System

Abstract

To provide a system.SOLUTION: A system includes: means for recognizing a feeling of a user using a feeling engine; means for analyzing a health condition of the user from information on meal, sleep, and exercise input by the user and biological information of the user; and means for generating a meal menu using a generative AI model on the basis of a prompt sentence obtained by combining the recognized feeling and the analyzed health condition.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, predictions of life expectancy based on a person's health and lifestyle are generally based on diagnoses by medical professionals and statistical data, but these methods have difficulty making precise predictions that reflect the subtle differences in each person's lifestyle and health. [Means for solving the problem]

[0005] This invention involves inputting information about a person's diet, sleep, and exercise, and obtaining various sensor information (such as pulse rate) from a wearable device. This information is processed by generative AI that processes natural language, and by using AI to simulate a person's lifespan based on this information, it makes possible precise lifespan predictions that reflect each individual's lifestyle and health condition. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, the user inputs information about their diet, sleep, and exercise via a device such as a smartphone or PC. Specifically, the user inputs information such as the contents of their meals, calorie intake, sleep time, and type and duration of exercise. The user also uses a wearable device (e.g., a smartwatch or fitness band) to obtain biometric information such as pulse rate and transmit it to the system.

[0029] "Example 2"

[0030] In this embodiment of the present invention, generative AI processes the information acquired above using natural language processing. Specifically, it analyzes information on diet, sleep, and exercise as text data and converts each piece of information into an appropriate format. For example, it may classify dietary content into food groups and nutrients, or divide sleep time into deep and light sleep periods.

[0031] "Example 3"

[0032] In this embodiment of the present invention, AI simulates a person's lifespan based on the information processed above. Specifically, it combines information on diet, sleep, and exercise with biometric information to evaluate the user's health condition and lifestyle habits, and predicts their lifespan based on that. The prediction results are fed back to the user and can be used to improve their health management and lifestyle habits.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user enters information about food, sleep, and exercise via a device such as a smartphone or computer. Specifically, the user enters information about the food they eat, the calories they consume, how much sleep they get, and the type and duration of their exercise.

[0036] Step 2: The user uses a wearable device (e.g., a smart watch or fitness band) to acquire biometric information such as pulse rate and transmit it to the system.

[0037] "Example 2"

[0038] Step 1: The generative AI performs natural language processing on the information acquired above. Specifically, it analyzes information about diet, sleep, and exercise as text data.

[0039] Step 2: Transform each piece of information into an appropriate format, such as categorizing your diet into food groups and nutrients, or dividing your sleep into periods of deep and light sleep.

[0040] "Example 3"

[0041] Step 1: Based on the information processed above, the AI ​​simulates a person's lifespan. Specifically, it combines information on diet, sleep, and exercise with biometric information to evaluate the user's health and lifestyle.

[0042] Step 2: Based on this, life expectancy is predicted. This prediction result is fed back to the user and used to help improve health management and lifestyle habits.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form 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."

[0045] Conventional health management systems have had difficulty effectively integrating information about diet, sleep, and exercise entered by users with biometric information obtained from wearable devices and providing the analysis results as feedback to users. Furthermore, there has been insufficient simulation of lifespan based on this information. This has made it difficult for users to accurately understand their own health status and maintain appropriate lifestyle habits.

[0046] 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.

[0047] In this invention, the server includes means for receiving information on diet, sleep, and exercise input by the user, means for receiving biometric information acquired from the wearable device, means for storing the received information in a database, means for analyzing the stored information, means for transmitting the analysis results to the user's terminal, means for performing natural language processing using generative AI, and AI means for simulating a person's lifespan based on the above information. This makes it possible to comprehensively analyze the information input by the user and the biometric information acquired from the wearable device and provide appropriate feedback to the user.

[0048] "Dietary information" refers to information about the contents of meals and calories consumed by the user.

[0049] "Sleep information" refers to information about the user's sleep time and sleep quality.

[0050] "Exercise information" refers to information about the type of exercise performed by the user, the duration of the exercise, and the calories burned.

[0051] "Sensor information" refers to biological information such as pulse rate obtained from a wearable device.

[0052] A "wearable device" is a device worn by a user that measures biometric information, and examples include smartwatches and fitness bands.

[0053] A "server" is a computer system that receives, stores, and analyzes information sent by users.

[0054] "Database" means a data management system for storing information received by the server.

[0055] "Analysis" is the process by which the server evaluates data based on stored information using statistical analysis and machine learning models.

[0056] "Generative AI" is an artificial intelligence model for performing natural language processing.

[0057] "Lifespan simulation" is the process of predicting a user's lifespan based on the user's input information and biometric information.

[0058] "Feedback" refers to the transmission of information to provide analysis results to users.

[0059] MODE FOR CARRYING OUT THE INVENTION

[0060] This invention is a system in which a user inputs information about diet, sleep, and exercise via a terminal such as a smartphone or a personal computer, and biometric information is acquired using a wearable device. Specific embodiments of this system are described below.

[0061] User Data Entry

[0062] Users use their smartphones or computers to input information about their diet, sleep, and exercise. For example, if a user inputs "two slices of toast, one banana, and one cup of coffee" for breakfast, the application will calculate the calories from this information and display the total calorie intake. The software used includes smartphone applications and web applications.

[0063] Acquisition of biometric information

[0064] Users wear a wearable device (e.g., a smartwatch or fitness band) and collect biometric information such as their pulse rate during exercise and daily life. For example, if a user goes for a one-hour run, the smartwatch will measure their pulse rate and calories burned while they run. The measured data is sent to a smartphone via Bluetooth or Wi-Fi.

[0065] Data transmission and storage

[0066] The device (smartphone or PC) sends the information entered by the user and the biometric information obtained from the wearable device to a server. The HTTPS protocol is used for transmission, and the data is encrypted. The server stores the received data in a database. A relational database such as MySQL (registered trademark) or PostgreSQL is used for the database.

[0067] Data analysis

[0068] The server analyzes the stored data using libraries such as Python (registered trademark) Pandas and Scikit-learn. For example, it checks whether the calorie intake of food exceeds the target value and evaluates the balance between the amount of exercise and the calories burned. It also uses generative AI to perform natural language processing and provide easy-to-understand feedback to the user.

[0069] Feedback of results

[0070] The server sends the analysis results to the user's device, where they can check them through a smartphone application. For example, if their calorie intake exceeds their target, the application will warn them. It will also suggest additional exercise if they are not getting enough exercise.

[0071] Specific examples

[0072] Example 1: Entering meal information

[0073] A user opens a smartphone application and enters their breakfast as "two slices of toast, one banana, and one cup of coffee." The application calculates the calories from this information and displays the total calorie intake. For example, it calculates two slices of toast as 200 kcal, one banana as 100 kcal, and one cup of coffee as 50 kcal, displaying a total of 350 kcal.

[0074] Example 2: Using a wearable device

[0075] The user wears a smartwatch and goes for a one-hour run. The smartwatch measures pulse rate and calories burned while running and sends the data to a smartphone. The smartphone then sends the received data to a server, which analyzes the data and provides feedback to the user. For example, the average pulse rate during the run is measured as 150 bpm and calories burned as 600 kcal.

[0076] Prompt Sentence Examples

[0077] Prompt 1: Enter meal information

[0078] "For breakfast, you had two slices of toast, one banana, and one cup of coffee. Calculate the total calories ingested from these meals."

[0079] Prompt 2: Wearable device data transmission

[0080] "I ran for an hour using my smartwatch. Please send my pulse rate and calories burned during the run to the server and let me know the analysis results."

[0081] In this way, the system involves users, terminals, and servers working together to input, transmit, analyze, and provide feedback on data.

[0082] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0083] Step 1:

[0084] Users use their smartphones or computers to input information about their diet, sleep, and exercise. For example, if a user inputs "two slices of toast, one banana, and one cup of coffee" for breakfast, the application will calculate the calories from this information and display the total calorie intake. The input data is the food content, calorie intake, sleep time, and type and time of exercise, and the output is a display of the total calorie intake and amount of exercise.

[0085] Step 2:

[0086] The user wears a wearable device and collects biometric information such as pulse rate during exercise and daily life. For example, if the user runs for an hour, the smartwatch measures their pulse rate and calories burned while they run. The measured data is sent to a smartphone via Bluetooth or Wi-Fi. The input data is pulse rate and calories burned, and the output is data sent to the smartphone.

[0087] Step 3:

[0088] The device (smartphone or PC) sends information entered by the user and biometric information obtained from the wearable device to a server. The HTTPS protocol is used for transmission, and the data is encrypted. The input data is the user's diet, sleep, exercise information, and biometric information, and the output is data sent to the server.

[0089] Step 4:

[0090] The server stores the received data in a database. A relational database such as MySQL (registered trademark) or PostgreSQL is used for the database. The data is organized by user and indexed for efficient access. The input data is the user's diet, sleep, exercise information, and biometric information, and the output is stored in the database.

[0091] Step 5:

[0092] The server analyzes the stored data using Python libraries such as Pandas and Scikit-learn. For example, it checks whether the calorie intake of a meal exceeds the target value and evaluates the balance between the amount of exercise and the calories burned. The input data is the user information stored in the database, and the output is the analysis results.

[0093] Step 6:

[0094] The server sends the analysis results to the user's device. The user can check the analysis results through a smartphone application. For example, if the calorie intake of a meal exceeds the target value, the application will display a warning to the user. If the amount of exercise is insufficient, the application will also suggest additional exercise. The input data is the analysis results, and the output is feedback to the user's device.

[0095] (Application example 1)

[0096] Next, a description will be given of Application Example 1 of Embodiment 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."

[0097] Health management is an important issue in modern society, but there is no system that can centrally manage individual diet, sleep, and exercise information and suggest optimal meal menus. Furthermore, there is a lack of a way to quickly order suggested meal menus from a food delivery service. This makes it difficult for users to take concrete actions to maintain a healthy lifestyle.

[0098] 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.

[0099] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the information, means for proposing an optimal meal menu based on the information, and means for ordering the proposed meal menu from a food delivery service. This allows the user to receive an optimal meal menu based on their own health condition and quickly order the menu.

[0100] "Dietary information" refers to information about the contents, calories, and nutrients of the meals consumed by the user.

[0101] "Sleep information" refers to information about the user's sleep time and sleep quality.

[0102] "Exercise information" refers to information about the type of exercise performed by the user, the duration, and the calories burned.

[0103] "Sensor information" refers to biological information such as pulse rate and number of steps acquired from a wearable device or the like.

[0104] "Generative AI" is artificial intelligence that performs natural language processing based on input information and generates appropriate output.

[0105] "Lifespan Simulation AI" is an artificial intelligence that simulates a user's lifespan based on their diet, sleep, exercise, and sensor information.

[0106] The "meal menu suggestion means" is a means for suggesting an optimal meal menu based on the user's health condition.

[0107] The "food delivery service ordering means" is a means for ordering the suggested meal menu from a food delivery service.

[0108] A system for implementing this invention includes a means for inputting information about a user's diet, sleep, and exercise, and a means for acquiring various sensor information (such as pulse rate) from a wearable device. This information is subjected to natural language processing by a generative AI and used to evaluate the user's health condition. Furthermore, a lifespan simulation AI simulates the user's lifespan based on this information. Next, a meal menu suggestion means suggests an optimal meal menu based on the user's health condition, and a food delivery service ordering means orders the suggested meal menu from a food delivery service.

[0109] Hardware and software used

[0110] Hardware: Smartphones, wearable devices (e.g., smartwatches)

[0111] Software: Python, Requests library (to send HTTP requests), food delivery API (a hypothetical API)

[0112] Data processing and calculation

[0113] 1. User input: Users input information about their diet, sleep, and exercise through a smartphone app, including what they ate, how many calories they consumed, how much sleep they had, and the type and duration of their exercise.

[0114] 2. Acquiring sensor information: Acquiring biometric information such as pulse rate and number of steps from wearable devices.

[0115] 3. Natural language processing using generative AI: The generative AI processes the acquired information using natural language to evaluate the user's health condition.

[0116] 4. Lifespan Simulation: Lifespan simulation AI simulates the user's lifespan based on their health condition.

[0117] 5. Meal menu suggestion: The meal menu suggestion means suggests the optimal meal menu based on the user's health condition.

[0118] 6. Order food delivery service: Order the suggested meal menu from a food delivery service.

[0119] Specific examples

[0120] For example, the user inputs the calories and nutrients for breakfast, lunch, and dinner, and the smartwatch retrieves their pulse rate and step count. Based on this information, the app suggests a "High Protein Salad" and orders it from a food delivery service.

[0121] Prompt Sentence Examples

[0122] "Create a Python program that suggests the best meal plan based on the user's diet, sleep, and exercise information, and biometric information obtained from a wearable device, and then orders it from a food delivery service."

[0123] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0124] Step 1:

[0125] Users enter information about their diet, sleep, and exercise through a smartphone app.

[0126] Input: Food content, calorie intake, sleep time, type and duration of exercise.

[0127] Output: The entered data is sent to the server.

[0128] Specific operation: The user enters information about food, sleep, and exercise into the application's input form and presses the submit button. The server receives this data and stores it in a database.

[0129] Step 2:

[0130] The server acquires various sensor information (heart rate, number of steps, etc.) from the wearable device.

[0131] Input: Sensor data from wearable devices.

[0132] Output: The acquired sensor information is sent to the server.

[0133] How it works: The wearable device periodically measures sensor information and sends it to the smartphone via Bluetooth or Wi-Fi. The smartphone then forwards this data to the server.

[0134] Step 3:

[0135] The server uses generative AI to process input information and sensor information in natural language.

[0136] Input: User's diet, sleep, exercise information and sensor information.

[0137] Output: Natural language processed data.

[0138] Specific operation: The server uses a generative AI model to analyze input information and sensor information and evaluate the user's health condition.

[0139] Step 4:

[0140] The server uses a lifespan simulation AI to simulate the user's lifespan.

[0141] Input: Natural language processed data.

[0142] Output: Life simulation results.

[0143] Specific operation: The server uses the lifespan simulation AI to predict the user's lifespan based on their health condition. The simulation results are stored in a database.

[0144] Step 5:

[0145] The server uses the meal menu suggestion means to suggest an optimum meal menu based on the health condition of the user.

[0146] Input: Lifespan simulation results and user health status.

[0147] Output: A suggested meal menu.

[0148] Specific operation: The server uses a meal menu suggestion algorithm to generate a meal menu that is optimal for the user's health condition. The suggested menu is then sent to the user's smartphone.

[0149] Step 6:

[0150] The server orders the suggested meal from a food delivery service.

[0151] Input: A suggested meal menu.

[0152] Output: Order confirmation to food delivery service.

[0153] Specific operation: The server uses the food delivery service's API to order the suggested meal menu. An order confirmation is sent to the user's smartphone.

[0154] Example 2

[0155] Next, a description will be given of Example 2 of Form 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."

[0156] Conventional health management systems have had difficulty properly analyzing the diet, sleep, and exercise information entered by users and providing specific advice or lifespan simulations. Effective use of various sensor information was also difficult, making it impossible to provide useful information to users. This resulted in the issue of users being unable to accurately grasp their own health status and take appropriate measures.

[0157] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0158] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for the generative AI to classify the diet information into food groups and nutrients, means for the generative AI to classify the sleep information into deep sleep and light sleep, and means for the generative AI to classify the exercise information into type and intensity. This allows the user to understand their own health condition in detail and receive appropriate advice.

[0159] "Dietary information" is information about the food and drinks consumed by the user.

[0160] "Sleep information" is information relating to the user's sleep time and sleep quality.

[0161] "Exercise information" is information relating to the type, intensity, and duration of exercise performed by the user.

[0162] "Sensor information" refers to biometric data such as pulse rate and activity level obtained from wearable devices.

[0163] "Generative AI" is an artificial intelligence that performs natural language processing and has the ability to analyze information entered by the user and convert it into an appropriate format.

[0164] "Food groups" are categories for classifying dietary information, and are classified based on nutrients such as carbohydrates, proteins, and lipids.

[0165] "Deep sleep" is the sleep stage that is considered to be the most restful for the user.

[0166] "Light sleep" is a sleep stage in which the user is relatively awake during sleep.

[0167] "Lifespan simulation" is a process of performing calculations and analyses to predict future lifespan based on a user's health information.

[0168] The present invention is a system for analyzing a user's health information in detail and providing appropriate advice and lifespan simulations. Specific embodiments of this system will be described below.

[0169] Program Generation

[0170] The system's program is designed to analyze the diet, sleep, and exercise information entered by the user and convert it into an appropriate format using a generative AI model, such as GPT-4 (registered trademark).

[0171] Program processing

[0172] This system performs data processing and calculation using the following hardware and software.

[0173] 1. Analysis of dietary information

[0174] The server receives the meal details entered by the user as text data.

[0175] The server uses a generative AI model (e.g., GPT-4) to categorize the meal contents into food groups and nutrients.

[0176] For example, information such as "I ate bread and eggs for breakfast" is converted into a format such as "bread (carbohydrate), eggs (protein)."

[0177] 2. Sleep information analysis

[0178] The server receives the information on the sleeping hours input by the user as text data.

[0179] The server uses a generative AI model to divide sleep time into periods of deep and light sleep.

[0180] For example, information such as "I slept 8 hours last night" can be converted into a format such as "Deep sleep: 3 hours, Light sleep: 5 hours."

[0181] 3. Analysis of movement information

[0182] The server receives the exercise details entered by the user as text data.

[0183] The server uses a generative AI model to analyze the type and intensity of exercise and convert it into an appropriate format.

[0184] For example, information such as "I jogged for 30 minutes" is converted into a format such as "Jogging (aerobic exercise), 30 minutes."

[0185] Adding specific examples

[0186] Below is an example of a prompt sentence to input to the generative AI model.

[0187] Example prompt sentence:

[0188] "Classify what the user ate for breakfast into food groups and nutrients. Input: I ate bread and eggs for breakfast."

[0189] "Please divide the user's sleep time into deep and light sleep. Input: I slept 8 hours last night."

[0190] "Please classify the type and intensity of exercise performed by the user. Input: 30 minutes of jogging."

[0191] This allows users to simply input information about their diet, sleep, and exercise, and the server will use a generative AI model to convert each piece of information into an appropriate format.

[0192] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0193] Step 1:

[0194] The user enters information about their diet, sleep, and exercise.

[0195] How it works: Users enter information about their diet, sleep, and exercise in text format using a dedicated application or web interface.

[0196] Input: Information such as "I had bread and eggs for breakfast," "I slept 8 hours last night," or "I jogged for 30 minutes."

[0197] Output: The text data entered by the user.

[0198] Step 2:

[0199] The terminal transmits the input information to the server.

[0200] Specific operation: The device sends the information entered by the user as text data to the server using the HTTPS protocol to ensure data security.

[0201] Input: Text data entered by the user.

[0202] Output: The text data sent to the server.

[0203] Step 3:

[0204] The server receives the information and generates a prompt for the generative AI model.

[0205] Specific operation: The server analyzes the information received from the device and generates a prompt sentence to pass to the generative AI model.

[0206] Input: Text data sent from the terminal.

[0207] Output: A prompt to pass to the generative AI model.

[0208] Step 4:

[0209] The server analyzes the information using a generative AI model.

[0210] What it does: The server uses a generative AI model (e.g., GPT-4) to parse the information based on the prompt.

[0211] Input: A prompt to pass to the generative AI model.

[0212] Output: Analysis result (e.g. "bread (carbohydrates), eggs (protein)").

[0213] Step 5:

[0214] The server sends the analysis results to the device.

[0215] How it works: The server sends the analysis results obtained from the generative AI model to the device, again using the HTTPS protocol to ensure data security.

[0216] Input: Analysis results obtained from a generative AI model.

[0217] Output: Analysis results sent to the device.

[0218] Step 6:

[0219] The terminal displays the analysis results to the user.

[0220] Specific operation: The terminal displays the analysis results received from the server to the user.

[0221] Input: Analysis results sent from the server.

[0222] Output: The analysis results displayed to the user's screen (e.g., "Breakfast: Bread (carbohydrates), eggs (protein)").

[0223] This allows users to easily input information about their diet, sleep, and exercise, and have that information converted into the appropriate format.

[0224] (Application example 2)

[0225] Next, a description will be given of Application Example 2 of Form 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."

[0226] Health management is an important issue in modern society, but there is no system that comprehensively analyzes individual diet, sleep, and exercise information and proposes appropriate meal plans. Furthermore, there is a lack of means for users to actually order the proposed meal plans. This makes it difficult for users to efficiently manage their health.

[0227] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for generating a meal menu based on health status and proposing a meal plan, and means for ordering the proposed meal menu in cooperation with an external meal provision service. This enables a user to easily obtain a meal plan based on their own health status and then efficiently order meals based on that plan.

[0228] "Dietary information" refers to data such as the content, amount, and time of meals consumed by the user.

[0229] "Sleep information" refers to data such as the user's sleep time, the time spent in deep and light sleep, and the quality of their sleep.

[0230] "Exercise information" refers to data such as the type, duration, and intensity of exercise performed by the user.

[0231] "Sensor information" refers to biological data such as pulse rate, body temperature, and activity level obtained from wearable devices.

[0232] "Generative AI" is artificial intelligence that processes input data using natural language processing and generates analytical results.

[0233] "Lifespan Simulation" is a simulation that predicts a user's lifespan based on input data.

[0234] "Meal menu generation" is the process of creating an appropriate meal plan based on the user's health status.

[0235] A "meal provision service" is an external service that provides meals ordered by a user.

[0236] The "ordering means" is a means for ordering the proposed meal menu from an external meal provision service.

[0237] The system for implementing this invention inputs information about the user's diet, sleep, and exercise, and based on this information, proposes a meal plan based on the user's health condition, and then orders meals based on that plan in cooperation with an external meal delivery service.

[0238] System Configuration

[0239] The system consists of the following main components:

[0240] 1. User device: A device used by a user to input information, such as a smartphone or tablet.

[0241] 2. Wearable device: A device for acquiring sensor information such as pulse rate and body temperature.

[0242] 3. Server: The central component that analyzes and processes data.

[0243] 4. Generative AI: Artificial intelligence that processes input data using natural language and generates analytical results.

[0244] 5. External meal service: An external service that provides a proposed meal menu.

[0245] Program processing

[0246] The server receives information on diet, sleep, and exercise from the user's device and acquires sensor information from the wearable device. This information is processed using natural language processing by generative AI, and a meal menu based on the user's health status is generated. The generated meal menu is then proposed to the user, and the menu selected by the user is ordered from an external meal delivery service.

[0247] Hardware and software used

[0248] Hardware: Smartphones, tablets, wearable devices

[0249] Software: Python, OpenAI® API, Food Delivery API

[0250] Data processing and calculation

[0251] 1. Data entry: The user enters information about their diet, sleep, and exercise into their smartphone or tablet.

[0252] 2. Data acquisition: Obtain sensor information such as pulse rate and body temperature from the wearable device.

[0253] 3. Data analysis: Generative AI (e.g., GPT-3 (registered trademark)) is used to analyze the input data and generate a meal menu based on health status.

[0254] 4. Data output: Display the generated meal menu to the user.

[0255] 5. Order processing: Using the food delivery API, the proposed menu is ordered from an external food delivery service.

[0256] Specific examples

[0257] For example, let's say a user had toast and eggs for breakfast, salad and chicken for lunch, and fish and vegetables for dinner. They also had 4 hours of deep sleep, 3 hours of light sleep, and went for a 30-minute run. With this information, the generative AI could use the following prompt to analyze:

[0258] Prompt Sentence Examples

[0259] Dietary information: I had toast and eggs for breakfast, salad and chicken for lunch, and fish and vegetables for dinner.

[0260] Sleep data: 4 hours of deep sleep, 3 hours of light sleep.

[0261] Exercise data: Ran for 30 minutes.

