system

Abstract

Provide a system. [Solution] a means for inputting user basic information and activity data; means for transmitting the basic information and activity data to a server; means for storing and analyzing the transmitted data; A means for predicting the user's future state from the analysis results; means for presenting the prediction result to a user and suggesting an action; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern society, many people spend their days without understanding the impact of their lifestyles and future health conditions. As a result, they often face serious health problems later in life. Furthermore, current health management systems and lifestyle improvement systems only accumulate past data and are limited in their ability to predict future outcomes or suggest specific actions. The present invention aims to solve these problems by providing a system that allows users to predict their own future health conditions and receive specific action suggestions. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting a user's basic information and activity data, a means for transmitting the basic information and activity data to a server, a means for storing and analyzing the transmitted data, a means for predicting the user's future condition based on the analysis results, and a means for presenting the prediction results to the user and suggesting actions. Specifically, the user inputs information such as their health condition and lifestyle habits into a terminal and transmits it to the server. The server analyzes the data using a machine learning algorithm to predict their future condition. The prediction results are displayed as graphs and statistical data on the terminal's dashboard, allowing the user to visually confirm them. This system enables users to intuitively understand future health risks and the impact of their lifestyle habits and take specific actions.

[0006] "Basic information" refers to initial data about the user, such as the user's health condition, educational background, and lifestyle habits.

[0007] "Activity Data" refers to digital data collected from devices that is information about a user's physical activity, such as the number of steps taken, heart rate, and sleep duration.

[0008] "Means" refers to components or functions for achieving a specific function or purpose.

[0009] "Server" refers to a computer system that receives, stores, processes data sent by users, and provides the necessary information.

[0010] "Prediction" is the estimation of a user's future state based on past and current data.

[0011] "Action suggestions" refer to specific advice or recommended actions to improve the user's lifestyle or health.

[0012] A "dashboard" refers to an interface that allows users to visually view data and information.

[0013] A "graph" refers to a diagram that visually represents numerical data or information.

[0014] "Statistical data" refers to the results of numerical analysis based on user activity data and basic information.

[0015] A "machine learning algorithm" refers to a computational method for extracting patterns and insights from data and building predictive models. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system that collects basic information and activity data of a user, analyzes the data on a server, predicts future conditions, and makes specific suggestions for actions to the user.

[0038] Basic system configuration

[0039] 1. Terminal

[0040] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[0041] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[0042] The collected data is periodically sent to a server.

[0043] 2. Server

[0044] The server receives the data sent from the terminal and stores it in a database.

[0045] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits.

[0046] The prediction results are visualized and presented to the user in an easy-to-understand format.

[0047] 3. Users

[0048] Users can check the forecast results through the device's dashboard, which are displayed in the form of graphs and statistical data.

[0049] Based on the prediction results, users will receive specific action suggestions. For example, if there is an increased risk of health problems, the system will suggest changing exercise habits or improving diet.

[0050] Program processing

[0051] Data Collection Phase

[0052] Terminal

[0053] The user enters basic information as the initial setting, including height, weight, educational background, smoking habits, and exercise habits.

[0054] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[0055] Data transmission phase

[0056] Terminal

[0057] The collected basic information and activity data is periodically sent to a server, usually in a format such as JSON.

[0058] Data Management Phase

[0059] server

[0060] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[0061] Maintain data consistency by integrating with past data.

[0062] Prediction Phase

[0063] server

[0064] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, assessing their health risk if they continue their current lifestyle.

[0065] The prediction results are analyzed and actions are suggested to the user as necessary.

[0066] Visualization phase

[0067] server

[0068] Based on the predictions, graphs and statistics are generated, including predictions of heart disease risk and weight change.

[0069] Terminal

[0070] Predictions are displayed on a dashboard, allowing users to visually review them and adjust their actions as needed.

[0071] Specific examples

[0072] Example 1: Predicting health risks

[0073] Terminal

[0074] Users enter the results of their past health checkups into the app, such as data on blood pressure and cholesterol levels.

[0075] server

[0076] The server stores this information in a database and integrates it with existing lifestyle data.

[0077] Use machine learning algorithms to predict future heart disease risk.

[0078] Terminal

[0079] The predicted risk of heart disease is displayed as a graph on the dashboard. For example, it may say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years."

[0080] Based on this, users receive suggestions for actions to improve their exercise habits and diet, and review their lifestyle.

[0081] Example 2: Predicting weight change

[0082] Terminal

[0083] The user inputs the details of their daily diet and the amount of exercise they do.

[0084] server

[0085] The server analyzes the input data and predicts future weight changes.

[0086] Terminal

[0087] The predicted results are displayed on the dashboard in the form of, for example, "If you continue your current lifestyle, your weight will increase by 5 kg in three months."

[0088] Users can use this information to create dietary and exercise plans.

