated and a risk assessment is performed.

[0192] Providing risk alerts

[0193] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device and displayed in a dedicated app.

[0194] Generate nutrition advice

[0195] The server uses the AI ​​to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information. Specific advice is provided, such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients. The device displays customized recipes as examples.

[0196] Example

[0197] Example 1: Case of middle-aged male user A

[0198] 1. Dietary data collection:

[0199] User A orders "chicken curry and white rice" for lunch from a food delivery service.

[0200] The app automatically retrieves meal information for "chicken curry" and "white rice" from your order history.

[0201] 2. Data Analysis:

[0202] The server uses a generation AI to calculate the amount of AGEs produced by cooking chicken curry and white rice at high temperatures.

[0203] The total AGE intake was calculated and the risk for User A was assessed.

[0204] 3. Providing risk alerts:

[0205] Based on the risk assessment, the server generates a risk alert to User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[0206] An alert will be displayed on the device to notify the user.

[0207] 4. Generating nutrition advice:

[0208] The server's generation AI suggests menu examples using low-temperature cooking and the use of steamed vegetables to User A.

[0209] The device displays a specific recipe example: "Steamed vegetables and low-temperature cooked chicken."

[0210] Prompt Sentence Examples

[0211] text

[0212] Input: "Calculate the amount of AGEs produced by cooking chicken curry at high temperatures and assess the user's risk."

[0213] Response: "Cooking chicken curry at high temperatures produces a high amount of AGEs, and risk assessment indicates that your AGE intake is at high risk. Try combining it with steamed vegetables or cooking it at low temperatures."

[0214] This will enable users to properly assess health risks and receive personalized nutritional advice when using food delivery services.

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] Collection of dietary data

[0218] Users input their daily dietary information using a dedicated app.

[0219] Input: Information entered by the user about the ingredient name, cooking method, serving size, and time of consumption.

[0220] Output: Meal information stored in a standard data format.

[0221] The device implements an algorithm that automatically retrieves meal information from the order history of food delivery services.

[0222] Input: Food delivery order history.

[0223] Output: Meal information stored in a standard data format.

[0224] Step 2:

[0225] Sending data

[0226] The terminal converts the meal information obtained from the user into a standard data format and transmits it to the backend server.

[0227] Input: Meal information in a standard data format.

[0228] Output: Sending meal information to backend server.

[0229] Step 3:

[0230] Data storage

[0231] The server stores the received meal information in a database.

[0232] Input: Meal information sent from the device.

[0233] Output: Meal information stored in a database.

[0234] Step 4:

[0235] Data analysis

[0236] The server retrieves the meal information stored in the database and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method.

[0237] Input: Meal information stored in a database.

[0238] Output: Calculation result of AGE production amount.

[0239] The server calculates the user's total AGE intake based on the calculated amount of AGE produced and performs a risk assessment.

[0240] Input: Calculation result of AGE production amount.

[0241] Output: The result of the user's risk assessment.

[0242] Step 5:

[0243] Generate and send risk alerts

[0244] The server generates a risk alert if the result of the risk assessment indicates a high risk.

[0245] Input: Risk assessment results.

[0246] Output: Generate a risk alert.

[0247] The server transmits the generated risk alert to the user's terminal.

[0248] Input: Generated risk alert.

[0249] Output: Sending a risk alert to the device.

[0250] Step 6:

[0251] Viewing risk alerts

[0252] The device displays the received risk alert on a dedicated app and notifies the user.

[0253] Input: The risk alert sent by the server.

[0254] Output: Display of risk alert in the app.

[0255] Step 7:

[0256] Generate nutrition advice

[0257] The server uses a generative AI to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information.

[0258] Input: Historical health data and dietary information.

[0259] Output: The generated nutrition advice.

[0260] The server provides specific advice, including low-temperature cooking methods and how to choose specific ingredients to reduce the production of AGEs.

[0261] Input: The result of the user's risk assessment.

[0262] Output: Specific nutritional advice.

[0263] Step 8:

[0264] Displaying nutritional advice

[0265] The device displays the nutrition advice provided by the server on a dedicated app.

[0266] Input: Generated nutrition advice.

[0267] Output: Display of nutrition advice on a dedicated app.

[0268] Step 9:

[0269] Enter your feedback

[0270] The user puts the advice into practice and inputs the results as feedback into a dedicated app.

[0271] Input: Feedback information entered by the user.

[0272] Output: Feedback information stored in a standard data format.

[0273] Step 10:

[0274] Update data

[0275] The server updates the user's health data in the database based on the feedback data.

[0276] Input: Feedback information.

[0277] Output: Updated health data.

[0278] This allows the system to properly manage the user's dietary information and provide personalized nutritional advice to reduce health risks.

[0279] 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.

[0280] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[0281] Program processing

[0282] The system of the present invention is implemented as a series of processes involving a server, a terminal, a user, and an emotion engine.

[0283] Collection of dietary data

[0284] User: Uses a dedicated app to input meal information, including the name of ingredients, cooking method, portion size, and time of intake.

[0285] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[0286] Server: Stores the received meal information in a database.

[0287] Data analysis

[0288] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[0289] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[0290] Emotion recognition

[0291] Terminal: Using an emotion engine, emotions are recognized from the user's input, reactions, facial expressions, voice, etc.

[0292] Terminal: Sends the recognized emotion information to the server.

[0293] Providing risk alerts

[0294] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes the specific details of the risk and countermeasures.

[0295] Server: Adjust the wording of risk alerts based on the user's emotional state. For example, choose gentler words for a user who is feeling stressed.

[0296] Server: Sends the generated risk alerts to the user's device.

[0297] Device: The received risk alert is displayed in the app and notified to the user.

[0298] Generate nutrition advice

[0299] Server: Checks the user's health status based on the user's past health data and dietary information.

[0300] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[0301] Server: Adjust the wording and content of nutrition advice based on the user's emotional information, for example by adding words of praise to increase motivation.

[0302] Server: Sends the generated nutrition advice to the user's device.

[0303] Displaying and implementing nutrition advice

[0304] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[0305] User: Prepares and follows the advice.

[0306] Gathering feedback and updating data

[0307] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[0308] Terminal: Sends the input feedback data to the server.

[0309] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[0310] Ongoing Wellness Support

[0311] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[0312] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[0313] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[0314] Specific examples

[0315] Example 1: Case of middle-aged male user A

[0316] 1. Collection of dietary data

[0317] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[0318] 2. Data Analysis

[0319] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[0320] 3. Emotional Recognition

[0321] Device: The app analyzes User A's facial expressions using an emotion engine and recognizes that he or she is tired.

[0322] Device: Recognized emotion information is sent to the server.

[0323] 4. Providing risk alerts

[0324] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[0325] Server: Based on the emotional information indicating fatigue, the alert is expressed in gentle words: "Please be careful. High-temperature cooking can affect your health."

[0326] Device: An alert is displayed in the app and notifies User A.

[0327] 5. Generating nutrition advice

[0328] Server: The generating AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[0329] Server: Based on emotional information, we added encouraging words to the advice: "Keep it up! With a little effort, you can improve your health."

[0330] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[0331] 6. Providing wellness support

[0332] Device: User A practices the suggested recipe and enters the results into the app.

[0333] Server: Updates user A's health data based on feedback data and provides ongoing support.

[0334] In this way, the system provides personalized AGE risk management and nutrition advice for each user, and by incorporating emotional information, effectively supports users in achieving healthy aging.

[0335] The processing flow will be explained below.

[0336] Step 1: Collect dietary data

[0337] User: Opens the app and enters meal information, including the name (e.g., steak), cooking method (e.g., grilled), portion size (e.g., 200g), and time of consumption (e.g., 12:30).

[0338] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server according to the communication protocol.

[0339] Server: The received meal information is stored in a database. The stored data includes the user ID, meal date and time, ingredient list, cooking method, etc.

[0340] Step 2: Recognize emotions

[0341] Device: Activates the emotion engine and captures the user's facial expressions and voice using the camera and microphone.

[0342] On the device: The emotion engine analyzes the captured data and recognizes the user's emotional state (e.g., joy, sadness, stress).

[0343] Terminal: Adds the recognized emotion information to the client data and sends it to the server.

[0344] Step 3: Saving and Retrieving Data

[0345] Server: The received emotion information is associated with the user's data and stored in a database.

[0346] Server: Extracts the target user's dietary and emotional information from the database for analysis. Extraction is performed using SQL queries, etc.

[0347] Step 4: Calculate the amount of AGE produced

[0348] Server: Using the generation AI, calculate the amount of AGE generated for each ingredient and cooking method based on the extracted meal information. The calculation method is based on a predefined algorithm.

[0349] Server: Calculates the user's total AGE intake based on the calculation results and saves the data.

[0350] Step 5: Risk assessment

[0351] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[0352] Server: The results of the risk assessment are stored in a database and used as the basis for the next processing step.

[0353] Step 6: Generate and send risk alerts

[0354] Server: If a high risk is determined, a risk alert is generated. The alert includes a specific risk description and countermeasures.

[0355] Server: Adjusts the wording of risk alerts based on the user's emotional state. For example, if the user is recognized as being in a stressful state, it selects a gentler message, such as "Be careful. Cooking at high temperatures can affect your health."

[0356] Server: Sends the generated risk alerts to the user's device.

[0357] Device: The received risk alert is displayed in the app and notified to the user.

[0358] Step 7: Generate nutrition advice

[0359] Server: Checks the user's health status based on the user's past health data, current dietary data, and emotional data.

[0360] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods, including low-temperature cooking methods and specific ingredients that reduce AGE production.

[0361] Server: Adjust the wording and content of nutrition advice based on emotional information. For example, add words of praise to boost motivation, such as, "Keep it up! With just a few simple changes, you can improve your health."

[0362] Server: Sends the generated nutrition advice to the user's device.

[0363] Step 8: Provide and implement nutrition advice

[0364] Device: The received nutrition advice is displayed in the app, and specific advice and recipes are provided for the user to review.

[0365] User: Prepares and follows the provided advice on meals.

[0366] Step 9: Gather feedback and update data

[0367] User: Enter the results of the practice, as well as their physical condition and emotional state after eating and drinking, into the app.

[0368] Terminal: Sends the input feedback data to the server.

[0369] Server: Receives the feedback data and updates the database, which contains the user's latest health and emotional information.

[0370] Step 10: Ongoing Wellness Support

[0371] Server: Generates new nutrition advice based on the updated data and provides it to the user.

[0372] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[0373] Device: Provides ongoing advice and alerts to help users maintain a healthy lifestyle.

[0374] In this way, the system provides individualized AGE risk management and nutrition advice for each user, and by taking emotional information into account, it achieves more effective and personalized health support.

[0375] Example 2

[0376] 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."

[0377] Conventional health management systems are capable of calculating the amount of advanced glycation end products (AGEs) produced based on a user's dietary information, conducting risk assessments, and providing nutritional advice. However, because they provide uniform advice without taking the user's emotional state into consideration, there is a problem in that effective advice and risk alerts cannot be received depending on the user's emotional state. In particular, when users are under high stress or feeling fatigued, they tend to lose motivation to take appropriate health management and improve their diet. Therefore, there is a need for a system that provides more effective health support that takes the user's emotional state into consideration.

[0378] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for recognizing the user's emotions, means for sending a risk alert to the user based on the risk assessment and the user's emotions, and means for generating nutritional advice according to the user's health condition and emotional information and providing the advice to the user. This enables personalized risk alerts and nutritional advice that take the user's emotional state into consideration.

[0379] "User" refers to an individual who uses the system to input and review their own health management information and dietary information.

[0380] "Dietary information" refers to data on detailed dietary content such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[0381] "Database" refers to an information system for storing and managing various data, including dietary information, health information, and emotional information, entered by users.

[0382] Advanced glycation end products (AGEs) are substances that are produced when sugars and proteins in food ingredients combine during high-temperature cooking and have various adverse effects on the human body.

[0383] "Risk assessment" refers to the process of assessing and determining the user's health risk based on the calculated amount of AGE production and other health information.

[0384] "Emotion recognition" refers to the technology of identifying and determining a user's emotional state from their input, reactions, facial expressions, voice, etc.

[0385] "Risk alert" refers to a notification that warns or warns the user about health issues based on the results of a risk assessment.

[0386] "Nutrition advice" refers to advice that suggests appropriate diet and nutritional intake methods based on the user's health condition, dietary information, and emotional information.

[0387] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[0388] The present invention is implemented in a series of processes involving a server, a terminal, a user, and an emotion engine.

[0389] First, the user uses a dedicated app to input meal information. Specific items include the names of ingredients, cooking methods, portions, and time of consumption. For example, suppose the user inputs "200g steak and grilled vegetables (broccoli and carrots) for lunch." The device converts the input information into a standard data format (such as JSON) and sends it to the server via an HTTP request.

[0390] The server receives the HTTP request and stores it in a database in the format of "user ID, date and time, ingredient name, cooking method, and portion size." The server then extracts the meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE generated based on each ingredient and cooking method. For example, it obtains data such as "200g of steak generates 35mg of AGE, and grilled vegetables generates 15mg of AGE." The server then adds up the AGEs of each ingredient to calculate the total AGE intake (e.g., 50mg), and uses this to perform a risk assessment. It determines whether the diet is "high risk," "medium risk," or "low risk."

[0391] Furthermore, the device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, when a user shoots and sends a short video using their smartphone camera, the emotion engine analyzes the data, such as "fatigue 50%," and sends it to the server.

[0392] If the server determines that the risk assessment is "high risk" based on the total AGE intake and emotional data, it generates a risk alert stating that "high AGE intake poses a health risk." Here, the server takes into account the user's emotional information, and if the user feels "50% fatigued," for example, it changes the alert to a more gentle expression such as "Take care of your health when you are tired." The generated risk alert is sent to the user's device as an HTTP response, and the alert is displayed in the app's notification bar.

[0393] Next, the server checks the user's health status based on their past health data and dietary information. Using a generative AI model, it analyzes the user's health status and dietary information and suggests recipes such as "low-temperature cooked steak recipes" and "steamed vegetable recipes." It also adjusts the wording of the advice based on emotional data. For example, it might say, "This is an easy recipe to make even when you're tired. Good luck!"

[0394] The user prepares a meal using the provided "low-temperature cooked steak recipe" as a reference, and then cooks the meal. After the meal, the user opens the "Feedback" section in the app and enters their impressions, such as "It was delicious" or "I feel great," as well as their physical condition. The device converts the input feedback data into a standard data format and sends it to the server as an HTTP request. The server receives this, stores it in a database, and updates the user's health data.

[0395] Based on the updated data, the server generates new nutrition advice and sends the results to the user's device. If new risks are discovered, the server performs a risk assessment again and generates and sends risk alerts as necessary. The device continuously displays the latest advice and risk alerts on the app, supporting the user in living a healthy lifestyle.

[0396] Prompt Sentence Examples

[0397] "Generate risk alerts and nutritional advice for the user based on dietary data and emotional information. Ingredients: 200g steak and grilled vegetables. Emotion: 50% fatigue."

[0398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0399] Step 1:

[0400] The user taps the "Enter Meal Information" button on the dedicated app screen and enters detailed meal information such as the ingredients, cooking method, portion size, and time of intake. For example, they might enter "200g steak, grilled vegetables (broccoli, carrots)."

[0401] Step 2:

[0402] The device receives the meal information entered by the user and converts it into a standard data format (e.g., JSON), which structures the information and prepares it for transmission to the server.

[0403] Step 3:

[0404] The device sends the converted data to the server in the form of an HTTP request, which includes the user ID, date and time, ingredient names, cooking methods, and quantities.

[0405] Step 4:

[0406] The server analyzes the received HTTP request and stores the meal information in a database, including the user ID, date and time, ingredient names, cooking methods, and serving sizes.

[0407] Step 5:

[0408] The server extracts meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE produced based on each ingredient and cooking method. For example, it can obtain results such as "200g of steak produces 35mg of AGE, and grilled vegetables produces 15mg of AGE."

[0409] Step 6:

[0410] The server calculates the total AGE intake by adding up the amount of AGE produced by each food ingredient based on the calculation results. For example, let's say a steak and grilled vegetables contain 50 mg of AGE combined. The server then performs a risk assessment based on the user's total AGE intake, determining whether they are at "high risk," "medium risk," or "low risk."

[0411] Step 7:

[0412] The device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, a user can shoot a short video with their smartphone camera and send it to obtain data such as "50% fatigue."

[0413] Step 8:

[0414] The device converts the recognized emotion data into a standard data format and sends it to the server. This request includes the user ID and the emotion recognition result.

[0415] Step 9:

[0416] The server receives the emotion data and generates a risk alert if the risk assessment results in a "high risk." For example, the alert might say, "High AGE intake poses a health risk."

[0417] Step 10:

[0418] The server adjusts the wording of the risk alert based on the user's emotional information. For example, if the user says "Feeling 50% fatigued," it will change the wording to something gentler, such as "Take care of your health when you're tired."

[0419] Step 11:

[0420] The server sends the generated risk alert to the user's device as an HTTP response.

[0421] Step 12:

[0422] The device will display the received risk alert in the app's notification bar and notify the user.

[0423] Step 13:

[0424] The server retrieves past health and dietary data from a database and uses a generative AI model to analyze the user's health status, suggesting recipes such as low-temperature cooked steak and steamed vegetables.

[0425] Step 14:

[0426] The server adjusts the content and wording of advice based on the emotional information, for example, "Here's a recipe that's easy to make even when you're tired. Good luck!"

[0427] Step 15:

[0428] The server sends the generated nutrition advice to the user's terminal as an HTTP response.

[0429] Step 16:

[0430] The device will display the received nutrition advice in the "Advice" section of the app, where users can view specific advice and recipes.

[0431] Step 17:

[0432] The user prepares and executes a meal based on the presented "low-temperature cooked steak recipe."

[0433] Step 18:

[0434] After eating, users open the "Feedback" section in the app and enter their impressions, such as "It was delicious" or "I feel great," as well as their physical condition.

[0435] Step 19:

[0436] The terminal converts the input feedback data into a standard data format and sends it to the server as an HTTP request.

[0437] Step 20:

[0438] The server receives the feedback data and stores it in a database to update the user's health data.

[0439] Step 21:

[0440] The server generates new nutrition advice based on the updated data and sends the results to the user's terminal.

[0441] Step 22:

[0442] If the server discovers any new risks, it will reassess them and generate and send risk alerts as necessary.

[0443] Step 23:

[0444] The device continuously displays the latest advice and risk alerts in the app, supporting users in living a healthy lifestyle.

[0445] (Application example 2)

[0446] 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."

[0447] Conventional dietary information analysis systems can assess the health risks posed by advanced glycation end products (AGEs) ingested by users and provide risk alerts and nutritional advice. However, they cannot take the user's emotional state into account, which means they are unable to provide effective health support. For example, a sudden health warning can be counterproductive for a stressed user, risking discouraging the user's motivation to improve their health. Therefore, there is a need for a health support system that takes the user's emotions into account.