[0262] Analyze this data and suggest a meal plan based on your health condition.

[0263] Based on this prompt, the generative AI analyzes it and suggests a meal menu that is optimal for the user's health condition. The suggested menu is displayed to the user, and the menu selected by the user is ordered from an external meal delivery service. This allows users to easily obtain a meal plan based on their health condition and then efficiently order meals based on that plan.

[0264] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0265] Step 1:

[0266] The user uses a smartphone or tablet to input information about their diet, sleep, and exercise. The input information includes the type, amount, and time of meals, sleep duration, duration of deep and light sleep, and type, duration, and intensity of exercise. This data is then sent to the server.

[0267] Step 2:

[0268] The server acquires sensor information from the wearable device. The sensor information includes biometric data such as pulse rate, body temperature, and activity level. The acquired sensor information is important data for evaluating the user's health condition.

[0269] Step 3:

[0270] The server uses generative AI to process the inputted diet, sleep, exercise, and sensor information in natural language. Specifically, the server inputs the following prompts into the generative AI:

[0271] Dietary Data: [Dietary Information]

[0272] Sleep data: [Sleep information]

[0273] Exercise data: [Exercise information]

[0274] Analyze this data and suggest a meal plan based on your health condition.

[0275] The generative AI analyzes the data based on this prompt and generates a meal menu based on the patient's health status.

[0276] Step 4:

[0277] The server sends the generated meal menu to the user's device, where the user can check the proposed meal menu on their smartphone or tablet. The meal menu includes a balanced meal plan.

[0278] Step 5:

[0279] The user selects the desired meal from the suggested menu, and the selected menu is sent to the server.

[0280] Step 6:

[0281] The server orders the selected meal from an external food service using a food delivery API. The order data includes the selected meal, the user's address, payment method, etc.

[0282] Step 7:

[0283] An external food delivery service receives the order and delivers the meal to the user, who can then receive a meal based on the suggested meal menu.

[0284] Through the above steps, a user can easily obtain a meal plan based on their own health condition and can then efficiently order meals based on that plan.

[0285] Example 3

[0286] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0287] Conventional health management systems can collect information on a user's diet, sleep, exercise, and biological information individually, but it is difficult to integrate this information to predict a user's lifespan. Furthermore, the preprocessing of collected data and the accuracy of lifespan predictions using AI models are also insufficient. This makes it difficult for users to comprehensively evaluate their health status and lifestyle habits and receive specific feedback for improvement.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0289] In this invention, the server includes a means for inputting information on a person's diet, sleep, and exercise, a means for acquiring various sensor information (biometric information) from the person, a means for preprocessing this information, a means for simulating a person's lifespan using a generative AI model based on the preprocessed information, and a means for feeding back the simulation results to the user. This makes it possible to comprehensively evaluate the user's health condition and lifestyle habits and provide specific feedback.

[0290] "Dietary information" refers to data such as the type, amount, and time of consumption of food and beverages consumed by the user.

[0291] "Sleep information" refers to data such as the user's sleep time, sleep quality, and wake-up time.

[0292] "Exercise information" refers to data such as the type, duration, and intensity of exercise performed by the user.

[0293] "Sensor information" refers to data obtained from various sensors that acquire biometric information about the user, such as pulse rate, blood pressure, and body temperature.

[0294] "Preprocessing" refers to processes such as cleaning the collected data, filling in missing values, removing outliers, and normalizing the data.

[0295] A "generative AI model" is an artificial intelligence model that predicts a user's lifespan based on collected data. Specifically, it includes machine learning algorithms such as neural networks.

[0296] "Feedback" refers to the provision of information to users that is useful for managing their health and improving their lifestyle habits by notifying them of the results predicted by the AI ​​model.

[0297] This invention is a system that collects information on a user's diet, sleep, exercise, and biological information, and uses a generative AI model based on this information to simulate a user's lifespan. Specific embodiments of this system are described below.

[0298] Data collection

[0299] Users use a smartphone app or web interface to input information about their diet, sleep, and exercise—for example, they ate oatmeal for breakfast, slept seven hours last night, and went on a 30-minute jog—and this information is sent from the device to a server.

[0300] Data storage and preprocessing

[0301] The server stores the received data in a database (e.g., MySQL). The stored data is preprocessed using Python libraries such as Pandas and NumPy. Specifically, the data is cleaned (missing values ​​are filled in and outliers are removed) and normalized. For example, missing sleep duration is filled in with the average value.

[0302] Lifespan prediction using AI models

[0303] The server inputs the preprocessed data into a generative AI model (e.g., a neural network using TENSORFLOW® or PyTorch). This model evaluates the user's health and lifestyle habits and predicts lifespan based on them. For example, the model may output "The user's predicted lifespan is 85 years."

[0304] Feedback of results

[0305] The server then provides the user with feedback on the life expectancy predictions generated by the AI ​​model. This feedback is provided via an app on the device or a web interface. Users can use this feedback to manage their health and improve their lifestyle habits. For example, the app screen might display, "Your predicted life expectancy is 85 years."

[0306] Specific examples

[0307] A user opens a smartphone app and enters information about their diet, sleep, and exercise. For example, they enter "Breakfast: Oatmeal" on the app's food input screen and "Sleep time: 7 hours" on the sleep input screen. The server stores the received data in a MySQL database and cleans it using the Pandas library. The preprocessed data is input into a TensorFlow model to predict lifespan. The server sends the prediction results in JSON format to the device, which then displays the received results on the app screen and informs the user, "Your predicted lifespan is 85 years."

[0308] Prompt Sentence Examples

[0309] "Evaluate your health and lifestyle based on your diet, sleep, exercise, and biological information, and predict your life expectancy."

[0310] In this way, a system is constructed in which the server, terminals, and users work together to collect and process data and simulate lifespan using an AI model. The flow of the specific processing in Example 3 will be described with reference to FIG.

[0311] Step 1:

[0312] Users use a smartphone app or web interface to input information about their diet, sleep, and exercise—for example, they ate oatmeal for breakfast, slept seven hours last night, and went on a 30-minute jog—and this information is sent from the device to a server.

[0313] Input: Diet, sleep, and exercise information

[0314] Output: User's lifestyle information sent to the server

[0315] Step 2:

[0316] The server stores the received data in a database (e.g., MySQL), including the user ID, meal details, sleep time, exercise details, etc.

[0317] Input: User's lifestyle information sent from the device

[0318] Output: User's lifestyle information stored in a database

[0319] Step 3:

[0320] The server preprocesses the stored data by using Python libraries such as Pandas and NumPy to clean (implant missing values ​​and remove outliers) and normalize the data. For example, missing sleep duration is imputed with the average value.

[0321] Input: User's lifestyle information stored in the database

[0322] Output: Preprocessed user lifestyle information

[0323] Step 4:

[0324] The server inputs the preprocessed data into a generative AI model (e.g., a neural network using TensorFlow or PyTorch). This model evaluates the user's health and lifestyle habits and predicts their lifespan based on that. For example, the model may output "The user's predicted lifespan is 85 years."

[0325] Input: Preprocessed user lifestyle information

[0326] Output: Lifespan prediction results from AI model

[0327] Step 5:

[0328] The server then provides the user with feedback on the life expectancy predictions generated by the AI ​​model. This feedback is provided via an app on the device or a web interface. Users can use this feedback to manage their health and improve their lifestyle habits. For example, the app screen might display, "Your predicted life expectancy is 85 years."

[0329] Input: Lifespan prediction results from AI model

[0330] Output: Life prediction results fed back to the user

[0331] (Application example 3)

[0332] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0333] Health management and lifestyle improvement are important issues in modern society. However, it is difficult for individual users to accurately evaluate their own health status and lifestyle habits and take appropriate measures to improve them based on the results. In particular, comprehensively evaluating information such as diet, sleep, and exercise and predicting life expectancy requires specialized knowledge and skills, making it difficult for average users. For this reason, there is a demand for a system that allows users to easily evaluate their own health status and obtain specific guidelines for improving their lifestyle habits.

[0334] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0335] In this invention, the server includes a means for inputting information on a person's diet, sleep, and exercise, a means for acquiring various sensor information (such as pulse rate) from the person, a generative AI means for natural language processing this information, an AI means for evaluating the person's health condition and lifestyle habits based on the above information and simulating lifespan, and a means for feeding back the evaluation results to the user. This enables the user to comprehensively evaluate their own health condition and obtain specific measures to improve their lifestyle habits.

[0336] "Dietary information" is data about the food and beverages consumed by a user.

[0337] "Sleep information" refers to data about the user's sleep time and quality.

[0338] "Exercise information" is data regarding the type, duration, and intensity of exercise performed by a user.

[0339] "Sensor information" refers to information obtained from various sensors for acquiring biometric data of the user.

[0340] "Generative AI" is artificial intelligence that uses natural language processing to analyze input information and generate appropriate output.

[0341] "Health status assessment" is the process of assessing a user's current health status based on the user's diet, sleep, exercise, and sensor information.

[0342] "Lifespan simulation" is the process of predicting a user's future lifespan based on their health condition and lifestyle habits.

[0343] "Feedback means" refers to a means for providing evaluation results and life expectancy prediction results to users to help them improve their lifestyle habits.

[0344] A system for implementing this invention includes a means for inputting information on a user's diet, sleep, and exercise, a means for acquiring various sensor information (such as pulse rate), a generative AI means for natural language processing this information, an AI means for evaluating the user's health condition and lifestyle habits based on the above information and simulating life expectancy, and a means for feeding back the evaluation results to the user.

[0345] System configuration

[0346] 1. User Device

[0347] The user terminal is a mobile device such as a smartphone or tablet, and the user uses this terminal to input information about their diet, sleep, and exercise.

[0348] 2. Wearable devices

[0349] Wearable devices include smartwatches and fitness trackers that collect biometric information such as the user's pulse rate, blood pressure, and body temperature.

[0350] 3. Server

[0351] The server receives data sent from the user's terminal and wearable device, and uses generative AI to perform natural language processing based on this information. It also evaluates health status and lifestyle habits and simulates life expectancy.

[0352] Program processing explanation

[0353] The server processes the data obtained from the user using Python and machine learning libraries (e.g., scikit-learn). Specifically, the process is carried out in the following steps:

[0354] 1. Data Acquisition

[0355] Information on diet, sleep, and exercise is collected from the user's device, and biometric information is collected from the wearable device.

[0356] 2. Data Analysis

[0357] The acquired data is processed using natural language processing with generative AI to evaluate the user's health condition and lifestyle habits.

[0358] 3. Life simulation

[0359] Based on the evaluation results, AI simulates the user's lifespan.

[0360] 4. Feedback

[0361] The simulation results are sent to the user's device and fed back to the user, allowing them to understand their own health condition and use it to improve their lifestyle habits.

[0362] Specific examples

[0363] For example, consider a scenario in which a user enters information about their diet, sleep, and exercise into an app every day, and their smartwatch automatically collects data on their heart rate and blood pressure. Based on this data, the server evaluates the user's health and predicts their life expectancy. The prediction results are fed back to the user, and specific lifestyle improvement measures are presented.

[0364] Prompt Sentence Examples

[0365] "Predict life expectancy based on the user's age, gender, heart rate, blood pressure, sleep time, exercise time, and diet score."

[0366] This prompt can be used to feed data into a generative AI model to predict lifespan.

[0367] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0368] Step 1:

[0369] The user device inputs information about meals, sleep, and exercise from the user. The input information includes the contents of meals, sleep time, type and time of exercise, etc. This information is temporarily stored in the user device.

[0370] Step 2:

[0371] Wearable devices acquire biometric information from users, specifically by measuring pulse rate, blood pressure, body temperature, and other data using sensors and transmitting this data to the user's device.

[0372] Step 3:

[0373] The user device sends the acquired information on food, sleep, exercise, and biometric data to the server. The data is sent in a standard data format such as JSON.

[0374] Step 4:

[0375] The server analyzes the received data. First, it formats and preprocesses the data. For example, it complements missing values ​​and detects and corrects outliers. Next, it uses generative AI to perform natural language processing and analyze the data.

[0376] Step 5:

[0377] The server evaluates the user's health condition and lifestyle habits based on the analysis results. Specifically, it evaluates and scores the balance of meals, quality of sleep, appropriateness of exercise, etc. The evaluation results are output as an index showing the user's health condition.

[0378] Step 6:

[0379] The server simulates lifespan based on the evaluation results. Using an AI model, it predicts future lifespan based on the user's current health condition and lifestyle habits. The results of this simulation are output as a lifespan prediction.

[0380] Step 7:

[0381] The server transmits the results of the lifespan simulation and the health status assessment to the user's device in a format that is easy for the user to understand (e.g., graphs or text).

[0382] Step 8:

[0383] The user device then displays the received evaluation results and life expectancy prediction results to the user, allowing the user to understand their own health condition and use these results to improve their lifestyle habits.

[0384] In this way, users can review their daily lifestyle habits and obtain specific guidelines for managing their health.

[0385] 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.

[0386] "Example 1"

[0387] In one embodiment of the present invention, an emotion engine that recognizes a user's emotions is incorporated. This emotion engine recognizes emotions from the user's voice, facial expressions, text input, etc. Specifically, it analyzes the voice of the user speaking through the microphone of a smartphone or computer, facial expressions captured through a camera, or text messages to determine the user's emotions.

[0388] "Example 2"

[0389] The output of the emotion engine influences the lifespan simulation. Specifically, the user's emotional state (joy, sadness, anger, surprise, etc.) is considered to affect their health and lifestyle, so this is incorporated into the lifespan simulation. For example, if a user is judged to be constantly stressed, it is predicted that their lifespan may be shortened.

[0390] "Example 3"

[0391] The output of the emotion engine is also used to provide feedback to users. Specifically, it helps users understand their emotional state and provides advice on how to improve their lifestyle based on that. For example, if it determines that a user has been feeling stressed for a certain period of time, it will send them a message recommending relaxation and moderate exercise.

[0392] The processing flow of each embodiment will be described below.

[0393] "Example 1"

[0394] Step 1: The user inputs speech through the microphone of their smartphone or computer, facial expressions captured through the camera, or text messages into the emotion engine.

[0395] Step 2: The emotion engine analyzes the input information and determines the user's emotion.

[0396] Step 3: The output of the emotion engine is incorporated as part of the lifespan simulation.

[0397] "Example 2"

[0398] Step 1: A user's emotional state is thought to affect their health and lifestyle, so incorporate this as part of the lifespan simulation.

[0399] Step 2: For example, if a user is determined to be constantly stressed, it is predicted that their lifespan may be shortened.

[0400] "Example 3"

[0401] Step 1: The output of the emotion engine is also used to provide feedback to the user. Step 2: The user understands their own emotional state and is then provided with advice on how to improve their lifestyle based on that.

[0402] Step 3: For example, if the user is determined to be stressed over a period of time, messages recommending relaxation and moderate exercise are sent to the user.

[0403] Example 1

[0404] Next, a description will be given of Example 1 of Form 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."

[0405] Conventional health management systems can collect information on a user's diet, sleep, exercise, and biometric information, but it is difficult to integrate and analyze this information and provide feedback that takes into account the user's emotional state. Furthermore, due to a lack of functionality to recognize the user's emotions, it is not possible to properly evaluate the user's psychological health state. This has led to the issue of insufficient comprehensive health management for users.

[0406] 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.

[0407] In this invention, the server includes means for inputting information on the user's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the user, generative AI means for natural language processing this information, AI means for simulating the user's lifespan based on the above information, means for recognizing emotions from the user's voice, facial expressions, and text input, means for integrating and analyzing the above information, and means for providing feedback based on the analysis results. This makes it possible to comprehensively evaluate the user's physiological and psychological health status and provide appropriate feedback.

[0408] "Dietary information" refers to data such as the type, amount, and calories of food consumed by the user.

[0409] "Sleep information" refers to data such as the user's sleep time, sleep quality, and wake-up time.

[0410] "Exercise information" refers to data such as the type of exercise the user performed, the duration of the exercise, and the calories burned.

[0411] "Sensor information" refers to biometric data such as the user's pulse rate, body temperature, and blood pressure.

[0412] "Generative AI" is artificial intelligence that performs natural language processing and analyzes information input by users.

[0413] "Lifespan Simulation AI" is an artificial intelligence that predicts lifespan based on a user's health data.

[0414] "Emotion recognition means" is a technology that analyzes and recognizes emotions from a user's voice, facial expressions, and text input.

[0415] "Data integration means" refers to technology that centrally manages and analyzes various data obtained from users.

[0416] "Feedback provision means" refers to technology that provides advice and notifications to users based on the analysis results.

[0417] This invention is a system in which a user inputs information about food, sleep, and exercise via a device such as a smartphone or a personal computer, obtains biometric information using a wearable device, and further recognizes emotions using an emotion engine. Specific embodiments of this system are described below.

[0418] Entering User Data

[0419] Users use a dedicated application on their smartphone or computer to enter information about their diet, sleep, and exercise. For example, a user might enter "I ate bread and eggs for breakfast. My calorie intake was 300 kcal." The application then sends this information in JSON format to the server.

[0420] Acquisition of biometric information

[0421] A user wears a wearable device such as a smartwatch to collect biometric information such as pulse rate. The smartwatch then sends the data to a smartphone via Bluetooth. The smartphone then sends the received data to a server. For example, the smartwatch measures "pulse rate: 75 bpm" and sends that data to the smartphone.

[0422] Emotion recognition by emotion engine

[0423] The device recognizes emotions from the user's voice, facial expressions, text input, etc. For example, if a user says "I'm very tired today" through the smartphone microphone, the device will convert this into text using voice recognition software (e.g., voice recognition API), then use an emotion analysis engine (e.g., emotion analysis API) to analyze the emotion and recognize "fatigue."

[0424] Data integration and analysis

[0425] The server aggregates the diet, sleep, exercise, biometric, and emotional data submitted by the user. The server organizes and analyzes the data using Python's Pandas library. For example, the server aggregates the user's daily data and generates a report to identify trends in their health and emotions.

[0426] Providing feedback

[0427] The server provides feedback to the user based on the analysis results. For example, if the analysis results show that the user has not been exercising much recently, the server generates advice such as "Get more exercise" and sends it to the user's smartphone. The notification is sent using a cloud messaging service.

[0428] Examples of specific examples and prompts

[0429] Specific examples

[0430] The user uses their smartphone to enter the following information:

[0431] Breakfast: Bread and eggs, 300 kcal

[0432] Sleep time: 7 hours

[0433] Exercise: Running, 30 minutes

[0434] The user also uses a smartwatch to measure their pulse rate and transmits the data to the system, and then speaks to the smartphone microphone, saying, "I'm very tired today."

[0435] Prompt Sentence Examples

[0436] "Describe a system in which a user uses a smartphone to input diet, sleep, and exercise information, and a wearable device to obtain pulse rate. Also, explain how an emotion engine can be used to recognize the user's emotions."

[0437] In this way, it clearly explains how the user, device, and server work together to collect, analyze, and provide feedback on data.

[0438] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0439] Step 1:

[0440] Users open a dedicated application on their smartphone or computer and enter information about their meals, sleep, and exercise. The entered information is sent to the server in JSON format. For example, a user might enter "I ate bread and eggs for breakfast. My calorie intake was 300 kcal." This information is converted to JSON format by the application and sent to the server.

[0441] Step 2:

[0442] A user wears a wearable device such as a smartwatch and collects biometric information such as pulse rate. The smartwatch sends the data to a smartphone via Bluetooth. The smartphone then sends the received data to a server. For example, the smartwatch measures "pulse rate: 75 bpm" and sends that data to the smartphone. This data is then sent to the server by the smartphone.

[0443] Step 3:

[0444] The device recognizes emotions from the user's voice, facial expressions, text input, etc. When a user says "I'm very tired today" through the smartphone microphone, the device uses voice recognition software to convert the speech into text. It then analyzes the text using an emotion analysis engine to recognize "fatigue." The analysis results are sent from the device to a server.

[0445] Step 4:

[0446] The server integrates the diet, sleep, exercise, biometric, and emotional data sent by the user. The server organizes and analyzes the data using Python's Pandas library. For example, the server may integrate the user's daily data and generate a report to understand their health and emotional trends. This report is then stored on the server.

[0447] Step 5:

[0448] The server provides feedback to the user based on the analysis results. For example, if the analysis results show that the user has not been exercising much recently, the server generates advice such as "Get more exercise" and sends it to the user's smartphone. The notification is sent using a cloud messaging service.

[0449] (Application example 1)

[0450] Next, a description will be given of Application Example 1 of Embodiment 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."

[0451] In modern society, proposing and quickly delivering optimal meal menus based on individual health conditions and emotions is an important issue. However, conventional food delivery services do not consider the user's health information or emotions when proposing meals, making it difficult to contribute to maintaining the user's health and emotional stability.

[0452] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, emotion engine means for recognizing a person's emotions, means for proposing an optimal meal menu based on the emotions recognized by the emotion engine and the diet, sleep, and exercise information, and means for requesting the proposed meal menu from a food delivery service. This makes it possible to propose and quickly provide an optimal meal menu based on the user's health condition and emotions.

[0453] "Diet, sleep, and exercise information" refers to data such as the type of food a user eats in their daily life, the calories they consume, the amount of sleep they get, and the type and duration of their exercise.

[0454] "Various sensor information" refers to biological information such as pulse rate, blood pressure, and body temperature obtained from wearable devices, etc.

[0455] "Generative AI" is artificial intelligence that uses natural language processing to analyze information entered by users and generate appropriate responses and suggestions.

[0456] "AI that simulates lifespan" is an artificial intelligence that predicts future health conditions and lifespans based on the user's health information.

[0457] An "emotion engine" is a system that recognizes emotions from the user's voice, facial expressions, text input, etc.

[0458] "Means for suggesting optimal meal menus" refers to a function that selects and suggests optimal meal menus for users based on their health information and emotions.

[0459] "Means for requesting food delivery services" refers to a function for ordering the suggested meal menu from a food delivery service.

[0460] A system for implementing this invention includes means for inputting information on a user's diet, sleep, and exercise, means for acquiring various sensor information from a person (such as pulse rate), generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, emotion engine means for recognizing a person's emotions, means for suggesting an optimal meal menu based on the emotions recognized by the emotion engine and the diet, sleep, and exercise information, and means for requesting the suggested meal menu from a food delivery service.

[0461] Program processing explanation

[0462] Hardware and Software Configuration

[0463] User Device: The user inputs information about their diet, sleep, and exercise using a smartphone or computer. This includes iOS and Android applications.

[0464] Wearable devices: Smartwatches and fitness bands are used to collect biometric information such as pulse rate. Examples include Fitbit and Apple Watch.

[0465] Server: The server for processing data uses a cloud service (e.g., AWS (registered trademark), Google (registered trademark) Cloud).

[0466] Generative AI: Generative AI models such as GPT-3 and BERT are used for natural language processing.

[0467] Emotion Engine: Uses Google Cloud Speech-to-Text API, OpenCV, Dlib, NLTK, etc. to recognize emotions from user voice, facial expressions, and text input.

[0468] Data processing and calculation

[0469] 1. User device: The user inputs information about food, sleep, and exercise. This data is sent to the server via the application.

[0470] 2. Wearable device: Biometric information (such as pulse rate) is acquired in real time and sent to a server.

[0471] 3. Server: The received data is input into a generative AI model and natural language processing is performed, which analyzes the user's health condition.

[0472] 4. Emotion Engine: Analyzes the user's voice, facial expressions, and text input to recognize emotions. The recognized emotions are input into a generative AI model.

[0473] 5. Meal Menu Suggestion: The generative AI model suggests optimal meal menus based on the user's health information and emotions.

[0474] 6. Request to food delivery service: The suggested meal menu is requested from the food delivery service.