[0089] Such a system allows users to understand in real time how their lifestyle habits will affect their future and guide them towards healthier lifestyles.

[0090] The processing flow will be explained below.

[0091] Step 1:

[0092] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[0093] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[0094] Step 2:

[0095] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[0096] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[0097] Step 3:

[0098] The device sends the collected basic information and activity data to the server.

[0099] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[0100] Step 4:

[0101] The server receives the transmitted data and stores it in a database.

[0102] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL (registered trademark)) in an appropriate format.

[0103] Step 5:

[0104] The server applies machine learning algorithms to analyze the accumulated data.

[0105] Specifically, it combines past and current data and runs machine learning models such as regression analysis and clustering, using, for example, Scikit-learn or Tensorflow (registered trademark).

[0106] Step 6:

[0107] The server predicts the user's future state based on the analysis results.

[0108] Specifically, future health risks and weight changes are calculated based on the output of the machine learning model.

[0109] Step 7:

[0110] The server generates data for visualizing the prediction results.

[0111] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[0112] Step 8:

[0113] The graphs and statistical data generated by the server are sent to the terminal.

[0114] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[0115] Step 9:

[0116] The device displays the prediction results on a dashboard.

[0117] Specifically, the received data is displayed as graphs and statistical data on a user interface using HTML and JavaScript (registered trademark).

[0118] Step 10:

[0119] The user sees the forecast results on the dashboard.

[0120] Specifically, the system looks at graphs of predicted health risks and weight changes to determine the necessary improvement actions.

[0121] Step 11:

[0122] The terminal notifies the user of specific suggested actions.

[0123] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" via push notifications and in-app messages.

[0124] This detailed processing step allows the system to predict the user's future health status and provide information for taking specific actions.

[0125] Example 1

[0126] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0127] In modern society, personal health management and lifestyle improvement are extremely important issues. However, many currently available health management systems lack the ability to effectively collect and analyze user data and predict future risks. Furthermore, the feedback users receive is limited to general information and does not translate into specific recommendations for action. This makes self-management a time-consuming process for users, and makes it difficult for them to find appropriate improvement measures.

[0128] 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.

[0129] In this invention, the server includes means for accumulating the transmitted data and storing it in a database while maintaining consistency, means for analyzing the accumulated data and predicting the user's future state using a machine learning algorithm, and means for visualizing the prediction results as graphs or statistical data and presenting them to the user, thereby enabling the user to receive specific behavioral suggestions based on their own lifestyle habits.

[0130] "Basic user information" refers to basic data about an individual, such as height, weight, educational background, smoking habits, and exercise habits.

[0131] "Activity data" is data that records specific actions taken in the user's daily life, including the number of steps taken, heart rate, and sleep time.

[0132] The term "means" refers to a function or module for executing each of the processing steps described above.

[0133] A "server" is a computer system that receives, stores, analyzes, predicts, and presents results of data.

[0134] A "database" is a system for centrally managing user data accumulated by a server.

[0135] A "machine learning algorithm" is a computational method for learning patterns and trends from data and predicting future states.

[0136] "Prediction results" are information about future states derived from the user's current and past data.

[0137] "Visualization" is a method of displaying prediction results in a way that is easy for users to understand, such as in the form of graphs or statistical data.

[0138] "Action suggestions" are specific actions or improvements recommended to users based on the prediction results.

[0139] A "dashboard" is an interface displayed on a user's device that visually presents collected data and prediction results.

[0140] "Notification" is a function that allows the server to notify the user's device of suggested actions and prediction results.

[0141] The present invention is a system that collects basic information and activity data of a user, analyzes it on a server, predicts future conditions, and suggests specific actions to the user. This system uses the following hardware and software.

[0142] 1. Terminal

[0143] The device provides a user interface for the user to enter basic information. For example, information such as height, weight, educational background, smoking habits, and exercise habits can be entered using forms and check boxes. Furthermore, the device connects to an activity tracker or smartwatch to automatically collect the user's daily activity data. The collected basic information and activity data are periodically sent to a server. This transmission is usually done in a format such as JSON.

[0144] Specific examples

[0145] Users enter information such as their height (170cm), weight (70kg), and non-smoking status into a form on the device. The device also receives data from a smartwatch and collects activity data such as the number of steps taken each day and heart rate. The collected data is sent to a server every night.

[0146] 2. Server

[0147] The server receives basic information and activity data sent from the device and stores it in a database. Data integrity is maintained by integrating existing data and updating it with new data. The server analyzes the accumulated data using machine learning algorithms to predict the user's future state. To do this, it utilizes Python libraries such as "pandas," "scikit-learn," and "Matplotlib."

[0148] Specific examples

[0149] The server uses Python's "pandas" to store the received data in a data frame, and then uses "scikit-learn"'s random forest model to predict future heart disease risk. The predicted results are visualized as a graph using "Matplotlib."