[0448] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0449] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for collecting emotional information about the user using an emotion engine that recognizes the user's emotions, means for adjusting the presentation of the risk alert based on the emotional information, and means for adjusting the content and presentation of the nutritional advice based on the emotional information. This enables more effective health support by providing risk alerts and nutritional advice that take the user's emotional state into consideration.

[0450] A "database" is a system for systematically storing information and for efficient searching and analysis.

[0451] "Meal information" is detailed information about the meal the user has eaten, such as the names of ingredients, cooking methods, and portions.

[0452] Advanced glycation end products (AGEs) are compounds that are produced by high-temperature cooking and accumulate in the body, posing a health risk.

[0453] A "risk alert" is a warning message that notifies the user of a health risk.

[0454] "Nutrition advice" refers to suggestions about appropriate diet and nutritional intake methods based on the user's health condition and lifestyle.

[0455] An "emotion engine" is a technology that recognizes and analyzes emotions from user input, reactions, facial expressions, voice, etc.

[0456] "Emotion information" is data about the user's emotional state as recognized by the emotion engine.

[0457] "Risk assessment" is the process of calculating the health risk for each user based on dietary information and the amount of AGE produced.

[0458] "Adjusting the expression method" means changing the content and display method of the message based on the user's emotional information.

[0459] This invention is based on a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. This system can also be combined with an emotion engine that recognizes the user's emotions, making it possible to adjust risk alerts and nutritional advice according to the user's emotions. Specific embodiments of this system are described below.

[0460] System Components

[0461] server

[0462] The server includes the following means:

[0463] 1. A means for having the user input meal information and storing the meal information in a database.

[0464] 2. A means of analyzing stored dietary information and calculating the amount of advanced glycation end products (AGEs) produced.

[0465] 3. A means of assessing risk for each user based on the calculated amount of AGE generated.

[0466] 4. A means of sending risk alerts to users based on risk assessment.

[0467] 5. A means for generating and providing nutritional advice tailored to the user's health and lifestyle.

[0468] 6. A means of collecting user emotion information using an emotion engine that recognizes user emotions.

[0469] 7. A means to tailor the wording of risk alerts based on sentiment information.

[0470] 8. Means of tailoring the content and presentation of nutrition advice based on emotional information.

[0471] Processing flow

[0472] Terminal

[0473] The device provides an application that allows users to input meal information. Through this application, information such as ingredient names, cooking methods, and portion sizes is collected and sent to a database. In addition, an emotion engine is used to recognize emotions from the user's input, reactions, facial expressions, and voice, and this information is also sent to the server.

[0474] server

[0475] The server analyzes the received meal information and uses a generation AI to calculate the amount of AGEs generated based on each ingredient and cooking method. It then calculates the user's total AGE intake and performs a risk assessment based on that information. If the risk assessment results in a high risk, a risk alert is generated and the presentation is adjusted based on the user's emotional information.

[0476] The server also generates nutrition advice based on the user's past health data and dietary information to suggest optimal nutritional balance and dietary methods. This includes low-temperature cooking methods that help reduce AGEs and how to select specific ingredients. Based on emotional information, the server adjusts the wording and content of the advice and provides it in an appropriate format for the user.

[0477] Specific examples

[0478] Example: Middle-aged male user

[0479] 1. Collection of dietary data

[0480] A user tells the app that they had steak and grilled vegetables for lunch, with the steak cooked at a high temperature and the vegetables cooked at the same time.

[0481] 2. Data Analysis

[0482] The server uses AI to calculate the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables, calculates the overall AGE intake, and assesses the user's risk.

[0483] 3. Emotional Recognition

[0484] The device uses an emotion engine to analyze the user's facial expressions through the app and recognizes that they are feeling tired.

[0485] 4. Providing risk alerts

[0486] Based on the risk assessment, the server generates a risk alert saying, "Caution is required as high-temperature cooking results in a high intake of AGEs." Based on the emotional information indicating fatigue, the alert is expressed in gentle words: "Be careful. High-temperature cooking can affect your health."

[0487] 5. Generating nutrition advice

[0488] The server suggests to the user how to cook steak using low-temperature cooking or how to use steamed vegetables. Based on the emotional information, the server adds encouraging words to the advice: "Good luck! A little effort will improve your health."

[0489] Prompt Sentence Examples

[0490] "The user ate the following ingredients: steak (cooked at high temperature), grilled vegetables (cooked at high temperature). The emotion was 'stress'. Please generate an alert and nutritional advice based on the risk assessment of AGE production and the emotion."

[0491] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0492] Step 1: Enter your meal data

[0493] The user inputs meal information through the application. Input items include the names of ingredients, cooking methods, and portions. Once this information is entered, the device converts it into a standard data format and sends it to the server. The input data is in the following format: {"Ingredient Name": "Steak", "Cooking Method": "High-Temperature Cooking", "Amount": "200g"}. The device calls an API to send this data.

[0494] Step 2: Enter emotion data

[0495] After inputting the meal information, the user inputs information related to their current emotional state. This input can be text, voice, or facial expression recognition. For example, they can upload a short comment or an image of their facial expression that indicates fatigue or stress. The device analyzes this information using an emotion engine and sends the results to the server. The input data is in the following format: {"emotion": "stress"}.

[0496] Step 3: Analyze dietary data

[0497] The server stores the received meal information in a database. It then uses a generative AI model to calculate the amount of AGEs produced based on each ingredient and cooking method. For example, it calculates the amount of AGEs produced by cooking a steak at high temperature, and adds them up to calculate the total AGE intake. The calculation result is in the following format: {"total AGE production": "1500 units"}.

[0498] Step 4: Risk assessment

[0499] The server performs a risk assessment for each user based on the total AGE generated in step 3. The risk assessment is judged to be high risk if it exceeds a certain threshold. For example, if the threshold is 1000 units, 1500 units is assessed as high risk. The assessment result is in the following format: {"Risk Assessment": "High Risk"}.

[0500] Step 5: Emotional Analysis

[0501] The server stores the emotion information received in step 2 in a database, and also stores the analysis results from the emotion engine. The emotion engine identifies emotions from the input text, voice, and facial expressions, and the analysis results are in the following format: {"emotion assessment": "stress"}.

[0502] Step 6: Generate a risk alert

[0503] The server generates a risk alert for the user based on the risk assessment and emotional information. For example, if the risk is assessed as high and the emotional information is "stress," a gentle warning is displayed. The message generated is "Be careful. Cooking at high temperatures can affect your health." The generated risk alert will be in the following format: {"risk alert": "Be careful. Cooking at high temperatures can affect your health"}.

[0504] Step 7: Generate nutrition advice

[0505] The server generates nutrition advice to suggest optimal nutritional balance and dietary methods based on the user's health status and past dietary data. This advice includes low-temperature cooking techniques and how to select specific ingredients, and also includes words of encouragement. The generated message is "Good luck! With a little effort, you can improve your health." The generated nutrition advice is in the following format: {"nutrition advice": "Try steamed vegetables and low-temperature cooked chicken. Good luck! With a little effort, you can improve your health"}.

[0506] Step 8: Providing risk alerts and nutritional advice

[0507] The server sends the generated risk alerts and nutrition advice to the user's device, which notifies and displays this information within the application. The user can check the alerts and advice and take necessary actions.

[0508] Through these steps, the system can manage the user's diet and emotional state as a whole and provide appropriate risk alerts and nutritional advice.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] [Second embodiment]

[0513] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0514] 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.

[0515] 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).

[0516] 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.

[0517] 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.

[0518] 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).

[0519] 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.

[0520] 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.

[0521] 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.

[0522] 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.

[0523] 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.

[0524] 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."

[0525] This invention is a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. It also provides optimal nutritional advice based on the user's health status and lifestyle, supporting the user in achieving healthy aging.

[0526] Program processing

[0527] The system of the present invention is implemented through a series of processes involving three parties: a server, a terminal, and a user.

[0528] Collection of dietary data

[0529] User: Using a dedicated app, the user enters information about their daily meals, including the names of ingredients, cooking methods, portions, and intake times.

[0530] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[0531] Server: Stores the received meal information in a database.

[0532] Data analysis

[0533] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[0534] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[0535] Providing risk alerts

[0536] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes a detailed risk description and a warning message.

[0537] Server: Sends the generated risk alerts to the user's device.

[0538] On the device: Display a risk alert in the user's app to notify the user.

[0539] Generate nutrition advice

[0540] Server: Based on the user's past health data and dietary information, the AI ​​checks their health condition and generates and proposes an appropriate nutritional balance and dietary plan.

[0541] Server: Provides specific advice such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients.

[0542] Nagetsu: Provides nutrition advice within the user's app, with specific recipes and actionable methods.

[0543] Providing wellness support

[0544] Device: The user puts the nutrition advice provided into practice and enters their results and progress into the app.

[0545] Server: Based on the feedback data, the database is updated to reflect the user's latest health status.

[0546] Server: Provides continuous advice based on updated data to support users in managing their health.

[0547] Specific examples

[0548] Example 1: Case of middle-aged male user A

[0549] 1. Collection of dietary data

[0550] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[0551] 2. Data Analysis

[0552] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[0553] 3. Providing risk alerts

[0554] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[0555] Device: An alert is displayed in the app and notifies User A.

[0556] 4. Generating nutrition advice

[0557] Server: The generative AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[0558] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[0559] 5. Providing wellness support

[0560] Device: User A practices the suggested recipe and enters the results into the app.

[0561] Server: Updates user A's health data based on feedback data and provides ongoing support.

[0562] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[0563] The processing flow will be explained below.

[0564] Step 1: Collect dietary data

[0565] User: Opens the dedicated app and enters meal information, including the names of ingredients, cooking methods, portions, and intake times.

[0566] Terminal: Processes the meal information entered by the user and converts it into a standard data format.

[0567] Terminal: Sends the converted meal information to the server.

[0568] Step 2: Save your data

[0569] Server: Receives the received meal information and stores it in a database.

[0570] Server: Adds metadata such as user ID, meal date and time, ingredient list, and cooking method to the saved meal information.

[0571] Step 3: Analyze the data

[0572] Server: Extracts the target user's meal information from the database and selects the necessary data using queries.

[0573] Server: Based on the meal information extracted by the generation AI, calculates the amount of AGE generated for each ingredient and cooking method. The calculation is performed according to the AGE generation amount calculation method.

[0574] Server: Based on the calculation results, calculate the user's total AGE intake.

[0575] Step 4: Risk assessment

[0576] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[0577] Server: Stores the results of the risk assessment in a database.

[0578] Step 5: Generate and send a risk alert

[0579] Server: If a high risk is determined, a risk alert is generated. The alert includes specific details of the risk and countermeasures.

[0580] Server: Sends the generated risk alerts to the user's device.

[0581] Device: The received risk alert is displayed in the app and notified to the user.

[0582] Step 6: Generate nutrition advice

[0583] Server: Checks the user's health status based on the user's past health data and dietary information.

[0584] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[0585] Server: Sends the generated nutrition advice to the user's device.

[0586] Step 7: Provide and implement nutrition advice

[0587] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[0588] User: Prepares and follows the advice.

[0589] Step 8: Gather feedback and update data

[0590] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[0591] Terminal: Sends the input feedback data to the server.

[0592] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[0593] Step 9: Ongoing Wellness Support

[0594] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[0595] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[0596] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[0597] In this way, the system provides personalized AGE risk management and nutrition advice to each user, effectively supporting them in achieving healthy aging.

[0598] Example 1

[0599] 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."

[0600] In today's busy lifestyles, it is difficult for users to fully understand the impact of their diet and cooking methods on their health and take appropriate measures. Furthermore, there are few systems that provide individualized healthy nutrition advice, particularly for managing the risk of advanced glycation end products (AGEs) accumulation caused by high-temperature cooking. Furthermore, there is a lack of methods for users to implement the advice they receive and receive ongoing feedback on the results to enable ongoing health management.

[0601] 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.

[0602] In this invention, the server includes means for having users input dietary information and storing the dietary information in a database, means for periodically retrieving the dietary information stored in the database by batch processing and calculating the amount of advanced glycation end products (AGEs) produced for each ingredient and cooking method, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, generating a risk alert for the user based on the results of the risk assessment, and transmitting the alert, means for generating nutritional advice tailored to the user's health condition and lifestyle based on the user's past health data and the input dietary information, and providing the advice to the user, and means for having the user input the results and progress of the nutritional advice put into practice by the user into the database and providing ongoing advice based on updated health data. This allows users to understand the impact of their diet on their health, receive appropriate risk management and personalized nutritional advice, and enable ongoing health management.

[0603] A "user" is an individual or entity that utilizes the system to input dietary information and follow the nutrition advice and risk alerts provided.

[0604] "Dietary information" refers to information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[0605] "Database" means an information management system for storing dietary information, health data, nutritional advice, and risk alerts entered by users.

[0606] "Batch processing" is a method of periodically retrieving data stored in a database and processing it all at once.

[0607] Advanced glycation end products (AGEs) are compounds produced when sugars and proteins in food react with each other. They are easily produced by high-temperature cooking and pose a risk to health.

[0608] "Risk assessment" is the process of assessing the health risk of a user based on the calculated amount of AGE production.

[0609] A "risk alert" is a message that warns the user about risks based on the results of risk assessment.

[0610] "Nutrition advice" is information that suggests optimal dietary and nutritional intake methods that are tailored to the user's health condition and lifestyle, based on the user's dietary information and health data.

[0611] A "prompt" is a sentence that is input to a generative AI model and is an instruction to generate advice or other output based on specific information.

[0612] A "generative AI model" is an artificial intelligence system that uses machine learning to analyze user data, calculate the amount of AGE production, and generate nutritional advice.

[0613] "Feedback data" refers to information entered into the app by users about the results and progress of the nutrition advice they have implemented.

[0614] This invention is a system that collects a user's dietary information, evaluates the risk of AGE accumulation due to high-temperature cooking, and provides optimal nutritional advice. This system is composed of three main components: a server, a terminal, and the user.

[0615] First, the user uses a dedicated application to input their daily dietary information. At this time, the user enters information such as "food name," "cooking method," "portion," and "time of intake" from the app's food record screen. For example, if the user has a fried egg (cooked at high temperature) and toast (fried) for breakfast, they enter that information into the app. This allows the user's dietary information to be collected.

[0616] Next, the device temporarily stores the meal information entered by the user locally and converts it into a standard data format (e.g., JSON). It then sends this to the server via an HTTP request. The server then stores the received meal information in a database. The database uses a common RDBMS (e.g., MySQL).

[0617] The server retrieves the dietary information stored in the database at regular intervals and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method. The generative AI model uses a machine learning model using, for example, PyTorch. This model can calculate the amount of AGE generated by a fried egg (cooked at high temperature) to be 100, and by toast (baked) to be 50. Based on these calculation results, the user's total AGE intake is calculated and a risk assessment is performed for each user.

[0618] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device via an HTTP request and displayed as a notification.

[0619] Furthermore, the server uses a generative AI model to suggest appropriate nutritional balance and dietary methods based on past health data and dietary information. For example, this includes advice on introducing low-temperature cooking techniques and how to select specific ingredients. The device receives this nutritional advice and displays it on the app's "Recommended Menu" screen. Specific recipe examples are also displayed.

[0620] The user puts the suggested nutrition advice into practice and enters their results and progress into the app, which generates user feedback data. The server receives this feedback data and updates it in a database. The server then continuously generates advice based on the updated data, supporting the user's health management.

[0621] As a concrete example, consider the case where middle-aged male User A eats steak and grilled vegetables for lunch. User A enters these meal details into the app. The server receives this and calculates that the AGE generation amount for steak (cooked at high temperature) is 200, and for grilled vegetables (cooked at high temperature) is 100. Based on the total AGE intake of 300, it is determined that the risk is high, and a risk alert is sent. Next, the server suggests to User A that they use low-temperature cooking for steak and steamed vegetables. User A puts the recipe into practice based on this advice and enters the results into the app.

[0622] An example of a specific prompt sentence to input to the generative AI model is as follows:

[0623] User's dietary information: steak (cooked at high temperature), grilled vegetables (cooked at high temperature)

[0624] Past health data: high blood pressure, prediabetes

[0625] User's lifestyle: Sedentary work, lack of exercise

[0626] Suggest specific nutritional advice to this user, such as low-temperature cooking techniques or choosing specific ingredients.

[0627] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[0628] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0629] Step 1: Enter your meal information

[0630] User: Using a dedicated app, the user inputs the details of their daily meals. The input details include the names of ingredients, cooking methods, portions, and intake times. For example, for breakfast, the user inputs "fried eggs (cooked at high temperature), toast (fried)." This allows the user's dietary information to be collected. The input data is temporarily stored in a local database.

[0631] Step 2: Submit your meal information

[0632] Terminal: The terminal converts the meal information entered by the user into a standard data format (such as JSON format). This converted data is sent to the server via an HTTP request. The input is the meal information entered by the user, and the output is the meal information converted into JSON format.

[0633] Step 3: Save your meal information

[0634] Server: Saves the received meal information in a database (e.g., MySQL database). The input is meal information in JSON format, and the output is the meal information stored in the database. This saving process permanently saves the meal information in the database.

[0635] Step 4: Extracting meal information

[0636] Server: The server retrieves the meal information stored in the database at regular intervals using batch processing. For example, it retrieves the previous day's meal data every night at midnight. The input is the meal information stored in the database, and the output is the meal information extracted by batch processing.

[0637] Step 5: Calculate the amount of AGE produced

[0638] Server: The extracted meal information is input into a generative AI model (for example, a machine learning model using PyTorch) to calculate the amount of AGE generated based on each ingredient and cooking method. The input is the meal information, and the generative AI model processes the data. The output is the amount of AGE generated for each ingredient and cooking method. For example, the amount of AGE generated for fried eggs (cooked at high temperature) is calculated to be 100, and for toast (fried) it is calculated to be 50.

[0639] Step 6: Conduct a risk assessment

[0640] Server: Based on the calculated amount of AGE produced, calculates the user's total AGE intake and performs a risk assessment. The input is the amount of AGE produced for each ingredient and cooking method, and the output is the total AGE intake for each user and the risk assessment results. For example, a fried egg and toast combined results in an AGE intake of 150, which is determined to be a high risk level.

[0641] Step 7: Generate and send risk alerts

[0642] Server: If the risk assessment results in a high risk, it generates a risk alert. The risk alert contains a detailed risk explanation and a warning message. The generated risk alert is sent to the user's terminal via an HTTP request. The input is the risk assessment result, and the output is the risk alert message.

[0643] Step 8: View risk alerts

[0644] Device: The device stores the received risk alert locally and notifies the user using the app's notification function. The alert content is displayed on the app's notification screen. The input is the risk alert message, and the output is the notification displayed in the app.