[0475] Specific examples

[0476] For example, if a user types "I feel tired today," the emotion engine will recognize "fatigue" and suggest low-calorie, nutritious meals. Below is an example of a prompt for the generative AI model:

[0477] Prompt Sentence Examples

[0478] If the user's emotion is "fatigue," their calorie intake is 2000 kcal, they have 6 hours of sleep, and they have 30 minutes of exercise, please suggest the optimal meal menu.

[0479] In this way, it becomes possible to suggest and quickly provide optimal meal menus based on the user's health condition and emotions.

[0480] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0481] Step 1:

[0482] Users use their smartphones or computers to enter information about their diet, sleep, and exercise. Specifically, they enter information about the food they eat, the calories they consume, how much sleep they get, and the type and duration of their exercise into the application's input form. This data is then sent from the user's device to the server. The input data is formatted in JSON, XML, or other formats.

[0483] Step 2:

[0484] Wearable devices (e.g., smartwatches and fitness bands) collect biometric information such as the user's pulse rate in real time. The collected data is sent to the user's device via Bluetooth or Wi-Fi, and then from the user's device to a server. The data format is generally JSON or CSV.

[0485] Step 3:

[0486] The server receives dietary, sleep, and exercise information sent by the user, as well as biometric information sent from the wearable device. The received data is input into a generative AI model for natural language processing. Specifically, the data is preprocessed and input as text data into a generative AI model (e.g., GPT-3 or BERT). The generative AI model analyzes the user's health condition and outputs the analysis results in text format.

[0487] Step 4:

[0488] The server inputs the user's voice, facial expression, and text input into the emotion engine to recognize emotions. Specifically, the voice data is converted to text using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV and Dlib. The text data is analyzed for emotions using NLTK. The emotion engine outputs the recognized emotions in text format.

[0489] Step 5:

[0490] The server proposes the optimal meal menu to the user based on the analysis results of the generative AI model and the output of the emotion engine. Specifically, a prompt sentence is input into the generative AI model to generate the optimal meal menu. An example of a prompt sentence is, "If the user's emotion is 'fatigue,' their calorie intake is 2000 kcal, they sleep for 6 hours, and they exercise for 30 minutes, please suggest the optimal meal menu." The generative AI model outputs the optimal meal menu in text format.

[0491] Step 6:

[0492] The server requests the suggested meal menu from the food delivery service. Specifically, it sends a request including the suggested meal menu to the food delivery service's API. The API request typically uses the HTTP POST method, and the request body contains data in JSON format. The food delivery service receives the request and delivers the meal to the user.

[0493] Example 2

[0494] Next, a description will be given of Example 2 of Form 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."

[0495] In modern society, personal health management is an important issue, but there is no system that can comprehensively analyze various information such as diet, sleep, exercise, and emotions to predict individual health conditions and life expectancy. Conventional systems can analyze these information individually, but it is difficult to comprehensively analyze them and reflect them in life expectancy simulations. Furthermore, there is a lack of systems that take into account the impact of emotional states on health conditions and life expectancy. This makes it difficult for users to accurately understand their own health conditions and maintain appropriate lifestyle habits.

[0496] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0497] In this invention, the server includes means for inputting information on diet, sleep, and exercise, means for acquiring various types of sensor information (such as pulse rate), generative AI means for natural language processing of this information, means for classifying dietary content into food groups and nutrients, means for dividing sleep time into deep sleep and light sleep, means for classifying exercise information into types and intensities of exercise, emotion engine means for analyzing emotional states, and AI means for simulating a person's lifespan based on the above information. This makes it possible to comprehensively analyze a user's diverse health information and perform a lifespan simulation that also takes emotional states into account.

[0498] "Dietary information" refers to the contents of the foods and drinks consumed by the user, and is information categorized into food groups and nutrients.

[0499] "Sleep information" is information that indicates the user's sleep time and quality, and is divided into deep sleep and light sleep time.

[0500] "Exercise information" is information that indicates the type and intensity of exercise performed by the user, and is classified as aerobic exercise, anaerobic exercise, etc.

[0501] "Sensor information" is data for measuring the user's physical condition, and includes physiological indicators such as pulse rate and body temperature.

[0502] "Generative AI" refers to artificial intelligence that analyzes input natural language data and converts it into a specific format.

[0503] The "emotion engine" is a system that analyzes the user's emotional state and classifies emotions such as joy, sadness, anger, and surprise.

[0504] "Lifespan Simulation" is the process of calculating a user's predicted lifespan based on their health, lifestyle, and emotional state.

[0505] MODE FOR CARRYING OUT THE INVENTION

[0506] The present invention is a system for integrating and analyzing a user's health information to perform a lifespan simulation. Specific embodiments of this system will be described below.

[0507] 1. System Configuration

[0508] The system consists of a terminal and a server that collects and analyzes information entered by users about diet, sleep, exercise, and emotions. Terminals include smartphones, PCs, and wearable devices. The server analyzes the data using a generative AI model and emotion engine to perform a lifespan simulation.

[0509] 2. Data Collection

[0510] The user uses a dedicated application to input information about their diet, sleep, exercise, and emotions. For example, the user might input, "I ate bread and eggs for breakfast," "I slept for seven hours last night," "I jogged for 30 minutes," or "I feel very happy right now." The device collects this information and sends it to the server.

[0511] 3. Data Analysis

[0512] The server passes the collected data to a generative AI model. The generative AI model categorizes dietary information into food groups and nutrients, sleep information into periods of deep and light sleep, and exercise information into types and intensities of exercise. For example, it might categorize "bread and eggs" as "carbohydrates, protein," "7 hours of sleep" as "2 hours of deep sleep, 5 hours of light sleep," and "30 minutes of jogging" as "aerobic exercise, moderate intensity."

[0513] 4. Emotion analysis

[0514] The user inputs their emotional state into a dedicated application. For example, they input "I'm very happy today." The device collects the emotional information and sends it to the server. The server then uses an emotion engine to analyze the emotional state and classifies "I'm very happy" as "joy."

[0515] 5. Life simulation

[0516] The server integrates the output of the generative AI model and the emotion engine to predict the user's lifespan based on their health and lifestyle. For example, if the server determines that the user is constantly stressed, it predicts that their lifespan may be shortened.

[0517] Specific examples

[0518] The user inputs information into the application, such as "I ate bread and eggs for breakfast," "I slept 7 hours last night," "I jogged for 30 minutes," and "I feel very happy right now." The device collects this information and sends it to the server. The server uses a generative AI model to classify the food information as "carbohydrates, protein," the sleep information as "2 hours of deep sleep, 5 hours of light sleep," and the exercise information as "aerobic exercise, moderate intensity." The server then uses an emotion engine to classify the emotional information as "joy." The server integrates this information and predicts lifespan based on the user's health condition and lifestyle habits.

[0519] Prompt Sentence Examples

[0520] "Please create a program that analyzes the diet, sleep, exercise, and emotional information entered by the user and performs a lifespan simulation. Specifically, please include processing to categorize dietary information into food groups and nutrients, divide sleep information into deep sleep and light sleep, and analyze emotional information to reflect in the lifespan simulation."

[0521] The above is a specific embodiment for carrying out the present invention.

[0522] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0523] Program processing flow

[0524] Step 1: Data entry

[0525] The user inputs information about diet, sleep, exercise, and emotions using a dedicated application.

[0526] Input: Text data entered by the user (e.g., "I had bread and eggs for breakfast," "I slept 7 hours last night," "I went jogging for 30 minutes," "I'm very happy right now")

[0527] Output: User input data stored on the device

[0528] Step 2: Data collection

[0529] The terminal collects the user's input data and sends it to the server.

[0530] Input: User input data stored on the device

[0531] Output: User input data sent to the server

[0532] Step 3: Analysis of dietary information

[0533] The server uses the generated AI model to analyze the dietary information and classify it into food groups and nutrients.

[0534] Input: Meal information sent to the server (e.g., "I had bread and eggs for breakfast")

[0535] Data manipulation: A generative AI model classifies "bread and eggs" as "carbohydrates, protein"

[0536] Output: Categorised food information (e.g. "Carbohydrates, Protein")

[0537] Step 4: Analyze your sleep information

[0538] The server uses the generated AI model to analyze sleep information and divide it into periods of deep sleep and light sleep.

[0539] Input: Sleep information sent to the server (e.g., "I slept 7 hours last night")

[0540] Data processing: A generative AI model classifies "7 hours of sleep" as "2 hours of deep sleep, 5 hours of light sleep"

[0541] Output: Categorised sleep information (e.g. "2 hours of deep sleep, 5 hours of light sleep")

[0542] Step 5: Analysis of movement information

[0543] The server uses the generated AI model to analyze the exercise information and classify it into exercise type and intensity.

[0544] Input: Exercise information sent to the server (e.g., "I jogged for 30 minutes")

[0545] Data processing: A generative AI model classifies "30 minutes of jogging" as "aerobic exercise, medium intensity"

[0546] Output: Classified exercise information (e.g., "Aerobic exercise, medium intensity")

[0547] Step 6: Emotional Analysis

[0548] The server uses an emotion engine to analyze the emotion information and classify the emotional state.

[0549] Input: Emotional information sent to the server (e.g., "I'm very happy right now")

[0550] Data processing: The emotion engine classifies "I'm very happy" as "Joy"

[0551] Output: Classified emotion information (e.g., "joy")

[0552] Step 7: Data Integration

[0553] The server integrates the output of the generative AI model and the emotion engine.

[0554] Input: Categorized food information, sleep information, exercise information, emotional information

[0555] Data processing: Compile each piece of information into a single data set

[0556] Output: A consolidated dataset

[0557] Step 8: Lifetime simulation

[0558] The server uses the integrated data set to predict life expectancy, taking into account the user's health condition and lifestyle habits.

[0559] Input: Integrated dataset

[0560] Data calculation: Applying algorithms to calculate life expectancy based on health status and lifestyle habits

[0561] Output: predicted lifespan (e.g. "lifespan is predicted to be 80 years")

[0562] The above are the specific processing steps of the program of this system.

[0563] (Application example 2)

[0564] Next, a description will be given of Application Example 2 of Form 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."

[0565] In modern society, it is important to provide appropriate meal plans based on individual health conditions and lifestyle habits. However, conventional food delivery services have difficulty proposing meal plans that take into account the user's health and emotional state, and are therefore unable to provide comprehensive support for the user's health. Furthermore, there is a lack of simulations that take into account the impact of the user's emotional state on lifespan, so more accurate health management is required.

[0566] 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.

[0567] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for analyzing the user's emotional state and reflecting it in the lifespan simulation, means for generating and notifying the user of an optimal meal plan based on the user's health state, and means for providing meals through a food delivery service. This makes it possible to propose and provide meal plans that comprehensively consider the user's health state and emotional state.

[0568] "Dietary information" refers to data such as the contents, quantity, and time of the food and beverages consumed by the user.

[0569] "Sleep information" refers to data such as the user's sleep time, the time spent in deep and light sleep, and the quality of their sleep.

[0570] "Exercise information" refers to data such as the type, duration, intensity, and calories burned of the exercise performed by the user.

[0571] "Sensor information" is information for acquiring biometric data such as the user's pulse rate, body temperature, and blood pressure.

[0572] "Generative AI" is artificial intelligence that uses natural language processing to analyze input data and convert it into an appropriate format.

[0573] "Lifespan Simulation" is a simulation that predicts a user's lifespan based on their health condition, lifestyle habits, and emotional state.

[0574] "Emotional state" refers to the user's emotional state, such as happiness, sadness, anger, or surprise.

[0575] A "meal plan" is a suggested meal plan based on the user's health and emotional state.

[0576] A "food delivery service" is a service that delivers meals ordered by a user to a specified location.

[0577] The system for implementing this invention inputs a user's diet, sleep, and exercise information, acquires various sensor information, analyzes this information using generative AI that processes natural language, and performs a lifespan simulation. Furthermore, it analyzes the user's emotional state, reflects it in the lifespan simulation, and generates and notifies the user of an optimal meal plan based on the user's health condition. The system then provides meals via a food delivery service.

[0578] System configuration

[0579] 1. Data Collection:

[0580] Hardware: Smartphones, smartwatches

[0581] Software: Health management app, emotion analysis app

[0582] Data: diet, sleep, exercise, emotional state

[0583] 2. Data Analysis:

[0584] Software: Natural language processing libraries (e.g., spaCy, NLTK)

[0585] What happens:

[0586] Categorize your meals into food groups and nutrients

[0587] Divide your sleep into deep and light sleep

[0588] Emotional state analysis and reflection in lifespan simulation

[0589] 3. Life simulation:

[0590] Software: Simulation engine (e.g. AnyLogic)

[0591] What happens:

[0592] Predict lifespan by taking into account the user's emotional state

[0593] 4. Meal plan suggestions:

[0594] Software: Recommendation systems (e.g., TensorFlow, PyTorch)

[0595] What happens:

[0596] Generates optimal meal plans based on the user's health status

[0597] 5. Notices and Orders:

[0598] Hardware: Smartphone

[0599] Software: Food delivery app

[0600] What happens:

[0601] Inform users about the best meal plan and take their order

[0602] Specific examples

[0603] The user enters their dietary information into a health management app on their smartphone, and their sleep and exercise data is collected using a smartwatch. An emotion analysis app analyzes the user's emotional state and performs a lifespan simulation based on this data. Based on the simulation results, the user is presented with an optimal meal plan, and the food delivery app completes the order.

[0604] Prompt Sentence Examples

[0605] Analyze the user's diet, sleep time, exercise amount, and emotional state to simulate their lifespan. Based on the simulation results, propose an optimal meal plan for the user and implement a function to accept orders via a food delivery app.

[0606] In this way, it becomes possible to propose and provide meal plans that take into consideration the user's overall health and emotional state.

[0607] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0608] Step 1:

[0609] A user inputs the details of their diet into a health management app on their smartphone. The data entered includes the name of the food, the amount consumed, and the time of consumption. This allows dietary information to be collected.

[0610] Step 2:

[0611] The user wears a smartwatch to record their sleep time and exercise amount. The smartwatch collects sensor information such as pulse rate, number of steps, exercise time, and sleep time, thereby collecting sleep and exercise information.

[0612] Step 3:

[0613] The device uses an emotion analysis app to analyze the user's emotional state. The input data includes the user's facial expressions, voice tone, text messages, etc. This allows the emotional state to be analyzed.

[0614] Step 4:

[0615] The server analyzes the collected dietary, sleep, exercise, and emotional state information using generative AI that processes natural language. Specifically, it categorizes dietary content into food groups and nutrients, divides sleep time into deep and light sleep, and quantifies emotional state. This converts the data into an appropriate format.

[0616] Step 5:

[0617] The server performs a lifespan simulation based on the data analyzed by the generative AI. Using a simulation engine, the server predicts the user's lifespan, taking into account their health and emotional state. This produces the lifespan simulation results.

[0618] Step 6:

[0619] The server generates an optimal meal plan for the user based on the results of the lifespan simulation. A recommendation system is used to suggest foods and meal menus that are suitable for the user's health condition. This generates a meal plan.

[0620] Step 7:

[0621] The server notifies the user of the generated meal plan via their smartphone. The user receives the notification and orders meals through a food delivery app, which provides the meal plan to the user.

[0622] Step 8:

[0623] The food delivery service accepts the user's order and delivers the meal to the specified location, allowing the user to receive meals based on the proposed meal plan.

[0624] Example 3

[0625] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0626] Conventional health management systems could collect information on a user's diet, sleep, exercise, and biological information individually, but it was difficult to analyze them comprehensively and simulate the user's lifespan. They also could not provide feedback that took emotional state into account. This meant that users could not accurately understand their own health status or receive specific advice on improving their lifestyle habits.

[0627] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0628] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various biological information of the person, means for preprocessing the information, means for evaluating the health state based on the preprocessed information, means for simulating the person's lifespan based on the evaluation results, means for generating feedback based on the simulation results, and means for analyzing the emotional state and generating feedback based on the emotions. This allows the user to comprehensively understand their own health state and receive specific advice for improving their lifestyle habits.

[0629] "Dietary information" refers to information about the contents and nutrients of the meals consumed by the user.

[0630] "Sleep information" refers to information about the user's sleep time and sleep quality.

[0631] "Exercise information" refers to information about the type, frequency, and intensity of exercise performed by the user.

[0632] "Biometric information" refers to physiological data such as the user's heart rate, blood pressure, and body temperature.

[0633] "Preprocessing" refers to the process of filling in missing values ​​in collected data and detecting and correcting outliers.

[0634] "Health status assessment" is the process of analyzing and assessing the user's health status based on the preprocessed data.

[0635] "Lifespan simulation" is the process of predicting future health risks and lifespan based on a user's current lifestyle and health status.

[0636] "Feedback" is specific advice or recommendations provided to users based on simulation results and health assessments.

[0637] "Emotional state analysis" is the process of analyzing a user's emotional data and assessing their emotional state, such as stress or happiness.

[0638] "Emotion-based feedback" is specific advice or recommendations provided to users based on an analysis of their emotional state.

[0639] MODE FOR CARRYING OUT THE INVENTION

[0640] The present invention is a system for comprehensively evaluating a user's health condition and simulating a user's lifespan. Specific embodiments of this system will be described below.

[0641] Data collection

[0642] Users use a smartphone app to input their daily diet, sleep time, and exercise, such as what they had for breakfast, what time they went to bed at night, and the distance they jog, to collect detailed data about the user's lifestyle.

[0643] The terminal automatically collects biometric information such as the user's heart rate and blood pressure through a wearable device (e.g., a smart watch), and transmits this data to a server in real time.

[0644] Data transmission and storage

[0645] The device sends the collected information on food, sleep, exercise, and biometric data to a server. The data is encrypted and sent securely. The server then stores the received data in a database, using a relational database such as MySQL or PostgreSQL.

[0646] Data Preprocessing

[0647] The server preprocesses the stored data, specifically by filling in missing values ​​and detecting outliers. For example, if the heart rate shows an abnormally high value, the data is excluded.

[0648] Health assessment

[0649] The server evaluates the user's health status based on the preprocessed data. It uses AI models (e.g., TensorFlow, PyTorch) to analyze the nutritional balance of meals, sleep quality, and exercise frequency and intensity. The evaluation results are stored in a database, allowing the user's health history to be tracked.

[0650] Lifespan Simulation

[0651] The server uses an AI model based on the evaluation results to simulate the user's lifespan. For example, it calculates the predicted lifespan if the user continues their current lifestyle. The simulation results are stored in a database, allowing users to compare them with past simulation results.

[0652] Providing feedback

[0653] The server generates feedback for the user based on the simulation results. For example, it creates specific advice such as, "Your recent meals have been well-balanced in terms of nutrition. Keep it up. Also, since you're not getting enough sleep, I recommend going to bed 30 minutes earlier each night." The generated feedback is sent to the user's device, and the user can check it via a smartphone app.

[0654] Use of emotion engine

[0655] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user has been feeling stressed for a certain period of time, it will proceed to the next step based on that information. The server then generates feedback for the user based on the results of the analysis of the emotional state. For example, it could create advice such as, "You seem to be under a lot of stress lately. We recommend relaxation and moderate exercise." The generated emotion-based feedback is sent to the user's device, where the user can check the feedback through a smartphone app.

[0656] Examples and prompts

[0657] As a specific example, a user enters their daily diet, sleep duration, and exercise amount through a smartphone app. A wearable device measures their heart rate and blood pressure, and sends this data to a server. The server uses this data to evaluate the user's health and simulates their lifespan using an AI model. As a result, the user is given feedback such as, "Your recent diet has been well-balanced. Please continue at this pace. Also, because you are not getting enough sleep, we recommend that you go to bed 30 minutes earlier each night."

[0658] An example of a prompt sentence is, "Evaluate the user's health status and simulate their lifespan based on their diet, sleep, exercise information, and biometric information. As a result, provide the user with advice that will help them manage their health and improve their lifestyle."

[0659] In this way, the user can understand his / her own health condition and receive specific advice for improving his / her lifestyle. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0660] Step 1:

[0661] Users use a smartphone app to input their daily diet, sleep time, and exercise amount. The input data is saved on the device as dietary information, sleep information, and exercise information. This allows detailed data on the user's lifestyle habits to be collected.

[0662] Step 2:

[0663] The terminal automatically collects biometric information such as the user's heart rate and blood pressure through the wearable device, and transmits the collected biometric information to a server in real time, thereby obtaining the user's physiological data.

[0664] Step 3:

[0665] The device sends the collected information on meals, sleep, exercise, and biometrics to a server. The data is encrypted and sent securely. The server stores the received data in a database. This allows all data to be managed centrally.

[0666] Step 4:

[0667] The server preprocesses the stored data. Specifically, it complements missing values ​​and detects outliers. For example, if the heart rate shows an abnormally high value, it will exclude that data. The preprocessed data is then converted into a format suitable for analysis.

[0668] Step 5:

[0669] The server evaluates the user's health status based on the preprocessed data. It uses AI models (e.g., TensorFlow, PyTorch) to analyze the nutritional balance of meals, sleep quality, and exercise frequency and intensity. The evaluation results are stored in a database as an index of the user's health status.

[0670] Step 6:

[0671] The server uses an AI model based on the evaluation results to simulate the user's lifespan. For example, it calculates the predicted lifespan if the user continues their current lifestyle. The simulation results are stored in a database, allowing users to compare them with past simulation results.

[0672] Step 7:

[0673] The server generates feedback for the user based on the simulation results. For example, it creates specific advice such as, "Your recent meals have been well-balanced in terms of nutrition. Keep it up. Also, you're not getting enough sleep, so I recommend you go to bed 30 minutes earlier each night." The generated feedback is sent to the user's device.

[0674] Step 8:

[0675] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user has been feeling stressed for a certain period of time, it uses that information to proceed to the next step. The results of the emotional state analysis are stored in a database.

[0676] Step 9:

[0677] The server generates feedback for the user based on the analysis of the emotional state. For example, it might create advice such as, "You seem to be under a lot of stress lately. We recommend relaxation and moderate exercise." The generated feedback based on the emotions is sent to the user's device.

[0678] In this way, users can understand their own health status and receive specific advice on how to improve their lifestyle habits.

[0679] (Application example 3)

[0680] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0681] Conventional health management systems can evaluate a user's health status based on information such as diet, sleep, and exercise, but they are unable to provide personalized advice that takes into account their emotional state. As a result, they are unable to provide appropriate feedback based on the user's emotional state, making comprehensive health management difficult. Furthermore, they do not offer lifespan simulations, meaning there is a lack of specific indicators for users to review their lifestyle habits.

[0682] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for analyzing emotional states, and means for providing personalized advice based on the health state and emotional states. This makes it possible to comprehensively evaluate the user's health state and emotional state and provide specific advice based on the results of the lifespan simulation.

[0683] "Dietary information" refers to data such as the types, amounts, and nutritional components of the foods and beverages consumed by the user.

[0684] "Sleep information" refers to data such as the user's sleep time, sleep quality, and how they fall asleep and wake up.

[0685] "Exercise information" refers to data such as the type, frequency, intensity, and duration of exercise performed by the user.

[0686] "Sensor information" refers to data obtained from various sensors for acquiring the user's biometric data, and specifically includes pulse rate, body temperature, blood pressure, and the like.

[0687] "Generative AI" is an artificial intelligence system that processes input data using natural language processing, extracting and analyzing necessary information.

[0688] "Lifespan Simulation AI" is an artificial intelligence system that predicts lifespan based on the user's health condition and lifestyle habits.

[0689] "Emotional state" is data that indicates the user's psychological state, including stress levels and mood fluctuations.

[0690] "Personalized advice" refers to specific improvement suggestions and feedback provided based on a user's individual health and emotional state.

[0691] The system for implementing this invention comprehensively evaluates the user's health and emotional state and provides specific advice based on the results of a lifespan simulation. Specific embodiments of this system are described below.