[0150] 3. Users

[0151] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data, allowing users to understand the results visually. Users can also receive specific action suggestions based on the prediction results. For example, if health risks increase, the system will suggest actions such as reviewing exercise habits or improving diet.

[0152] Specific examples

[0153] The dashboard displays a graph of predicted results, such as, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years." Based on these results, users receive suggestions to improve their exercise habits and eat healthier meals.

[0154] In this way, this system collects basic information and activity data from users, analyzes this data on the server, and predicts future conditions, allowing the system to suggest specific actions to users. This allows users to understand in real time how their lifestyle habits will affect the future, and to take specific actions to maintain a healthy lifestyle.

[0155] Example prompt sentence:

[0156] "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years. We suggest that you review your exercise habits and improve your diet."

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1: Data Entry Phase

[0159] Terminal

[0160] Specific operation: The user uses the device's user interface to enter basic information, such as height, weight, educational background, smoking habits, and exercise habits, using the device's forms and check boxes.

[0161] Input and Output: As input, basic information of the user (e.g., height 170 cm, weight 70 kg, non-smoker, exercise 3 times a week) is received. As output, this data is stored on the device.

[0162] Step 2: Data collection phase

[0163] Terminal

[0164] Specific operation: The device works in conjunction with an activity tracker or smartwatch to automatically collect the user's daily activity data (number of steps, heart rate, sleep time, etc.).

[0165] Input and Output: As input, it receives real-time data from an activity tracker or smartwatch (e.g., 10,000 steps per day, heart rate 75 bpm, 7 hours of sleep). As output, it stores the collected activity data on the device.

[0166] Step 3: Data transmission phase

[0167] Terminal

[0168] How it works: The device periodically sends the collected basic information and activity data to the server. The data is usually sent in a format such as JSON.

[0169] Input and Output: As input, we use the saved basic information and activity data (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, these data are sent to the server.

[0170] Step 4: Data management phase

[0171] server

[0172] Specific operation: The server receives the data sent from the device and stores it in a database. It maintains data integrity by integrating it with existing data and updating it with new data.

[0173] Input and output: As input, it receives data sent from the device (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, it stores these data in a database.

[0174] Step 5: Data analysis and prediction phase

[0175] server

[0176] How it works: The server analyzes the accumulated data and uses machine learning algorithms to predict the user's future state. It stores the data in a data frame using Python's "pandas," preprocesses the data using "scikit-learn," and makes predictions using algorithms such as the random forest model.

[0177] Input and Output: The input is data stored in a database (e.g., health data from the past few months). The output is a prediction result (e.g., "20% increase in risk of heart disease within five years").

[0178] Step 6: Visualization phase

[0179] server

[0180] How it works: The server generates graphs and statistical data based on the prediction results, using libraries such as "Matplotlib" and "Seaborn."

[0181] Input and Output: As input, a prediction result (e.g., "20% increase in risk of heart disease within 5 years") is used. As output, a graph or statistical data (e.g., line graph, bar graph) is generated.

[0182] Terminal

[0183] Specific operation: The device displays the generated graphs and statistical data on the dashboard.

[0184] Input and Output: As input, it receives graphs and statistical data sent from the server. As output, it displays these data on the dashboard.

[0185] Step 7: Action proposal phase

[0186] server

[0187] Specific actions: Based on the prediction results, the server generates specific action suggestions for the user, such as suggestions for improving exercise habits or diet.

[0188] Input and Output: The input is a prediction result (e.g., "High risk of heart disease"). The output is an action suggestion (e.g., "Add 30 minutes of walking each day").

[0189] Terminal

[0190] Specific operation: The device notifies and displays the suggested actions to the user.

[0191] Input and Output: As input, it receives action suggestions sent from the server. As output, it displays the action suggestions to the user in push notifications and on the dashboard.

[0192] (Application example 1)

[0193] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0194] With increasing health awareness, many people are trying to manage and improve their lifestyles and health status. However, choosing healthy meals in daily life is not easy. In particular, when using food delivery services, there is a lack of specific guidance on reducing health risks and selecting appropriate meal plans. Therefore, there is a need for a system that can suggest optimal meal plans based on the user's basic information and activity data.

[0195] 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.

[0196] In this invention, the server includes means for inputting basic information and activity data of a user, means for transmitting the basic information and activity data to the server, means for storing and analyzing the transmitted data, means for predicting the user's future state from the analysis results, means for presenting the prediction results to the user and suggesting actions, and means for proposing an optimal meal plan to the user based on the basic information and activity data, thereby enabling the user to select an appropriate meal plan taking into account their health condition and lifestyle habits.

[0197] "Basic information" refers to personal data such as the user's health condition, educational background, and lifestyle habits.