[0645] Step 9: Generate and send nutrition advice

[0646] Server: The generative AI model proposes appropriate nutritional balance and dietary methods based on past health data and dietary information. Specifically, this includes introducing low-temperature cooking techniques and selecting specific ingredients. The server generates this nutritional advice and sends it to the device in JSON format. The input is past health data and dietary information, and the output is nutritional advice.

[0647] Step 10: View nutrition advice

[0648] Device: The device displays the received nutrition advice on the app's "Recommended Menu" screen. Specific recipe examples are also displayed. The input is the nutrition advice, and the output is the nutrition advice display within the app.

[0649] Step 11: Enter feedback data

[0650] User: The user puts the provided nutrition advice into practice and enters their results and progress into the app. The input data is temporarily stored in a local database. For example, the user might enter, "I tried making steamed vegetables and slow-cooked chicken."

[0651] Step 12: Submit and store feedback data

[0652] Terminal: The feedback data entered by the user is converted into a standard data format and sent to the server via an HTTP request. The server stores the received feedback data in a database. The input is the feedback data entered by the user, and the output is the feedback data stored in the database.

[0653] Step 13: Generating Ongoing Advice

[0654] Server: Based on the updated feedback data, the server continuously generates new nutrition advice using a generative AI model to analyze the user's health status and provide the next optimal advice. The input is the feedback data, and the output is the next nutrition advice.

[0655] In this way, the system provides personalized AGE risk management and nutrition advice for each user, supporting healthy aging.

[0656] (Application example 1)

[0657] 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."

[0658] In modern society, it is difficult to consistently consume a nutritionally balanced diet, and the risk of ingesting advanced glycation end products (AGEs) caused by high-temperature cooking is a particular concern. As a result, various health risks increase, so effective means are needed for users to manage their own diet and reduce these risks. It is also important to assess health risks in real time and provide personalized nutritional advice through food delivery services that users use on a daily basis. Current systems are unable to adequately resolve these issues.

[0659] 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.

[0660] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for automatically acquiring dietary information from the user's past order history, means for evaluating the amount of AGEs produced in real time when the user uses a food delivery service and displaying a risk alert, and means for providing customized recipe examples based on specific health advice. This allows users to have their health risks appropriately assessed and receive personalized nutritional advice even when using food delivery services.

[0661] A "user" is someone who uses this system to input dietary information and manage their health.

[0662] "Dietary information" refers to detailed information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[0663] A "database" is a data storage system for storing a user's dietary information, health data, and analysis results.

[0664] Advanced glycation end products (AGEs) are substances produced by high-temperature cooking and other processes, and their accumulation in the body can pose various health risks.

[0665] "Risk assessment" is the process of calculating the health risk to the user based on the amount of AGEs produced calculated based on dietary information.

[0666] "Risk Alerts" are notifications sent to users that include warnings about foods or cooking methods that are assessed as high risk.

[0667] "Nutrition advice" is information that suggests specific dietary methods and recipes for maintaining an appropriate nutritional balance based on the user's health condition and lifestyle.

[0668] "Order history" is a record of meals that a user has ordered in the past using a food delivery service.

[0669] "Real-time evaluation" is a process in which the amount of AGE production is instantly evaluated based on the meal selection made at the time a user uses a food delivery service.

[0670] "Customized recipes" are cooking methods and menus suggested based on specific health advice and tailored to the user's health condition and lifestyle.

[0671] This invention is a system that collects and analyzes a user's dietary information, evaluates the risk of accumulating advanced glycation end products (AGEs), and provides optimal nutritional advice. Specific embodiments of this system are described below.

[0672] System configuration

[0673] The system consists of three main components:

[0674] 1. User's device (terminal): This is assumed to be a smartphone or tablet with an application for entering meal information installed.

[0675] 2. Backend server: Built on the cloud, it stores and analyzes users' dietary and health data.

[0676] 3. Generative AI model: Using OpenAI GPT-4, the system calculates the amount of AGE production and provides personalized nutritional advice based on user data.

[0677] Program processing details

[0678] Collection of dietary data

[0679] Users use a dedicated app to input their daily meal plans. The app automatically captures specific information such as ingredients, cooking methods, portions, and consumption times. When users use food delivery services, meal information is automatically retrieved from their past order history.

[0680] Data analysis

[0681] The device converts the input dietary information into a standard data format and sends it to a backend server. The server extracts the dietary information stored in the database and uses a generative AI model to calculate the amount of AGEs generated based on each ingredient and cooking method. Based on the calculated data, the user's total AGE intake is calculated and a risk assessment is performed.

[0682] Providing risk alerts

[0683] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device and displayed in a dedicated app.

[0684] Generate nutrition advice

[0685] The server uses the AI ​​to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information. Specific advice is provided, such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients. The device displays customized recipes as examples.

[0686] Example

[0687] Example 1: Case of middle-aged male user A

[0688] 1. Dietary data collection:

[0689] User A orders "chicken curry and white rice" for lunch from a food delivery service.

[0690] The app automatically retrieves meal information for "chicken curry" and "white rice" from your order history.

[0691] 2. Data Analysis:

[0692] The server uses a generation AI to calculate the amount of AGEs produced by cooking chicken curry and white rice at high temperatures.

[0693] The total AGE intake was calculated and the risk for User A was assessed.

[0694] 3. Providing risk alerts:

[0695] Based on the risk assessment, the server generates a risk alert to User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[0696] An alert will be displayed on the device to notify the user.

[0697] 4. Generating nutrition advice:

[0698] The server's generation AI suggests menu examples using low-temperature cooking and the use of steamed vegetables to User A.

[0699] The device displays a specific recipe example: "Steamed vegetables and low-temperature cooked chicken."

[0700] Prompt Sentence Examples

[0701] text

[0702] Input: "Calculate the amount of AGEs produced by cooking chicken curry at high temperatures and assess the user's risk."

[0703] Response: "Cooking chicken curry at high temperatures produces a high amount of AGEs, and risk assessment indicates that your AGE intake is at high risk. Try combining it with steamed vegetables or cooking it at low temperatures."

[0704] This will enable users to properly assess health risks and receive personalized nutritional advice when using food delivery services.

[0705] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0706] Step 1:

[0707] Collection of dietary data

[0708] Users input their daily dietary information using a dedicated app.

[0709] Input: Information entered by the user about the ingredient name, cooking method, serving size, and time of consumption.

[0710] Output: Meal information stored in a standard data format.

[0711] The device implements an algorithm that automatically retrieves meal information from the order history of food delivery services.

[0712] Input: Food delivery order history.

[0713] Output: Meal information stored in a standard data format.

[0714] Step 2:

[0715] Sending data

[0716] The terminal converts the meal information obtained from the user into a standard data format and transmits it to the backend server.

[0717] Input: Meal information in a standard data format.

[0718] Output: Sending meal information to backend server.

[0719] Step 3:

[0720] Data storage

[0721] The server stores the received meal information in a database.

[0722] Input: Meal information sent from the device.

[0723] Output: Meal information stored in a database.

[0724] Step 4:

[0725] Data analysis

[0726] The server retrieves the meal information stored in the database and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method.

[0727] Input: Meal information stored in a database.

[0728] Output: Calculation result of AGE production amount.

[0729] The server calculates the user's total AGE intake based on the calculated amount of AGE produced and performs a risk assessment.

[0730] Input: Calculation result of AGE production amount.

[0731] Output: The result of the user's risk assessment.

[0732] Step 5:

[0733] Generate and send risk alerts

[0734] The server generates a risk alert if the result of the risk assessment indicates a high risk.

[0735] Input: Risk assessment results.

[0736] Output: Generate a risk alert.

[0737] The server transmits the generated risk alert to the user's terminal.

[0738] Input: Generated risk alert.

[0739] Output: Sending a risk alert to the device.

[0740] Step 6:

[0741] Viewing risk alerts

[0742] The device displays the received risk alert on a dedicated app and notifies the user.

[0743] Input: The risk alert sent by the server.

[0744] Output: Display of risk alert in the app.

[0745] Step 7:

[0746] Generate nutrition advice

[0747] The server uses a generative AI to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information.

[0748] Input: Historical health data and dietary information.

[0749] Output: The generated nutrition advice.

[0750] The server provides specific advice, including low-temperature cooking methods and how to choose specific ingredients to reduce the production of AGEs.

[0751] Input: The result of the user's risk assessment.

[0752] Output: Specific nutritional advice.

[0753] Step 8:

[0754] Displaying nutritional advice

[0755] The device displays the nutrition advice provided by the server on a dedicated app.

[0756] Input: Generated nutrition advice.

[0757] Output: Display of nutrition advice on a dedicated app.

[0758] Step 9:

[0759] Enter your feedback

[0760] The user puts the advice into practice and inputs the results as feedback into a dedicated app.

[0761] Input: Feedback information entered by the user.

[0762] Output: Feedback information stored in a standard data format.

[0763] Step 10:

[0764] Update data

[0765] The server updates the user's health data in the database based on the feedback data.

[0766] Input: Feedback information.

[0767] Output: Updated health data.

[0768] This allows the system to properly manage the user's dietary information and provide personalized nutritional advice to reduce health risks.

[0769] 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.

[0770] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[0771] Program processing

[0772] The system of the present invention is implemented as a series of processes involving a server, a terminal, a user, and an emotion engine.

[0773] Collection of dietary data

[0774] User: Uses a dedicated app to input meal information, including the name of ingredients, cooking method, portion size, and time of intake.

[0775] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[0776] Server: Stores the received meal information in a database.

[0777] Data analysis

[0778] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[0779] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[0780] Emotion recognition

[0781] Terminal: Using an emotion engine, emotions are recognized from the user's input, reactions, facial expressions, voice, etc.

[0782] Terminal: Sends the recognized emotion information to the server.

[0783] Providing risk alerts

[0784] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes the specific details of the risk and countermeasures.

[0785] Server: Adjust the wording of risk alerts based on the user's emotional state. For example, choose gentler words for a user who is feeling stressed.

[0786] Server: Sends the generated risk alerts to the user's device.

[0787] Device: The received risk alert is displayed in the app and notified to the user.

[0788] Generate nutrition advice

[0789] Server: Checks the user's health status based on the user's past health data and dietary information.

[0790] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[0791] Server: Adjust the wording and content of nutrition advice based on the user's emotional information, for example by adding words of praise to increase motivation.

[0792] Server: Sends the generated nutrition advice to the user's device.

[0793] Displaying and implementing nutrition advice

[0794] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[0795] User: Prepares and follows the advice.

[0796] Gathering feedback and updating data

[0797] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[0798] Terminal: Sends the input feedback data to the server.

[0799] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[0800] Ongoing Wellness Support

[0801] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[0802] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[0803] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[0804] Specific examples

[0805] Example 1: Case of middle-aged male user A

[0806] 1. Collection of dietary data

[0807] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[0808] 2. Data Analysis

[0809] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[0810] 3. Emotional Recognition

[0811] Device: The app analyzes User A's facial expressions using an emotion engine and recognizes that he or she is tired.

[0812] Device: Recognized emotion information is sent to the server.

[0813] 4. Providing risk alerts

[0814] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[0815] Server: Based on the emotional information indicating fatigue, the alert is expressed in gentle words: "Please be careful. High-temperature cooking can affect your health."

[0816] Device: An alert is displayed in the app and notifies User A.

[0817] 5. Generating nutrition advice

[0818] Server: The generating AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[0819] Server: Based on emotional information, we added encouraging words to the advice: "Keep it up! With a little effort, you can improve your health."

[0820] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[0821] 6. Providing wellness support

[0822] Device: User A practices the suggested recipe and enters the results into the app.

[0823] Server: Updates user A's health data based on feedback data and provides ongoing support.

[0824] In this way, the system provides personalized AGE risk management and nutrition advice for each user, and by incorporating emotional information, effectively supports users in achieving healthy aging.

[0825] The processing flow will be explained below.

[0826] Step 1: Collect dietary data

[0827] User: Opens the app and enters meal information, including the name (e.g., steak), cooking method (e.g., grilled), portion size (e.g., 200g), and time of consumption (e.g., 12:30).

[0828] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server according to the communication protocol.

[0829] Server: The received meal information is stored in a database. The stored data includes the user ID, meal date and time, ingredient list, cooking method, etc.

[0830] Step 2: Recognize emotions

[0831] Device: Activates the emotion engine and captures the user's facial expressions and voice using the camera and microphone.

[0832] On the device: The emotion engine analyzes the captured data and recognizes the user's emotional state (e.g., joy, sadness, stress).

[0833] Terminal: Adds the recognized emotion information to the client data and sends it to the server.

[0834] Step 3: Saving and Retrieving Data

[0835] Server: The received emotion information is associated with the user's data and stored in a database.

[0836] Server: Extracts the target user's dietary and emotional information from the database for analysis. Extraction is performed using SQL queries, etc.

[0837] Step 4: Calculate the amount of AGE produced

[0838] Server: Using the generation AI, calculate the amount of AGE generated for each ingredient and cooking method based on the extracted meal information. The calculation method is based on a predefined algorithm.

[0839] Server: Calculates the user's total AGE intake based on the calculation results and saves the data.

[0840] Step 5: Risk assessment

[0841] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[0842] Server: The results of the risk assessment are stored in a database and used as the basis for the next processing step.

[0843] Step 6: Generate and send risk alerts

[0844] Server: If a high risk is determined, a risk alert is generated. The alert includes a specific risk description and countermeasures.

[0845] Server: Adjusts the wording of risk alerts based on the user's emotional state. For example, if the user is recognized as being in a stressful state, it selects a gentler message, such as "Be careful. Cooking at high temperatures can affect your health."

[0846] Server: Sends the generated risk alerts to the user's device.

[0847] Device: The received risk alert is displayed in the app and notified to the user.

[0848] Step 7: Generate nutrition advice

[0849] Server: Checks the user's health status based on the user's past health data, current dietary data, and emotional data.

[0850] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods, including low-temperature cooking methods and specific ingredients that reduce AGE production.

[0851] Server: Adjust the wording and content of nutrition advice based on emotional information. For example, add words of praise to boost motivation, such as, "Keep it up! With just a few simple changes, you can improve your health."

[0852] Server: Sends the generated nutrition advice to the user's device.

[0853] Step 8: Provide and implement nutrition advice

[0854] Device: The received nutrition advice is displayed in the app, and specific advice and recipes are provided for the user to review.

[0855] User: Prepares and follows the provided advice on meals.

[0856] Step 9: Gather feedback and update data

[0857] User: Enter the results of the practice, as well as their physical condition and emotional state after eating and drinking, into the app.

[0858] Terminal: Sends the input feedback data to the server.

[0859] Server: Receives the feedback data and updates the database, which contains the user's latest health and emotional information.

[0860] Step 10: Ongoing Wellness Support

[0861] Server: Generates new nutrition advice based on the updated data and provides it to the user.

[0862] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[0863] Device: Provides ongoing advice and alerts to help users maintain a healthy lifestyle.

[0864] In this way, the system provides individualized AGE risk management and nutrition advice for each user, and by taking emotional information into account, it achieves more effective and personalized health support.

[0865] Example 2

[0866] 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."

[0867] Conventional health management systems are capable of calculating the amount of advanced glycation end products (AGEs) produced based on a user's dietary information, conducting risk assessments, and providing nutritional advice. However, because they provide uniform advice without taking the user's emotional state into consideration, there is a problem in that effective advice and risk alerts cannot be received depending on the user's emotional state. In particular, when users are under high stress or feeling fatigued, they tend to lose motivation to take appropriate health management and improve their diet. Therefore, there is a need for a system that provides more effective health support that takes the user's emotional state into consideration.

[0868] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for recognizing the user's emotions, means for sending a risk alert to the user based on the risk assessment and the user's emotions, and means for generating nutritional advice according to the user's health condition and emotional information and providing the advice to the user. This enables personalized risk alerts and nutritional advice that take the user's emotional state into consideration.

[0869] "User" refers to an individual who uses the system to input and review their own health management information and dietary information.

[0870] "Dietary information" refers to data on detailed dietary content such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[0871] "Database" refers to an information system for storing and managing various data, including dietary information, health information, and emotional information, entered by users.

[0872] Advanced glycation end products (AGEs) are substances that are produced when sugars and proteins in food ingredients combine during high-temperature cooking and have various adverse effects on the human body.

[0873] "Risk assessment" refers to the process of assessing and determining the user's health risk based on the calculated amount of AGE production and other health information.

[0874] "Emotion recognition" refers to the technology of identifying and determining a user's emotional state from their input, reactions, facial expressions, voice, etc.

[0875] "Risk alert" refers to a notification that warns or warns the user about health issues based on the results of a risk assessment.

[0876] "Nutrition advice" refers to advice that suggests appropriate diet and nutritional intake methods based on the user's health condition, dietary information, and emotional information.

[0877] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[0878] The present invention is implemented in a series of processes involving a server, a terminal, a user, and an emotion engine.

[0879] First, the user uses a dedicated app to input meal information. Specific items include the names of ingredients, cooking methods, portions, and time of consumption. For example, suppose the user inputs "200g steak and grilled vegetables (broccoli and carrots) for lunch." The device converts the input information into a standard data format (such as JSON) and sends it to the server via an HTTP request.

[0880] The server receives the HTTP request and stores it in a database in the format of "user ID, date and time, ingredient name, cooking method, and portion size." The server then extracts the meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE generated based on each ingredient and cooking method. For example, it obtains data such as "200g of steak generates 35mg of AGE, and grilled vegetables generates 15mg of AGE." The server then adds up the AGEs of each ingredient to calculate the total AGE intake (e.g., 50mg), and uses this to perform a risk assessment. It determines whether the diet is "high risk," "medium risk," or "low risk."

[0881] Furthermore, the device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, when a user shoots and sends a short video using their smartphone camera, the emotion engine analyzes the data, such as "fatigue 50%," and sends it to the server.

[0882] If the server determines that the risk assessment is "high risk" based on the total AGE intake and emotional data, it generates a risk alert stating that "high AGE intake poses a health risk." Here, the server takes into account the user's emotional information, and if the user feels "50% fatigued," for example, it changes the alert to a more gentle expression such as "Take care of your health when you are tired." The generated risk alert is sent to the user's device as an HTTP response, and the alert is displayed in the app's notification bar.

[0883] Next, the server checks the user's health status based on their past health data and dietary information. Using a generative AI model, it analyzes the user's health status and dietary information and suggests recipes such as "low-temperature cooked steak recipes" and "steamed vegetable recipes." It also adjusts the wording of the advice based on emotional data. For example, it might say, "This is an easy recipe to make even when you're tired. Good luck!"

[0884] The user prepares a meal using the provided "low-temperature cooked steak recipe" as a reference, and then cooks the meal. After the meal, the user opens the "Feedback" section in the app and enters their impressions, such as "It was delicious" or "I feel great," as well as their physical condition. The device converts the input feedback data into a standard data format and sends it to the server as an HTTP request. The server receives this, stores it in a database, and updates the user's health data.