[0692] System Configuration

[0693] The system consists of the following main components:

[0694] 1. User device: A device such as a smartphone or tablet that provides an interface for users to enter information about their diet, sleep, and exercise.

[0695] 2. Wearable devices: Devices that collect biometric data such as a user's pulse rate, body temperature, and blood pressure. These include smartwatches and fitness trackers.

[0696] 3. Server: The central component that processes and analyzes data and has the following functions:

[0697] Generative AI: Performs natural language processing on data entered by the user, extracting and analyzing necessary information.

[0698] Lifespan Simulation AI: Predicts lifespan based on health status and lifestyle habits.

[0699] Emotion Engine: Analyzes the user's emotional state and generates appropriate feedback.

[0700] Personalized advice generation: Providing specific improvement suggestions to users based on their health and emotional state.

[0701] Data acquisition and processing

[0702] The user device receives information about diet, sleep, and exercise entered by the user and sends it to a server. The wearable device collects the user's biometric data in real time and sends it to the server. The server receives this data and uses generative AI to perform natural language processing to extract the necessary information.

[0703] Health and lifespan simulation

[0704] The server evaluates the user's health status based on the extracted data and predicts the user's lifespan using a lifespan simulation AI. The prediction results are then fed back to the user's device.

[0705] Emotional state analysis and feedback

[0706] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user has been feeling stressed for a certain period of time, it generates messages recommending relaxation and moderate exercise.

[0707] Providing personalized advice

[0708] The server generates specific improvement suggestions for the user based on their health and emotional state, and these suggestions are sent to the user's device for them to put into practice in their daily lives.

[0709] Specific examples

[0710] For example, when a user inputs information about their diet, sleep, exercise, and biometrics into the app, the server calculates a health score based on this data and predicts their life expectancy. It also analyzes the user's emotional state and provides relaxation advice if they are under a lot of stress.

[0711] Prompt Sentence Examples

[0712] "Write a Python program that calculates a health score based on the user's diet, sleep, exercise, and biological information, and predicts their lifespan. Also, add a function that uses an emotion engine to analyze the user's emotional state and generate appropriate feedback."

[0713] In this way, a system is realized that comprehensively evaluates the user's health and emotional state and provides specific suggestions for improvement, thereby supporting the user in living a healthier life.

[0714] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0715] Step 1:

[0716] The user device receives information about meals, sleep, and exercise entered by the user. The entered information includes detailed data such as the type and amount of meals, the duration and quality of sleep, and the type and frequency of exercise. This data is then sent from the user device to the server.

[0717] Step 2:

[0718] The wearable device collects the user's biometric data in real time, including pulse rate, body temperature, blood pressure, etc. This biometric data is also sent from the wearable device to a server.

[0719] Step 3:

[0720] The server receives data sent from the user's terminal and wearable device. The received data undergoes natural language processing using generative AI to extract the necessary information. Specifically, the data is normalized and missing values ​​are filled in.

[0721] Step 4:

[0722] The server evaluates the user's health status based on the extracted data, including calculating a health score based on a comprehensive evaluation of diet, sleep, exercise, and biometric data.

[0723] Step 5:

[0724] The server uses the health score as input to predict the user's lifespan using a lifespan simulation AI, and the predicted lifespan is fed back to the user's device.

[0725] Step 6:

[0726] The server uses an emotion engine to analyze the user's emotional state, including stress levels and mood swings. The emotion engine evaluates the user's emotional state based on the user's input data and biometric data.

[0727] Step 7:

[0728] The server generates appropriate feedback based on the analysis of the user's emotional state. For example, if the server determines that the user has been feeling stressed for a certain period of time, it generates a message recommending relaxation or moderate exercise.

[0729] Step 8:

[0730] The server generates personalized advice based on the user's health and emotional state. The advice is then sent to the user's device, allowing them to put it into practice in their daily lives. Specific advice includes suggestions for improving their diet and recommending exercise.

[0731] The above processing steps realize a system that comprehensively evaluates the user's health and emotional state and provides specific suggestions for improvement.

[0732] 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.

[0733] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0734] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0735] 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.

[0736] [Second embodiment]

[0737] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0738] 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.

[0739] 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).

[0740] 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.

[0741] 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.

[0742] 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).

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] In the smart glasses 214, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. 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 performed by the processor 46 executing the reception output program 60 on the RAM 48.

[0748] This is realized by operating as the control unit 46A in accordance with the force program 60.

[0749] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0750] "Example 1"

[0751] In one embodiment of the present invention, the user inputs information about food, sleep, and exercise via a device such as a smartphone or PC. Specifically, the user inputs information such as the contents of meals, calorie intake, sleep time, and type and time of exercise. The user also uses a wearable device (e.g., a smartwatch or fitness band) to obtain biometric information such as pulse rate and transmit it to the system. "Embodiment Example 2"

[0752] In this embodiment of the present invention, generative AI processes the information acquired above using natural language processing. Specifically, it analyzes information on diet, sleep, and exercise as text data and converts each piece of information into an appropriate format. For example, it may classify dietary content into food groups and nutrients, or divide sleep time into deep and light sleep periods.

[0753] "Example 3"

[0754] In this embodiment of the present invention, AI simulates a person's lifespan based on the information processed above. Specifically, it combines information on diet, sleep, and exercise with biometric information to evaluate the user's health condition and lifestyle habits, and predicts their lifespan based on that. The prediction results are fed back to the user and can be used to improve their health management and lifestyle habits.

[0755] The processing flow of each embodiment will be described below.

[0756] "Example 1"

[0757] Step 1: The user enters information about food, sleep, and exercise via a device such as a smartphone or computer. Specifically, the user enters information about the food they eat, the calories they consume, how much sleep they get, and the type and duration of their exercise.

[0758] Step 2: The user uses a wearable device (e.g., a smart watch or fitness band) to acquire biometric information such as pulse rate and transmit it to the system.

[0759] "Example 2"

[0760] Step 1: The generative AI performs natural language processing on the information acquired above. Specifically, it analyzes information about diet, sleep, and exercise as text data.

[0761] Step 2: Transform each piece of information into an appropriate format, such as categorizing your diet into food groups and nutrients, or dividing your sleep into periods of deep and light sleep.

[0762] "Example 3"

[0763] Step 1: Based on the information processed above, the AI ​​simulates a person's lifespan. Specifically, it combines information on diet, sleep, and exercise with biometric information to evaluate the user's health and lifestyle.

[0764] Step 2: Based on this, life expectancy is predicted. This prediction result is fed back to the user and used to help improve health management and lifestyle habits.

[0765] Example 1

[0766] Next, a description will be given of Example 1 of Form 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."

[0767] Conventional health management systems have had difficulty effectively integrating information about diet, sleep, and exercise entered by users with biometric information obtained from wearable devices and providing the analysis results as feedback to users. Furthermore, there has been insufficient simulation of lifespan based on this information. This has made it difficult for users to accurately understand their own health status and maintain appropriate lifestyle habits.

[0768] 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.

[0769] In this invention, the server includes means for receiving information on diet, sleep, and exercise input by the user, means for receiving biometric information acquired from the wearable device, means for storing the received information in a database, means for analyzing the stored information, means for transmitting the analysis results to the user's terminal, means for performing natural language processing using generative AI, and AI means for simulating a person's lifespan based on the above information. This makes it possible to comprehensively analyze the information input by the user and the biometric information acquired from the wearable device and provide appropriate feedback to the user.

[0770] "Dietary information" refers to information about the contents of meals and calories consumed by the user.

[0771] "Sleep information" refers to information about the user's sleep time and sleep quality.

[0772] "Exercise information" refers to information about the type of exercise performed by the user, the duration of the exercise, and the calories burned.

[0773] "Sensor information" refers to biological information such as pulse rate obtained from a wearable device.

[0774] A "wearable device" is a device worn by a user that measures biometric information, and examples include smartwatches and fitness bands.

[0775] A "server" is a computer system that receives, stores, and analyzes information sent by users.

[0776] "Database" means a data management system for storing information received by the server.

[0777] "Analysis" is the process by which the server evaluates data based on stored information using statistical analysis and machine learning models.

[0778] "Generative AI" is an artificial intelligence model for performing natural language processing.

[0779] "Lifespan simulation" is the process of predicting a user's lifespan based on the user's input information and biometric information.

[0780] "Feedback" refers to the transmission of information to provide analysis results to users.

[0781] MODE FOR CARRYING OUT THE INVENTION

[0782] This invention is a system in which a user inputs information about diet, sleep, and exercise via a terminal such as a smartphone or a personal computer, and biometric information is acquired using a wearable device. Specific embodiments of this system are described below.

[0783] User Data Entry

[0784] Users use their smartphones or computers to input information about their diet, sleep, and exercise. For example, if a user inputs "two slices of toast, one banana, and one cup of coffee" for breakfast, the application will calculate the calories from this information and display the total calorie intake. The software used includes smartphone applications and web applications.

[0785] Acquisition of biometric information

[0786] Users wear a wearable device (e.g., a smartwatch or fitness band) and collect biometric information such as their pulse rate during exercise and daily life. For example, if a user goes for a one-hour run, the smartwatch will measure their pulse rate and calories burned while they run. The measured data is sent to a smartphone via Bluetooth or Wi-Fi.

[0787] Data transmission and storage

[0788] The device (smartphone or PC) sends the information entered by the user and the biometric information obtained from the wearable device to a server. The HTTPS protocol is used for transmission, and the data is encrypted. The server stores the received data in a database, which uses a relational database such as MySQL or PostgreSQL.

[0789] Data analysis

[0790] The server analyzes the stored data using Python libraries such as Pandas and Scikit-learn. For example, it checks whether the calorie intake of a meal exceeds the target value and evaluates the balance between the amount of exercise and the calories burned. It also uses generative AI to perform natural language processing and provide easy-to-understand feedback to the user.

[0791] Feedback of results

[0792] The server sends the analysis results to the user's device, where they can check them through a smartphone application. For example, if their calorie intake exceeds their target, the application will warn them. It will also suggest additional exercise if they are not getting enough exercise.

[0793] Specific examples

[0794] Example 1: Entering meal information

[0795] A user opens a smartphone application and enters their breakfast as "two slices of toast, one banana, and one cup of coffee." The application calculates the calories from this information and displays the total calorie intake. For example, it calculates two slices of toast as 200 kcal, one banana as 100 kcal, and one cup of coffee as 50 kcal, displaying a total of 350 kcal.

[0796] Example 2: Using a wearable device

[0797] The user wears a smartwatch and goes for a one-hour run. The smartwatch measures pulse rate and calories burned while running and sends the data to a smartphone. The smartphone then sends the received data to a server, which analyzes the data and provides feedback to the user. For example, the average pulse rate during the run is measured as 150 bpm and calories burned as 600 kcal.

[0798] Prompt Sentence Examples

[0799] Prompt 1: Enter meal information

[0800] "For breakfast, you had two slices of toast, one banana, and one cup of coffee. Calculate the total calories ingested from these meals."

[0801] Prompt 2: Wearable device data transmission

[0802] "I ran for an hour using my smartwatch. Please send my pulse rate and calories burned during the run to the server and let me know the analysis results."

[0803] In this way, the system involves users, terminals, and servers working together to input, transmit, analyze, and provide feedback on data.

[0804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0805] Step 1:

[0806] Users use their smartphones or computers to input information about their diet, sleep, and exercise. For example, if a user inputs "two slices of toast, one banana, and one cup of coffee" for breakfast, the application will calculate the calories from this information and display the total calorie intake. The input data is the food content, calorie intake, sleep time, and type and time of exercise, and the output is a display of the total calorie intake and amount of exercise.

[0807] Step 2:

[0808] The user wears a wearable device and collects biometric information such as pulse rate during exercise and daily life. For example, if the user runs for an hour, the smartwatch measures their pulse rate and calories burned while they run. The measured data is sent to a smartphone via Bluetooth or Wi-Fi. The input data is pulse rate and calories burned, and the output is data sent to the smartphone.

[0809] Step 3:

[0810] The device (smartphone or PC) sends information entered by the user and biometric information obtained from the wearable device to a server. The HTTPS protocol is used for transmission, and the data is encrypted. The input data is the user's diet, sleep, exercise information, and biometric information, and the output is data sent to the server.

[0811] Step 4:

[0812] The server stores the received data in a database. A relational database such as MySQL or PostgreSQL is used for the database. The data is organized by user and indexed for efficient access. The input data is the user's diet, sleep, exercise information, and biometric information, and the output is stored in the database.

[0813] Step 5:

[0814] The server analyzes the stored data using Python libraries such as Pandas and Scikit-learn. For example, it checks whether the calorie intake of a meal exceeds the target value and evaluates the balance between the amount of exercise and the calories burned. The input data is the user information stored in the database, and the output is the analysis results.

[0815] Step 6:

[0816] The server sends the analysis results to the user's device. The user can check the analysis results through a smartphone application. For example, if the calorie intake of a meal exceeds the target value, the application will display a warning to the user. If the amount of exercise is insufficient, the application will also suggest additional exercise. The input data is the analysis results, and the output is feedback to the user's device.

[0817] (Application example 1)

[0818] Next, a description will be given of Application Example 1 of Form 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."

[0819] Health management is an important issue in modern society, but there is no system that can centrally manage individual diet, sleep, and exercise information and suggest optimal meal menus. Furthermore, there is a lack of a way to quickly order suggested meal menus from a food delivery service. This makes it difficult for users to take concrete actions to maintain a healthy lifestyle.

[0820] 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.

[0821] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the information, means for proposing an optimal meal menu based on the information, and means for ordering the proposed meal menu from a food delivery service. This allows the user to receive an optimal meal menu based on their own health condition and quickly order the menu.

[0822] "Dietary information" refers to information about the contents, calories, and nutrients of the meals consumed by the user.

[0823] "Sleep information" refers to information about the user's sleep time and sleep quality.

[0824] "Exercise information" refers to information about the type of exercise performed by the user, the duration, and the calories burned.

[0825] "Sensor information" refers to biological information such as pulse rate and number of steps acquired from a wearable device or the like.

[0826] "Generative AI" is artificial intelligence that performs natural language processing based on input information and generates appropriate output.

[0827] "Lifespan Simulation AI" is an artificial intelligence that simulates a user's lifespan based on their diet, sleep, exercise, and sensor information.

[0828] The "meal menu suggestion means" is a means for suggesting an optimal meal menu based on the user's health condition.

[0829] The "food delivery service ordering means" is a means for ordering the suggested meal menu from a food delivery service.

[0830] A system for implementing this invention includes a means for inputting information about a user's diet, sleep, and exercise, and a means for acquiring various sensor information (such as pulse rate) from a wearable device. This information is subjected to natural language processing by a generative AI and used to evaluate the user's health condition. Furthermore, a lifespan simulation AI simulates the user's lifespan based on this information. Next, a meal menu suggestion means suggests an optimal meal menu based on the user's health condition, and a food delivery service ordering means orders the suggested meal menu from a food delivery service.

[0831] Hardware and software used

[0832] Hardware: Smartphones, wearable devices (e.g., smartwatches)

[0833] Software: Python, Requests library (to send HTTP requests), food delivery API (a hypothetical API)

[0834] Data processing and calculation

[0835] 1. User input: Users input information about their diet, sleep, and exercise through a smartphone app, including what they ate, how many calories they consumed, how much sleep they had, and the type and duration of their exercise.

[0836] 2. Acquiring sensor information: Acquiring biometric information such as pulse rate and number of steps from wearable devices.

[0837] 3. Natural language processing using generative AI: The generative AI processes the acquired information using natural language to evaluate the user's health condition.

[0838] 4. Lifespan Simulation: Lifespan simulation AI simulates the user's lifespan based on their health condition.

[0839] 5. Meal menu suggestion: The meal menu suggestion means suggests the optimal meal menu based on the user's health condition.

[0840] 6. Order food delivery service: Order the suggested meal menu from a food delivery service.

[0841] Specific examples

[0842] For example, the user inputs the calories and nutrients for breakfast, lunch, and dinner, and the smartwatch retrieves their pulse rate and step count. Based on this information, the app suggests a "High Protein Salad" and orders it from a food delivery service.

[0843] Prompt Sentence Examples

[0844] "Create a Python program that suggests the best meal plan based on the user's diet, sleep, and exercise information, and biometric information obtained from a wearable device, and then orders it from a food delivery service."

[0845] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0846] Step 1:

[0847] Users enter information about their diet, sleep, and exercise through a smartphone app.

[0848] Input: Food content, calorie intake, sleep time, type and duration of exercise.

[0849] Output: The entered data is sent to the server.

[0850] Specific operation: The user enters information about food, sleep, and exercise into the application's input form and presses the submit button. The server receives this data and stores it in a database.

[0851] Step 2:

[0852] The server acquires various sensor information (heart rate, number of steps, etc.) from the wearable device.

[0853] Input: Sensor data from wearable devices.

[0854] Output: The acquired sensor information is sent to the server.

[0855] How it works: The wearable device periodically measures sensor information and sends it to the smartphone via Bluetooth or Wi-Fi. The smartphone then forwards this data to the server.

[0856] Step 3:

[0857] The server uses generative AI to process input information and sensor information in natural language.

[0858] Input: User's diet, sleep, exercise information and sensor information.

[0859] Output: Natural language processed data.

[0860] Specific operation: The server uses a generative AI model to analyze input information and sensor information and evaluate the user's health condition.

[0861] Step 4:

[0862] The server uses a lifespan simulation AI to simulate the user's lifespan.

[0863] Input: Natural language processed data.

[0864] Output: Life simulation results.

[0865] Specific operation: The server uses the lifespan simulation AI to predict the user's lifespan based on their health condition. The simulation results are stored in a database.

[0866] Step 5:

[0867] The server uses the meal menu suggestion means to suggest an optimum meal menu based on the health condition of the user.

[0868] Input: Lifespan simulation results and user health status.

[0869] Output: A suggested meal menu.

[0870] Specific operation: The server uses a meal menu suggestion algorithm to generate a meal menu that is optimal for the user's health condition. The suggested menu is then sent to the user's smartphone.

[0871] Step 6:

[0872] The server orders the suggested meal from a food delivery service.

[0873] Input: A suggested meal menu.

[0874] Output: Order confirmation to food delivery service.

[0875] Specific operation: The server uses the food delivery service's API to order the suggested meal menu. An order confirmation is sent to the user's smartphone.

[0876] Example 2

[0877] Next, a description will be given of Example 2 of Form 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."

[0878] Conventional health management systems have had difficulty properly analyzing the diet, sleep, and exercise information entered by users and providing specific advice or lifespan simulations. Effective use of various sensor information was also difficult, making it impossible to provide useful information to users. This resulted in the issue of users being unable to accurately grasp their own health status and take appropriate measures.

[0879] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0880] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for the generative AI to classify the diet information into food groups and nutrients, means for the generative AI to classify the sleep information into deep sleep and light sleep, and means for the generative AI to classify the exercise information into type and intensity. This allows the user to understand their own health condition in detail and receive appropriate advice.

[0881] "Dietary information" is information about the food and drinks consumed by the user.

[0882] "Sleep information" is information relating to the user's sleep time and sleep quality.

[0883] "Exercise information" is information relating to the type, intensity, and duration of exercise performed by the user.

[0884] "Sensor information" refers to biometric data such as pulse rate and activity level obtained from wearable devices.

[0885] "Generative AI" is an artificial intelligence that performs natural language processing and has the ability to analyze information entered by the user and convert it into an appropriate format.

[0886] "Food groups" are categories for classifying dietary information, and are classified based on nutrients such as carbohydrates, proteins, and lipids.

[0887] "Deep sleep" is the sleep stage that is considered to be the most restful for the user.

[0888] "Light sleep" is a sleep stage in which the user is relatively awake during sleep.

[0889] "Lifespan simulation" is a process of performing calculations and analyses to predict future lifespan based on a user's health information.

[0890] The present invention is a system for analyzing a user's health information in detail and providing appropriate advice and lifespan simulations. Specific embodiments of this system will be described below.

[0891] Program Generation

[0892] The system's program is designed to analyze the diet, sleep, and exercise information entered by the user and convert it into an appropriate format using a generative AI model, such as GPT-4.

[0893] Program processing

[0894] This system performs data processing and calculation using the following hardware and software.

[0895] 1. Analysis of dietary information

[0896] The server receives the meal details entered by the user as text data.

[0897] The server uses a generative AI model (e.g., GPT-4) to categorize the meal contents into food groups and nutrients.

[0898] For example, information such as "I ate bread and eggs for breakfast" is converted into a format such as "bread (carbohydrate), eggs (protein)."

[0899] 2. Sleep information analysis

[0900] The server receives the information on the sleeping hours input by the user as text data.

[0901] The server uses a generative AI model to divide sleep time into periods of deep and light sleep.

[0902] For example, information such as "I slept 8 hours last night" can be converted into a format such as "Deep sleep: 3 hours, Light sleep: 5 hours."

[0903] 3. Analysis of movement information

[0904] The server receives the exercise details entered by the user as text data.

[0905] The server uses a generative AI model to analyze the type and intensity of exercise and convert it into an appropriate format.

[0906] For example, information such as "I jogged for 30 minutes" is converted into a format such as "Jogging (aerobic exercise), 30 minutes."

[0907] Adding specific examples

[0908] Below is an example of a prompt sentence to input to the generative AI model.

[0909] Example prompt sentence:

[0910] "Classify what the user ate for breakfast into food groups and nutrients. Input: I ate bread and eggs for breakfast."

[0911] "Please divide the user's sleep time into deep and light sleep. Input: I slept 8 hours last night."

[0912] "Please classify the type and intensity of exercise performed by the user. Input: 30 minutes of jogging."

[0913] This allows users to simply input information about their diet, sleep, and exercise, and the server will use a generative AI model to convert each piece of information into an appropriate format.

[0914] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0915] Step 1:

[0916] The user enters information about their diet, sleep, and exercise.

[0917] How it works: Users enter information about their diet, sleep, and exercise in text format using a dedicated application or web interface.

[0918] Input: Information such as "I had bread and eggs for breakfast," "I slept 8 hours last night," or "I jogged for 30 minutes."

[0919] Output: The text data entered by the user.

[0920] Step 2:

[0921] The terminal transmits the input information to the server.

[0922] Specific operation: The device sends the information entered by the user as text data to the server using the HTTPS protocol to ensure data security.

[0923] Input: Text data entered by the user.

[0924] Output: The text data sent to the server.

[0925] Step 3:

[0926] The server receives the information and generates a prompt for the generative AI model.

[0927] Specific operation: The server analyzes the information received from the device and generates a prompt sentence to pass to the generative AI model.

[0928] Input: Text data sent from the terminal.

[0929] Output: A prompt to pass to the generative AI model.

[0930] Step 4:

[0931] The server analyzes the information using a generative AI model.

[0932] What it does: The server uses a generative AI model (e.g., GPT-4) to parse the information based on the prompt.

[0933] Input: A prompt to pass to the generative AI model.

[0934] Output: Analysis result (e.g. "bread (carbohydrates), eggs (protein)").

[0935] Step 5:

[0936] The server sends the analysis results to the device.

[0937] How it works: The server sends the analysis results obtained from the generative AI model to the device, again using the HTTPS protocol to ensure data security.

[0938] Input: Analysis results obtained from a generative AI model.

[0939] Output: Analysis results sent to the device.

[0940] Step 6:

[0941] The terminal displays the analysis results to the user.

[0942] Specific operation: The terminal displays the analysis results received from the server to the user.

[0943] Input: Analysis results sent from the server.

[0944] Output: The analysis results displayed to the user's screen (e.g., "Breakfast: Bread (carbohydrates), eggs (protein)").

[0945] This allows users to easily input information about their diet, sleep, and exercise, and have that information converted into the appropriate format.

[0946] (Application example 2)

[0947] Next, a description will be given of Application Example 2 of Form 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."