[0198] "Activity data" refers to data related to the user's physical activity, such as the number of steps taken, heart rate, and sleep time.

[0199] A "server" is a system for receiving, storing, and analyzing data sent by users.

[0200] "Future state" is the future state of a user's health and lifestyle, predicted using machine learning algorithms based on current data.

[0201] The means for suggesting "actions" is a function that presents the user with a specific action plan based on the prediction results.

[0202] The "means for suggesting meal plans" is a function that provides optimal meal options based on the user's basic information and activity data.

[0203] A "dashboard" is an interface that visually displays prediction results and statistical data to users.

[0204] "Graphs and statistical data" refers to information that visually represents the predicted results of the user's health risks and future conditions.

[0205] The present invention is a system that collects and analyzes basic information and activity data of a user to predict future conditions and propose an optimal meal plan to the user. The system includes the following components:

[0206] Basic system configuration

[0207] 1. Terminal

[0208] The device provides a user interface for users to enter basic information (health status, educational background, lifestyle habits, etc.). This includes forms and check boxes. The device connects to devices such as activity trackers and smartwatches to automatically collect daily activity data (number of steps, heart rate, sleep time, etc.). The collected data is periodically sent to a server.

[0209] 2. Server

[0210] The server receives the data sent from the device and stores it in a database. It uses machine learning algorithms to analyze the accumulated data and predict the user's future condition. For example, it can assess future health risks based on current lifestyle habits. The prediction results are visualized and presented to the user in an easy-to-understand format.

[0211] 3. Users

[0212] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data. Based on the prediction results, users are given an optimal meal plan. For example, if there is an increased risk of health problems, the system will suggest calorie restriction or improvements to their diet.

[0213] Program processing

[0214] Data Collection Phase

[0215] The device provides an interface for users to input basic information as an initial setting, including height, weight, educational background, smoking habits, exercise habits, etc. The device also connects to an activity tracker or smartwatch to collect activity data such as steps taken, heart rate, and sleep time in real time.

[0216] Data transmission phase

[0217] The device periodically sends the collected basic information and activity data to a server, usually in a format such as JSON.

[0218] Data Management Phase

[0219] The server receives the data and stores it in a database. It integrates it with existing data and updates it with new data. To maintain data consistency, it is managed together with past data.

[0220] Prediction Phase

[0221] The server uses machine learning algorithms (such as Sci-kit Learn's Linear Regression) to analyze the user's current and past data and predict their future condition. For example, it assesses the health risks if the user continues their current lifestyle. Based on this prediction, it proposes an optimal diet plan for the user.

[0222] Visualization phase

[0223] The server generates graphs and statistical data based on the predictions, including predictions of heart disease risk and weight change. The device displays the predictions on a dashboard, allowing users to visually check the results and adjust their behavior as needed.

[0224] Specific examples

[0225] Example 1: Predicting health risks

[0226] The device provides an interface for users to input past health checkup results into the app, including data such as blood pressure and cholesterol levels. The server stores this information in a database and integrates it with existing lifestyle data. Machine learning algorithms are used to predict future heart disease risk. The device displays the predicted heart disease risk as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within three years."

[0227] Example 2: Meal plan suggestions

[0228] The device provides an interface for users to input their daily dietary information. The server analyzes the input data and predicts future health risks. Based on the results, the server provides the user with an optimal meal plan. For example, the server may suggest, "We will provide you with a meal plan that takes into account calorie restriction and appropriate nutritional balance."

[0229] Example prompts to input to the generative AI model

[0230] "If you continue your current lifestyle habits, your health risks will increase by 15% after three months. To improve this, we recommend the following diet plan."

[0231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0232] Step 1:

[0233] The device provides an interface where the user can input basic information (health status, educational background, lifestyle habits, etc.). The input data includes height, weight, smoking habits, exercise habits, etc. This allows the user's basic information to be collected. The input data is formatted for storage in a database using a format such as JSON.

[0234] Step 2:

[0235] The terminal connects to devices such as activity monitors and smartwatches to collect daily activity data (number of steps, heart rate, sleep time, etc.) in real time. This data is collected, formatted in JSON format or other formats, and prepared for transmission to the next processing step, either in batch processing or at specified intervals.

[0236] Step 3:

[0237] The device periodically sends the collected basic information and activity data to the server using HTTP or HTTPS, with the Content-Type header set to application / json. The device then verifies that the data reaches the server without any errors.

[0238] Step 4:

[0239] The server receives data sent from the device and stores it in a database. Using a database such as SQLite or MySQL, the received data is integrated with the existing database. A timestamp is added to the new data and it is managed together with past data.

[0240] Step 5:

[0241] The server applies machine learning algorithms to the basic information and activity data stored in the database. Using Scikit-Learn's Linear Regression model, it matches the input data with the training data to generate a predictive model. This model is then used to predict the user's future health status and activity patterns.