[0885] Based on the updated data, the server generates new nutrition advice and sends the results to the user's device. If new risks are discovered, the server performs a risk assessment again and generates and sends risk alerts as necessary. The device continuously displays the latest advice and risk alerts on the app, supporting the user in living a healthy lifestyle.

[0886] Prompt Sentence Examples

[0887] "Generate risk alerts and nutritional advice for the user based on dietary data and emotional information. Ingredients: 200g steak and grilled vegetables. Emotion: 50% fatigue."

[0888] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0889] Step 1:

[0890] The user taps the "Enter Meal Information" button on the dedicated app screen and enters detailed meal information such as the ingredients, cooking method, portion size, and time of intake. For example, they might enter "200g steak, grilled vegetables (broccoli, carrots)."

[0891] Step 2:

[0892] The device receives the meal information entered by the user and converts it into a standard data format (e.g., JSON), which structures the information and prepares it for transmission to the server.

[0893] Step 3:

[0894] The device sends the converted data to the server in the form of an HTTP request, which includes the user ID, date and time, ingredient names, cooking methods, and quantities.

[0895] Step 4:

[0896] The server analyzes the received HTTP request and stores the meal information in a database, including the user ID, date and time, ingredient names, cooking methods, and serving sizes.

[0897] Step 5:

[0898] The server extracts meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE produced based on each ingredient and cooking method. For example, it can obtain results such as "200g of steak produces 35mg of AGE, and grilled vegetables produces 15mg of AGE."

[0899] Step 6:

[0900] The server calculates the total AGE intake by adding up the amount of AGE produced by each food ingredient based on the calculation results. For example, let's say a steak and grilled vegetables contain 50 mg of AGE combined. The server then performs a risk assessment based on the user's total AGE intake, determining whether they are at "high risk," "medium risk," or "low risk."

[0901] Step 7:

[0902] The device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, a user can shoot a short video with their smartphone camera and send it to obtain data such as "50% fatigue."

[0903] Step 8:

[0904] The device converts the recognized emotion data into a standard data format and sends it to the server. This request includes the user ID and the emotion recognition result.

[0905] Step 9:

[0906] The server receives the emotion data and generates a risk alert if the risk assessment results in a "high risk." For example, the alert might say, "High AGE intake poses a health risk."

[0907] Step 10:

[0908] The server adjusts the wording of the risk alert based on the user's emotional information. For example, if the user says "Feeling 50% fatigued," it will change the wording to something gentler, such as "Take care of your health when you're tired."

[0909] Step 11:

[0910] The server sends the generated risk alert to the user's device as an HTTP response.

[0911] Step 12:

[0912] The device will display the received risk alert in the app's notification bar and notify the user.

[0913] Step 13:

[0914] The server retrieves past health and dietary data from a database and uses a generative AI model to analyze the user's health status, suggesting recipes such as low-temperature cooked steak and steamed vegetables.

[0915] Step 14:

[0916] The server adjusts the content and wording of advice based on the emotional information, for example, "Here's a recipe that's easy to make even when you're tired. Good luck!"

[0917] Step 15:

[0918] The server sends the generated nutrition advice to the user's terminal as an HTTP response.

[0919] Step 16:

[0920] The device will display the received nutrition advice in the "Advice" section of the app, where users can view specific advice and recipes.

[0921] Step 17:

[0922] The user prepares and executes a meal based on the presented "low-temperature cooked steak recipe."

[0923] Step 18:

[0924] After eating, users open the "Feedback" section in the app and enter their impressions, such as "It was delicious" or "I feel great," as well as their physical condition.

[0925] Step 19:

[0926] The terminal converts the input feedback data into a standard data format and sends it to the server as an HTTP request.

[0927] Step 20:

[0928] The server receives the feedback data and stores it in a database to update the user's health data.

[0929] Step 21:

[0930] The server generates new nutrition advice based on the updated data and sends the results to the user's terminal.

[0931] Step 22:

[0932] If the server discovers any new risks, it will reassess them and generate and send risk alerts as necessary.

[0933] Step 23:

[0934] The device continuously displays the latest advice and risk alerts in the app, supporting users in living a healthy lifestyle.

[0935] (Application example 2)

[0936] 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."

[0937] Conventional dietary information analysis systems can assess the health risks posed by advanced glycation end products (AGEs) ingested by users and provide risk alerts and nutritional advice. However, they cannot take the user's emotional state into account, which means they are unable to provide effective health support. For example, a sudden health warning can be counterproductive for a stressed user, risking discouraging the user's motivation to improve their health. Therefore, there is a need for a health support system that takes the user's emotions into account.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0939] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for collecting emotional information about the user using an emotion engine that recognizes the user's emotions, means for adjusting the presentation of the risk alert based on the emotional information, and means for adjusting the content and presentation of the nutritional advice based on the emotional information. This enables more effective health support by providing risk alerts and nutritional advice that take the user's emotional state into consideration.

[0940] A "database" is a system for systematically storing information and for efficient searching and analysis.

[0941] "Meal information" is detailed information about the meal the user has eaten, such as the names of ingredients, cooking methods, and portions.

[0942] Advanced glycation end products (AGEs) are compounds that are produced by high-temperature cooking and accumulate in the body, posing a health risk.

[0943] A "risk alert" is a warning message that notifies the user of a health risk.

[0944] "Nutrition advice" refers to suggestions about appropriate diet and nutritional intake methods based on the user's health condition and lifestyle.

[0945] An "emotion engine" is a technology that recognizes and analyzes emotions from user input, reactions, facial expressions, voice, etc.

[0946] "Emotion information" is data about the user's emotional state as recognized by the emotion engine.

[0947] "Risk assessment" is the process of calculating the health risk for each user based on dietary information and the amount of AGE produced.

[0948] "Adjusting the expression method" means changing the content and display method of the message based on the user's emotional information.

[0949] This invention is based on a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. This system can also be combined with an emotion engine that recognizes the user's emotions, making it possible to adjust risk alerts and nutritional advice according to the user's emotions. Specific embodiments of this system are described below.

[0950] System Components

[0951] server

[0952] The server includes the following means:

[0953] 1. A means for having the user input meal information and storing the meal information in a database.

[0954] 2. A means of analyzing stored dietary information and calculating the amount of advanced glycation end products (AGEs) produced.

[0955] 3. A means of assessing risk for each user based on the calculated amount of AGE generated.

[0956] 4. A means of sending risk alerts to users based on risk assessment.

[0957] 5. A means for generating and providing nutritional advice tailored to the user's health and lifestyle.

[0958] 6. A means of collecting user emotion information using an emotion engine that recognizes user emotions.

[0959] 7. A means to tailor the wording of risk alerts based on sentiment information.

[0960] 8. Means of tailoring the content and presentation of nutrition advice based on emotional information.

[0961] Processing flow

[0962] Terminal

[0963] The device provides an application that allows users to input meal information. Through this application, information such as ingredient names, cooking methods, and portion sizes is collected and sent to a database. In addition, an emotion engine is used to recognize emotions from the user's input, reactions, facial expressions, and voice, and this information is also sent to the server.

[0964] server

[0965] The server analyzes the received meal information and uses a generation AI to calculate the amount of AGEs generated based on each ingredient and cooking method. It then calculates the user's total AGE intake and performs a risk assessment based on that information. If the risk assessment results in a high risk, a risk alert is generated and the presentation is adjusted based on the user's emotional information.

[0966] The server also generates nutrition advice based on the user's past health data and dietary information to suggest optimal nutritional balance and dietary methods. This includes low-temperature cooking methods that help reduce AGEs and how to select specific ingredients. Based on emotional information, the server adjusts the wording and content of the advice and provides it in an appropriate format for the user.

[0967] Specific examples

[0968] Example: Middle-aged male user

[0969] 1. Collection of dietary data

[0970] A user tells the app that they had steak and grilled vegetables for lunch, with the steak cooked at a high temperature and the vegetables cooked at the same time.

[0971] 2. Data Analysis

[0972] The server uses AI to calculate the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables, calculates the overall AGE intake, and assesses the user's risk.

[0973] 3. Emotional Recognition

[0974] The device uses an emotion engine to analyze the user's facial expressions through the app and recognizes that they are feeling tired.

[0975] 4. Providing risk alerts

[0976] Based on the risk assessment, the server generates a risk alert saying, "Caution is required as high-temperature cooking results in a high intake of AGEs." Based on the emotional information indicating fatigue, the alert is expressed in gentle words: "Be careful. High-temperature cooking can affect your health."

[0977] 5. Generating nutrition advice

[0978] The server suggests to the user how to cook steak using low-temperature cooking or how to use steamed vegetables. Based on the emotional information, the server adds encouraging words to the advice: "Good luck! A little effort will improve your health."

[0979] Prompt Sentence Examples

[0980] "The user ate the following ingredients: steak (cooked at high temperature), grilled vegetables (cooked at high temperature). The emotion was 'stress'. Please generate an alert and nutritional advice based on the risk assessment of AGE production and the emotion."

[0981] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0982] Step 1: Enter your meal data

[0983] The user inputs meal information through the application. Input items include the names of ingredients, cooking methods, and portions. Once this information is entered, the device converts it into a standard data format and sends it to the server. The input data is in the following format: {"Ingredient Name": "Steak", "Cooking Method": "High-Temperature Cooking", "Amount": "200g"}. The device calls an API to send this data.

[0984] Step 2: Enter emotion data

[0985] After inputting the meal information, the user inputs information related to their current emotional state. This input can be text, voice, or facial expression recognition. For example, they can upload a short comment or an image of their facial expression that indicates fatigue or stress. The device analyzes this information using an emotion engine and sends the results to the server. The input data is in the following format: {"emotion": "stress"}.

[0986] Step 3: Analyze dietary data

[0987] The server stores the received meal information in a database. It then uses a generative AI model to calculate the amount of AGEs produced based on each ingredient and cooking method. For example, it calculates the amount of AGEs produced by cooking a steak at high temperature, and adds them up to calculate the total AGE intake. The calculation result is in the following format: {"total AGE production": "1500 units"}.

[0988] Step 4: Risk assessment

[0989] The server performs a risk assessment for each user based on the total AGE generated in step 3. The risk assessment is judged to be high risk if it exceeds a certain threshold. For example, if the threshold is 1000 units, 1500 units is assessed as high risk. The assessment result is in the following format: {"Risk Assessment": "High Risk"}.

[0990] Step 5: Emotional Analysis

[0991] The server stores the emotion information received in step 2 in a database, and also stores the analysis results from the emotion engine. The emotion engine identifies emotions from the input text, voice, and facial expressions, and the analysis results are in the following format: {"emotion assessment": "stress"}.

[0992] Step 6: Generate a risk alert

[0993] The server generates a risk alert for the user based on the risk assessment and emotional information. For example, if the risk is assessed as high and the emotional information is "stress," a gentle warning is displayed. The message generated is "Be careful. Cooking at high temperatures can affect your health." The generated risk alert will be in the following format: {"risk alert": "Be careful. Cooking at high temperatures can affect your health"}.

[0994] Step 7: Generate nutrition advice

[0995] The server generates nutrition advice to suggest optimal nutritional balance and dietary methods based on the user's health status and past dietary data. This advice includes low-temperature cooking techniques and how to select specific ingredients, and also includes words of encouragement. The generated message is "Good luck! With a little effort, you can improve your health." The generated nutrition advice is in the following format: {"nutrition advice": "Try steamed vegetables and low-temperature cooked chicken. Good luck! With a little effort, you can improve your health"}.

[0996] Step 8: Providing risk alerts and nutritional advice

[0997] The server sends the generated risk alerts and nutrition advice to the user's device, which notifies and displays this information within the application. The user can check the alerts and advice and take necessary actions.

[0998] Through these steps, the system can manage the user's diet and emotional state as a whole and provide appropriate risk alerts and nutritional advice.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] [Third embodiment]

[1003] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1004] 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.

[1005] 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).

[1006] 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.

[1007] 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.

[1008] 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).

[1009] 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.

[1010] 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.

[1011] 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.

[1012] 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.

[1013] 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.

[1014] 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."

[1015] This invention is a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. It also provides optimal nutritional advice based on the user's health status and lifestyle, supporting the user in achieving healthy aging.

[1016] Program processing

[1017] The system of the present invention is implemented through a series of processes involving three parties: a server, a terminal, and a user.

[1018] Collection of dietary data

[1019] User: Using a dedicated app, the user enters information about their daily meals, including the names of ingredients, cooking methods, portions, and intake times.

[1020] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[1021] Server: Stores the received meal information in a database.

[1022] Data analysis

[1023] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[1024] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[1025] Providing risk alerts

[1026] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes a detailed risk description and a warning message.

[1027] Server: Sends the generated risk alerts to the user's device.

[1028] On the device: Display a risk alert in the user's app to notify the user.

[1029] Generate nutrition advice

[1030] Server: Based on the user's past health data and dietary information, the AI ​​checks their health condition and generates and proposes an appropriate nutritional balance and dietary plan.

[1031] Server: Provides specific advice such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients.

[1032] Nagetsu: Provides nutrition advice within the user's app, with specific recipes and actionable methods.

[1033] Providing wellness support

[1034] Device: The user puts the nutrition advice provided into practice and enters their results and progress into the app.

[1035] Server: Based on the feedback data, the database is updated to reflect the user's latest health status.

[1036] Server: Provides continuous advice based on updated data to support users in managing their health.

[1037] Specific examples

[1038] Example 1: Case of middle-aged male user A

[1039] 1. Collection of dietary data

[1040] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[1041] 2. Data Analysis

[1042] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[1043] 3. Providing risk alerts

[1044] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[1045] Device: An alert is displayed in the app and notifies User A.

[1046] 4. Generating nutrition advice

[1047] Server: The generative AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[1048] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[1049] 5. Providing wellness support

[1050] Device: User A practices the suggested recipe and enters the results into the app.

[1051] Server: Updates user A's health data based on feedback data and provides ongoing support.

[1052] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[1053] The processing flow will be explained below.

[1054] Step 1: Collect dietary data

[1055] User: Opens the dedicated app and enters meal information, including the names of ingredients, cooking methods, portions, and intake times.

[1056] Terminal: Processes the meal information entered by the user and converts it into a standard data format.

[1057] Terminal: Sends the converted meal information to the server.

[1058] Step 2: Save your data

[1059] Server: Receives the received meal information and stores it in a database.

[1060] Server: Adds metadata such as user ID, meal date and time, ingredient list, and cooking method to the saved meal information.

[1061] Step 3: Analyze the data

[1062] Server: Extracts the target user's meal information from the database and selects the necessary data using queries.

[1063] Server: Based on the meal information extracted by the generation AI, calculates the amount of AGE generated for each ingredient and cooking method. The calculation is performed according to the AGE generation amount calculation method.

[1064] Server: Based on the calculation results, calculate the user's total AGE intake.

[1065] Step 4: Risk assessment

[1066] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[1067] Server: Stores the results of the risk assessment in a database.

[1068] Step 5: Generate and send a risk alert

[1069] Server: If a high risk is determined, a risk alert is generated. The alert includes specific details of the risk and countermeasures.

[1070] Server: Sends the generated risk alerts to the user's device.

[1071] Device: The received risk alert is displayed in the app and notified to the user.

[1072] Step 6: Generate nutrition advice

[1073] Server: Checks the user's health status based on the user's past health data and dietary information.

[1074] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[1075] Server: Sends the generated nutrition advice to the user's device.

[1076] Step 7: Provide and implement nutrition advice

[1077] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[1078] User: Prepares and follows the advice.

[1079] Step 8: Gather feedback and update data

[1080] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[1081] Terminal: Sends the input feedback data to the server.

[1082] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[1083] Step 9: Ongoing Wellness Support

[1084] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[1085] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[1086] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[1087] In this way, the system provides personalized AGE risk management and nutrition advice to each user, effectively supporting them in achieving healthy aging.

[1088] Example 1

[1089] 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."

[1090] In today's busy lifestyles, it is difficult for users to fully understand the impact of their diet and cooking methods on their health and take appropriate measures. Furthermore, there are few systems that provide individualized healthy nutrition advice, particularly for managing the risk of advanced glycation end products (AGEs) accumulation caused by high-temperature cooking. Furthermore, there is a lack of methods for users to implement the advice they receive and receive ongoing feedback on the results to enable ongoing health management.

[1091] 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.

[1092] In this invention, the server includes means for having users input dietary information and storing the dietary information in a database, means for periodically retrieving the dietary information stored in the database by batch processing and calculating the amount of advanced glycation end products (AGEs) produced for each ingredient and cooking method, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, generating a risk alert for the user based on the results of the risk assessment, and transmitting the alert, means for generating nutritional advice tailored to the user's health condition and lifestyle based on the user's past health data and the input dietary information, and providing the advice to the user, and means for having the user input the results and progress of the nutritional advice put into practice by the user into the database and providing ongoing advice based on updated health data. This allows users to understand the impact of their diet on their health, receive appropriate risk management and personalized nutritional advice, and enable ongoing health management.

[1093] A "user" is an individual or entity that utilizes the system to input dietary information and follow the nutrition advice and risk alerts provided.

[1094] "Dietary information" refers to information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[1095] "Database" means an information management system for storing dietary information, health data, nutritional advice, and risk alerts entered by users.

[1096] "Batch processing" is a method of periodically retrieving data stored in a database and processing it all at once.

[1097] Advanced glycation end products (AGEs) are compounds produced when sugars and proteins in food react with each other. They are easily produced by high-temperature cooking and pose a risk to health.

[1098] "Risk assessment" is the process of assessing the health risk of a user based on the calculated amount of AGE production.

[1099] A "risk alert" is a message that warns the user about risks based on the results of risk assessment.

[1100] "Nutrition advice" is information that suggests optimal dietary and nutritional intake methods that are tailored to the user's health condition and lifestyle, based on the user's dietary information and health data.

[1101] A "prompt" is a sentence that is input to a generative AI model and is an instruction to generate advice or other output based on specific information.

[1102] A "generative AI model" is an artificial intelligence system that uses machine learning to analyze user data, calculate the amount of AGE production, and generate nutritional advice.

[1103] "Feedback data" refers to information entered into the app by users about the results and progress of the nutrition advice they have implemented.

[1104] This invention is a system that collects a user's dietary information, evaluates the risk of AGE accumulation due to high-temperature cooking, and provides optimal nutritional advice. This system is composed of three main components: a server, a terminal, and the user.

[1105] First, the user uses a dedicated application to input their daily dietary information. At this time, the user enters information such as "food name," "cooking method," "portion," and "time of intake" from the app's food record screen. For example, if the user has a fried egg (cooked at high temperature) and toast (fried) for breakfast, they enter that information into the app. This allows the user's dietary information to be collected.

[1106] Next, the device temporarily stores the meal information entered by the user locally and converts it into a standard data format (e.g., JSON). It then sends this to the server via an HTTP request. The server then stores the received meal information in a database. The database uses a common RDBMS (e.g., MySQL).