[0948] Health management is an important issue in modern society, but there is no system that comprehensively analyzes individual diet, sleep, and exercise information and proposes appropriate meal plans. Furthermore, there is a lack of means for users to actually order the proposed meal plans. This makes it difficult for users to efficiently manage their health.

[0949] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for generating a meal menu based on health status and proposing a meal plan, and means for ordering the proposed meal menu in cooperation with an external meal provision service. This enables a user to easily obtain a meal plan based on their own health status and then efficiently order meals based on that plan.

[0950] "Dietary information" refers to data such as the content, amount, and time of meals consumed by the user.

[0951] "Sleep information" refers to data such as the user's sleep time, the time spent in deep and light sleep, and the quality of their sleep.

[0952] "Exercise information" refers to data such as the type, duration, and intensity of exercise performed by the user.

[0953] "Sensor information" refers to biological data such as pulse rate, body temperature, and activity level obtained from wearable devices.

[0954] "Generative AI" is artificial intelligence that processes input data using natural language processing and generates analytical results.

[0955] "Lifespan Simulation" is a simulation that predicts a user's lifespan based on input data.

[0956] "Meal menu generation" is the process of creating an appropriate meal plan based on the user's health status.

[0957] A "meal provision service" is an external service that provides meals ordered by a user.

[0958] The "ordering means" is a means for ordering the proposed meal menu from an external meal provision service.

[0959] The system for implementing this invention inputs information about the user's diet, sleep, and exercise, and based on this information, proposes a meal plan based on the user's health condition, and then orders meals based on that plan in cooperation with an external meal delivery service.

[0960] System Configuration

[0961] The system consists of the following main components:

[0962] 1. User device: A device used by a user to input information, such as a smartphone or tablet.

[0963] 2. Wearable device: A device for acquiring sensor information such as pulse rate and body temperature.

[0964] 3. Server: The central component that analyzes and processes data.

[0965] 4. Generative AI: Artificial intelligence that processes input data using natural language and generates analytical results.

[0966] 5. External meal service: An external service that provides a proposed meal menu.

[0967] Program processing

[0968] The server receives information on diet, sleep, and exercise from the user's device and acquires sensor information from the wearable device. This information is processed using natural language processing by generative AI, and a meal menu based on the user's health status is generated. The generated meal menu is then proposed to the user, and the menu selected by the user is ordered from an external meal delivery service.

[0969] Hardware and software used

[0970] Hardware: Smartphones, tablets, wearable devices

[0971] Software: Python, OpenAI API, Food Delivery API

[0972] Data processing and calculation

[0973] 1. Data entry: The user enters information about their diet, sleep, and exercise into their smartphone or tablet.

[0974] 2. Data acquisition: Obtain sensor information such as pulse rate and body temperature from the wearable device.

[0975] 3. Data analysis: Using generative AI (e.g., GPT-3), the input data is analyzed and a meal menu is generated based on health status.

[0976] 4. Data output: Display the generated meal menu to the user.

[0977] 5. Order processing: Using the food delivery API, the proposed menu is ordered from an external food delivery service.

[0978] Specific examples

[0979] For example, let's say a user had toast and eggs for breakfast, salad and chicken for lunch, and fish and vegetables for dinner. They also had 4 hours of deep sleep, 3 hours of light sleep, and went for a 30-minute run. With this information, the generative AI could use the following prompt to analyze:

[0980] Prompt Sentence Examples

[0981] Dietary information: I had toast and eggs for breakfast, salad and chicken for lunch, and fish and vegetables for dinner.

[0982] Sleep data: 4 hours of deep sleep, 3 hours of light sleep.

[0983] Exercise data: Ran for 30 minutes.

[0984] Analyze this data and suggest a meal plan based on your health condition.

[0985] Based on this prompt, the generative AI analyzes it and suggests a meal menu that is optimal for the user's health condition. The suggested menu is displayed to the user, and the menu selected by the user is ordered from an external meal delivery service. This allows users to easily obtain a meal plan based on their health condition and then efficiently order meals based on that plan.

[0986] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0987] Step 1:

[0988] The user uses a smartphone or tablet to input information about their diet, sleep, and exercise. The input information includes the type, amount, and time of meals, sleep duration, duration of deep and light sleep, and type, duration, and intensity of exercise. This data is then sent to the server.

[0989] Step 2:

[0990] The server acquires sensor information from the wearable device. The sensor information includes biometric data such as pulse rate, body temperature, and activity level. The acquired sensor information is important data for evaluating the user's health condition.

[0991] Step 3:

[0992] The server uses generative AI to process the inputted diet, sleep, exercise, and sensor information in natural language. Specifically, the server inputs the following prompts into the generative AI:

[0993] Dietary Data: [Dietary Information]

[0994] Sleep data: [Sleep information]

[0995] Exercise data: [Exercise information]

[0996] Analyze this data and suggest a meal plan based on your health condition.

[0997] The generative AI analyzes the data based on this prompt and generates a meal menu based on the patient's health status.

[0998] Step 4:

[0999] The server sends the generated meal menu to the user's device, where the user can check the proposed meal menu on their smartphone or tablet. The meal menu includes a balanced meal plan.

[1000] Step 5:

[1001] The user selects the desired meal from the suggested menu, and the selected menu is sent to the server.

[1002] Step 6:

[1003] The server orders the selected meal from an external food service using a food delivery API. The order data includes the selected meal, the user's address, payment method, etc.

[1004] Step 7:

[1005] An external food delivery service receives the order and delivers the meal to the user, who can then receive a meal based on the suggested meal menu.

[1006] Through the above steps, a user can easily obtain a meal plan based on their own health condition and can then efficiently order meals based on that plan.

[1007] Example 3

[1008] Next, a description will be given of Example 3 of Form Example 3. 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."

[1009] Conventional health management systems can collect information on a user's diet, sleep, exercise, and biological information individually, but it is difficult to integrate this information to predict a user's lifespan. Furthermore, the preprocessing of collected data and the accuracy of lifespan predictions using AI models are also insufficient. This makes it difficult for users to comprehensively evaluate their health status and lifestyle habits and receive specific feedback for improvement.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1011] In this invention, the server includes a means for inputting information on a person's diet, sleep, and exercise, a means for acquiring various sensor information (biometric information) from the person, a means for preprocessing this information, a means for simulating a person's lifespan using a generative AI model based on the preprocessed information, and a means for feeding back the simulation results to the user. This makes it possible to comprehensively evaluate the user's health condition and lifestyle habits and provide specific feedback.

[1012] "Dietary information" refers to data such as the type, amount, and time of consumption of food and beverages consumed by the user.

[1013] "Sleep information" refers to data such as the user's sleep time, sleep quality, and wake-up time.

[1014] "Exercise information" refers to data such as the type, duration, and intensity of exercise performed by the user.

[1015] "Sensor information" refers to data obtained from various sensors that acquire biometric information about the user, such as pulse rate, blood pressure, and body temperature.

[1016] "Preprocessing" refers to processes such as cleaning the collected data, filling in missing values, removing outliers, and normalizing the data.

[1017] A "generative AI model" is an artificial intelligence model that predicts a user's lifespan based on collected data. Specifically, it includes machine learning algorithms such as neural networks.

[1018] "Feedback" refers to the provision of information to users that is useful for managing their health and improving their lifestyle habits by notifying them of the results predicted by the AI ​​model.

[1019] This invention is a system that collects information on a user's diet, sleep, exercise, and biological information, and uses a generative AI model based on this information to simulate a user's lifespan. Specific embodiments of this system are described below.

[1020] Data collection

[1021] Users use a smartphone app or web interface to input information about their diet, sleep, and exercise—for example, they ate oatmeal for breakfast, slept seven hours last night, and went on a 30-minute jog—and this information is sent from the device to a server.

[1022] Data storage and preprocessing

[1023] The server stores the received data in a database (e.g., MySQL). The stored data is preprocessed using Python libraries such as Pandas and NumPy. Specifically, the data is cleaned (missing values ​​are filled in and outliers are removed) and normalized. For example, missing sleep duration is filled in with the average value.

[1024] Lifespan prediction using AI models

[1025] The server inputs the preprocessed data into a generative AI model (e.g., a neural network using TensorFlow or PyTorch). This model evaluates the user's health and lifestyle habits and predicts their lifespan based on that. For example, the model may output "The user's predicted lifespan is 85 years."

[1026] Feedback of results

[1027] The server then provides the user with feedback on the life expectancy predictions generated by the AI ​​model. This feedback is provided via an app on the device or a web interface. Users can use this feedback to manage their health and improve their lifestyle habits. For example, the app screen might display, "Your predicted life expectancy is 85 years."

[1028] Specific examples

[1029] A user opens a smartphone app and enters information about their diet, sleep, and exercise. For example, they enter "Breakfast: Oatmeal" on the app's food input screen and "Sleep time: 7 hours" on the sleep input screen. The server stores the received data in a MySQL database and cleans it using the Pandas library. The preprocessed data is input into a TensorFlow model to predict lifespan. The server sends the prediction results in JSON format to the device, which then displays the received results on the app screen and informs the user, "Your predicted lifespan is 85 years."

[1030] Prompt Sentence Examples

[1031] "Evaluate your health and lifestyle based on your diet, sleep, exercise, and biological information, and predict your life expectancy."

[1032] In this way, a system is constructed in which the server, terminals, and users work together to collect and process data and simulate lifespan using an AI model. The flow of the specific processing in Example 3 will be described with reference to FIG.

[1033] Step 1:

[1034] Users use a smartphone app or web interface to input information about their diet, sleep, and exercise—for example, they ate oatmeal for breakfast, slept seven hours last night, and went on a 30-minute jog—and this information is sent from the device to a server.

[1035] Input: Diet, sleep, and exercise information

[1036] Output: User's lifestyle information sent to the server

[1037] Step 2:

[1038] The server stores the received data in a database (e.g., MySQL), including the user ID, meal details, sleep time, exercise details, etc.

[1039] Input: User's lifestyle information sent from the device

[1040] Output: User's lifestyle information stored in a database

[1041] Step 3:

[1042] The server preprocesses the stored data by using Python libraries such as Pandas and NumPy to clean (implant missing values ​​and remove outliers) and normalize the data. For example, missing sleep duration is imputed with the average value.

[1043] Input: User's lifestyle information stored in the database

[1044] Output: Preprocessed user lifestyle information

[1045] Step 4:

[1046] The server inputs the preprocessed data into a generative AI model (e.g., a neural network using TensorFlow or PyTorch). This model evaluates the user's health and lifestyle habits and predicts their lifespan based on that. For example, the model may output "The user's predicted lifespan is 85 years."

[1047] Input: Preprocessed user lifestyle information

[1048] Output: Lifespan prediction results from AI model

[1049] Step 5:

[1050] The server then provides the user with feedback on the life expectancy predictions generated by the AI ​​model. This feedback is provided via an app on the device or a web interface. Users can use this feedback to manage their health and improve their lifestyle habits. For example, the app screen might display, "Your predicted life expectancy is 85 years."

[1051] Input: Lifespan prediction results from AI model

[1052] Output: Life prediction results fed back to the user

[1053] (Application example 3)

[1054] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1055] Health management and lifestyle improvement are important issues in modern society. However, it is difficult for individual users to accurately evaluate their own health status and lifestyle habits and take appropriate measures to improve them based on the results. In particular, comprehensively evaluating information such as diet, sleep, and exercise and predicting life expectancy requires specialized knowledge and skills, making it difficult for average users. For this reason, there is a demand for a system that allows users to easily evaluate their own health status and obtain specific guidelines for improving their lifestyle habits.

[1056] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1057] In this invention, the server includes a means for inputting information on a person's diet, sleep, and exercise, a means for acquiring various sensor information (such as pulse rate) from the person, a generative AI means for natural language processing this information, an AI means for evaluating the person's health condition and lifestyle habits based on the above information and simulating lifespan, and a means for feeding back the evaluation results to the user. This enables the user to comprehensively evaluate their own health condition and obtain specific measures to improve their lifestyle habits.

[1058] "Dietary information" is data about the food and beverages consumed by a user.

[1059] "Sleep information" refers to data about the user's sleep time and quality.

[1060] "Exercise information" is data regarding the type, duration, and intensity of exercise performed by a user.

[1061] "Sensor information" refers to information obtained from various sensors for acquiring biometric data of the user.

[1062] "Generative AI" is artificial intelligence that uses natural language processing to analyze input information and generate appropriate output.

[1063] "Health status assessment" is the process of assessing a user's current health status based on the user's diet, sleep, exercise, and sensor information.

[1064] "Lifespan simulation" is the process of predicting a user's future lifespan based on their health condition and lifestyle habits.

[1065] "Feedback means" refers to a means for providing evaluation results and life expectancy prediction results to users to help them improve their lifestyle habits.

[1066] A system for implementing this invention includes a means for inputting information on a user's diet, sleep, and exercise, a means for acquiring various sensor information (such as pulse rate), a generative AI means for natural language processing this information, an AI means for evaluating the user's health condition and lifestyle habits based on the above information and simulating life expectancy, and a means for feeding back the evaluation results to the user.

[1067] System configuration

[1068] 1. User Device

[1069] The user terminal is a mobile device such as a smartphone or tablet, and the user uses this terminal to input information about their diet, sleep, and exercise.

[1070] 2. Wearable devices

[1071] Wearable devices include smartwatches and fitness trackers that collect biometric information such as the user's pulse rate, blood pressure, and body temperature.

[1072] 3. Server

[1073] The server receives data sent from the user's terminal and wearable device, and uses generative AI to perform natural language processing based on this information. It also evaluates health status and lifestyle habits and simulates life expectancy.

[1074] Program processing explanation

[1075] The server processes the data obtained from the user using Python and machine learning libraries (e.g., scikit-learn). Specifically, the process is carried out in the following steps:

[1076] 1. Data Acquisition

[1077] Information on diet, sleep, and exercise is collected from the user's device, and biometric information is collected from the wearable device.

[1078] 2. Data Analysis

[1079] The acquired data is processed using natural language processing with generative AI to evaluate the user's health condition and lifestyle habits.

[1080] 3. Life simulation

[1081] Based on the evaluation results, AI simulates the user's lifespan.

[1082] 4. Feedback

[1083] The simulation results are sent to the user's device and fed back to the user, allowing them to understand their own health condition and use it to improve their lifestyle habits.

[1084] Specific examples

[1085] For example, consider a scenario in which a user enters information about their diet, sleep, and exercise into an app every day, and their smartwatch automatically collects data on their heart rate and blood pressure. Based on this data, the server evaluates the user's health and predicts their life expectancy. The prediction results are fed back to the user, and specific lifestyle improvement measures are presented.

[1086] Prompt Sentence Examples

[1087] "Predict life expectancy based on the user's age, gender, heart rate, blood pressure, sleep time, exercise time, and diet score."

[1088] This prompt can be used to feed data into a generative AI model to predict lifespan.

[1089] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1090] Step 1:

[1091] The user device inputs information about meals, sleep, and exercise from the user. The input information includes the contents of meals, sleep time, type and time of exercise, etc. This information is temporarily stored in the user device.

[1092] Step 2:

[1093] Wearable devices acquire biometric information from users, specifically by measuring pulse rate, blood pressure, body temperature, and other data using sensors and transmitting this data to the user's device.

[1094] Step 3:

[1095] The user device sends the acquired information on food, sleep, exercise, and biometric data to the server. The data is sent in a standard data format such as JSON.

[1096] Step 4:

[1097] The server analyzes the received data. First, it formats and preprocesses the data. For example, it complements missing values ​​and detects and corrects outliers. Next, it uses generative AI to perform natural language processing and analyze the data.

[1098] Step 5:

[1099] The server evaluates the user's health condition and lifestyle habits based on the analysis results. Specifically, it evaluates and scores the balance of meals, quality of sleep, appropriateness of exercise, etc. The evaluation results are output as an index showing the user's health condition.

[1100] Step 6:

[1101] The server simulates lifespan based on the evaluation results. Using an AI model, it predicts future lifespan based on the user's current health condition and lifestyle habits. The results of this simulation are output as a lifespan prediction.

[1102] Step 7:

[1103] The server transmits the results of the lifespan simulation and the health status assessment to the user's device in a format that is easy for the user to understand (e.g., graphs or text).

[1104] Step 8:

[1105] The user device then displays the received evaluation results and life expectancy prediction results to the user, allowing the user to understand their own health condition and use these results to improve their lifestyle habits.

[1106] In this way, users can review their daily lifestyle habits and obtain specific guidelines for managing their health.

[1107] 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.

[1108] "Example 1"

[1109] In one embodiment of the present invention, an emotion engine that recognizes a user's emotions is incorporated. This emotion engine recognizes emotions from the user's voice, facial expressions, text input, etc. Specifically, it analyzes the voice of the user speaking through the microphone of a smartphone or computer, facial expressions captured through a camera, or text messages to determine the user's emotions.

[1110] "Example 2"

[1111] The output of the emotion engine influences the lifespan simulation. Specifically, the user's emotional state (joy, sadness, anger, surprise, etc.) is considered to affect their health and lifestyle, so this is incorporated into the lifespan simulation. For example, if a user is judged to be constantly stressed, it is predicted that their lifespan may be shortened.

[1112] "Example 3"

[1113] The output of the emotion engine is also used to provide feedback to users. Specifically, it helps users understand their emotional state and provides advice on how to improve their lifestyle based on that. For example, if it determines that a user has been feeling stressed for a certain period of time, it will send them a message recommending relaxation and moderate exercise.

[1114] The processing flow of each embodiment will be described below.

[1115] "Example 1"

[1116] Step 1: The user inputs speech through the microphone of their smartphone or computer, facial expressions captured through the camera, or text messages into the emotion engine.

[1117] Step 2: The emotion engine analyzes the input information and determines the user's emotion.

[1118] Step 3: The output of the emotion engine is incorporated as part of the lifespan simulation.

[1119] "Example 2"

[1120] Step 1: A user's emotional state is thought to affect their health and lifestyle, so incorporate this as part of the lifespan simulation.

[1121] Step 2: For example, if a user is determined to be constantly stressed, it is predicted that their lifespan may be shortened.

[1122] "Example 3"

[1123] Step 1: The output of the emotion engine is also used to provide feedback to the user. Step 2: The user understands their own emotional state and is then provided with advice on how to improve their lifestyle based on that.

[1124] Step 3: For example, if the user is determined to be stressed over a period of time, messages recommending relaxation and moderate exercise are sent to the user.

[1125] Example 1

[1126] Next, a description will be given of Example 1 of Form 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."

[1127] Conventional health management systems can collect information on a user's diet, sleep, exercise, and biometric information, but it is difficult to integrate and analyze this information and provide feedback that takes into account the user's emotional state. Furthermore, due to a lack of functionality to recognize the user's emotions, it is not possible to properly evaluate the user's psychological health state. This has led to the issue of insufficient comprehensive health management for users.

[1128] 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.

[1129] In this invention, the server includes means for inputting information on the user's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the user, generative AI means for natural language processing this information, AI means for simulating the user's lifespan based on the above information, means for recognizing emotions from the user's voice, facial expressions, and text input, means for integrating and analyzing the above information, and means for providing feedback based on the analysis results. This makes it possible to comprehensively evaluate the user's physiological and psychological health status and provide appropriate feedback.

[1130] "Dietary information" refers to data such as the type, amount, and calories of food consumed by the user.

[1131] "Sleep information" refers to data such as the user's sleep time, sleep quality, and wake-up time.

[1132] "Exercise information" refers to data such as the type of exercise the user performed, the duration of the exercise, and the calories burned.

[1133] "Sensor information" refers to biometric data such as the user's pulse rate, body temperature, and blood pressure.

[1134] "Generative AI" is artificial intelligence that performs natural language processing and analyzes information input by users.

[1135] "Lifespan Simulation AI" is an artificial intelligence that predicts lifespan based on a user's health data.

[1136] "Emotion recognition means" is a technology that analyzes and recognizes emotions from a user's voice, facial expressions, and text input.

[1137] "Data integration means" refers to technology that centrally manages and analyzes various data obtained from users.

[1138] "Feedback provision means" refers to technology that provides advice and notifications to users based on the analysis results.

[1139] This invention is a system in which a user inputs information about food, sleep, and exercise via a device such as a smartphone or a personal computer, obtains biometric information using a wearable device, and further recognizes emotions using an emotion engine. Specific embodiments of this system are described below.

[1140] Entering User Data

[1141] Users use a dedicated application on their smartphone or computer to enter information about their diet, sleep, and exercise. For example, a user might enter "I ate bread and eggs for breakfast. My calorie intake was 300 kcal." The application then sends this information in JSON format to the server.

[1142] Acquisition of biometric information

[1143] A user wears a wearable device such as a smartwatch to collect biometric information such as pulse rate. The smartwatch then sends the data to a smartphone via Bluetooth. The smartphone then sends the received data to a server. For example, the smartwatch measures "pulse rate: 75 bpm" and sends that data to the smartphone.

[1144] Emotion recognition by emotion engine

[1145] The device recognizes emotions from the user's voice, facial expressions, text input, etc. For example, if a user says "I'm very tired today" through the smartphone microphone, the device will convert this into text using voice recognition software (e.g., voice recognition API), then use an emotion analysis engine (e.g., emotion analysis API) to analyze the emotion and recognize "fatigue."

[1146] Data integration and analysis

[1147] The server aggregates the diet, sleep, exercise, biometric, and emotional data submitted by the user. The server organizes and analyzes the data using Python's Pandas library. For example, the server aggregates the user's daily data and generates a report to identify trends in their health and emotions.

[1148] Providing feedback

[1149] The server provides feedback to the user based on the analysis results. For example, if the analysis results show that the user has not been exercising much recently, the server generates advice such as "Get more exercise" and sends it to the user's smartphone. The notification is sent using a cloud messaging service.

[1150] Examples of specific examples and prompts

[1151] Specific examples

[1152] The user uses their smartphone to enter the following information:

[1153] Breakfast: Bread and eggs, 300 kcal

[1154] Sleep time: 7 hours

[1155] Exercise: Running, 30 minutes

[1156] The user also uses a smartwatch to measure their pulse rate and transmits the data to the system, and then speaks to the smartphone microphone, saying, "I'm very tired today."

[1157] Prompt Sentence Examples

[1158] "Describe a system in which a user uses a smartphone to input diet, sleep, and exercise information, and a wearable device to obtain pulse rate. Also, explain how an emotion engine can be used to recognize the user's emotions."

[1159] In this way, it clearly explains how the user, device, and server work together to collect, analyze, and provide feedback on data.

[1160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1161] Step 1:

[1162] Users open a dedicated application on their smartphone or computer and enter information about their meals, sleep, and exercise. The entered information is sent to the server in JSON format. For example, a user might enter "I ate bread and eggs for breakfast. My calorie intake was 300 kcal." This information is converted to JSON format by the application and sent to the server.

[1163] Step 2:

[1164] A user wears a wearable device such as a smartwatch and collects biometric information such as pulse rate. The smartwatch sends the data to a smartphone via Bluetooth. The smartphone then sends the received data to a server. For example, the smartwatch measures "pulse rate: 75 bpm" and sends that data to the smartphone. This data is then sent to the server by the smartphone.

[1165] Step 3:

[1166] The device recognizes emotions from the user's voice, facial expressions, text input, etc. When a user says "I'm very tired today" through the smartphone microphone, the device uses voice recognition software to convert the speech into text. It then analyzes the text using an emotion analysis engine to recognize "fatigue." The analysis results are sent from the device to a server.

[1167] Step 4:

[1168] The server integrates the diet, sleep, exercise, biometric, and emotional data sent by the user. The server organizes and analyzes the data using Python's Pandas library. For example, the server may integrate the user's daily data and generate a report to understand their health and emotional trends. This report is then stored on the server.

[1169] Step 5:

[1170] The server provides feedback to the user based on the analysis results. For example, if the analysis results show that the user has not been exercising much recently, the server generates advice such as "Get more exercise" and sends it to the user's smartphone. The notification is sent using a cloud messaging service.