[0242] Step 6:

[0243] The server generates an optimal meal plan based on the prediction results. The generated meal plan is optimized taking into account the user's calorie intake, nutritional balance, and past dietary information. The predictions and suggestions are integrated and generated as JSON format data to be provided to the user.

[0244] Step 7:

[0245] The device displays the prediction results and meal plans obtained from the server on a dashboard. Libraries such as Matplotlib and Chart.js are used to visualize the results as graphs and statistical data, allowing users to intuitively understand the predicted health risks and recommended meal plans.

[0246] Step 8:

[0247] Users can check the prediction results and suggestions displayed on the dashboard and adjust their diet and lifestyle accordingly. For example, they may see a prompt such as, "If you continue your current lifestyle, your health risk will increase by 15% in three months. To improve this, we recommend the following meal plan."

[0248] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0249] This system collects basic information, activity data, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[0250] Basic system configuration

[0251] 1. Terminal

[0252] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[0253] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[0254] The device uses a camera, microphone, and text input to collect the user's emotional data (facial expressions, tone of voice, and text input).

[0255] The collected data is periodically sent to a server.

[0256] 2. Server

[0257] The server receives the basic information, activity data, and emotion data sent from the terminal and stores them in a database.

[0258] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits and emotional state.

[0259] The prediction results are visualized and presented to the user in an easy-to-understand format.

[0260] 3. Emotion Engine

[0261] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state.

[0262] The emotion engine's analysis results are used to personalize suggested actions for the user, for example, relaxation suggestions when the user is feeling stressed.

[0263] 4. Users

[0264] Users can view the prediction results and their emotional state through a dashboard on their device, which is displayed in the form of graphs and statistical data.

[0265] Based on the prediction results and emotional state, users receive specific action suggestions to improve their lifestyle habits.

[0266] Program processing

[0267] Data Collection Phase

[0268] Terminal

[0269] The user enters basic information as the initial setting, including height, weight, education, smoking habits, and exercise frequency.

[0270] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[0271] It uses the camera, microphone, and text input to collect user emotional data.

[0272] Data transmission phase

[0273] Terminal

[0274] The collected basic information, activity data, and emotion data are periodically sent to a server, usually in a format such as JSON.

[0275] Data Management Phase

[0276] server

[0277] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[0278] Maintain data consistency by integrating with past data.

[0279] Prediction Phase

[0280] server

[0281] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, by considering their lifestyle habits and emotional state together to assess future health risks.

[0282] The prediction results are analyzed and actions are suggested to the user as necessary.

[0283] Sentiment Analysis Phase

[0284] Emotion Engine

[0285] Recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and text input, for example, using image processing and natural language processing techniques.

[0286] Visualization phase

[0287] server

[0288] Based on the predictions and your emotional state, graphs and statistics are generated, including predictions of heart disease risk, weight change, and stress levels.

[0289] Terminal

[0290] The predictions and sentiment analysis results are displayed on a dashboard, allowing users to visually check them and adjust their actions as needed.

[0291] Specific examples

[0292] Example 1: Predicting health risks

[0293] Terminal

[0294] Users input their past health check results and daily emotional state (e.g., daily stress level and mood) into the app.

[0295] server

[0296] The server stores this information in a database and integrates it with existing lifestyle data.

[0297] It uses machine learning algorithms to predict future heart disease risk, and an emotion engine to analyze a user's stress state.

[0298] Terminal

[0299] The predicted heart disease risk and emotional state are displayed as a graph on the dashboard, for example, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years."

[0300] Based on this, users receive action suggestions to improve their exercise habits, diet, and stress management methods, and review their lives.

[0301] Example 2: Predicting weight change

[0302] Terminal

[0303] The user inputs their daily diet and exercise, as well as their emotional state for that day (e.g., happy, sad, angry).

[0304] server

[0305] The server analyzes the input data and predicts future weight changes and psychological states. It also uses an emotion engine to analyze the user's emotional state regarding food and exercise.

[0306] Terminal

[0307] The prediction results are displayed on a dashboard in the form of, for example, "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect your diet and exercise.

[0308] Users can use this information to plan their diet and exercise, and manage their emotions, thereby improving their lives more effectively.

[0309] Such a system allows users to understand in real time how their lifestyle habits and emotions affect their future, and to take concrete actions to build healthy lifestyles.

[0310] The processing flow will be explained below.

[0311] Step 1:

[0312] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[0313] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[0314] Step 2:

[0315] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[0316] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[0317] Step 3:

[0318] The device collects user emotional data using the camera, microphone, and text input.

[0319] Specifically, it uses facial recognition technology to analyze facial expressions, voice recognition technology to analyze tone of voice, and natural language processing to analyze emotions from text input.