[1107] The server retrieves the dietary information stored in the database at regular intervals and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method. The generative AI model uses a machine learning model using, for example, PyTorch. This model can calculate the amount of AGE generated by a fried egg (cooked at high temperature) to be 100, and by toast (baked) to be 50. Based on these calculation results, the user's total AGE intake is calculated and a risk assessment is performed for each user.

[1108] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device via an HTTP request and displayed as a notification.

[1109] Furthermore, the server uses a generative AI model to suggest appropriate nutritional balance and dietary methods based on past health data and dietary information. For example, this includes advice on introducing low-temperature cooking techniques and how to select specific ingredients. The device receives this nutritional advice and displays it on the app's "Recommended Menu" screen. Specific recipe examples are also displayed.

[1110] The user puts the suggested nutrition advice into practice and enters their results and progress into the app, which generates user feedback data. The server receives this feedback data and updates it in a database. The server then continuously generates advice based on the updated data, supporting the user's health management.

[1111] As a concrete example, consider the case where middle-aged male User A eats steak and grilled vegetables for lunch. User A enters these meal details into the app. The server receives this and calculates that the AGE generation amount for steak (cooked at high temperature) is 200, and for grilled vegetables (cooked at high temperature) is 100. Based on the total AGE intake of 300, it is determined that the risk is high, and a risk alert is sent. Next, the server suggests to User A that they use low-temperature cooking for steak and steamed vegetables. User A puts the recipe into practice based on this advice and enters the results into the app.

[1112] An example of a specific prompt sentence to input to the generative AI model is as follows:

[1113] User's dietary information: steak (cooked at high temperature), grilled vegetables (cooked at high temperature)

[1114] Past health data: high blood pressure, prediabetes

[1115] User's lifestyle: Sedentary work, lack of exercise

[1116] Suggest specific nutritional advice to this user, such as low-temperature cooking techniques or choosing specific ingredients.

[1117] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[1118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1119] Step 1: Enter your meal information

[1120] User: Using a dedicated app, the user inputs the details of their daily meals. The input details include the names of ingredients, cooking methods, portions, and intake times. For example, for breakfast, the user inputs "fried eggs (cooked at high temperature), toast (fried)." This allows the user's dietary information to be collected. The input data is temporarily stored in a local database.

[1121] Step 2: Submit your meal information

[1122] Terminal: The terminal converts the meal information entered by the user into a standard data format (such as JSON format). This converted data is sent to the server via an HTTP request. The input is the meal information entered by the user, and the output is the meal information converted into JSON format.

[1123] Step 3: Save your meal information

[1124] Server: Saves the received meal information in a database (e.g., MySQL database). The input is meal information in JSON format, and the output is the meal information stored in the database. This saving process permanently saves the meal information in the database.

[1125] Step 4: Extracting meal information

[1126] Server: The server retrieves the meal information stored in the database at regular intervals using batch processing. For example, it retrieves the previous day's meal data every night at midnight. The input is the meal information stored in the database, and the output is the meal information extracted by batch processing.

[1127] Step 5: Calculate the amount of AGE produced

[1128] Server: The extracted meal information is input into a generative AI model (for example, a machine learning model using PyTorch) to calculate the amount of AGE generated based on each ingredient and cooking method. The input is the meal information, and the generative AI model processes the data. The output is the amount of AGE generated for each ingredient and cooking method. For example, the amount of AGE generated for fried eggs (cooked at high temperature) is calculated to be 100, and for toast (fried) it is calculated to be 50.

[1129] Step 6: Conduct a risk assessment

[1130] Server: Based on the calculated amount of AGE produced, calculates the user's total AGE intake and performs a risk assessment. The input is the amount of AGE produced for each ingredient and cooking method, and the output is the total AGE intake for each user and the risk assessment results. For example, a fried egg and toast combined results in an AGE intake of 150, which is determined to be a high risk level.

[1131] Step 7: Generate and send risk alerts

[1132] Server: If the risk assessment results in a high risk, it generates a risk alert. The risk alert contains a detailed risk explanation and a warning message. The generated risk alert is sent to the user's terminal via an HTTP request. The input is the risk assessment result, and the output is the risk alert message.

[1133] Step 8: View risk alerts

[1134] Device: The device stores the received risk alert locally and notifies the user using the app's notification function. The alert content is displayed on the app's notification screen. The input is the risk alert message, and the output is the notification displayed in the app.

[1135] Step 9: Generate and send nutrition advice

[1136] Server: The generative AI model proposes appropriate nutritional balance and dietary methods based on past health data and dietary information. Specifically, this includes introducing low-temperature cooking techniques and selecting specific ingredients. The server generates this nutritional advice and sends it to the device in JSON format. The input is past health data and dietary information, and the output is nutritional advice.

[1137] Step 10: View nutrition advice

[1138] Device: The device displays the received nutrition advice on the app's "Recommended Menu" screen. Specific recipe examples are also displayed. The input is the nutrition advice, and the output is the nutrition advice display within the app.

[1139] Step 11: Enter feedback data

[1140] User: The user puts the provided nutrition advice into practice and enters their results and progress into the app. The input data is temporarily stored in a local database. For example, the user might enter, "I tried making steamed vegetables and slow-cooked chicken."

[1141] Step 12: Submit and store feedback data

[1142] Terminal: The feedback data entered by the user is converted into a standard data format and sent to the server via an HTTP request. The server stores the received feedback data in a database. The input is the feedback data entered by the user, and the output is the feedback data stored in the database.

[1143] Step 13: Generating Ongoing Advice

[1144] Server: Based on the updated feedback data, the server continuously generates new nutrition advice using a generative AI model to analyze the user's health status and provide the next optimal advice. The input is the feedback data, and the output is the next nutrition advice.

[1145] In this way, the system provides personalized AGE risk management and nutrition advice for each user, supporting healthy aging.

[1146] (Application example 1)

[1147] 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."

[1148] In modern society, it is difficult to consistently consume a nutritionally balanced diet, and the risk of ingesting advanced glycation end products (AGEs) caused by high-temperature cooking is a particular concern. As a result, various health risks increase, so effective means are needed for users to manage their own diet and reduce these risks. It is also important to assess health risks in real time and provide personalized nutritional advice through food delivery services that users use on a daily basis. Current systems are unable to adequately resolve these issues.

[1149] 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.

[1150] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for automatically acquiring dietary information from the user's past order history, means for evaluating the amount of AGEs produced in real time when the user uses a food delivery service and displaying a risk alert, and means for providing customized recipe examples based on specific health advice. This allows users to have their health risks appropriately assessed and receive personalized nutritional advice even when using food delivery services.

[1151] A "user" is someone who uses this system to input dietary information and manage their health.

[1152] "Dietary information" refers to detailed information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[1153] A "database" is a data storage system for storing a user's dietary information, health data, and analysis results.

[1154] Advanced glycation end products (AGEs) are substances produced by high-temperature cooking and other processes, and their accumulation in the body can pose various health risks.

[1155] "Risk assessment" is the process of calculating the health risk to the user based on the amount of AGEs produced calculated based on dietary information.

[1156] "Risk Alerts" are notifications sent to users that include warnings about foods or cooking methods that are assessed as high risk.

[1157] "Nutrition advice" is information that suggests specific dietary methods and recipes for maintaining an appropriate nutritional balance based on the user's health condition and lifestyle.

[1158] "Order history" is a record of meals that a user has ordered in the past using a food delivery service.

[1159] "Real-time evaluation" is a process in which the amount of AGE production is instantly evaluated based on the meal selection made at the time a user uses a food delivery service.

[1160] "Customized recipes" are cooking methods and menus suggested based on specific health advice and tailored to the user's health condition and lifestyle.

[1161] This invention is a system that collects and analyzes a user's dietary information, evaluates the risk of accumulating advanced glycation end products (AGEs), and provides optimal nutritional advice. Specific embodiments of this system are described below.

[1162] System configuration

[1163] The system consists of three main components:

[1164] 1. User's device (terminal): This is assumed to be a smartphone or tablet with an application for entering meal information installed.

[1165] 2. Backend server: Built on the cloud, it stores and analyzes users' dietary and health data.

[1166] 3. Generative AI model: Using OpenAI GPT-4, the system calculates the amount of AGE production and provides personalized nutritional advice based on user data.

[1167] Program processing details

[1168] Collection of dietary data

[1169] Users use a dedicated app to input their daily meal plans. The app automatically captures specific information such as ingredients, cooking methods, portions, and consumption times. When users use food delivery services, meal information is automatically retrieved from their past order history.

[1170] Data analysis

[1171] The device converts the input dietary information into a standard data format and sends it to a backend server. The server extracts the dietary information stored in the database and uses a generative AI model to calculate the amount of AGEs generated based on each ingredient and cooking method. Based on the calculated data, the user's total AGE intake is calculated and a risk assessment is performed.

[1172] Providing risk alerts

[1173] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device and displayed in a dedicated app.

[1174] Generate nutrition advice

[1175] The server uses the AI ​​to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information. Specific advice is provided, such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients. The device displays customized recipes as examples.

[1176] Example

[1177] Example 1: Case of middle-aged male user A

[1178] 1. Dietary data collection:

[1179] User A orders "chicken curry and white rice" for lunch from a food delivery service.

[1180] The app automatically retrieves meal information for "chicken curry" and "white rice" from your order history.

[1181] 2. Data Analysis:

[1182] The server uses a generation AI to calculate the amount of AGEs produced by cooking chicken curry and white rice at high temperatures.

[1183] The total AGE intake was calculated and the risk for User A was assessed.

[1184] 3. Providing risk alerts:

[1185] Based on the risk assessment, the server generates a risk alert to User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[1186] An alert will be displayed on the device to notify the user.

[1187] 4. Generating nutrition advice:

[1188] The server's generation AI suggests menu examples using low-temperature cooking and the use of steamed vegetables to User A.

[1189] The device displays a specific recipe example: "Steamed vegetables and low-temperature cooked chicken."

[1190] Prompt Sentence Examples

[1191] text

[1192] Input: "Calculate the amount of AGEs produced by cooking chicken curry at high temperatures and assess the user's risk."

[1193] Response: "Cooking chicken curry at high temperatures produces a high amount of AGEs, and risk assessment indicates that your AGE intake is at high risk. Try combining it with steamed vegetables or cooking it at low temperatures."

[1194] This will enable users to properly assess health risks and receive personalized nutritional advice when using food delivery services.

[1195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1196] Step 1:

[1197] Collection of dietary data

[1198] Users input their daily dietary information using a dedicated app.

[1199] Input: Information entered by the user about the ingredient name, cooking method, serving size, and time of consumption.

[1200] Output: Meal information stored in a standard data format.

[1201] The device implements an algorithm that automatically retrieves meal information from the order history of food delivery services.

[1202] Input: Food delivery order history.

[1203] Output: Meal information stored in a standard data format.

[1204] Step 2:

[1205] Sending data

[1206] The terminal converts the meal information obtained from the user into a standard data format and transmits it to the backend server.

[1207] Input: Meal information in a standard data format.

[1208] Output: Sending meal information to backend server.

[1209] Step 3:

[1210] Data storage

[1211] The server stores the received meal information in a database.

[1212] Input: Meal information sent from the device.

[1213] Output: Meal information stored in a database.

[1214] Step 4:

[1215] Data analysis

[1216] The server retrieves the meal information stored in the database and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method.

[1217] Input: Meal information stored in a database.

[1218] Output: Calculation result of AGE production amount.

[1219] The server calculates the user's total AGE intake based on the calculated amount of AGE produced and performs a risk assessment.

[1220] Input: Calculation result of AGE production amount.

[1221] Output: The result of the user's risk assessment.

[1222] Step 5:

[1223] Generate and send risk alerts

[1224] The server generates a risk alert if the result of the risk assessment indicates a high risk.

[1225] Input: Risk assessment results.

[1226] Output: Generate a risk alert.

[1227] The server transmits the generated risk alert to the user's terminal.

[1228] Input: Generated risk alert.

[1229] Output: Sending a risk alert to the device.

[1230] Step 6:

[1231] Viewing risk alerts

[1232] The device displays the received risk alert on a dedicated app and notifies the user.

[1233] Input: The risk alert sent by the server.

[1234] Output: Display of risk alert in the app.

[1235] Step 7:

[1236] Generate nutrition advice

[1237] The server uses a generative AI to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information.

[1238] Input: Historical health data and dietary information.

[1239] Output: The generated nutrition advice.

[1240] The server provides specific advice, including low-temperature cooking methods and how to choose specific ingredients to reduce the production of AGEs.

[1241] Input: The result of the user's risk assessment.

[1242] Output: Specific nutritional advice.

[1243] Step 8:

[1244] Displaying nutritional advice

[1245] The device displays the nutrition advice provided by the server on a dedicated app.

[1246] Input: Generated nutrition advice.

[1247] Output: Display of nutrition advice on a dedicated app.

[1248] Step 9:

[1249] Enter your feedback

[1250] The user puts the advice into practice and inputs the results as feedback into a dedicated app.

[1251] Input: Feedback information entered by the user.

[1252] Output: Feedback information stored in a standard data format.

[1253] Step 10:

[1254] Update data

[1255] The server updates the user's health data in the database based on the feedback data.

[1256] Input: Feedback information.

[1257] Output: Updated health data.

[1258] This allows the system to properly manage the user's dietary information and provide personalized nutritional advice to reduce health risks.

[1259] 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.

[1260] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[1261] Program processing

[1262] The system of the present invention is implemented as a series of processes involving a server, a terminal, a user, and an emotion engine.

[1263] Collection of dietary data

[1264] User: Uses a dedicated app to input meal information, including the name of ingredients, cooking method, portion size, and time of intake.

[1265] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[1266] Server: Stores the received meal information in a database.

[1267] Data analysis

[1268] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[1269] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[1270] Emotion recognition

[1271] Terminal: Using an emotion engine, emotions are recognized from the user's input, reactions, facial expressions, voice, etc.

[1272] Terminal: Sends the recognized emotion information to the server.

[1273] Providing risk alerts

[1274] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes the specific details of the risk and countermeasures.

[1275] Server: Adjust the wording of risk alerts based on the user's emotional state. For example, choose gentler words for a user who is feeling stressed.

[1276] Server: Sends the generated risk alerts to the user's device.

[1277] Device: The received risk alert is displayed in the app and notified to the user.

[1278] Generate nutrition advice

[1279] Server: Checks the user's health status based on the user's past health data and dietary information.

[1280] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[1281] Server: Adjust the wording and content of nutrition advice based on the user's emotional information, for example by adding words of praise to increase motivation.

[1282] Server: Sends the generated nutrition advice to the user's device.

[1283] Displaying and implementing nutrition advice

[1284] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[1285] User: Prepares and follows the advice.

[1286] Gathering feedback and updating data

[1287] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[1288] Terminal: Sends the input feedback data to the server.

[1289] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[1290] Ongoing Wellness Support

[1291] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[1292] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[1293] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[1294] Specific examples

[1295] Example 1: Case of middle-aged male user A

[1296] 1. Collection of dietary data

[1297] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[1298] 2. Data Analysis

[1299] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[1300] 3. Emotional Recognition

[1301] Device: The app analyzes User A's facial expressions using an emotion engine and recognizes that he or she is tired.

[1302] Device: Recognized emotion information is sent to the server.

[1303] 4. Providing risk alerts

[1304] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[1305] Server: Based on the emotional information indicating fatigue, the alert is expressed in gentle words: "Please be careful. High-temperature cooking can affect your health."

[1306] Device: An alert is displayed in the app and notifies User A.

[1307] 5. Generating nutrition advice

[1308] Server: The generating AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[1309] Server: Based on emotional information, we added encouraging words to the advice: "Keep it up! With a little effort, you can improve your health."

[1310] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[1311] 6. Providing wellness support

[1312] Device: User A practices the suggested recipe and enters the results into the app.

[1313] Server: Updates user A's health data based on feedback data and provides ongoing support.

[1314] In this way, the system provides personalized AGE risk management and nutrition advice for each user, and by incorporating emotional information, effectively supports users in achieving healthy aging.

[1315] The processing flow will be explained below.

[1316] Step 1: Collect dietary data

[1317] User: Opens the app and enters meal information, including the name (e.g., steak), cooking method (e.g., grilled), portion size (e.g., 200g), and time of consumption (e.g., 12:30).

[1318] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server according to the communication protocol.

[1319] Server: The received meal information is stored in a database. The stored data includes the user ID, meal date and time, ingredient list, cooking method, etc.

[1320] Step 2: Recognize emotions

[1321] Device: Activates the emotion engine and captures the user's facial expressions and voice using the camera and microphone.

[1322] On the device: The emotion engine analyzes the captured data and recognizes the user's emotional state (e.g., joy, sadness, stress).

[1323] Terminal: Adds the recognized emotion information to the client data and sends it to the server.

[1324] Step 3: Saving and Retrieving Data

[1325] Server: The received emotion information is associated with the user's data and stored in a database.

[1326] Server: Extracts the target user's dietary and emotional information from the database for analysis. Extraction is performed using SQL queries, etc.

[1327] Step 4: Calculate the amount of AGE produced

[1328] Server: Using the generation AI, calculate the amount of AGE generated for each ingredient and cooking method based on the extracted meal information. The calculation method is based on a predefined algorithm.

[1329] Server: Calculates the user's total AGE intake based on the calculation results and saves the data.

[1330] Step 5: Risk assessment

[1331] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[1332] Server: The results of the risk assessment are stored in a database and used as the basis for the next processing step.

[1333] Step 6: Generate and send risk alerts

[1334] Server: If a high risk is determined, a risk alert is generated. The alert includes a specific risk description and countermeasures.

[1335] Server: Adjusts the wording of risk alerts based on the user's emotional state. For example, if the user is recognized as being in a stressful state, it selects a gentler message, such as "Be careful. Cooking at high temperatures can affect your health."

[1336] Server: Sends the generated risk alerts to the user's device.

[1337] Device: The received risk alert is displayed in the app and notified to the user.

[1338] Step 7: Generate nutrition advice

[1339] Server: Checks the user's health status based on the user's past health data, current dietary data, and emotional data.

[1340] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods, including low-temperature cooking methods and specific ingredients that reduce AGE production.

[1341] Server: Adjust the wording and content of nutrition advice based on emotional information. For example, add words of praise to boost motivation, such as, "Keep it up! With just a few simple changes, you can improve your health."

[1342] Server: Sends the generated nutrition advice to the user's device.

[1343] Step 8: Provide and implement nutrition advice

[1344] Device: The received nutrition advice is displayed in the app, and specific advice and recipes are provided for the user to review.

[1345] User: Prepares and follows the provided advice on meals.

[1346] Step 9: Gather feedback and update data

[1347] User: Enter the results of the practice, as well as their physical condition and emotional state after eating and drinking, into the app.

[1348] Terminal: Sends the input feedback data to the server.

[1349] Server: Receives the feedback data and updates the database, which contains the user's latest health and emotional information.