[1171] (Application example 1)

[1172] Next, a description will be given of Application Example 1 of Form 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."

[1173] In modern society, proposing and quickly delivering optimal meal menus based on individual health conditions and emotions is an important issue. However, conventional food delivery services do not consider the user's health information or emotions when proposing meals, making it difficult to contribute to maintaining the user's health and emotional stability.

[1174] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, emotion engine means for recognizing a person's emotions, means for proposing an optimal meal menu based on the emotions recognized by the emotion engine and the diet, sleep, and exercise information, and means for requesting the proposed meal menu from a food delivery service. This makes it possible to propose and quickly provide an optimal meal menu based on the user's health condition and emotions.

[1175] "Diet, sleep, and exercise information" refers to data such as the type of food a user eats in their daily life, the calories they consume, the amount of sleep they get, and the type and duration of their exercise.

[1176] "Various sensor information" refers to biological information such as pulse rate, blood pressure, and body temperature obtained from wearable devices, etc.

[1177] "Generative AI" is artificial intelligence that uses natural language processing to analyze information entered by users and generate appropriate responses and suggestions.

[1178] "AI that simulates lifespan" is an artificial intelligence that predicts future health conditions and lifespans based on the user's health information.

[1179] An "emotion engine" is a system that recognizes emotions from the user's voice, facial expressions, text input, etc.

[1180] "Means for suggesting optimal meal menus" refers to a function that selects and suggests optimal meal menus for users based on their health information and emotions.

[1181] "Means for requesting food delivery services" refers to a function for ordering the suggested meal menu from a food delivery service.

[1182] A system for implementing this invention includes means for inputting information on a user's diet, sleep, and exercise, means for acquiring various sensor information from a person (such as pulse rate), generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, emotion engine means for recognizing a person's emotions, means for suggesting an optimal meal menu based on the emotions recognized by the emotion engine and the diet, sleep, and exercise information, and means for requesting the suggested meal menu from a food delivery service.

[1183] Program processing explanation

[1184] Hardware and Software Configuration

[1185] User Device: A smartphone or computer on which users input information about their diet, sleep, and exercise. This includes iOS and Android applications.

[1186] Wearable devices: Smartwatches and fitness bands are used to collect biometric information such as pulse rate. Examples include Fitbit and Apple Watch.

[1187] Server: The server for processing data uses cloud services (e.g., AWS, Google Cloud).

[1188] Generative AI: Generative AI models such as GPT-3 and BERT are used for natural language processing.

[1189] Emotion Engine: Uses Google Cloud Speech-to-Text API, OpenCV, Dlib, NLTK, etc. to recognize emotions from user voice, facial expressions, and text input.

[1190] Data processing and calculation

[1191] 1. User device: The user inputs information about food, sleep, and exercise. This data is sent to the server via the application.

[1192] 2. Wearable device: Biometric information (such as pulse rate) is acquired in real time and sent to a server.

[1193] 3. Server: The received data is input into a generative AI model and natural language processing is performed, which analyzes the user's health condition.

[1194] 4. Emotion Engine: Analyzes the user's voice, facial expressions, and text input to recognize emotions. The recognized emotions are input into a generative AI model.

[1195] 5. Meal Menu Suggestion: The generative AI model suggests optimal meal menus based on the user's health information and emotions.

[1196] 6. Request to food delivery service: The suggested meal menu is requested from the food delivery service.

[1197] Specific examples

[1198] For example, if a user types "I feel tired today," the emotion engine will recognize "fatigue" and suggest low-calorie, nutritious meals. Below is an example of a prompt for the generative AI model:

[1199] Prompt Sentence Examples

[1200] If the user's emotion is "fatigue," their calorie intake is 2000 kcal, they have 6 hours of sleep, and they have 30 minutes of exercise, please suggest the optimal meal menu.

[1201] In this way, it becomes possible to suggest and quickly provide optimal meal menus based on the user's health condition and emotions.

[1202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1203] Step 1:

[1204] Users use their smartphones or computers to enter information about their diet, sleep, and exercise. Specifically, they enter information about the food they eat, the calories they consume, how much sleep they get, and the type and duration of their exercise into the application's input form. This data is then sent from the user's device to the server. The input data is formatted in JSON, XML, or other formats.

[1205] Step 2:

[1206] Wearable devices (e.g., smartwatches and fitness bands) collect biometric information such as the user's pulse rate in real time. The collected data is sent to the user's device via Bluetooth or Wi-Fi, and then from the user's device to a server. The data format is generally JSON or CSV.

[1207] Step 3:

[1208] The server receives dietary, sleep, and exercise information sent by the user, as well as biometric information sent from the wearable device. The received data is input into a generative AI model for natural language processing. Specifically, the data is preprocessed and input as text data into a generative AI model (e.g., GPT-3 or BERT). The generative AI model analyzes the user's health condition and outputs the analysis results in text format.

[1209] Step 4:

[1210] The server inputs the user's voice, facial expression, and text input into the emotion engine to recognize emotions. Specifically, the voice data is converted to text using the Google Cloud Speech-to-Text API, and the facial expression data is analyzed using OpenCV and Dlib. The text data is analyzed for emotions using NLTK. The emotion engine outputs the recognized emotions in text format.

[1211] Step 5:

[1212] The server proposes the optimal meal menu to the user based on the analysis results of the generative AI model and the output of the emotion engine. Specifically, a prompt sentence is input into the generative AI model to generate the optimal meal menu. An example of a prompt sentence is, "If the user's emotion is 'fatigue,' their calorie intake is 2000 kcal, they sleep for 6 hours, and they exercise for 30 minutes, please suggest the optimal meal menu." The generative AI model outputs the optimal meal menu in text format.

[1213] Step 6:

[1214] The server requests the suggested meal menu from the food delivery service. Specifically, it sends a request including the suggested meal menu to the food delivery service's API. The API request typically uses the HTTP POST method, and the request body contains data in JSON format. The food delivery service receives the request and delivers the meal to the user.

[1215] Example 2

[1216] Next, a description will be given of Example 2 of Form 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."

[1217] In modern society, personal health management is an important issue, but there is no system that can comprehensively analyze various information such as diet, sleep, exercise, and emotions to predict individual health conditions and life expectancy. Conventional systems can analyze these information individually, but it is difficult to comprehensively analyze them and reflect them in life expectancy simulations. Furthermore, there is a lack of systems that take into account the impact of emotional states on health conditions and life expectancy. This makes it difficult for users to accurately understand their own health conditions and maintain appropriate lifestyle habits.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1219] In this invention, the server includes means for inputting information on diet, sleep, and exercise, means for acquiring various types of sensor information (such as pulse rate), generative AI means for natural language processing of this information, means for classifying dietary content into food groups and nutrients, means for dividing sleep time into deep sleep and light sleep, means for classifying exercise information into types and intensities of exercise, emotion engine means for analyzing emotional states, and AI means for simulating a person's lifespan based on the above information. This makes it possible to comprehensively analyze a user's diverse health information and perform a lifespan simulation that also takes emotional states into account.

[1220] "Dietary information" refers to the contents of the foods and drinks consumed by the user, and is information categorized into food groups and nutrients.

[1221] "Sleep information" is information that indicates the user's sleep time and quality, and is divided into deep sleep and light sleep time.

[1222] "Exercise information" is information that indicates the type and intensity of exercise performed by the user, and is classified as aerobic exercise, anaerobic exercise, etc.

[1223] "Sensor information" is data for measuring the user's physical condition, and includes physiological indicators such as pulse rate and body temperature.

[1224] "Generative AI" refers to artificial intelligence that analyzes input natural language data and converts it into a specific format.

[1225] The "emotion engine" is a system that analyzes the user's emotional state and classifies emotions such as joy, sadness, anger, and surprise.

[1226] "Lifespan Simulation" is the process of calculating a user's predicted lifespan based on their health, lifestyle, and emotional state.

[1227] MODE FOR CARRYING OUT THE INVENTION

[1228] The present invention is a system for integrating and analyzing a user's health information to perform a lifespan simulation. Specific embodiments of this system will be described below.

[1229] 1. System Configuration

[1230] The system consists of a terminal and a server that collects and analyzes information entered by users about diet, sleep, exercise, and emotions. Terminals include smartphones, PCs, and wearable devices. The server analyzes the data using a generative AI model and emotion engine to perform a lifespan simulation.

[1231] 2. Data Collection

[1232] The user uses a dedicated application to input information about their diet, sleep, exercise, and emotions. For example, the user might input, "I ate bread and eggs for breakfast," "I slept for seven hours last night," "I jogged for 30 minutes," or "I feel very happy right now." The device collects this information and sends it to the server.

[1233] 3. Data Analysis

[1234] The server passes the collected data to a generative AI model. The generative AI model categorizes dietary information into food groups and nutrients, sleep information into periods of deep and light sleep, and exercise information into types and intensities of exercise. For example, it might categorize "bread and eggs" as "carbohydrates, protein," "7 hours of sleep" as "2 hours of deep sleep, 5 hours of light sleep," and "30 minutes of jogging" as "aerobic exercise, moderate intensity."

[1235] 4. Emotion analysis

[1236] The user inputs their emotional state into a dedicated application. For example, they input "I'm very happy today." The device collects the emotional information and sends it to the server. The server then uses an emotion engine to analyze the emotional state and classifies "I'm very happy" as "joy."

[1237] 5. Life simulation

[1238] The server integrates the output of the generative AI model and the emotion engine to predict the user's lifespan based on their health and lifestyle. For example, if the server determines that the user is constantly stressed, it predicts that their lifespan may be shortened.

[1239] Specific examples

[1240] The user inputs information into the application, such as "I ate bread and eggs for breakfast," "I slept 7 hours last night," "I jogged for 30 minutes," and "I feel very happy right now." The device collects this information and sends it to the server. The server uses a generative AI model to classify the food information as "carbohydrates, protein," the sleep information as "2 hours of deep sleep, 5 hours of light sleep," and the exercise information as "aerobic exercise, moderate intensity." The server then uses an emotion engine to classify the emotional information as "joy." The server integrates this information and predicts lifespan based on the user's health condition and lifestyle habits.

[1241] Prompt Sentence Examples

[1242] "Please create a program that analyzes the diet, sleep, exercise, and emotional information entered by the user and performs a lifespan simulation. Specifically, please include processing to categorize dietary information into food groups and nutrients, divide sleep information into deep sleep and light sleep, and analyze emotional information to reflect in the lifespan simulation."

[1243] The above is a specific embodiment for carrying out the present invention.

[1244] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1245] Program processing flow

[1246] Step 1: Data entry

[1247] The user inputs information about diet, sleep, exercise, and emotions using a dedicated application.

[1248] Input: Text data entered by the user (e.g., "I had bread and eggs for breakfast," "I slept 7 hours last night," "I went jogging for 30 minutes," "I'm very happy right now")

[1249] Output: User input data stored on the device

[1250] Step 2: Data collection

[1251] The terminal collects the user's input data and sends it to the server.

[1252] Input: User input data stored on the device

[1253] Output: User input data sent to the server

[1254] Step 3: Analysis of dietary information

[1255] The server uses the generated AI model to analyze the dietary information and classify it into food groups and nutrients.

[1256] Input: Meal information sent to the server (e.g., "I had bread and eggs for breakfast")

[1257] Data manipulation: A generative AI model classifies "bread and eggs" as "carbohydrates, protein"

[1258] Output: Categorised food information (e.g. "Carbohydrates, Protein")

[1259] Step 4: Analyze your sleep information

[1260] The server uses the generated AI model to analyze sleep information and divide it into periods of deep sleep and light sleep.

[1261] Input: Sleep information sent to the server (e.g., "I slept 7 hours last night")

[1262] Data processing: A generative AI model classifies "7 hours of sleep" as "2 hours of deep sleep, 5 hours of light sleep"

[1263] Output: Categorised sleep information (e.g. "2 hours of deep sleep, 5 hours of light sleep")

[1264] Step 5: Analysis of movement information

[1265] The server uses the generated AI model to analyze the exercise information and classify it into exercise type and intensity.

[1266] Input: Exercise information sent to the server (e.g., "I jogged for 30 minutes")

[1267] Data processing: A generative AI model classifies "30 minutes of jogging" as "aerobic exercise, medium intensity"

[1268] Output: Classified exercise information (e.g., "Aerobic exercise, medium intensity")

[1269] Step 6: Emotional Analysis

[1270] The server uses an emotion engine to analyze the emotion information and classify the emotional state.

[1271] Input: Emotional information sent to the server (e.g., "I'm very happy right now")

[1272] Data processing: The emotion engine classifies "I'm very happy" as "Joy"

[1273] Output: Classified emotion information (e.g., "joy")

[1274] Step 7: Data Integration

[1275] The server integrates the output of the generative AI model and the emotion engine.

[1276] Input: Categorized food information, sleep information, exercise information, emotional information

[1277] Data processing: Compile each piece of information into a single data set

[1278] Output: A consolidated dataset

[1279] Step 8: Lifetime simulation

[1280] The server uses the integrated data set to predict life expectancy, taking into account the user's health condition and lifestyle habits.

[1281] Input: Integrated dataset

[1282] Data calculation: Applying algorithms to calculate life expectancy based on health status and lifestyle habits

[1283] Output: predicted lifespan (e.g. "lifespan is predicted to be 80 years")

[1284] The above are the specific processing steps of the program of this system.

[1285] (Application example 2)

[1286] Next, a description will be given of Application Example 2 of Form 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."

[1287] In modern society, it is important to provide appropriate meal plans based on individual health conditions and lifestyle habits. However, conventional food delivery services have difficulty proposing meal plans that take into account the user's health and emotional state, and are therefore unable to provide comprehensive support for the user's health. Furthermore, there is a lack of simulations that take into account the impact of the user's emotional state on lifespan, so more accurate health management is required.

[1288] 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.

[1289] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for analyzing the user's emotional state and reflecting it in the lifespan simulation, means for generating and notifying the user of an optimal meal plan based on the user's health state, and means for providing meals through a food delivery service. This makes it possible to propose and provide meal plans that comprehensively consider the user's health state and emotional state.

[1290] "Dietary information" refers to data such as the contents, quantity, and time of the food and beverages consumed by the user.

[1291] "Sleep information" refers to data such as the user's sleep time, the time spent in deep and light sleep, and the quality of their sleep.

[1292] "Exercise information" refers to data such as the type, duration, intensity, and calories burned of the exercise performed by the user.

[1293] "Sensor information" is information for acquiring biometric data such as the user's pulse rate, body temperature, and blood pressure.

[1294] "Generative AI" is artificial intelligence that uses natural language processing to analyze input data and convert it into an appropriate format.

[1295] "Lifespan Simulation" is a simulation that predicts a user's lifespan based on their health condition, lifestyle habits, and emotional state.

[1296] "Emotional state" refers to the user's emotional state, such as happiness, sadness, anger, or surprise.

[1297] A "meal plan" is a suggested meal plan based on the user's health and emotional state.

[1298] A "food delivery service" is a service that delivers meals ordered by a user to a specified location.

[1299] The system for implementing this invention inputs a user's diet, sleep, and exercise information, acquires various sensor information, analyzes this information using generative AI that processes natural language, and performs a lifespan simulation. Furthermore, it analyzes the user's emotional state, reflects it in the lifespan simulation, and generates and notifies the user of an optimal meal plan based on the user's health condition. The system then provides meals via a food delivery service.

[1300] System configuration

[1301] 1. Data Collection:

[1302] Hardware: Smartphones, smartwatches

[1303] Software: Health management app, emotion analysis app

[1304] Data: diet, sleep, exercise, emotional state

[1305] 2. Data Analysis:

[1306] Software: Natural language processing libraries (e.g., spaCy, NLTK)

[1307] What happens:

[1308] Categorize your meals into food groups and nutrients

[1309] Divide your sleep into deep and light sleep

[1310] Emotional state analysis and reflection in lifespan simulation

[1311] 3. Life simulation:

[1312] Software: Simulation engine (e.g. AnyLogic)

[1313] What happens:

[1314] Predict lifespan by taking into account the user's emotional state

[1315] 4. Meal plan suggestions:

[1316] Software: Recommendation systems (e.g., TensorFlow, PyTorch)

[1317] What happens:

[1318] Generates optimal meal plans based on the user's health status

[1319] 5. Notices and Orders:

[1320] Hardware: Smartphone

[1321] Software: Food delivery app

[1322] What happens:

[1323] Inform users about the best meal plan and take their order

[1324] Specific examples

[1325] The user enters their dietary information into a health management app on their smartphone, and their sleep and exercise data is collected using a smartwatch. An emotion analysis app analyzes the user's emotional state and performs a lifespan simulation based on this data. Based on the simulation results, the user is presented with an optimal meal plan, and the food delivery app completes the order.

[1326] Prompt Sentence Examples

[1327] Analyze the user's diet, sleep time, exercise amount, and emotional state to simulate their lifespan. Based on the simulation results, propose an optimal meal plan for the user and implement a function to accept orders via a food delivery app.

[1328] In this way, it becomes possible to propose and provide meal plans that take into consideration the user's overall health and emotional state.

[1329] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1330] Step 1:

[1331] A user inputs the details of their diet into a health management app on their smartphone. The data entered includes the name of the food, the amount consumed, and the time of consumption. This allows dietary information to be collected.

[1332] Step 2:

[1333] The user wears a smartwatch to record their sleep time and exercise amount. The smartwatch collects sensor information such as pulse rate, number of steps, exercise time, and sleep time, thereby collecting sleep and exercise information.

[1334] Step 3:

[1335] The device uses an emotion analysis app to analyze the user's emotional state. The input data includes the user's facial expressions, voice tone, text messages, etc. This allows the emotional state to be analyzed.

[1336] Step 4:

[1337] The server analyzes the collected dietary, sleep, exercise, and emotional state information using generative AI that processes natural language. Specifically, it categorizes dietary content into food groups and nutrients, divides sleep time into deep and light sleep, and quantifies emotional state. This converts the data into an appropriate format.

[1338] Step 5:

[1339] The server performs a lifespan simulation based on the data analyzed by the generative AI. Using a simulation engine, the server predicts the user's lifespan, taking into account their health and emotional state. This produces the lifespan simulation results.

[1340] Step 6:

[1341] The server generates an optimal meal plan for the user based on the results of the lifespan simulation. A recommendation system is used to suggest foods and meal menus that are suitable for the user's health condition. This generates a meal plan.

[1342] Step 7:

[1343] The server notifies the user of the generated meal plan via their smartphone. The user receives the notification and orders meals through a food delivery app, which provides the meal plan to the user.

[1344] Step 8:

[1345] The food delivery service accepts the user's order and delivers the meal to the specified location, allowing the user to receive meals based on the proposed meal plan.

[1346] Example 3

[1347] Next, a description will be given of Example 3 of Form Example 3. 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."

[1348] Conventional health management systems could collect information on a user's diet, sleep, exercise, and biological information individually, but it was difficult to analyze them comprehensively and simulate the user's lifespan. They also could not provide feedback that took emotional state into account. This meant that users could not accurately understand their own health status or receive specific advice on improving their lifestyle habits.

[1349] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1350] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various biological information of the person, means for preprocessing the information, means for evaluating the health state based on the preprocessed information, means for simulating the person's lifespan based on the evaluation results, means for generating feedback based on the simulation results, and means for analyzing the emotional state and generating feedback based on the emotions. This allows the user to comprehensively understand their own health state and receive specific advice for improving their lifestyle habits.

[1351] "Dietary information" refers to information about the contents and nutrients of the meals consumed by the user.

[1352] "Sleep information" refers to information about the user's sleep time and sleep quality.

[1353] "Exercise information" refers to information about the type, frequency, and intensity of exercise performed by the user.

[1354] "Biometric information" refers to physiological data such as the user's heart rate, blood pressure, and body temperature.

[1355] "Preprocessing" refers to the process of filling in missing values ​​in collected data and detecting and correcting outliers.

[1356] "Health status assessment" is the process of analyzing and assessing the user's health status based on the preprocessed data.

[1357] "Lifespan simulation" is the process of predicting future health risks and lifespan based on a user's current lifestyle and health status.

[1358] "Feedback" is specific advice or recommendations provided to users based on simulation results and health assessments.

[1359] "Emotional state analysis" is the process of analyzing a user's emotional data and assessing their emotional state, such as stress or happiness.

[1360] "Emotion-based feedback" is specific advice or recommendations provided to users based on an analysis of their emotional state.

[1361] MODE FOR CARRYING OUT THE INVENTION

[1362] The present invention is a system for comprehensively evaluating a user's health condition and simulating a user's lifespan. Specific embodiments of this system will be described below.

[1363] Data collection

[1364] Users use a smartphone app to input their daily diet, sleep time, and exercise, such as what they had for breakfast, what time they went to bed at night, and the distance they jog, to collect detailed data about the user's lifestyle.

[1365] The terminal automatically collects biometric information such as the user's heart rate and blood pressure through a wearable device (e.g., a smart watch), and transmits this data to a server in real time.

[1366] Data transmission and storage

[1367] The device sends the collected information on food, sleep, exercise, and biometric data to a server. The data is encrypted and sent securely. The server then stores the received data in a database, using a relational database such as MySQL or PostgreSQL.

[1368] Data Preprocessing

[1369] The server preprocesses the stored data, specifically by filling in missing values ​​and detecting outliers. For example, if the heart rate shows an abnormally high value, the data is excluded.

[1370] Health assessment

[1371] The server evaluates the user's health status based on the preprocessed data. It uses AI models (e.g., TensorFlow, PyTorch) to analyze the nutritional balance of meals, sleep quality, and exercise frequency and intensity. The evaluation results are stored in a database, allowing the user's health history to be tracked.

[1372] Lifespan Simulation

[1373] The server uses an AI model based on the evaluation results to simulate the user's lifespan. For example, it calculates the predicted lifespan if the user continues their current lifestyle. The simulation results are stored in a database, allowing users to compare them with past simulation results.

[1374] Providing feedback

[1375] The server generates feedback for the user based on the simulation results. For example, it creates specific advice such as, "Your recent meals have been well-balanced in terms of nutrition. Keep it up. Also, since you're not getting enough sleep, I recommend going to bed 30 minutes earlier each night." The generated feedback is sent to the user's device, and the user can check it via a smartphone app.

[1376] Use of emotion engine

[1377] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user has been feeling stressed for a certain period of time, it will proceed to the next step based on that information. The server then generates feedback for the user based on the results of the analysis of the emotional state. For example, it could create advice such as, "You seem to be under a lot of stress lately. We recommend relaxation and moderate exercise." The generated emotion-based feedback is sent to the user's device, where the user can check the feedback through a smartphone app.

[1378] Examples and prompts

[1379] As a specific example, a user enters their daily diet, sleep duration, and exercise amount through a smartphone app. A wearable device measures their heart rate and blood pressure, and sends this data to a server. The server uses this data to evaluate the user's health and simulates their lifespan using an AI model. As a result, the user is given feedback such as, "Your recent diet has been well-balanced. Please continue at this pace. Also, because you are not getting enough sleep, we recommend that you go to bed 30 minutes earlier each night."

[1380] An example of a prompt sentence is, "Evaluate the user's health status and simulate their lifespan based on their diet, sleep, exercise information, and biometric information. As a result, provide the user with advice that will help them manage their health and improve their lifestyle."

[1381] In this way, the user can understand his / her own health condition and receive specific advice for improving his / her lifestyle. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1382] Step 1:

[1383] Users use a smartphone app to input their daily diet, sleep time, and exercise amount. The input data is saved on the device as dietary information, sleep information, and exercise information. This allows detailed data on the user's lifestyle habits to be collected.

[1384] Step 2:

[1385] The terminal automatically collects biometric information such as the user's heart rate and blood pressure through the wearable device, and transmits the collected biometric information to a server in real time, thereby obtaining the user's physiological data.