[0320] Step 4:

[0321] The device transmits the collected basic information, activity data, and emotion data to the server.

[0322] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[0323] Step 5:

[0324] The server receives the transmitted data and stores it in a database.

[0325] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL) in the appropriate format.

[0326] Step 6:

[0327] The server applies machine learning algorithms to analyze the accumulated data.

[0328] Specifically, it combines past and present data and runs machine learning models such as regression analysis and clustering using, for example, Scikit-learn or TensorFlow.

[0329] Step 7:

[0330] The server applies an emotion engine to analyze the user's emotion data.

[0331] Specifically, the emotion engine analyzes the user's facial expressions, tone of voice, and text input and stores them in a database.

[0332] Step 8:

[0333] The server predicts the user's future state based on the results of machine learning and the emotion engine.

[0334] Specifically, the results of both analyses will be integrated to generate future health risks and action recommendations.

[0335] Step 9:

[0336] The server generates data for visualizing the prediction results.

[0337] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[0338] Step 10:

[0339] The graphs and statistical data generated by the server are sent to the terminal.

[0340] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[0341] Step 11:

[0342] The device displays prediction results and sentiment analysis results on a dashboard.

[0343] Specifically, the received data is displayed as graphs and statistical data on the user interface using HTML and JavaScript.

[0344] Step 12:

[0345] The user sees the forecast results on the dashboard.

[0346] Specifically, the system looks at graphs of predicted health risks, weight changes, and emotional states to determine the necessary improvement actions.

[0347] Step 13:

[0348] The terminal notifies the user of specific suggested actions.

[0349] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" and "incorporate relaxation techniques to relieve stress" via push notifications and in-app messages.

[0350] Through this detailed processing step, the system allows users to understand their own health and emotional state in real time, predict future risks, and receive specific action suggestions.

[0351] Example 2

[0352] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0353] While conventional systems were capable of analyzing a user's basic information and activity information, they had the problem of not being able to make personalized suggestions that took into account the user's emotional state. This led to problems such as users overlooking health risks due to stress or emotional changes, or not being able to take effective actions. In addition, because the analysis results and suggested actions were displayed individually, it was difficult for users to grasp their overall health status.

[0354] 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.

[0355] In this invention, the server includes a means for inputting the user's basic information and activity information, a means for inputting the user's emotional state, and a means for accumulating and analyzing the transmitted data. This enables the user's basic information, activity information, and emotional state data to be analyzed in an integrated manner, enabling personalized behavioral suggestions. Furthermore, by displaying the analysis results and emotional state as graphs and statistical data on the display device of the user's terminal, the user can easily visually grasp changes in their own health condition and emotions. As a result, the user can more effectively manage health risks and work to improve their lifestyle habits.

[0356] "Basic user information" refers to personal information such as height, weight, educational background, smoking habits, and exercise frequency entered by the user.

[0357] "Activity information" refers to data on daily activities such as steps taken, heart rate, and sleep time collected from activity monitors and smartwatches.

[0358] "Emotional state" is data about emotions collected from a user's facial expressions, tone of voice, and text input.

[0359] "Input means" refers to the interface through which a user inputs data, such as a form, checkboxes, camera, or microphone.

[0360] "Means for transmitting" refers to the communication protocol or communication module used to transmit collected data to the server.

[0361] "Means of storage and analysis" refers to the server's function of storing received data in a database and analyzing the data using machine learning algorithms and data analysis tools.

[0362] "Means for predicting a user's future health risks and lifestyle changes" refers to the process of using a machine learning model to predict a user's future health risks and lifestyle changes based on the user's past and current data.

[0363] "Means for suggesting actions" refers to functions, such as notifications and alerts, that suggest specific actions to the user based on the prediction results.

[0364] "Display device" refers to a screen or display that allows a user to visually confirm analysis results and suggestions.

[0365] This system collects basic information, activity information, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[0366] Basic system configuration

[0367] 1. Terminal

[0368] The device provides a user interface for users to input basic information, including forms and checkboxes. It also connects with devices such as activity trackers and smartwatches to collect activity information in real time. It also uses a camera, microphone, and text input to collect the user's emotional state. The collected data is periodically sent to a server.

[0369] 2. Server

[0370] The server receives basic information, activity information, and emotion data sent from the device and stores them in a database. It also uses machine learning algorithms to analyze the accumulated data and predict the user's future state. The prediction results are visualized and provided to the user in an easy-to-understand format.

[0371] 3. Emotion Engine

[0372] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state, using image processing and natural language processing techniques, and the results of the analysis are used to personalize suggested actions for the user.

[0373] 4. Users

[0374] Users can check their prediction results and emotional state through the device's dashboard. The prediction results are displayed in the form of graphs and statistical data. Based on the prediction results and emotional state, users can receive specific action suggestions to improve their lifestyle habits.