[1350] Step 10: Ongoing Wellness Support

[1351] Server: Generates new nutrition advice based on the updated data and provides it to the user.

[1352] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[1353] Device: Provides ongoing advice and alerts to help users maintain a healthy lifestyle.

[1354] In this way, the system provides individualized AGE risk management and nutrition advice for each user, and by taking emotional information into account, it achieves more effective and personalized health support.

[1355] Example 2

[1356] 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."

[1357] Conventional health management systems are capable of calculating the amount of advanced glycation end products (AGEs) produced based on a user's dietary information, conducting risk assessments, and providing nutritional advice. However, because they provide uniform advice without taking the user's emotional state into consideration, there is a problem in that effective advice and risk alerts cannot be received depending on the user's emotional state. In particular, when users are under high stress or feeling fatigued, they tend to lose motivation to take appropriate health management and improve their diet. Therefore, there is a need for a system that provides more effective health support that takes the user's emotional state into consideration.

[1358] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for recognizing the user's emotions, means for sending a risk alert to the user based on the risk assessment and the user's emotions, and means for generating nutritional advice according to the user's health condition and emotional information and providing the advice to the user. This enables personalized risk alerts and nutritional advice that take the user's emotional state into consideration.

[1359] "User" refers to an individual who uses the system to input and review their own health management information and dietary information.

[1360] "Dietary information" refers to data on detailed dietary content such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[1361] "Database" refers to an information system for storing and managing various data, including dietary information, health information, and emotional information, entered by users.

[1362] Advanced glycation end products (AGEs) are substances that are produced when sugars and proteins in food ingredients combine during high-temperature cooking and have various adverse effects on the human body.

[1363] "Risk assessment" refers to the process of assessing and determining the user's health risk based on the calculated amount of AGE production and other health information.

[1364] "Emotion recognition" refers to the technology of identifying and determining a user's emotional state from their input, reactions, facial expressions, voice, etc.

[1365] "Risk alert" refers to a notification that warns or warns the user about health issues based on the results of a risk assessment.

[1366] "Nutrition advice" refers to advice that suggests appropriate diet and nutritional intake methods based on the user's health condition, dietary information, and emotional information.

[1367] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[1368] The present invention is implemented in a series of processes involving a server, a terminal, a user, and an emotion engine.

[1369] First, the user uses a dedicated app to input meal information. Specific items include the names of ingredients, cooking methods, portions, and time of consumption. For example, suppose the user inputs "200g steak and grilled vegetables (broccoli and carrots) for lunch." The device converts the input information into a standard data format (such as JSON) and sends it to the server via an HTTP request.

[1370] The server receives the HTTP request and stores it in a database in the format of "user ID, date and time, ingredient name, cooking method, and portion size." The server then extracts the meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE generated based on each ingredient and cooking method. For example, it obtains data such as "200g of steak generates 35mg of AGE, and grilled vegetables generates 15mg of AGE." The server then adds up the AGEs of each ingredient to calculate the total AGE intake (e.g., 50mg), and uses this to perform a risk assessment. It determines whether the diet is "high risk," "medium risk," or "low risk."

[1371] Furthermore, the device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, when a user shoots and sends a short video using their smartphone camera, the emotion engine analyzes the data, such as "fatigue 50%," and sends it to the server.

[1372] If the server determines that the risk assessment is "high risk" based on the total AGE intake and emotional data, it generates a risk alert stating that "high AGE intake poses a health risk." Here, the server takes into account the user's emotional information, and if the user feels "50% fatigued," for example, it changes the alert to a more gentle expression such as "Take care of your health when you are tired." The generated risk alert is sent to the user's device as an HTTP response, and the alert is displayed in the app's notification bar.

[1373] Next, the server checks the user's health status based on their past health data and dietary information. Using a generative AI model, it analyzes the user's health status and dietary information and suggests recipes such as "low-temperature cooked steak recipes" and "steamed vegetable recipes." It also adjusts the wording of the advice based on emotional data. For example, it might say, "This is an easy recipe to make even when you're tired. Good luck!"

[1374] The user prepares a meal using the provided "low-temperature cooked steak recipe" as a reference, and then cooks the meal. After the meal, the user opens the "Feedback" section in the app and enters their impressions, such as "It was delicious" or "I feel great," as well as their physical condition. The device converts the input feedback data into a standard data format and sends it to the server as an HTTP request. The server receives this, stores it in a database, and updates the user's health data.

[1375] Based on the updated data, the server generates new nutrition advice and sends the results to the user's device. If new risks are discovered, the server performs a risk assessment again and generates and sends risk alerts as necessary. The device continuously displays the latest advice and risk alerts on the app, supporting the user in living a healthy lifestyle.

[1376] Prompt Sentence Examples

[1377] "Generate risk alerts and nutritional advice for the user based on dietary data and emotional information. Ingredients: 200g steak and grilled vegetables. Emotion: 50% fatigue."

[1378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1379] Step 1:

[1380] The user taps the "Enter Meal Information" button on the dedicated app screen and enters detailed meal information such as the ingredients, cooking method, portion size, and time of intake. For example, they might enter "200g steak, grilled vegetables (broccoli, carrots)."

[1381] Step 2:

[1382] The device receives the meal information entered by the user and converts it into a standard data format (e.g., JSON), which structures the information and prepares it for transmission to the server.

[1383] Step 3:

[1384] The device sends the converted data to the server in the form of an HTTP request, which includes the user ID, date and time, ingredient names, cooking methods, and quantities.

[1385] Step 4:

[1386] The server analyzes the received HTTP request and stores the meal information in a database, including the user ID, date and time, ingredient names, cooking methods, and serving sizes.

[1387] Step 5:

[1388] The server extracts meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE produced based on each ingredient and cooking method. For example, it can obtain results such as "200g of steak produces 35mg of AGE, and grilled vegetables produces 15mg of AGE."

[1389] Step 6:

[1390] The server calculates the total AGE intake by adding up the amount of AGE produced by each food ingredient based on the calculation results. For example, let's say a steak and grilled vegetables contain 50 mg of AGE combined. The server then performs a risk assessment based on the user's total AGE intake, determining whether they are at "high risk," "medium risk," or "low risk."

[1391] Step 7:

[1392] The device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, a user can shoot a short video with their smartphone camera and send it to obtain data such as "50% fatigue."

[1393] Step 8:

[1394] The device converts the recognized emotion data into a standard data format and sends it to the server. This request includes the user ID and the emotion recognition result.

[1395] Step 9:

[1396] The server receives the emotion data and generates a risk alert if the risk assessment results in a "high risk." For example, the alert might say, "High AGE intake poses a health risk."

[1397] Step 10:

[1398] The server adjusts the wording of the risk alert based on the user's emotional information. For example, if the user says "Feeling 50% fatigued," it will change the wording to something gentler, such as "Take care of your health when you're tired."

[1399] Step 11:

[1400] The server sends the generated risk alert to the user's device as an HTTP response.

[1401] Step 12:

[1402] The device will display the received risk alert in the app's notification bar and notify the user.

[1403] Step 13:

[1404] The server retrieves past health and dietary data from a database and uses a generative AI model to analyze the user's health status, suggesting recipes such as low-temperature cooked steak and steamed vegetables.

[1405] Step 14:

[1406] The server adjusts the content and wording of advice based on the emotional information, for example, "Here's a recipe that's easy to make even when you're tired. Good luck!"

[1407] Step 15:

[1408] The server sends the generated nutrition advice to the user's terminal as an HTTP response.

[1409] Step 16:

[1410] The device will display the received nutrition advice in the "Advice" section of the app, where users can view specific advice and recipes.

[1411] Step 17:

[1412] The user prepares and executes a meal based on the presented "low-temperature cooked steak recipe."

[1413] Step 18:

[1414] After eating, users open the "Feedback" section in the app and enter their impressions, such as "It was delicious" or "I feel great," as well as their physical condition.

[1415] Step 19:

[1416] The terminal converts the input feedback data into a standard data format and sends it to the server as an HTTP request.

[1417] Step 20:

[1418] The server receives the feedback data and stores it in a database to update the user's health data.

[1419] Step 21:

[1420] The server generates new nutrition advice based on the updated data and sends the results to the user's terminal.

[1421] Step 22:

[1422] If the server discovers any new risks, it will reassess them and generate and send risk alerts as necessary.

[1423] Step 23:

[1424] The device continuously displays the latest advice and risk alerts in the app, supporting users in living a healthy lifestyle.

[1425] (Application example 2)

[1426] 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."

[1427] Conventional dietary information analysis systems can assess the health risks posed by advanced glycation end products (AGEs) ingested by users and provide risk alerts and nutritional advice. However, they cannot take the user's emotional state into account, which means they are unable to provide effective health support. For example, a sudden health warning can be counterproductive for a stressed user, risking discouraging the user's motivation to improve their health. Therefore, there is a need for a health support system that takes the user's emotions into account.

[1428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1429] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for collecting emotional information about the user using an emotion engine that recognizes the user's emotions, means for adjusting the presentation of the risk alert based on the emotional information, and means for adjusting the content and presentation of the nutritional advice based on the emotional information. This enables more effective health support by providing risk alerts and nutritional advice that take the user's emotional state into consideration.

[1430] A "database" is a system for systematically storing information and for efficient searching and analysis.

[1431] "Meal information" is detailed information about the meal the user has eaten, such as the names of ingredients, cooking methods, and portions.

[1432] Advanced glycation end products (AGEs) are compounds that are produced by high-temperature cooking and accumulate in the body, posing a health risk.

[1433] A "risk alert" is a warning message that notifies the user of a health risk.

[1434] "Nutrition advice" refers to suggestions about appropriate diet and nutritional intake methods based on the user's health condition and lifestyle.

[1435] An "emotion engine" is a technology that recognizes and analyzes emotions from user input, reactions, facial expressions, voice, etc.

[1436] "Emotion information" is data about the user's emotional state as recognized by the emotion engine.

[1437] "Risk assessment" is the process of calculating the health risk for each user based on dietary information and the amount of AGE produced.

[1438] "Adjusting the expression method" means changing the content and display method of the message based on the user's emotional information.

[1439] This invention is based on a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. This system can also be combined with an emotion engine that recognizes the user's emotions, making it possible to adjust risk alerts and nutritional advice according to the user's emotions. Specific embodiments of this system are described below.

[1440] System Components

[1441] server

[1442] The server includes the following means:

[1443] 1. A means for having the user input meal information and storing the meal information in a database.

[1444] 2. A means of analyzing stored dietary information and calculating the amount of advanced glycation end products (AGEs) produced.

[1445] 3. A means of assessing risk for each user based on the calculated amount of AGE generated.

[1446] 4. A means of sending risk alerts to users based on risk assessment.

[1447] 5. A means for generating and providing nutritional advice tailored to the user's health and lifestyle.

[1448] 6. A means of collecting user emotion information using an emotion engine that recognizes user emotions.

[1449] 7. A means to tailor the wording of risk alerts based on sentiment information.

[1450] 8. Means of tailoring the content and presentation of nutrition advice based on emotional information.

[1451] Processing flow

[1452] Terminal

[1453] The device provides an application that allows users to input meal information. Through this application, information such as ingredient names, cooking methods, and portion sizes is collected and sent to a database. In addition, an emotion engine is used to recognize emotions from the user's input, reactions, facial expressions, and voice, and this information is also sent to the server.

[1454] server

[1455] The server analyzes the received meal information and uses a generation AI to calculate the amount of AGEs generated based on each ingredient and cooking method. It then calculates the user's total AGE intake and performs a risk assessment based on that information. If the risk assessment results in a high risk, a risk alert is generated and the presentation is adjusted based on the user's emotional information.

[1456] The server also generates nutrition advice based on the user's past health data and dietary information to suggest optimal nutritional balance and dietary methods. This includes low-temperature cooking methods that help reduce AGEs and how to select specific ingredients. Based on emotional information, the server adjusts the wording and content of the advice and provides it in an appropriate format for the user.

[1457] Specific examples

[1458] Example: Middle-aged male user

[1459] 1. Collection of dietary data

[1460] A user tells the app that they had steak and grilled vegetables for lunch, with the steak cooked at a high temperature and the vegetables cooked at the same time.

[1461] 2. Data Analysis

[1462] The server uses AI to calculate the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables, calculates the overall AGE intake, and assesses the user's risk.

[1463] 3. Emotional Recognition

[1464] The device uses an emotion engine to analyze the user's facial expressions through the app and recognizes that they are feeling tired.

[1465] 4. Providing risk alerts

[1466] Based on the risk assessment, the server generates a risk alert saying, "Caution is required as high-temperature cooking results in a high intake of AGEs." Based on the emotional information indicating fatigue, the alert is expressed in gentle words: "Be careful. High-temperature cooking can affect your health."

[1467] 5. Generating nutrition advice

[1468] The server suggests to the user how to cook steak using low-temperature cooking or how to use steamed vegetables. Based on the emotional information, the server adds encouraging words to the advice: "Good luck! A little effort will improve your health."

[1469] Prompt Sentence Examples

[1470] "The user ate the following ingredients: steak (cooked at high temperature), grilled vegetables (cooked at high temperature). The emotion was 'stress'. Please generate an alert and nutritional advice based on the risk assessment of AGE production and the emotion."

[1471] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1472] Step 1: Enter your meal data

[1473] The user inputs meal information through the application. Input items include the names of ingredients, cooking methods, and portions. Once this information is entered, the device converts it into a standard data format and sends it to the server. The input data is in the following format: {"Ingredient Name": "Steak", "Cooking Method": "High-Temperature Cooking", "Amount": "200g"}. The device calls an API to send this data.

[1474] Step 2: Enter emotion data

[1475] After inputting the meal information, the user inputs information related to their current emotional state. This input can be text, voice, or facial expression recognition. For example, they can upload a short comment or an image of their facial expression that indicates fatigue or stress. The device analyzes this information using an emotion engine and sends the results to the server. The input data is in the following format: {"emotion": "stress"}.

[1476] Step 3: Analyze dietary data

[1477] The server stores the received meal information in a database. It then uses a generative AI model to calculate the amount of AGEs produced based on each ingredient and cooking method. For example, it calculates the amount of AGEs produced by cooking a steak at high temperature, and adds them up to calculate the total AGE intake. The calculation result is in the following format: {"total AGE production": "1500 units"}.

[1478] Step 4: Risk assessment

[1479] The server performs a risk assessment for each user based on the total AGE generated in step 3. The risk assessment is judged to be high risk if it exceeds a certain threshold. For example, if the threshold is 1000 units, 1500 units is assessed as high risk. The assessment result is in the following format: {"Risk Assessment": "High Risk"}.

[1480] Step 5: Emotional Analysis

[1481] The server stores the emotion information received in step 2 in a database, and also stores the analysis results from the emotion engine. The emotion engine identifies emotions from the input text, voice, and facial expressions, and the analysis results are in the following format: {"emotion assessment": "stress"}.

[1482] Step 6: Generate a risk alert

[1483] The server generates a risk alert for the user based on the risk assessment and emotional information. For example, if the risk is assessed as high and the emotional information is "stress," a gentle warning is displayed. The message generated is "Be careful. Cooking at high temperatures can affect your health." The generated risk alert will be in the following format: {"risk alert": "Be careful. Cooking at high temperatures can affect your health"}.

[1484] Step 7: Generate nutrition advice

[1485] The server generates nutrition advice to suggest optimal nutritional balance and dietary methods based on the user's health status and past dietary data. This advice includes low-temperature cooking techniques and how to select specific ingredients, and also includes words of encouragement. The generated message is "Good luck! With a little effort, you can improve your health." The generated nutrition advice is in the following format: {"nutrition advice": "Try steamed vegetables and low-temperature cooked chicken. Good luck! With a little effort, you can improve your health"}.

[1486] Step 8: Providing risk alerts and nutritional advice

[1487] The server sends the generated risk alerts and nutrition advice to the user's device, which notifies and displays this information within the application. The user can check the alerts and advice and take necessary actions.

[1488] Through these steps, the system can manage the user's diet and emotional state as a whole and provide appropriate risk alerts and nutritional advice.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] [Fourth embodiment]

[1493] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1494] 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.

[1495] 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).

[1496] 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.

[1497] 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.

[1498] 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).

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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."

[1506] This invention is a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. It also provides optimal nutritional advice based on the user's health status and lifestyle, supporting the user in achieving healthy aging.

[1507] Program processing

[1508] The system of the present invention is implemented through a series of processes involving three parties: a server, a terminal, and a user.

[1509] Collection of dietary data

[1510] User: Using a dedicated app, the user enters information about their daily meals, including the names of ingredients, cooking methods, portions, and intake times.

[1511] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[1512] Server: Stores the received meal information in a database.

[1513] Data analysis

[1514] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[1515] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[1516] Providing risk alerts

[1517] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes a detailed risk description and a warning message.

[1518] Server: Sends the generated risk alerts to the user's device.

[1519] On the device: Display a risk alert in the user's app to notify the user.

[1520] Generate nutrition advice

[1521] Server: Based on the user's past health data and dietary information, the AI ​​checks their health condition and generates and proposes an appropriate nutritional balance and dietary plan.

[1522] Server: Provides specific advice such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients.

[1523] Nagetsu: Provides nutrition advice within the user's app, with specific recipes and actionable methods.

[1524] Providing wellness support

[1525] Device: The user puts the nutrition advice provided into practice and enters their results and progress into the app.

[1526] Server: Based on the feedback data, the database is updated to reflect the user's latest health status.

[1527] Server: Provides continuous advice based on updated data to support users in managing their health.

[1528] Specific examples

[1529] Example 1: Case of middle-aged male user A

[1530] 1. Collection of dietary data

[1531] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[1532] 2. Data Analysis

[1533] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[1534] 3. Providing risk alerts

[1535] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[1536] Device: An alert is displayed in the app and notifies User A.

[1537] 4. Generating nutrition advice

[1538] Server: The generative AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[1539] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[1540] 5. Providing wellness support

[1541] Device: User A practices the suggested recipe and enters the results into the app.

[1542] Server: Updates user A's health data based on feedback data and provides ongoing support.

[1543] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[1544] The processing flow will be explained below.

[1545] Step 1: Collect dietary data

[1546] User: Opens the dedicated app and enters meal information, including the names of ingredients, cooking methods, portions, and intake times.

[1547] Terminal: Processes the meal information entered by the user and converts it into a standard data format.

[1548] Terminal: Sends the converted meal information to the server.

[1549] Step 2: Save your data

[1550] Server: Receives the received meal information and stores it in a database.

[1551] Server: Adds metadata such as user ID, meal date and time, ingredient list, and cooking method to the saved meal information.

[1552] Step 3: Analyze the data

[1553] Server: Extracts the target user's meal information from the database and selects the necessary data using queries.

[1554] Server: Based on the meal information extracted by the generation AI, calculates the amount of AGE generated for each ingredient and cooking method. The calculation is performed according to the AGE generation amount calculation method.

[1555] Server: Based on the calculation results, calculate the user's total AGE intake.