[1386] Step 3:

[1387] The device sends the collected information on meals, sleep, exercise, and biometrics to a server. The data is encrypted and sent securely. The server stores the received data in a database. This allows all data to be managed centrally.

[1388] Step 4:

[1389] The server preprocesses the stored data. Specifically, it complements missing values ​​and detects outliers. For example, if the heart rate shows an abnormally high value, it will exclude that data. The preprocessed data is then converted into a format suitable for analysis.

[1390] Step 5:

[1391] The server evaluates the user's health status based on the preprocessed data. It uses AI models (e.g., TensorFlow, PyTorch) to analyze the nutritional balance of meals, sleep quality, and exercise frequency and intensity. The evaluation results are stored in a database as an index of the user's health status.

[1392] Step 6:

[1393] The server uses an AI model based on the evaluation results to simulate the user's lifespan. For example, it calculates the predicted lifespan if the user continues their current lifestyle. The simulation results are stored in a database, allowing users to compare them with past simulation results.

[1394] Step 7:

[1395] The server generates feedback for the user based on the simulation results. For example, it creates specific advice such as, "Your recent meals have been well-balanced in terms of nutrition. Keep it up. Also, you're not getting enough sleep, so I recommend you go to bed 30 minutes earlier each night." The generated feedback is sent to the user's device.

[1396] Step 8:

[1397] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user has been feeling stressed for a certain period of time, it uses that information to proceed to the next step. The results of the emotional state analysis are stored in a database.

[1398] Step 9:

[1399] The server generates feedback for the user based on the analysis of the emotional state. For example, it might create advice such as, "You seem to be under a lot of stress lately. We recommend relaxation and moderate exercise." The generated feedback based on the emotions is sent to the user's device.

[1400] In this way, users can understand their own health status and receive specific advice on how to improve their lifestyle habits.

[1401] (Application example 3)

[1402] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1403] Conventional health management systems can evaluate a user's health status based on information such as diet, sleep, and exercise, but they are unable to provide personalized advice that takes into account their emotional state. As a result, they are unable to provide appropriate feedback based on the user's emotional state, making comprehensive health management difficult. Furthermore, they do not offer lifespan simulations, meaning there is a lack of specific indicators for users to review their lifestyle habits.

[1404] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for analyzing emotional states, and means for providing personalized advice based on the health state and emotional states. This makes it possible to comprehensively evaluate the user's health state and emotional state and provide specific advice based on the results of the lifespan simulation.

[1405] "Dietary information" refers to data such as the types, amounts, and nutritional components of the foods and beverages consumed by the user.

[1406] "Sleep information" refers to data such as the user's sleep time, sleep quality, and how they fall asleep and wake up.

[1407] "Exercise information" refers to data such as the type, frequency, intensity, and duration of exercise performed by the user.

[1408] "Sensor information" refers to data obtained from various sensors for acquiring the user's biometric data, and specifically includes pulse rate, body temperature, blood pressure, and the like.

[1409] "Generative AI" is an artificial intelligence system that processes input data using natural language processing, extracting and analyzing necessary information.

[1410] "Lifespan Simulation AI" is an artificial intelligence system that predicts lifespan based on the user's health condition and lifestyle habits.

[1411] "Emotional state" is data that indicates the user's psychological state, including stress levels and mood fluctuations.

[1412] "Personalized advice" refers to specific improvement suggestions and feedback provided based on a user's individual health and emotional state.

[1413] The system for implementing this invention comprehensively evaluates the user's health and emotional state and provides specific advice based on the results of a lifespan simulation. Specific embodiments of this system are described below.

[1414] System Configuration

[1415] The system consists of the following main components:

[1416] 1. User device: A device such as a smartphone or tablet that provides an interface for users to enter information about their diet, sleep, and exercise.

[1417] 2. Wearable devices: Devices that collect biometric data such as a user's pulse rate, body temperature, and blood pressure. These include smartwatches and fitness trackers.

[1418] 3. Server: The central component that processes and analyzes data and has the following functions:

[1419] Generative AI: Performs natural language processing on data entered by the user, extracting and analyzing necessary information.

[1420] Lifespan Simulation AI: Predicts lifespan based on health status and lifestyle habits.

[1421] Emotion Engine: Analyzes the user's emotional state and generates appropriate feedback.

[1422] Personalized advice generation: Providing specific improvement suggestions to users based on their health and emotional state.

[1423] Data acquisition and processing

[1424] The user device receives information about diet, sleep, and exercise entered by the user and sends it to a server. The wearable device collects the user's biometric data in real time and sends it to the server. The server receives this data and uses generative AI to perform natural language processing to extract the necessary information.

[1425] Health and lifespan simulation

[1426] The server evaluates the user's health status based on the extracted data and predicts the user's lifespan using a lifespan simulation AI. The prediction results are then fed back to the user's device.

[1427] Emotional state analysis and feedback

[1428] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user has been feeling stressed for a certain period of time, it generates messages recommending relaxation and moderate exercise.

[1429] Providing personalized advice

[1430] The server generates specific improvement suggestions for the user based on their health and emotional state, and these suggestions are sent to the user's device for them to put into practice in their daily lives.

[1431] Specific examples

[1432] For example, when a user inputs information about their diet, sleep, exercise, and biometrics into the app, the server calculates a health score based on this data and predicts their life expectancy. It also analyzes the user's emotional state and provides relaxation advice if they are under a lot of stress.

[1433] Prompt Sentence Examples

[1434] "Write a Python program that calculates a health score based on the user's diet, sleep, exercise, and biological information, and predicts their lifespan. Also, add a function that uses an emotion engine to analyze the user's emotional state and generate appropriate feedback."

[1435] In this way, a system is realized that comprehensively evaluates the user's health and emotional state and provides specific suggestions for improvement, thereby supporting the user in living a healthier life.

[1436] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1437] Step 1:

[1438] The user device receives information about meals, sleep, and exercise entered by the user. The entered information includes detailed data such as the type and amount of meals, the duration and quality of sleep, and the type and frequency of exercise. This data is then sent from the user device to the server.

[1439] Step 2:

[1440] The wearable device collects the user's biometric data in real time, including pulse rate, body temperature, blood pressure, etc. This biometric data is also sent from the wearable device to a server.

[1441] Step 3:

[1442] The server receives data sent from the user's terminal and wearable device. The received data undergoes natural language processing using generative AI to extract the necessary information. Specifically, the data is normalized and missing values ​​are filled in.

[1443] Step 4:

[1444] The server evaluates the user's health status based on the extracted data, including calculating a health score based on a comprehensive evaluation of diet, sleep, exercise, and biometric data.

[1445] Step 5:

[1446] The server uses the health score as input to predict the user's lifespan using a lifespan simulation AI, and the predicted lifespan is fed back to the user's device.

[1447] Step 6:

[1448] The server uses an emotion engine to analyze the user's emotional state, including stress levels and mood swings. The emotion engine evaluates the user's emotional state based on the user's input data and biometric data.

[1449] Step 7:

[1450] The server generates appropriate feedback based on the analysis of the user's emotional state. For example, if the server determines that the user has been feeling stressed for a certain period of time, it generates a message recommending relaxation or moderate exercise.

[1451] Step 8:

[1452] The server generates personalized advice based on the user's health and emotional state. The advice is then sent to the user's device, allowing them to put it into practice in their daily lives. Specific advice includes suggestions for improving their diet and recommending exercise.

[1453] The above processing steps realize a system that comprehensively evaluates the user's health and emotional state and provides specific suggestions for improvement.

[1454] 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.

[1455] 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> ) 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.

[1456] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1457] 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.

[1458] [Third embodiment]

[1459] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1460] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1461] 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).

[1462] 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.

[1463] 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.

[1464] 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).

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1471] "Example 1"

[1472] In one embodiment of the present invention, the user inputs information about food, sleep, and exercise via a device such as a smartphone or PC. Specifically, the user inputs information such as the contents of meals, calorie intake, sleep time, and type and time of exercise. The user also uses a wearable device (e.g., a smartwatch or fitness band) to obtain biometric information such as pulse rate and transmit it to the system. "Embodiment Example 2"

[1473] In this embodiment of the present invention, generative AI processes the information acquired above using natural language processing. Specifically, it analyzes information on diet, sleep, and exercise as text data and converts each piece of information into an appropriate format. For example, it may classify dietary content into food groups and nutrients, or divide sleep time into deep and light sleep periods.

[1474] "Example 3"

[1475] In this embodiment of the present invention, AI simulates a person's lifespan based on the information processed above. Specifically, it combines information on diet, sleep, and exercise with biometric information to evaluate the user's health condition and lifestyle habits, and predicts their lifespan based on that. The prediction results are fed back to the user and can be used to improve their health management and lifestyle habits.

[1476] The processing flow of each embodiment will be described below.

[1477] "Example 1"

[1478] Step 1: The user enters information about food, sleep, and exercise via a device such as a smartphone or computer. Specifically, the user enters information about the food they eat, the calories they consume, how much sleep they get, and the type and duration of their exercise.

[1479] Step 2: The user uses a wearable device (e.g., a smart watch or fitness band) to acquire biometric information such as pulse rate and transmit it to the system.

[1480] "Example 2"

[1481] Step 1: The generative AI performs natural language processing on the information acquired above. Specifically, it analyzes information about diet, sleep, and exercise as text data.

[1482] Step 2: Transform each piece of information into an appropriate format, such as categorizing your diet into food groups and nutrients, or dividing your sleep into periods of deep and light sleep.

[1483] "Example 3"

[1484] Step 1: Based on the information processed above, the AI ​​simulates a person's lifespan. Specifically, it combines information on diet, sleep, and exercise with biometric information to evaluate the user's health and lifestyle.

[1485] Step 2: Based on this, the lifespan is predicted. The prediction result is fed back to the user.

[1486] This will be useful for managing health and improving lifestyle habits.

[1487] Example 1

[1488] Next, a description will be given of Example 1 of Form 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."

[1489] Conventional health management systems have had difficulty effectively integrating information about diet, sleep, and exercise entered by users with biometric information obtained from wearable devices and providing the analysis results as feedback to users. Furthermore, there has been insufficient simulation of lifespan based on this information. This has made it difficult for users to accurately understand their own health status and maintain appropriate lifestyle habits.

[1490] 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.

[1491] In this invention, the server includes means for receiving information on diet, sleep, and exercise input by the user, means for receiving biometric information acquired from the wearable device, means for storing the received information in a database, means for analyzing the stored information, means for transmitting the analysis results to the user's terminal, means for performing natural language processing using generative AI, and AI means for simulating a person's lifespan based on the above information. This makes it possible to comprehensively analyze the information input by the user and the biometric information acquired from the wearable device and provide appropriate feedback to the user.

[1492] "Dietary information" refers to information about the contents of meals and calories consumed by the user.

[1493] "Sleep information" refers to information about the user's sleep time and sleep quality.

[1494] "Exercise information" refers to information about the type of exercise performed by the user, the duration of the exercise, and the calories burned.

[1495] "Sensor information" refers to biological information such as pulse rate obtained from a wearable device.

[1496] A "wearable device" is a device worn by a user that measures biometric information, and examples include smartwatches and fitness bands.

[1497] A "server" is a computer system that receives, stores, and analyzes information sent by users.

[1498] "Database" means a data management system for storing information received by the server.

[1499] "Analysis" is the process by which the server evaluates data based on stored information using statistical analysis and machine learning models.

[1500] "Generative AI" is an artificial intelligence model for performing natural language processing.

[1501] "Lifespan simulation" is the process of predicting a user's lifespan based on the user's input information and biometric information.

[1502] "Feedback" refers to the transmission of information to provide analysis results to users.

[1503] MODE FOR CARRYING OUT THE INVENTION

[1504] This invention is a system in which a user inputs information about diet, sleep, and exercise via a terminal such as a smartphone or a personal computer, and biometric information is acquired using a wearable device. Specific embodiments of this system are described below.

[1505] User Data Entry

[1506] Users use their smartphones or computers to input information about their diet, sleep, and exercise. For example, if a user inputs "two slices of toast, one banana, and one cup of coffee" for breakfast, the application will calculate the calories from this information and display the total calorie intake. The software used includes smartphone applications and web applications.

[1507] Acquisition of biometric information

[1508] Users wear a wearable device (e.g., a smartwatch or fitness band) and collect biometric information such as their pulse rate during exercise and daily life. For example, if a user goes for a one-hour run, the smartwatch will measure their pulse rate and calories burned while they run. The measured data is sent to a smartphone via Bluetooth or Wi-Fi.

[1509] Data transmission and storage

[1510] The device (smartphone or PC) sends the information entered by the user and the biometric information obtained from the wearable device to a server. The HTTPS protocol is used for transmission, and the data is encrypted. The server stores the received data in a database, which uses a relational database such as MySQL or PostgreSQL.

[1511] Data analysis

[1512] The server analyzes the stored data using Python libraries such as Pandas and Scikit-learn. For example, it checks whether the calorie intake of a meal exceeds the target value and evaluates the balance between the amount of exercise and the calories burned. It also uses generative AI to perform natural language processing and provide easy-to-understand feedback to the user.

[1513] Feedback of results

[1514] The server sends the analysis results to the user's device, where they can check them through a smartphone application. For example, if their calorie intake exceeds their target, the application will warn them. It will also suggest additional exercise if they are not getting enough exercise.

[1515] Specific examples

[1516] Example 1: Entering meal information

[1517] A user opens a smartphone application and enters their breakfast as "two slices of toast, one banana, and one cup of coffee." The application calculates the calories from this information and displays the total calorie intake. For example, it calculates two slices of toast as 200 kcal, one banana as 100 kcal, and one cup of coffee as 50 kcal, displaying a total of 350 kcal.

[1518] Example 2: Using a wearable device

[1519] The user wears a smartwatch and goes for a one-hour run. The smartwatch measures pulse rate and calories burned while running and sends the data to a smartphone. The smartphone then sends the received data to a server, which analyzes the data and provides feedback to the user. For example, the average pulse rate during the run is measured as 150 bpm and calories burned as 600 kcal.

[1520] Prompt Sentence Examples

[1521] Prompt 1: Enter meal information

[1522] "For breakfast, you had two slices of toast, one banana, and one cup of coffee. Calculate the total calories ingested from these meals."

[1523] Prompt 2: Wearable device data transmission

[1524] "I ran for an hour using my smartwatch. Please send my pulse rate and calories burned during the run to the server and let me know the analysis results."

[1525] In this way, the system involves users, terminals, and servers working together to input, transmit, analyze, and provide feedback on data.

[1526] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1527] Step 1:

[1528] Users use their smartphones or computers to input information about their diet, sleep, and exercise. For example, if a user inputs "two slices of toast, one banana, and one cup of coffee" for breakfast, the application will calculate the calories from this information and display the total calorie intake. The input data is the food content, calorie intake, sleep time, and type and time of exercise, and the output is a display of the total calorie intake and amount of exercise.

[1529] Step 2:

[1530] The user wears a wearable device and collects biometric information such as pulse rate during exercise and daily life. For example, if the user runs for an hour, the smartwatch measures their pulse rate and calories burned while they run. The measured data is sent to a smartphone via Bluetooth or Wi-Fi. The input data is pulse rate and calories burned, and the output is data sent to the smartphone.

[1531] Step 3:

[1532] The device (smartphone or PC) sends information entered by the user and biometric information obtained from the wearable device to a server. The HTTPS protocol is used for transmission, and the data is encrypted. The input data is the user's diet, sleep, exercise information, and biometric information, and the output is data sent to the server.

[1533] Step 4:

[1534] The server stores the received data in a database. A relational database such as MySQL or PostgreSQL is used for the database. The data is organized by user and indexed for efficient access. The input data is the user's diet, sleep, exercise information, and biometric information, and the output is stored in the database.

[1535] Step 5:

[1536] The server analyzes the stored data using Python libraries such as Pandas and Scikit-learn. For example, it checks whether the calorie intake of a meal exceeds the target value and evaluates the balance between the amount of exercise and the calories burned. The input data is the user information stored in the database, and the output is the analysis results.

[1537] Step 6:

[1538] The server sends the analysis results to the user's device. The user can check the analysis results through a smartphone application. For example, if the calorie intake of a meal exceeds the target value, the application will display a warning to the user. If the amount of exercise is insufficient, the application will also suggest additional exercise. The input data is the analysis results, and the output is feedback to the user's device.

[1539] (Application example 1)

[1540] Next, a description will be given of Application Example 1 of Form 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."

[1541] Health management is an important issue in modern society, but there is no system that can centrally manage individual diet, sleep, and exercise information and suggest optimal meal menus. Furthermore, there is a lack of a way to quickly order suggested meal menus from a food delivery service. This makes it difficult for users to take concrete actions to maintain a healthy lifestyle.

[1542] 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.

[1543] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the information, means for proposing an optimal meal menu based on the information, and means for ordering the proposed meal menu from a food delivery service. This allows the user to receive an optimal meal menu based on their own health condition and quickly order the menu.

[1544] "Dietary information" refers to information about the contents, calories, and nutrients of the meals consumed by the user.

[1545] "Sleep information" refers to information about the user's sleep time and sleep quality.

[1546] "Exercise information" refers to information about the type of exercise performed by the user, the duration, and the calories burned.

[1547] "Sensor information" refers to biological information such as pulse rate and number of steps acquired from a wearable device or the like.

[1548] "Generative AI" is artificial intelligence that performs natural language processing based on input information and generates appropriate output.

[1549] "Lifespan Simulation AI" is an artificial intelligence that simulates a user's lifespan based on their diet, sleep, exercise, and sensor information.

[1550] The "meal menu suggestion means" is a means for suggesting an optimal meal menu based on the user's health condition.

[1551] The "food delivery service ordering means" is a means for ordering the suggested meal menu from a food delivery service.

[1552] A system for implementing this invention includes a means for inputting information about a user's diet, sleep, and exercise, and a means for acquiring various sensor information (such as pulse rate) from a wearable device. This information is subjected to natural language processing by a generative AI and used to evaluate the user's health condition. Furthermore, a lifespan simulation AI simulates the user's lifespan based on this information. Next, a meal menu suggestion means suggests an optimal meal menu based on the user's health condition, and a food delivery service ordering means orders the suggested meal menu from a food delivery service.

[1553] Hardware and software used

[1554] Hardware: Smartphones, wearable devices (e.g., smartwatches)

[1555] Software: Python, Requests library (to send HTTP requests), food delivery API (a hypothetical API)

[1556] Data processing and calculation

[1557] 1. User input: Users input information about their diet, sleep, and exercise through a smartphone app, including what they ate, how many calories they consumed, how much sleep they had, and the type and duration of their exercise.

[1558] 2. Acquiring sensor information: Acquiring biometric information such as pulse rate and number of steps from wearable devices.

[1559] 3. Natural language processing using generative AI: The generative AI processes the acquired information using natural language to evaluate the user's health condition.

[1560] 4. Lifespan Simulation: Lifespan simulation AI simulates the user's lifespan based on their health condition.

[1561] 5. Meal menu suggestion: The meal menu suggestion means suggests the optimal meal menu based on the user's health condition.

[1562] 6. Order food delivery service: Order the suggested meal menu from a food delivery service.

[1563] Specific examples

[1564] For example, the user inputs the calories and nutrients for breakfast, lunch, and dinner, and the smartwatch retrieves their pulse rate and step count. Based on this information, the app suggests a "High Protein Salad" and orders it from a food delivery service.

[1565] Prompt Sentence Examples

[1566] "Create a Python program that suggests the best meal plan based on the user's diet, sleep, and exercise information, and biometric information obtained from a wearable device, and then orders it from a food delivery service."

[1567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1568] Step 1:

[1569] Users enter information about their diet, sleep, and exercise through a smartphone app.

[1570] Input: Food content, calorie intake, sleep time, type and duration of exercise.

[1571] Output: The entered data is sent to the server.

[1572] Specific operation: The user enters information about food, sleep, and exercise into the application's input form and presses the submit button. The server receives this data and stores it in a database.

[1573] Step 2:

[1574] The server acquires various sensor information (heart rate, number of steps, etc.) from the wearable device.

[1575] Input: Sensor data from wearable devices.

[1576] Output: The acquired sensor information is sent to the server.

[1577] How it works: The wearable device periodically measures sensor information and sends it to the smartphone via Bluetooth or Wi-Fi. The smartphone then forwards this data to the server.

[1578] Step 3:

[1579] The server uses generative AI to process input information and sensor information in natural language.

[1580] Input: User's diet, sleep, exercise information and sensor information.

[1581] Output: Natural language processed data.

[1582] Specific operation: The server uses a generative AI model to analyze input information and sensor information and evaluate the user's health condition.

[1583] Step 4:

[1584] The server uses a lifespan simulation AI to simulate the user's lifespan.

[1585] Input: Natural language processed data.

[1586] Output: Life simulation results.

[1587] Specific operation: The server uses the lifespan simulation AI to predict the user's lifespan based on their health condition. The simulation results are stored in a database.

[1588] Step 5:

[1589] The server uses the meal menu suggestion means to suggest an optimum meal menu based on the health condition of the user.

[1590] Input: Lifespan simulation results and user health status.

[1591] Output: A suggested meal menu.

[1592] Specific operation: The server uses a meal menu suggestion algorithm to generate a meal menu that is optimal for the user's health condition. The suggested menu is then sent to the user's smartphone.

[1593] Step 6:

[1594] The server orders the suggested meal from a food delivery service.

[1595] Input: A suggested meal menu.

[1596] Output: Order confirmation to food delivery service.

[1597] Specific operation: The server uses the food delivery service's API to order the suggested meal menu. An order confirmation is sent to the user's smartphone.

[1598] Example 2

[1599] Next, a description will be given of Example 2 of Form 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."

[1600] Conventional health management systems have had difficulty properly analyzing the diet, sleep, and exercise information entered by users and providing specific advice or lifespan simulations. Effective use of various sensor information was also difficult, making it impossible to provide useful information to users. This resulted in the issue of users being unable to accurately grasp their own health status and take appropriate measures.

[1601] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1602] In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for the generative AI to classify the diet information into food groups and nutrients, means for the generative AI to classify the sleep information into deep sleep and light sleep, and means for the generative AI to classify the exercise information into type and intensity. This allows the user to understand their own health condition in detail and receive appropriate advice.

[1603] "Dietary information" is information about the food and drinks consumed by the user.

[1604] "Sleep information" is information relating to the user's sleep time and sleep quality.

[1605] "Exercise information" is information relating to the type, intensity, and duration of exercise performed by the user.

[1606] "Sensor information" refers to biometric data such as pulse rate and activity level obtained from wearable devices.

[1607] "Generative AI" is an artificial intelligence that performs natural language processing and has the ability to analyze information entered by the user and convert it into an appropriate format.

[1608] "Food groups" are categories for classifying dietary information, and are classified based on nutrients such as carbohydrates, proteins, and lipids.

[1609] "Deep sleep" is the sleep stage that is considered to be the most restful for the user.

[1610] "Light sleep" is a sleep stage in which the user is relatively awake during sleep.

[1611] "Lifespan simulation" is a process of performing calculations and analyses to predict future lifespan based on a user's health information.

[1612] The present invention is a system for analyzing a user's health information in detail and providing appropriate advice and lifespan simulations. Specific embodiments of this system will be described below.

[1613] Program Generation

[1614] The system's program is designed to analyze the diet, sleep, and exercise information entered by the user and convert it into an appropriate format using a generative AI model, such as GPT-4.

[1615] Program processing

[1616] This system performs data processing and calculation using the following hardware and software.

[1617] 1. Analysis of dietary information

[1618] The server receives the meal details entered by the user as text data.

[1619] The server uses a generative AI model (e.g., GPT-4) to categorize the meal contents into food groups and nutrients.