[0375] Specific actions

[0376] Example 1: Predicting health risks

[0377] Users enter their past health checkup results and daily emotional state into the app. The server stores this information in a database and integrates it with existing lifestyle data. A machine learning algorithm is used to predict future heart disease risk. An emotion engine is also used to analyze the user's stress level. The device displays the predicted heart disease risk and emotional state as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years." Based on this, users receive action suggestions for improving their exercise habits, diet, and stress management methods.

[0378] Example 2: Predicting weight change

[0379] The user inputs their daily diet and exercise routine, as well as their emotional state for that day. The server analyzes the input data and predicts future weight changes and their psychological state. It also uses an emotion engine to analyze the user's emotional state regarding diet and exercise. The device displays the predicted results on a dashboard, such as "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect diet and exercise. Users can use this information to create dietary restrictions and exercise plans, and manage their emotions.

[0380] Example prompt

[0381] "Use the user's lifestyle data to predict future health risks and suggest specific actions to improve them."

[0382] "Analyze user sentiment data and provide personalized health recommendations based on it."

[0383] The system allows users to understand in real time how their lifestyle habits and emotions affect their future, and take concrete actions to build healthy lifestyle habits.

[0384] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0385] Step 1:

[0386] Enter basic information

[0387] The device provides a screen where the user can enter basic information (height, weight, educational background, smoking habits, exercise frequency, etc.). The user enters this information into a form. The input data is temporarily stored in local storage or device memory. This allows the basic information to be collected.

[0388] Input: User's height, weight, education, smoking habits, and exercise frequency

[0389] Output: Basic information data stored in the device

[0390] Step 2:

[0391] Collection of activity information

[0392] The device collects real-time activity information (number of steps, heart rate, sleep time, etc.) from activity monitors and smartwatches via Bluetooth or Wi-Fi. This data is updated at regular intervals and stored internally on the device.

[0393] Input: Activity information obtained from activity trackers and smartwatches

[0394] Output: Activity information data stored in the device

[0395] Step 3:

[0396] Collecting emotional states

[0397] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and collects this as emotional data. In addition, text data entered by the user is also collected as emotional data.

[0398] Input: facial expression data obtained from a camera or microphone, voice data, and text data entered by the user

[0399] Output: Emotion data stored in the device

[0400] Step 4:

[0401] Data transmission

[0402] The device periodically transmits the collected basic information, activity information, and emotion data to a server, structured in a standard format such as JSON, using a secure communication protocol.

[0403] Input: Basic information, activity information, and emotional data stored on the device

[0404] Output: Various data sent to the server

[0405] Step 5:

[0406] Receiving and storing data

[0407] The server receives the data sent from the device. The received data is stored in a dedicated database (e.g., MySQL, MongoDB), and is updated by integrating it with past data.

[0408] Input: Basic information, activity information, and emotional data sent from the device

[0409] Output: Various data stored in the server database

[0410] Step 6:

[0411] Running the prediction algorithm

[0412] The server analyzes the received data using machine learning models (e.g., TensorFlow, PyTorch), and predicts future health risks and weight changes based on the user's lifestyle and emotional state.

[0413] Input: Basic information, activity information, and emotion data stored in the database

[0414] Output: Predicted health risks and weight change data

[0415] Step 7:

[0416] Performing sentiment analysis

[0417] The emotion engine analyzes facial expressions, voice, and text data sent from the device, and uses image processing technology (e.g., OpenCV) and natural language processing technology (e.g., NLTK, spaCy) to identify the device's emotional state.

[0418] Input: facial expression data, voice data, text data

[0419] Output: Recognized emotional state data

[0420] Step 8:

[0421] Visualizing the results

[0422] The server generates graphs and statistical data based on the prediction results and emotional states (e.g., Matplotlib, D3.js), which makes it easier for users to understand visually.

[0423] Input: predicted health risk, weight change data, emotional state data

[0424] Output: Visualized graphs and statistical data

[0425] Step 9:

[0426] Viewing the Dashboard

[0427] The device displays the analysis results and prediction data sent from the server as a dashboard, allowing users to check their own predictions and sentiment analysis results.

[0428] Input: Analysis results and prediction data sent from the server

[0429] Output: Analysis results and forecast data displayed on a dashboard

[0430] Step 10:

[0431] action suggestion

[0432] The device will suggest specific actions based on the predictions and your emotional state, such as "take 10 minutes of deep breathing exercises to relax."

[0433] Input: Prediction result, emotional state

[0434] Output: Specific action suggestions provided to the user

[0435] Through each of the above steps, users can understand in real time how their lifestyle habits and emotions affect their future and take concrete action.