[1556] Step 4: Risk assessment

[1557] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[1558] Server: Stores the results of the risk assessment in a database.

[1559] Step 5: Generate and send a risk alert

[1560] Server: If a high risk is determined, a risk alert is generated. The alert includes specific details of the risk and countermeasures.

[1561] Server: Sends the generated risk alerts to the user's device.

[1562] Device: The received risk alert is displayed in the app and notified to the user.

[1563] Step 6: Generate nutrition advice

[1564] Server: Checks the user's health status based on the user's past health data and dietary information.

[1565] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[1566] Server: Sends the generated nutrition advice to the user's device.

[1567] Step 7: Provide and implement nutrition advice

[1568] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[1569] User: Prepares and follows the advice.

[1570] Step 8: Gather feedback and update data

[1571] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[1572] Terminal: Sends the input feedback data to the server.

[1573] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[1574] Step 9: Ongoing Wellness Support

[1575] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[1576] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[1577] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[1578] In this way, the system provides personalized AGE risk management and nutrition advice to each user, effectively supporting them in achieving healthy aging.

[1579] Example 1

[1580] 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."

[1581] In today's busy lifestyles, it is difficult for users to fully understand the impact of their diet and cooking methods on their health and take appropriate measures. Furthermore, there are few systems that provide individualized healthy nutrition advice, particularly for managing the risk of advanced glycation end products (AGEs) accumulation caused by high-temperature cooking. Furthermore, there is a lack of methods for users to implement the advice they receive and receive ongoing feedback on the results to enable ongoing health management.

[1582] 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.

[1583] In this invention, the server includes means for having users input dietary information and storing the dietary information in a database, means for periodically retrieving the dietary information stored in the database by batch processing and calculating the amount of advanced glycation end products (AGEs) produced for each ingredient and cooking method, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, generating a risk alert for the user based on the results of the risk assessment, and transmitting the alert, means for generating nutritional advice tailored to the user's health condition and lifestyle based on the user's past health data and the input dietary information, and providing the advice to the user, and means for having the user input the results and progress of the nutritional advice put into practice by the user into the database and providing ongoing advice based on updated health data. This allows users to understand the impact of their diet on their health, receive appropriate risk management and personalized nutritional advice, and enable ongoing health management.

[1584] A "user" is an individual or entity that utilizes the system to input dietary information and follow the nutrition advice and risk alerts provided.

[1585] "Dietary information" refers to information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[1586] "Database" means an information management system for storing dietary information, health data, nutritional advice, and risk alerts entered by users.

[1587] "Batch processing" is a method of periodically retrieving data stored in a database and processing it all at once.

[1588] Advanced glycation end products (AGEs) are compounds produced when sugars and proteins in food react with each other. They are easily produced by high-temperature cooking and pose a risk to health.

[1589] "Risk assessment" is the process of assessing the health risk of a user based on the calculated amount of AGE production.

[1590] A "risk alert" is a message that warns the user about risks based on the results of risk assessment.

[1591] "Nutrition advice" is information that suggests optimal dietary and nutritional intake methods that are tailored to the user's health condition and lifestyle, based on the user's dietary information and health data.

[1592] A "prompt" is a sentence that is input to a generative AI model and is an instruction to generate advice or other output based on specific information.

[1593] A "generative AI model" is an artificial intelligence system that uses machine learning to analyze user data, calculate the amount of AGE production, and generate nutritional advice.

[1594] "Feedback data" refers to information entered into the app by users about the results and progress of the nutrition advice they have implemented.

[1595] This invention is a system that collects a user's dietary information, evaluates the risk of AGE accumulation due to high-temperature cooking, and provides optimal nutritional advice. This system is composed of three main components: a server, a terminal, and the user.

[1596] First, the user uses a dedicated application to input their daily dietary information. At this time, the user enters information such as "food name," "cooking method," "portion," and "time of intake" from the app's food record screen. For example, if the user has a fried egg (cooked at high temperature) and toast (fried) for breakfast, they enter that information into the app. This allows the user's dietary information to be collected.

[1597] Next, the device temporarily stores the meal information entered by the user locally and converts it into a standard data format (e.g., JSON). It then sends this to the server via an HTTP request. The server then stores the received meal information in a database. The database uses a common RDBMS (e.g., MySQL).

[1598] The server retrieves the dietary information stored in the database at regular intervals and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method. The generative AI model uses a machine learning model using, for example, PyTorch. This model can calculate the amount of AGE generated by a fried egg (cooked at high temperature) to be 100, and by toast (baked) to be 50. Based on these calculation results, the user's total AGE intake is calculated and a risk assessment is performed for each user.

[1599] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device via an HTTP request and displayed as a notification.

[1600] Furthermore, the server uses a generative AI model to suggest appropriate nutritional balance and dietary methods based on past health data and dietary information. For example, this includes advice on introducing low-temperature cooking techniques and how to select specific ingredients. The device receives this nutritional advice and displays it on the app's "Recommended Menu" screen. Specific recipe examples are also displayed.

[1601] The user puts the suggested nutrition advice into practice and enters their results and progress into the app, which generates user feedback data. The server receives this feedback data and updates it in a database. The server then continuously generates advice based on the updated data, supporting the user's health management.

[1602] As a concrete example, consider the case where middle-aged male User A eats steak and grilled vegetables for lunch. User A enters these meal details into the app. The server receives this and calculates that the AGE generation amount for steak (cooked at high temperature) is 200, and for grilled vegetables (cooked at high temperature) is 100. Based on the total AGE intake of 300, it is determined that the risk is high, and a risk alert is sent. Next, the server suggests to User A that they use low-temperature cooking for steak and steamed vegetables. User A puts the recipe into practice based on this advice and enters the results into the app.

[1603] An example of a specific prompt sentence to input to the generative AI model is as follows:

[1604] User's dietary information: steak (cooked at high temperature), grilled vegetables (cooked at high temperature)

[1605] Past health data: high blood pressure, prediabetes

[1606] User's lifestyle: Sedentary work, lack of exercise

[1607] Suggest specific nutritional advice to this user, such as low-temperature cooking techniques or choosing specific ingredients.

[1608] In this way, the system provides users with personalized AGE risk management and nutritional advice to support healthy aging.

[1609] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1610] Step 1: Enter your meal information

[1611] User: Using a dedicated app, the user inputs the details of their daily meals. The input details include the names of ingredients, cooking methods, portions, and intake times. For example, for breakfast, the user inputs "fried eggs (cooked at high temperature), toast (fried)." This allows the user's dietary information to be collected. The input data is temporarily stored in a local database.

[1612] Step 2: Submit your meal information

[1613] Terminal: The terminal converts the meal information entered by the user into a standard data format (such as JSON format). This converted data is sent to the server via an HTTP request. The input is the meal information entered by the user, and the output is the meal information converted into JSON format.

[1614] Step 3: Save your meal information

[1615] Server: Saves the received meal information in a database (e.g., MySQL database). The input is meal information in JSON format, and the output is the meal information stored in the database. This saving process permanently saves the meal information in the database.

[1616] Step 4: Extracting meal information

[1617] Server: The server retrieves the meal information stored in the database at regular intervals using batch processing. For example, it retrieves the previous day's meal data every night at midnight. The input is the meal information stored in the database, and the output is the meal information extracted by batch processing.

[1618] Step 5: Calculate the amount of AGE produced

[1619] Server: The extracted meal information is input into a generative AI model (for example, a machine learning model using PyTorch) to calculate the amount of AGE generated based on each ingredient and cooking method. The input is the meal information, and the generative AI model processes the data. The output is the amount of AGE generated for each ingredient and cooking method. For example, the amount of AGE generated for fried eggs (cooked at high temperature) is calculated to be 100, and for toast (fried) it is calculated to be 50.

[1620] Step 6: Conduct a risk assessment

[1621] Server: Based on the calculated amount of AGE produced, calculates the user's total AGE intake and performs a risk assessment. The input is the amount of AGE produced for each ingredient and cooking method, and the output is the total AGE intake for each user and the risk assessment results. For example, a fried egg and toast combined results in an AGE intake of 150, which is determined to be a high risk level.

[1622] Step 7: Generate and send risk alerts

[1623] Server: If the risk assessment results in a high risk, it generates a risk alert. The risk alert contains a detailed risk explanation and a warning message. The generated risk alert is sent to the user's terminal via an HTTP request. The input is the risk assessment result, and the output is the risk alert message.

[1624] Step 8: View risk alerts

[1625] Device: The device stores the received risk alert locally and notifies the user using the app's notification function. The alert content is displayed on the app's notification screen. The input is the risk alert message, and the output is the notification displayed in the app.

[1626] Step 9: Generate and send nutrition advice

[1627] Server: The generative AI model proposes appropriate nutritional balance and dietary methods based on past health data and dietary information. Specifically, this includes introducing low-temperature cooking techniques and selecting specific ingredients. The server generates this nutritional advice and sends it to the device in JSON format. The input is past health data and dietary information, and the output is nutritional advice.

[1628] Step 10: View nutrition advice

[1629] Device: The device displays the received nutrition advice on the app's "Recommended Menu" screen. Specific recipe examples are also displayed. The input is the nutrition advice, and the output is the nutrition advice display within the app.

[1630] Step 11: Enter feedback data

[1631] User: The user puts the provided nutrition advice into practice and enters their results and progress into the app. The input data is temporarily stored in a local database. For example, the user might enter, "I tried making steamed vegetables and slow-cooked chicken."

[1632] Step 12: Submit and store feedback data

[1633] Terminal: The feedback data entered by the user is converted into a standard data format and sent to the server via an HTTP request. The server stores the received feedback data in a database. The input is the feedback data entered by the user, and the output is the feedback data stored in the database.

[1634] Step 13: Generating Ongoing Advice

[1635] Server: Based on the updated feedback data, the server continuously generates new nutrition advice using a generative AI model to analyze the user's health status and provide the next optimal advice. The input is the feedback data, and the output is the next nutrition advice.

[1636] In this way, the system provides personalized AGE risk management and nutrition advice for each user, supporting healthy aging.

[1637] (Application example 1)

[1638] 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."

[1639] In modern society, it is difficult to consistently consume a nutritionally balanced diet, and the risk of ingesting advanced glycation end products (AGEs) caused by high-temperature cooking is a particular concern. As a result, various health risks increase, so effective means are needed for users to manage their own diet and reduce these risks. It is also important to assess health risks in real time and provide personalized nutritional advice through food delivery services that users use on a daily basis. Current systems are unable to adequately resolve these issues.

[1640] 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.

[1641] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for conducting a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for automatically acquiring dietary information from the user's past order history, means for evaluating the amount of AGEs produced in real time when the user uses a food delivery service and displaying a risk alert, and means for providing customized recipe examples based on specific health advice. This allows users to have their health risks appropriately assessed and receive personalized nutritional advice even when using food delivery services.

[1642] A "user" is someone who uses this system to input dietary information and manage their health.

[1643] "Dietary information" refers to detailed information such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[1644] A "database" is a data storage system for storing a user's dietary information, health data, and analysis results.

[1645] Advanced glycation end products (AGEs) are substances produced by high-temperature cooking and other processes, and their accumulation in the body can pose various health risks.

[1646] "Risk assessment" is the process of calculating the health risk to the user based on the amount of AGEs produced calculated based on dietary information.

[1647] "Risk Alerts" are notifications sent to users that include warnings about foods or cooking methods that are assessed as high risk.

[1648] "Nutrition advice" is information that suggests specific dietary methods and recipes for maintaining an appropriate nutritional balance based on the user's health condition and lifestyle.

[1649] "Order history" is a record of meals that a user has ordered in the past using a food delivery service.

[1650] "Real-time evaluation" is a process in which the amount of AGE production is instantly evaluated based on the meal selection made at the time a user uses a food delivery service.

[1651] "Customized recipes" are cooking methods and menus suggested based on specific health advice and tailored to the user's health condition and lifestyle.

[1652] This invention is a system that collects and analyzes a user's dietary information, evaluates the risk of accumulating advanced glycation end products (AGEs), and provides optimal nutritional advice. Specific embodiments of this system are described below.

[1653] System configuration

[1654] The system consists of three main components:

[1655] 1. User's device (terminal): This is assumed to be a smartphone or tablet with an application for entering meal information installed.

[1656] 2. Backend server: Built on the cloud, it stores and analyzes users' dietary and health data.

[1657] 3. Generative AI model: Using OpenAI GPT-4, the system calculates the amount of AGE production and provides personalized nutritional advice based on user data.

[1658] Program processing details

[1659] Collection of dietary data

[1660] Users use a dedicated app to input their daily meal plans. The app automatically captures specific information such as ingredients, cooking methods, portions, and consumption times. When users use food delivery services, meal information is automatically retrieved from their past order history.

[1661] Data analysis

[1662] The device converts the input dietary information into a standard data format and sends it to a backend server. The server extracts the dietary information stored in the database and uses a generative AI model to calculate the amount of AGEs generated based on each ingredient and cooking method. Based on the calculated data, the user's total AGE intake is calculated and a risk assessment is performed.

[1663] Providing risk alerts

[1664] If the risk assessment results in a high risk, the server generates a risk alert, which includes a detailed risk description and a warning message. The generated risk alert is sent to the user's device and displayed in a dedicated app.

[1665] Generate nutrition advice

[1666] The server uses the AI ​​to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information. Specific advice is provided, such as low-temperature cooking methods to suppress the production of AGEs and how to select specific ingredients. The device displays customized recipes as examples.

[1667] Example

[1668] Example 1: Case of middle-aged male user A

[1669] 1. Dietary data collection:

[1670] User A orders "chicken curry and white rice" for lunch from a food delivery service.

[1671] The app automatically retrieves meal information for "chicken curry" and "white rice" from your order history.

[1672] 2. Data Analysis:

[1673] The server uses a generation AI to calculate the amount of AGEs produced by cooking chicken curry and white rice at high temperatures.

[1674] The total AGE intake was calculated and the risk for User A was assessed.

[1675] 3. Providing risk alerts:

[1676] Based on the risk assessment, the server generates a risk alert to User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[1677] An alert will be displayed on the device to notify the user.

[1678] 4. Generating nutrition advice:

[1679] The server's generation AI suggests menu examples using low-temperature cooking and the use of steamed vegetables to User A.

[1680] The device displays a specific recipe example: "Steamed vegetables and low-temperature cooked chicken."

[1681] Prompt Sentence Examples

[1682] text

[1683] Input: "Calculate the amount of AGEs produced by cooking chicken curry at high temperatures and assess the user's risk."

[1684] Response: "Cooking chicken curry at high temperatures produces a high amount of AGEs, and risk assessment indicates that your AGE intake is at high risk. Try combining it with steamed vegetables or cooking it at low temperatures."

[1685] This will enable users to properly assess health risks and receive personalized nutritional advice when using food delivery services.

[1686] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1687] Step 1:

[1688] Collection of dietary data

[1689] Users input their daily dietary information using a dedicated app.

[1690] Input: Information entered by the user about the ingredient name, cooking method, serving size, and time of consumption.

[1691] Output: Meal information stored in a standard data format.

[1692] The device implements an algorithm that automatically retrieves meal information from the order history of food delivery services.

[1693] Input: Food delivery order history.

[1694] Output: Meal information stored in a standard data format.

[1695] Step 2:

[1696] Sending data

[1697] The terminal converts the meal information obtained from the user into a standard data format and transmits it to the backend server.

[1698] Input: Meal information in a standard data format.

[1699] Output: Sending meal information to backend server.

[1700] Step 3:

[1701] Data storage

[1702] The server stores the received meal information in a database.

[1703] Input: Meal information sent from the device.

[1704] Output: Meal information stored in a database.

[1705] Step 4:

[1706] Data analysis

[1707] The server retrieves the meal information stored in the database and uses a generative AI model to calculate the amount of AGE generated based on each ingredient and cooking method.

[1708] Input: Meal information stored in a database.

[1709] Output: Calculation result of AGE production amount.

[1710] The server calculates the user's total AGE intake based on the calculated amount of AGE produced and performs a risk assessment.

[1711] Input: Calculation result of AGE production amount.

[1712] Output: The result of the user's risk assessment.

[1713] Step 5:

[1714] Generate and send risk alerts

[1715] The server generates a risk alert if the result of the risk assessment indicates a high risk.

[1716] Input: Risk assessment results.

[1717] Output: Generate a risk alert.

[1718] The server transmits the generated risk alert to the user's terminal.

[1719] Input: Generated risk alert.

[1720] Output: Sending a risk alert to the device.

[1721] Step 6:

[1722] Viewing risk alerts

[1723] The device displays the received risk alert on a dedicated app and notifies the user.

[1724] Input: The risk alert sent by the server.

[1725] Output: Display of risk alert in the app.

[1726] Step 7:

[1727] Generate nutrition advice

[1728] The server uses a generative AI to suggest appropriate nutritional balance and dietary methods based on the user's past health data and dietary information.

[1729] Input: Historical health data and dietary information.

[1730] Output: The generated nutrition advice.

[1731] The server provides specific advice, including low-temperature cooking methods and how to choose specific ingredients to reduce the production of AGEs.

[1732] Input: The result of the user's risk assessment.

[1733] Output: Specific nutritional advice.

[1734] Step 8:

[1735] Displaying nutritional advice

[1736] The device displays the nutrition advice provided by the server on a dedicated app.

[1737] Input: Generated nutrition advice.

[1738] Output: Display of nutrition advice on a dedicated app.

[1739] Step 9:

[1740] Enter your feedback

[1741] The user puts the advice into practice and inputs the results as feedback into a dedicated app.

[1742] Input: Feedback information entered by the user.

[1743] Output: Feedback information stored in a standard data format.

[1744] Step 10:

[1745] Update data

[1746] The server updates the user's health data in the database based on the feedback data.

[1747] Input: Feedback information.

[1748] Output: Updated health data.

[1749] This allows the system to properly manage the user's dietary information and provide personalized nutritional advice to reduce health risks.

[1750] 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.

[1751] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[1752] Program processing

[1753] The system of the present invention is implemented as a series of processes involving a server, a terminal, a user, and an emotion engine.

[1754] Collection of dietary data

[1755] User: Uses a dedicated app to input meal information, including the name of ingredients, cooking method, portion size, and time of intake.

[1756] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server.

[1757] Server: Stores the received meal information in a database.

[1758] Data analysis

[1759] Server: Extracts the meal information stored in the database and uses generation AI to calculate the amount of AGE generated based on each ingredient and cooking method.

[1760] Server: Based on the calculation results, calculate the user's total AGE intake and perform a risk assessment for the user based on that information.

[1761] Emotion recognition

[1762] Terminal: Using an emotion engine, emotions are recognized from the user's input, reactions, facial expressions, voice, etc.

[1763] Terminal: Sends the recognized emotion information to the server.

[1764] Providing risk alerts

[1765] Server: If the risk assessment results in a high risk, it generates a risk alert, which includes the specific details of the risk and countermeasures.