[1620] For example, information such as "I ate bread and eggs for breakfast" is converted into a format such as "bread (carbohydrate), eggs (protein)."

[1621] 2. Sleep information analysis

[1622] The server receives the information on the sleeping hours input by the user as text data.

[1623] The server uses a generative AI model to divide sleep time into periods of deep and light sleep.

[1624] For example, information such as "I slept 8 hours last night" can be converted into a format such as "Deep sleep: 3 hours, Light sleep: 5 hours."

[1625] 3. Analysis of movement information

[1626] The server receives the exercise details entered by the user as text data.

[1627] The server uses a generative AI model to analyze the type and intensity of exercise and convert it into an appropriate format.

[1628] For example, information such as "I jogged for 30 minutes" is converted into a format such as "Jogging (aerobic exercise), 30 minutes."

[1629] Adding specific examples

[1630] Below is an example of a prompt sentence to input to the generative AI model.

[1631] Example prompt sentence:

[1632] "Classify what the user ate for breakfast into food groups and nutrients. Input: I ate bread and eggs for breakfast."

[1633] "Please divide the user's sleep time into deep and light sleep. Input: I slept 8 hours last night."

[1634] "Please classify the type and intensity of exercise performed by the user. Input: 30 minutes of jogging."

[1635] This allows users to simply input information about their diet, sleep, and exercise, and the server will use a generative AI model to convert each piece of information into an appropriate format.

[1636] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1637] Step 1:

[1638] The user enters information about their diet, sleep, and exercise.

[1639] How it works: Users enter information about their diet, sleep, and exercise in text format using a dedicated application or web interface.

[1640] Input: Information such as "I had bread and eggs for breakfast," "I slept 8 hours last night," or "I jogged for 30 minutes."

[1641] Output: The text data entered by the user.

[1642] Step 2:

[1643] The terminal transmits the input information to the server.

[1644] Specific operation: The device sends the information entered by the user as text data to the server using the HTTPS protocol to ensure data security.

[1645] Input: Text data entered by the user.

[1646] Output: The text data sent to the server.

[1647] Step 3:

[1648] The server receives the information and generates a prompt for the generative AI model.

[1649] Specific operation: The server analyzes the information received from the device and generates a prompt sentence to pass to the generative AI model.

[1650] Input: Text data sent from the terminal.

[1651] Output: A prompt to pass to the generative AI model.

[1652] Step 4:

[1653] The server analyzes the information using a generative AI model.

[1654] What it does: The server uses a generative AI model (e.g., GPT-4) to parse the information based on the prompt.

[1655] Input: A prompt to pass to the generative AI model.

[1656] Output: Analysis result (e.g. "bread (carbohydrates), eggs (protein)").

[1657] Step 5:

[1658] The server sends the analysis results to the device.

[1659] How it works: The server sends the analysis results obtained from the generative AI model to the device, again using the HTTPS protocol to ensure data security.

[1660] Input: Analysis results obtained from a generative AI model.

[1661] Output: Analysis results sent to the device.

[1662] Step 6:

[1663] The terminal displays the analysis results to the user.

[1664] Specific operation: The terminal displays the analysis results received from the server to the user.

[1665] Input: Analysis results sent from the server.

[1666] Output: The analysis results displayed to the user's screen (e.g., "Breakfast: Bread (carbohydrates), eggs (protein)").

[1667] This allows users to easily input information about their diet, sleep, and exercise, and have that information converted into the appropriate format.

[1668] (Application example 2)

[1669] Next, a description will be given of Application Example 2 of Form 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."

[1670] Health management is an important issue in modern society, but there is no system that comprehensively analyzes individual diet, sleep, and exercise information and proposes appropriate meal plans. Furthermore, there is a lack of means for users to actually order the proposed meal plans. This makes it difficult for users to efficiently manage their health.

[1671] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting information on a person's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the person, generative AI means for natural language processing this information, AI means for simulating a person's lifespan based on the above information, means for generating a meal menu based on health status and proposing a meal plan, and means for ordering the proposed meal menu in cooperation with an external meal provision service. This enables a user to easily obtain a meal plan based on their own health status and then efficiently order meals based on that plan.

[1672] "Dietary information" refers to data such as the content, amount, and time of meals consumed by the user.

[1673] "Sleep information" refers to data such as the user's sleep time, the time spent in deep and light sleep, and the quality of their sleep.

[1674] "Exercise information" refers to data such as the type, duration, and intensity of exercise performed by the user.

[1675] "Sensor information" refers to biological data such as pulse rate, body temperature, and activity level obtained from wearable devices.

[1676] "Generative AI" is artificial intelligence that processes input data using natural language processing and generates analytical results.

[1677] "Lifespan Simulation" is a simulation that predicts a user's lifespan based on input data.

[1678] "Meal menu generation" is the process of creating an appropriate meal plan based on the user's health status.

[1679] A "meal provision service" is an external service that provides meals ordered by a user.

[1680] The "ordering means" is a means for ordering the proposed meal menu from an external meal provision service.

[1681] The system for implementing this invention inputs information about the user's diet, sleep, and exercise, and based on this information, proposes a meal plan based on the user's health condition, and then orders meals based on that plan in cooperation with an external meal delivery service.

[1682] System Configuration

[1683] The system consists of the following main components:

[1684] 1. User device: A device used by a user to input information, such as a smartphone or tablet.

[1685] 2. Wearable device: A device for acquiring sensor information such as pulse rate and body temperature.

[1686] 3. Server: The central component that analyzes and processes data.

[1687] 4. Generative AI: Artificial intelligence that processes input data using natural language and generates analytical results.

[1688] 5. External meal service: An external service that provides a proposed meal menu.

[1689] Program processing

[1690] The server receives information on diet, sleep, and exercise from the user's device and acquires sensor information from the wearable device. This information is processed using natural language processing by generative AI, and a meal menu based on the user's health status is generated. The generated meal menu is then proposed to the user, and the menu selected by the user is ordered from an external meal delivery service.

[1691] Hardware and software used

[1692] Hardware: Smartphones, tablets, wearable devices

[1693] Software: Python, OpenAI API, Food Delivery API

[1694] Data processing and calculation

[1695] 1. Data entry: The user enters information about their diet, sleep, and exercise into their smartphone or tablet.

[1696] 2. Data acquisition: Obtain sensor information such as pulse rate and body temperature from the wearable device.

[1697] 3. Data analysis: Using generative AI (e.g., GPT-3), the input data is analyzed and a meal menu is generated based on health status.

[1698] 4. Data output: Display the generated meal menu to the user.

[1699] 5. Order processing: Using the food delivery API, the proposed menu is ordered from an external food delivery service.

[1700] Specific examples

[1701] For example, let's say a user had toast and eggs for breakfast, salad and chicken for lunch, and fish and vegetables for dinner. They also had 4 hours of deep sleep, 3 hours of light sleep, and went for a 30-minute run. With this information, the generative AI could use the following prompt to analyze:

[1702] Prompt Sentence Examples

[1703] Dietary information: I had toast and eggs for breakfast, salad and chicken for lunch, and fish and vegetables for dinner.

[1704] Sleep data: 4 hours of deep sleep, 3 hours of light sleep.

[1705] Exercise data: Ran for 30 minutes.

[1706] Analyze this data and suggest a meal plan based on your health condition.

[1707] Based on this prompt, the generative AI analyzes it and suggests a meal menu that is optimal for the user's health condition. The suggested menu is displayed to the user, and the menu selected by the user is ordered from an external meal delivery service. This allows users to easily obtain a meal plan based on their health condition and then efficiently order meals based on that plan.

[1708] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1709] Step 1:

[1710] The user uses a smartphone or tablet to input information about their diet, sleep, and exercise. The input information includes the type, amount, and time of meals, sleep duration, duration of deep and light sleep, and type, duration, and intensity of exercise. This data is then sent to the server.

[1711] Step 2:

[1712] The server acquires sensor information from the wearable device. The sensor information includes biometric data such as pulse rate, body temperature, and activity level. The acquired sensor information is important data for evaluating the user's health condition.

[1713] Step 3:

[1714] The server uses generative AI to process the inputted diet, sleep, exercise, and sensor information in natural language. Specifically, the server inputs the following prompts into the generative AI:

[1715] Dietary Data: [Dietary Information]

[1716] Sleep data: [Sleep information]

[1717] Exercise data: [Exercise information]

[1718] Analyze this data and suggest a meal plan based on your health condition.

[1719] The generative AI analyzes the data based on this prompt and generates a meal menu based on the patient's health status.

[1720] Step 4:

[1721] The server sends the generated meal menu to the user's device, where the user can check the proposed meal menu on their smartphone or tablet. The meal menu includes a balanced meal plan.

[1722] Step 5:

[1723] The user selects the desired meal from the suggested menu, and the selected menu is sent to the server.

[1724] Step 6:

[1725] The server orders the selected meal from an external food service using a food delivery API. The order data includes the selected meal, the user's address, payment method, etc.

[1726] Step 7:

[1727] An external food delivery service receives the order and delivers the meal to the user, who can then receive a meal based on the suggested meal menu.

[1728] Through the above steps, a user can easily obtain a meal plan based on their own health condition and can then efficiently order meals based on that plan.

[1729] Example 3

[1730] Next, a third embodiment of the third embodiment will be described. 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."

[1731] Conventional health management systems can collect information on a user's diet, sleep, exercise, and biological information individually, but it is difficult to integrate this information to predict a user's lifespan. Furthermore, the preprocessing of collected data and the accuracy of lifespan predictions using AI models are also insufficient. This makes it difficult for users to comprehensively evaluate their health status and lifestyle habits and receive specific feedback for improvement.

[1732] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1733] In this invention, the server includes a means for inputting information on a person's diet, sleep, and exercise, a means for acquiring various sensor information (biometric information) from the person, a means for preprocessing this information, a means for simulating a person's lifespan using a generative AI model based on the preprocessed information, and a means for feeding back the simulation results to the user. This makes it possible to comprehensively evaluate the user's health condition and lifestyle habits and provide specific feedback.

[1734] "Dietary information" refers to data such as the type, amount, and time of consumption of food and beverages consumed by the user.

[1735] "Sleep information" refers to data such as the user's sleep time, sleep quality, and wake-up time.

[1736] "Exercise information" refers to data such as the type, duration, and intensity of exercise performed by the user.

[1737] "Sensor information" refers to data obtained from various sensors that acquire biometric information about the user, such as pulse rate, blood pressure, and body temperature.

[1738] "Preprocessing" refers to processes such as cleaning the collected data, filling in missing values, removing outliers, and normalizing the data.

[1739] A "generative AI model" is an artificial intelligence model that predicts a user's lifespan based on collected data. Specifically, it includes machine learning algorithms such as neural networks.

[1740] "Feedback" refers to the provision of information to users that is useful for managing their health and improving their lifestyle habits by notifying them of the results predicted by the AI ​​model.

[1741] This invention is a system that collects information on a user's diet, sleep, exercise, and biological information, and uses a generative AI model based on this information to simulate a user's lifespan. Specific embodiments of this system are described below.

[1742] Data collection

[1743] Users use a smartphone app or web interface to input information about their diet, sleep, and exercise—for example, they ate oatmeal for breakfast, slept seven hours last night, and went on a 30-minute jog—and this information is sent from the device to a server.

[1744] Data storage and preprocessing

[1745] The server stores the received data in a database (e.g., MySQL). The stored data is preprocessed using Python libraries such as Pandas and NumPy. Specifically, the data is cleaned (missing values ​​are filled in and outliers are removed) and normalized. For example, missing sleep duration is filled in with the average value.

[1746] Lifespan prediction using AI models

[1747] The server inputs the preprocessed data into a generative AI model (e.g., a neural network using TensorFlow or PyTorch). This model evaluates the user's health and lifestyle habits and predicts their lifespan based on that. For example, the model may output "The user's predicted lifespan is 85 years."

[1748] Feedback of results

[1749] The server then provides the user with feedback on the life expectancy predictions generated by the AI ​​model. This feedback is provided via an app on the device or a web interface. Users can use this feedback to manage their health and improve their lifestyle habits. For example, the app screen might display, "Your predicted life expectancy is 85 years."

[1750] Specific examples

[1751] A user opens a smartphone app and enters information about their diet, sleep, and exercise. For example, they enter "Breakfast: Oatmeal" on the app's food input screen and "Sleep time: 7 hours" on the sleep input screen. The server stores the received data in a MySQL database and cleans it using the Pandas library. The preprocessed data is input into a TensorFlow model to predict lifespan. The server sends the prediction results in JSON format to the device, which then displays the received results on the app screen and informs the user, "Your predicted lifespan is 85 years."

[1752] Prompt Sentence Examples

[1753] "Evaluate your health and lifestyle based on your diet, sleep, exercise, and biological information, and predict your life expectancy."

[1754] In this way, a system is constructed in which the server, terminals, and users work together to collect and process data and simulate lifespan using an AI model. The flow of the specific processing in Example 3 will be described with reference to FIG.

[1755] Step 1:

[1756] Users use a smartphone app or web interface to input information about their diet, sleep, and exercise—for example, they ate oatmeal for breakfast, slept seven hours last night, and went on a 30-minute jog—and this information is sent from the device to a server.

[1757] Input: Diet, sleep, and exercise information

[1758] Output: User's lifestyle information sent to the server

[1759] Step 2:

[1760] The server stores the received data in a database (e.g., MySQL), including the user ID, meal details, sleep time, exercise details, etc.

[1761] Input: User's lifestyle information sent from the device

[1762] Output: User's lifestyle information stored in a database

[1763] Step 3:

[1764] The server preprocesses the stored data by using Python libraries such as Pandas and NumPy to clean (implant missing values ​​and remove outliers) and normalize the data. For example, missing sleep duration is imputed with the average value.

[1765] Input: User's lifestyle information stored in the database

[1766] Output: Preprocessed user lifestyle information

[1767] Step 4:

[1768] The server inputs the preprocessed data into a generative AI model (e.g., a neural network using TensorFlow or PyTorch). This model evaluates the user's health and lifestyle habits and predicts their lifespan based on that. For example, the model may output "The user's predicted lifespan is 85 years."

[1769] Input: Preprocessed user lifestyle information

[1770] Output: Lifespan prediction results from AI model

[1771] Step 5:

[1772] The server then provides the user with feedback on the life expectancy predictions generated by the AI ​​model. This feedback is provided via an app on the device or a web interface. Users can use this feedback to manage their health and improve their lifestyle habits. For example, the app screen might display, "Your predicted life expectancy is 85 years."

[1773] Input: Lifespan prediction results from AI model

[1774] Output: Life prediction results fed back to the user

[1775] (Application example 3)

[1776] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1777] Health management and lifestyle improvement are important issues in modern society. However, it is difficult for individual users to accurately evaluate their own health status and lifestyle habits and take appropriate measures to improve them based on the results. In particular, comprehensively evaluating information such as diet, sleep, and exercise and predicting life expectancy requires specialized knowledge and skills, making it difficult for average users. For this reason, there is a demand for a system that allows users to easily evaluate their own health status and obtain specific guidelines for improving their lifestyle habits.

[1778] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1779] In this invention, the server includes a means for inputting information on a person's diet, sleep, and exercise, a means for acquiring various sensor information (such as pulse rate) from the person, a generative AI means for natural language processing this information, an AI means for evaluating the person's health condition and lifestyle habits based on the above information and simulating lifespan, and a means for feeding back the evaluation results to the user. This enables the user to comprehensively evaluate their own health condition and obtain specific measures to improve their lifestyle habits.

[1780] "Dietary information" is data about the food and beverages consumed by a user.

[1781] "Sleep information" refers to data about the user's sleep time and quality.

[1782] "Exercise information" is data regarding the type, duration, and intensity of exercise performed by a user.

[1783] "Sensor information" refers to information obtained from various sensors for acquiring biometric data of the user.

[1784] "Generative AI" is artificial intelligence that uses natural language processing to analyze input information and generate appropriate output.

[1785] "Health status assessment" is the process of assessing a user's current health status based on the user's diet, sleep, exercise, and sensor information.

[1786] "Lifespan simulation" is the process of predicting a user's future lifespan based on their health condition and lifestyle habits.

[1787] "Feedback means" refers to a means for providing evaluation results and life expectancy prediction results to users to help them improve their lifestyle habits.

[1788] A system for implementing this invention includes a means for inputting information on a user's diet, sleep, and exercise, a means for acquiring various sensor information (such as pulse rate), a generative AI means for natural language processing this information, an AI means for evaluating the user's health condition and lifestyle habits based on the above information and simulating life expectancy, and a means for feeding back the evaluation results to the user.

[1789] System configuration

[1790] 1. User Device

[1791] The user terminal is a mobile device such as a smartphone or tablet, and the user uses this terminal to input information about their diet, sleep, and exercise.

[1792] 2. Wearable devices

[1793] Wearable devices include smartwatches and fitness trackers that collect biometric information such as the user's pulse rate, blood pressure, and body temperature.

[1794] 3. Server

[1795] The server receives data sent from the user's terminal and wearable device, and uses generative AI to perform natural language processing based on this information. It also evaluates health status and lifestyle habits and simulates life expectancy.

[1796] Program processing explanation

[1797] The server processes the data obtained from the user using Python and machine learning libraries (e.g., scikit-learn). Specifically, the process is carried out in the following steps:

[1798] 1. Data Acquisition

[1799] Information on diet, sleep, and exercise is collected from the user's device, and biometric information is collected from the wearable device.

[1800] 2. Data Analysis

[1801] The acquired data is processed using natural language processing with generative AI to evaluate the user's health condition and lifestyle habits.

[1802] 3. Life simulation

[1803] Based on the evaluation results, AI simulates the user's lifespan.

[1804] 4. Feedback

[1805] The simulation results are sent to the user's device and fed back to the user, allowing them to understand their own health condition and use it to improve their lifestyle habits.

[1806] Specific examples

[1807] For example, consider a scenario in which a user enters information about their diet, sleep, and exercise into an app every day, and their smartwatch automatically collects data on their heart rate and blood pressure. Based on this data, the server evaluates the user's health and predicts their life expectancy. The prediction results are fed back to the user, and specific lifestyle improvement measures are presented.

[1808] Prompt Sentence Examples

[1809] "Predict life expectancy based on the user's age, gender, heart rate, blood pressure, sleep time, exercise time, and diet score."

[1810] This prompt can be used to feed data into a generative AI model to predict lifespan.

[1811] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1812] Step 1:

[1813] The user device inputs information about meals, sleep, and exercise from the user. The input information includes the contents of meals, sleep time, type and time of exercise, etc. This information is temporarily stored in the user device.

[1814] Step 2:

[1815] Wearable devices acquire biometric information from users, specifically by measuring pulse rate, blood pressure, body temperature, and other data using sensors and transmitting this data to the user's device.

[1816] Step 3:

[1817] The user device sends the acquired information on food, sleep, exercise, and biometric data to the server. The data is sent in a standard data format such as JSON.

[1818] Step 4:

[1819] The server analyzes the received data. First, it formats and preprocesses the data. For example, it complements missing values ​​and detects and corrects outliers. Next, it uses generative AI to perform natural language processing and analyze the data.

[1820] Step 5:

[1821] The server evaluates the user's health condition and lifestyle habits based on the analysis results. Specifically, it evaluates and scores the balance of meals, quality of sleep, appropriateness of exercise, etc. The evaluation results are output as an index showing the user's health condition.

[1822] Step 6:

[1823] The server simulates lifespan based on the evaluation results. Using an AI model, it predicts future lifespan based on the user's current health condition and lifestyle habits. The results of this simulation are output as a lifespan prediction.

[1824] Step 7:

[1825] The server transmits the results of the lifespan simulation and the health status assessment to the user's device in a format that is easy for the user to understand (e.g., graphs or text).

[1826] Step 8:

[1827] The user device then displays the received evaluation results and life expectancy prediction results to the user, allowing the user to understand their own health condition and use these results to improve their lifestyle habits.

[1828] In this way, users can review their daily lifestyle habits and obtain specific guidelines for managing their health.

[1829] 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.

[1830] "Example 1"

[1831] In one embodiment of the present invention, an emotion engine that recognizes a user's emotions is incorporated. This emotion engine recognizes emotions from the user's voice, facial expressions, text input, etc. Specifically, it analyzes the voice of the user speaking through the microphone of a smartphone or computer, facial expressions captured through a camera, or text messages to determine the user's emotions.

[1832] "Example 2"

[1833] The output of the emotion engine influences the lifespan simulation. Specifically, the user's emotional state (joy, sadness, anger, surprise, etc.) is considered to affect their health and lifestyle, so this is incorporated into the lifespan simulation. For example, if a user is judged to be constantly stressed, it is predicted that their lifespan may be shortened.

[1834] "Example 3"

[1835] The output of the emotion engine is also used to provide feedback to users. Specifically, it helps users understand their emotional state and provides advice on how to improve their lifestyle based on that. For example, if it determines that a user has been feeling stressed for a certain period of time, it will send them a message recommending relaxation and moderate exercise.

[1836] The processing flow of each embodiment will be described below.

[1837] "Example 1"

[1838] Step 1: The user inputs speech through the microphone of their smartphone or computer, facial expressions captured through the camera, or text messages into the emotion engine.

[1839] Step 2: The emotion engine analyzes the input information and determines the user's emotion.

[1840] Step 3: The output of the emotion engine is incorporated as part of the lifespan simulation.

[1841] "Example 2"

[1842] Step 1: A user's emotional state is thought to affect their health and lifestyle, so incorporate this as part of the lifespan simulation.

[1843] Step 2: For example, if a user is determined to be constantly stressed, it is predicted that their lifespan may be shortened.

[1844] "Example 3"

[1845] Step 1: The output of the emotion engine is also used to provide feedback to the user. Step 2: The user understands their own emotional state and is then provided with advice on how to improve their lifestyle based on that.

[1846] Step 3: For example, if the user is determined to be stressed over a period of time, messages recommending relaxation and moderate exercise are sent to the user.

[1847] Example 1

[1848] Next, a description will be given of Example 1 of Form 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."

[1849] Conventional health management systems can collect information on a user's diet, sleep, exercise, and biometric information, but it is difficult to integrate and analyze this information and provide feedback that takes into account the user's emotional state. Furthermore, due to a lack of functionality to recognize the user's emotions, it is not possible to properly evaluate the user's psychological health state. This has led to the issue of insufficient comprehensive health management for users.

[1850] 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.

[1851] In this invention, the server includes means for inputting information on the user's diet, sleep, and exercise, means for acquiring various sensor information (such as pulse rate) from the user, generative AI means for natural language processing this information, AI means for simulating the user's lifespan based on the above information, means for recognizing emotions from the user's voice, facial expressions, and text input, means for integrating and analyzing the above information, and means for providing feedback based on the analysis results. This makes it possible to comprehensively evaluate the user's physiological and psychological health status and provide appropriate feedback.

[1852] "Dietary information" refers to data such as the type, amount, and calories of food consumed by the user.

[1853] "Sleep information" refers to data such as the user's sleep time, sleep quality, and wake-up time.

[1854] "Exercise information" refers to data such as the type of exercise the user performed, the duration of the exercise, and the calories burned.

[1855] "Sensor information" refers to biometric data such as the user's pulse rate, body temperature, and blood pressure.

[1856] "Generative AI" is artificial intelligence that performs natural language processing and analyzes information input by users.

[1857] "Lifespan Simulation AI" is an artificial intelligence that predicts lifespan...

Claims

1. means for recognizing a user's emotion using an emotion engine; A means for analyzing the health condition of the user based on the diet, sleep, and exercise information input by the user and the user's biological information; A means for generating a meal menu using a generative AI model based on a prompt sentence combining the recognized emotion and the analyzed health condition; A system including:

2. The system of claim 1 , further comprising means for requesting the generated meal menu from a food delivery service.

3. The system of claim 1 , wherein the biometric information is obtained from a wearable device.

Images