[1766] Server: Adjust the wording of risk alerts based on the user's emotional state. For example, choose gentler words for a user who is feeling stressed.

[1767] Server: Sends the generated risk alerts to the user's device.

[1768] Device: The received risk alert is displayed in the app and notified to the user.

[1769] Generate nutrition advice

[1770] Server: Checks the user's health status based on the user's past health data and dietary information.

[1771] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods. Suggestions include low-temperature cooking methods that help reduce AGEs and how to select specific ingredients.

[1772] Server: Adjust the wording and content of nutrition advice based on the user's emotional information, for example by adding words of praise to increase motivation.

[1773] Server: Sends the generated nutrition advice to the user's device.

[1774] Displaying and implementing nutrition advice

[1775] Device: The received nutrition advice is displayed in the app, where users can check specific advice and recipes.

[1776] User: Prepares and follows the advice.

[1777] Gathering feedback and updating data

[1778] User: Enter the results of the exercise and their physical condition after eating and drinking into the app.

[1779] Terminal: Sends the input feedback data to the server.

[1780] Server: Receives the feedback data and updates the database, which contains the user's latest health information.

[1781] Ongoing Wellness Support

[1782] Server: Based on the updated data, generate new nutrition advice and provide it to the user.

[1783] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[1784] Device: Continuously displays advice and alerts to help users live a healthier lifestyle.

[1785] Specific examples

[1786] Example 1: Case of middle-aged male user A

[1787] 1. Collection of dietary data

[1788] User A: Enters into the app that he had steak and grilled vegetables for lunch. The steak was cooked at a high temperature, as were the grilled vegetables.

[1789] 2. Data Analysis

[1790] Server: The AI ​​calculates the amount of AGEs generated by high-temperature cooking of steak and grilled vegetables. It calculates the overall amount of AGE intake and assesses the risk for User A.

[1791] 3. Emotional Recognition

[1792] Device: The app analyzes User A's facial expressions using an emotion engine and recognizes that he or she is tired.

[1793] Device: Recognized emotion information is sent to the server.

[1794] 4. Providing risk alerts

[1795] Server: Based on the risk assessment, a risk alert is generated for User A stating, "Caution is required as high-temperature cooking results in a high intake of AGEs."

[1796] Server: Based on the emotional information indicating fatigue, the alert is expressed in gentle words: "Please be careful. High-temperature cooking can affect your health."

[1797] Device: An alert is displayed in the app and notifies User A.

[1798] 5. Generating nutrition advice

[1799] Server: The generating AI suggests to User A how to cook steak using low-temperature cooking and how to use steamed vegetables.

[1800] Server: Based on emotional information, we added encouraging words to the advice: "Keep it up! With a little effort, you can improve your health."

[1801] Terminal: A specific recipe example is presented: "Steamed vegetables and low-temperature cooked chicken."

[1802] 6. Providing wellness support

[1803] Device: User A practices the suggested recipe and enters the results into the app.

[1804] Server: Updates user A's health data based on feedback data and provides ongoing support.

[1805] In this way, the system provides personalized AGE risk management and nutrition advice for each user, and by incorporating emotional information, effectively supports users in achieving healthy aging.

[1806] The processing flow will be explained below.

[1807] Step 1: Collect dietary data

[1808] User: Opens the app and enters meal information, including the name (e.g., steak), cooking method (e.g., grilled), portion size (e.g., 200g), and time of consumption (e.g., 12:30).

[1809] Terminal: Converts the meal information entered by the user into a standard data format and sends it to the server according to the communication protocol.

[1810] Server: The received meal information is stored in a database. The stored data includes the user ID, meal date and time, ingredient list, cooking method, etc.

[1811] Step 2: Recognize emotions

[1812] Device: Activates the emotion engine and captures the user's facial expressions and voice using the camera and microphone.

[1813] On the device: The emotion engine analyzes the captured data and recognizes the user's emotional state (e.g., joy, sadness, stress).

[1814] Terminal: Adds the recognized emotion information to the client data and sends it to the server.

[1815] Step 3: Saving and Retrieving Data

[1816] Server: The received emotion information is associated with the user's data and stored in a database.

[1817] Server: Extracts the target user's dietary and emotional information from the database for analysis. Extraction is performed using SQL queries, etc.

[1818] Step 4: Calculate the amount of AGE produced

[1819] Server: Using the generation AI, calculate the amount of AGE generated for each ingredient and cooking method based on the extracted meal information. The calculation method is based on a predefined algorithm.

[1820] Server: Calculates the user's total AGE intake based on the calculation results and saves the data.

[1821] Step 5: Risk assessment

[1822] Server: Conducts a risk assessment of the user based on the total amount of AGE intake. Based on the assessment criteria, the risk is determined as high, medium, or low.

[1823] Server: The results of the risk assessment are stored in a database and used as the basis for the next processing step.

[1824] Step 6: Generate and send risk alerts

[1825] Server: If a high risk is determined, a risk alert is generated. The alert includes a specific risk description and countermeasures.

[1826] Server: Adjusts the wording of risk alerts based on the user's emotional state. For example, if the user is recognized as being in a stressful state, it selects a gentler message, such as "Be careful. Cooking at high temperatures can affect your health."

[1827] Server: Sends the generated risk alerts to the user's device.

[1828] Device: The received risk alert is displayed in the app and notified to the user.

[1829] Step 7: Generate nutrition advice

[1830] Server: Checks the user's health status based on the user's past health data, current dietary data, and emotional data.

[1831] Server: The AI ​​analyzes the user's health condition and dietary information and suggests optimal nutritional balance and dietary methods, including low-temperature cooking methods and specific ingredients that reduce AGE production.

[1832] Server: Adjust the wording and content of nutrition advice based on emotional information. For example, add words of praise to boost motivation, such as, "Keep it up! With just a few simple changes, you can improve your health."

[1833] Server: Sends the generated nutrition advice to the user's device.

[1834] Step 8: Provide and implement nutrition advice

[1835] Device: The received nutrition advice is displayed in the app, and specific advice and recipes are provided for the user to review.

[1836] User: Prepares and follows the provided advice on meals.

[1837] Step 9: Gather feedback and update data

[1838] User: Enter the results of the practice, as well as their physical condition and emotional state after eating and drinking, into the app.

[1839] Terminal: Sends the input feedback data to the server.

[1840] Server: Receives the feedback data and updates the database, which contains the user's latest health and emotional information.

[1841] Step 10: Ongoing Wellness Support

[1842] Server: Generates new nutrition advice based on the updated data and provides it to the user.

[1843] Server: Re-performs risk assessments as needed and sends risk alerts if new risks are discovered.

[1844] Device: Provides ongoing advice and alerts to help users maintain a healthy lifestyle.

[1845] In this way, the system provides individualized AGE risk management and nutrition advice for each user, and by taking emotional information into account, it achieves more effective and personalized health support.

[1846] Example 2

[1847] 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."

[1848] Conventional health management systems are capable of calculating the amount of advanced glycation end products (AGEs) produced based on a user's dietary information, conducting risk assessments, and providing nutritional advice. However, because they provide uniform advice without taking the user's emotional state into consideration, there is a problem in that effective advice and risk alerts cannot be received depending on the user's emotional state. In particular, when users are under high stress or feeling fatigued, they tend to lose motivation to take appropriate health management and improve their diet. Therefore, there is a need for a system that provides more effective health support that takes the user's emotional state into consideration.

[1849] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for recognizing the user's emotions, means for sending a risk alert to the user based on the risk assessment and the user's emotions, and means for generating nutritional advice according to the user's health condition and emotional information and providing the advice to the user. This enables personalized risk alerts and nutritional advice that take the user's emotional state into consideration.

[1850] "User" refers to an individual who uses the system to input and review their own health management information and dietary information.

[1851] "Dietary information" refers to data on detailed dietary content such as the names of ingredients consumed by the user, cooking methods, portions, and consumption times.

[1852] "Database" refers to an information system for storing and managing various data, including dietary information, health information, and emotional information, entered by users.

[1853] Advanced glycation end products (AGEs) are substances that are produced when sugars and proteins in food ingredients combine during high-temperature cooking and have various adverse effects on the human body.

[1854] "Risk assessment" refers to the process of assessing and determining the user's health risk based on the calculated amount of AGE production and other health information.

[1855] "Emotion recognition" refers to the technology of identifying and determining a user's emotional state from their input, reactions, facial expressions, voice, etc.

[1856] "Risk alert" refers to a notification that warns or warns the user about health issues based on the results of a risk assessment.

[1857] "Nutrition advice" refers to advice that suggests appropriate diet and nutritional intake methods based on the user's health condition, dietary information, and emotional information.

[1858] This invention combines a system that collects and analyzes a user's dietary information and evaluates the risk of accumulating advanced glycation end products (AGEs) due to high-temperature cooking with an emotion engine that recognizes the user's emotions. This makes it possible to adjust the content of risk alerts and nutritional advice according to the user's emotions and provide more effective health support.

[1859] The present invention is implemented in a series of processes involving a server, a terminal, a user, and an emotion engine.

[1860] First, the user uses a dedicated app to input meal information. Specific items include the names of ingredients, cooking methods, portions, and time of consumption. For example, suppose the user inputs "200g steak and grilled vegetables (broccoli and carrots) for lunch." The device converts the input information into a standard data format (such as JSON) and sends it to the server via an HTTP request.

[1861] The server receives the HTTP request and stores it in a database in the format of "user ID, date and time, ingredient name, cooking method, and portion size." The server then extracts the meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE generated based on each ingredient and cooking method. For example, it obtains data such as "200g of steak generates 35mg of AGE, and grilled vegetables generates 15mg of AGE." The server then adds up the AGEs of each ingredient to calculate the total AGE intake (e.g., 50mg), and uses this to perform a risk assessment. It determines whether the diet is "high risk," "medium risk," or "low risk."

[1862] Furthermore, the device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, when a user shoots and sends a short video using their smartphone camera, the emotion engine analyzes the data, such as "fatigue 50%," and sends it to the server.

[1863] If the server determines that the risk assessment is "high risk" based on the total AGE intake and emotional data, it generates a risk alert stating that "high AGE intake poses a health risk." Here, the server takes into account the user's emotional information, and if the user feels "50% fatigued," for example, it changes the alert to a more gentle expression such as "Take care of your health when you are tired." The generated risk alert is sent to the user's device as an HTTP response, and the alert is displayed in the app's notification bar.

[1864] Next, the server checks the user's health status based on their past health data and dietary information. Using a generative AI model, it analyzes the user's health status and dietary information and suggests recipes such as "low-temperature cooked steak recipes" and "steamed vegetable recipes." It also adjusts the wording of the advice based on emotional data. For example, it might say, "This is an easy recipe to make even when you're tired. Good luck!"

[1865] The user prepares a meal using the provided "low-temperature cooked steak recipe" as a reference, and then cooks the meal. After the meal, the user opens the "Feedback" section in the app and enters their impressions, such as "It was delicious" or "I feel great," as well as their physical condition. The device converts the input feedback data into a standard data format and sends it to the server as an HTTP request. The server receives this, stores it in a database, and updates the user's health data.

[1866] Based on the updated data, the server generates new nutrition advice and sends the results to the user's device. If new risks are discovered, the server performs a risk assessment again and generates and sends risk alerts as necessary. The device continuously displays the latest advice and risk alerts on the app, supporting the user in living a healthy lifestyle.

[1867] Prompt Sentence Examples

[1868] "Generate risk alerts and nutritional advice for the user based on dietary data and emotional information. Ingredients: 200g steak and grilled vegetables. Emotion: 50% fatigue."

[1869] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1870] Step 1:

[1871] The user taps the "Enter Meal Information" button on the dedicated app screen and enters detailed meal information such as the ingredients, cooking method, portion size, and time of intake. For example, they might enter "200g steak, grilled vegetables (broccoli, carrots)."

[1872] Step 2:

[1873] The device receives the meal information entered by the user and converts it into a standard data format (e.g., JSON), which structures the information and prepares it for transmission to the server.

[1874] Step 3:

[1875] The device sends the converted data to the server in the form of an HTTP request, which includes the user ID, date and time, ingredient names, cooking methods, and quantities.

[1876] Step 4:

[1877] The server analyzes the received HTTP request and stores the meal information in a database, including the user ID, date and time, ingredient names, cooking methods, and serving sizes.

[1878] Step 5:

[1879] The server extracts meal information from the database and uses a generative AI model (e.g., ChatGPT API) to calculate the amount of AGE produced based on each ingredient and cooking method. For example, it can obtain results such as "200g of steak produces 35mg of AGE, and grilled vegetables produces 15mg of AGE."

[1880] Step 6:

[1881] The server calculates the total AGE intake by adding up the amount of AGE produced by each food ingredient based on the calculation results. For example, let's say a steak and grilled vegetables contain 50 mg of AGE combined. The server then performs a risk assessment based on the user's total AGE intake, determining whether they are at "high risk," "medium risk," or "low risk."

[1882] Step 7:

[1883] The device uses an emotion engine (e.g., Emotion API) to recognize emotions from the user's input, reactions, facial expressions, voice, etc. For example, a user can shoot a short video with their smartphone camera and send it to obtain data such as "50% fatigue."

[1884] Step 8:

[1885] The device converts the recognized emotion data into a standard data format and sends it to the server. This request includes the user ID and the emotion recognition result.

[1886] Step 9:

[1887] The server receives the emotion data and generates a risk alert if the risk assessment results in a "high risk." For example, the alert might say, "High AGE intake poses a health risk."

[1888] Step 10:

[1889] The server adjusts the wording of the risk alert based on the user's emotional information. For example, if the user says "Feeling 50% fatigued," it will change the wording to something gentler, such as "Take care of your health when you're tired."

[1890] Step 11:

[1891] The server sends the generated risk alert to the user's device as an HTTP response.

[1892] Step 12:

[1893] The device will display the received risk alert in the app's notification bar and notify the user.

[1894] Step 13:

[1895] The server retrieves past health and dietary data from a database and uses a generative AI model to analyze the user's health status, suggesting recipes such as low-temperature cooked steak and steamed vegetables.

[1896] Step 14:

[1897] The server adjusts the content and wording of advice based on the emotional information, for example, "Here's a recipe that's easy to make even when you're tired. Good luck!"

[1898] Step 15:

[1899] The server sends the generated nutrition advice to the user's terminal as an HTTP response.

[1900] Step 16:

[1901] The device will display the received nutrition advice in the "Advice" section of the app, where users can view specific advice and recipes.

[1902] Step 17:

[1903] The user prepares and executes a meal based on the presented "low-temperature cooked steak recipe."

[1904] Step 18:

[1905] After eating, users open the "Feedback" section in the app and enter their impressions, such as "It was delicious" or "I feel great," as well as their physical condition.

[1906] Step 19:

[1907] The terminal converts the input feedback data into a standard data format and sends it to the server as an HTTP request.

[1908] Step 20:

[1909] The server receives the feedback data and stores it in a database to update the user's health data.

[1910] Step 21:

[1911] The server generates new nutrition advice based on the updated data and sends the results to the user's terminal.

[1912] Step 22:

[1913] If the server discovers any new risks, it will reassess them and generate and send risk alerts as necessary.

[1914] Step 23:

[1915] The device continuously displays the latest advice and risk alerts in the app, supporting users in living a healthy lifestyle.

[1916] (Application example 2)

[1917] 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."

[1918] Conventional dietary information analysis systems can assess the health risks posed by advanced glycation end products (AGEs) ingested by users and provide risk alerts and nutritional advice. However, they cannot take the user's emotional state into account, which means they are unable to provide effective health support. For example, a sudden health warning can be counterproductive for a stressed user, risking discouraging the user's motivation to improve their health. Therefore, there is a need for a health support system that takes the user's emotions into account.

[1919] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1920] In this invention, the server includes means for having a user input dietary information and storing the dietary information in a database, means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced, means for performing a risk assessment for each user based on the calculated amount of AGEs produced, means for sending a risk alert to the user based on the risk assessment, means for generating nutritional advice tailored to the user's health condition and lifestyle and providing the advice to the user, means for collecting emotional information about the user using an emotion engine that recognizes the user's emotions, means for adjusting the presentation of the risk alert based on the emotional information, and means for adjusting the content and presentation of the nutritional advice based on the emotional information. This enables more effective health support by providing risk alerts and nutritional advice that take the user's emotional state into consideration.

[1921] A "database" is a system for systematically storing information and for efficient searching and analysis.

[1922] "Meal information" is detailed information about the meal the user has eaten, such as the names of ingredients, cooking methods, and portions.

[1923] Advanced glycation end products (AGEs) are compounds that are produced by high-temperature cooking and accumulate in the body, posing a health risk.

[1924] A "risk alert" is a warning message that notifies the user of a health risk.

[1925] "Nutrition advice" refers to suggestions about appropriate diet and nutritional intake methods based on the user's health condition and lifestyle.

[1926] An "emotion engine" is a technology that recognizes and analyzes emotions from user input, reactions, facial expressions, voice, etc.

[1927] "Emotion information" is data about the user's emotional state as recognized by the emotion engine.

[1928] "Risk assessment" is the process of calculating the health risk for each user based on dietary information and the amount of AGE produced.

[1929] "Adjusting the expression method" means changing the content and display method of the message based on the user's emotional information.

[1930] This invention is based on a system that collects and analyzes a user's dietary information and evaluates the risk of advanced glycation end products (AGE) accumulation due to high-temperature cooking. This system can also be combined with an emotion engine that recognizes the user's emotions, making it possible to adjust risk alerts and nutritional advice according to the user's emotions. Specific embodiments of this system are described below.

[1931] System Components

[1932] server

[1933] The server includes the following means:

[1934] 1. A means for having the user input meal information and storing the meal information in a database.

[1935] 2. A means of analyzing stored dietary information and calculating the amount of advanced glycation end products (AGEs) produced.

[1936] 3. A means of assessing risk for each user based on the calculated amount of AGE generated.

[1937] 4. A means of sending risk alerts to users based on risk assessment.

[1938] 5. A means for generating and providing nutritional advice tailored to the user's health and lifestyle.

[1939] 6. A means of collecting user emotion information using an emotion engine that recognizes user emotions.

[1940] 7. A means to tailor the wording of risk alerts based on sentiment information.

[1941] 8. Means of tailoring the content and presentation of nu...

Claims

1. a means for allowing a user to input meal information and storing the meal information in a database; a means for analyzing the dietary information stored in the database and calculating the amount of advanced glycation end products (AGEs) produced; a means for performing risk assessment for each user based on the calculated amount of AGE generated; means for sending a risk alert to a user based on said risk assessment; means for generating nutrition advice tailored to the user's health condition and lifestyle and providing the advice to the user; A system including:

2. 2. The system according to claim 1, wherein the input of meal information is received as information including names of ingredients, cooking methods, and portions.

3. 2. The system of claim 1, wherein the system stores the user's health data in a database and generates nutritional advice based on the health data.

Images