[0436] (Application example 2)

[0437] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0438] Conventional online shopping sites lack personalized product recommendations that take into account the user's health and emotional state. In particular, they are unable to provide appropriate product suggestions to reduce stress and health risks, making it difficult for users to find the products they truly need. In addition, understanding a user's emotional state in real time and recommending products accordingly is a challenge.

[0439] 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.

[0440] In this invention, the server includes a means for inputting basic information and activity data of a user, a means for analyzing the emotional state of the user using an emotion engine, a means for recommending personalized products to the user based on the basic information, activity data, and emotional state, and a means for displaying the recommendation results on the smart glasses, thereby enabling reliable product recommendations based on the user's health condition and emotional state.

[0441] (Word definition)

[0442] "Basic information of a user" refers to basic information related to an individual, such as the user's height, weight, age, lifestyle, and health condition.

[0443] "Activity data" is data related to the user's daily activities, and includes, for example, the number of steps taken, the amount of exercise, the heart rate, and the amount of sleep.

[0444] "Server" means a computer system on a network that stores and analyzes collected data.

[0445] An "emotion engine" is an algorithm or software that recognizes a user's emotional state by analyzing data such as facial expressions, tone of voice, and text input collected from sensors such as cameras and microphones.

[0446] The "prediction means" is a means for predicting the user's future state using a machine learning algorithm based on the collected basic information, activity data, and emotion data.

[0447] A "means for recommending personalized products" is a means for selecting and recommending products suitable for individual users by taking into consideration the user's basic information, activity data, and emotional state.

[0448] "Smart glasses" are eyeglass-type wearable devices with a built-in display device that can display information directly in the user's field of vision.

[0449] The "result display means" is a means for visually displaying prediction results and product recommendation results on the user's device.

[0450] The system for realizing this application example is configured as follows.

[0451] First, the core hardware of the system consists of a server, smart glasses, an activity tracker, a smartwatch, a camera, and a microphone. The server is responsible for storing data, analyzing it, and sending the results, while the smart glasses are responsible for displaying the data. The activity tracker and smartwatch collect the user's activity data, and the camera and microphone collect emotion data.

[0452] The system includes the following main software components:

[0453] 1. Data collection software: Collects basic user information, activity data, and emotional data using a camera and microphone.

[0454] 2. Data transmission software: periodically transmits collected data to the server.

[0455] 3. Database software: stores and manages the transmitted data.

[0456] 4. Machine learning algorithms: These run on the server and analyze the collected data to predict the user's future state.

[0457] 5. Sentiment Engine: A software component for performing sentiment analysis.

[0458] 6. Product recommendation software: Selects and recommends the most suitable products based on the user's health and emotional state.

[0459] 7. Display software: Visually display the product recommendation results on the smart glasses.

[0460] Data collection

[0461] The user wears the smart glasses and inputs basic information and activity data. The activity tracker or smartwatch automatically collects the user's daily activity data (e.g., number of steps, heart rate, and sleep time). The camera and microphone also analyze the user's facial expressions and tone of voice to collect their emotional state. The collected data is periodically sent to a server and stored in a database.

[0462] Data analysis

[0463] The server uses machine learning algorithms to analyze the accumulated basic information, activity data, and emotional data. The analysis results are used to predict the user's future health and emotional state. Furthermore, an emotion engine analyzes the user's real-time emotional state and makes product recommendations based on this.

[0464] Product recommendation

[0465] The server selects personalized products for the user based on the prediction results and the emotional state, and sends the recommendation results to the smart glasses via the product recommendation software.

[0466] display

[0467] The smart glasses visually display recommended products, allowing users to easily obtain product information based on their health and emotional state.

[0468] For example, when a user is feeling stressed, the emotion engine analyzes the user's stress level and recommends relaxation products and calming clothing. The results are displayed on the smart glasses, allowing the user to check in real time which products are suitable for their emotional state.

[0469] (Example of a prompt)

[0470] When the user feels stressed, a prompt is displayed that takes into account health risks: "Recommend relaxation products based on my health condition and emotions."

[0471] This enables personalized product recommendations based on the user's health and emotional state, contributing to improving the user's lifestyle habits.

[0472] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0473] Step 1:

[0474] The user puts on the smart glasses and inputs basic information, such as height, weight, age, lifestyle habits, and health status, into the application form. This information is then stored on the device.

[0475] Input: Basic information such as height, weight, age, lifestyle habits, and health condition

[0476] Output: Saved basic information data

[0477] Step 2:

[0478] Activity trackers and smartwatches collect users' activity data in real time, including the number of steps taken, heart rate, and sleep time. This data is also sent to the device and stored.

[0479] Input: User's daily activity data (number of steps, heart rate, sleep time, etc.)

[0480] Output: Saved activity data

[0481] Step 3:

[0482] The smart glasses' cameras and microphones capture the user's facial expressions and tone of voice to collect emotional data, which is then analyzed in real time by an emotion engine.

[0483] Input: Facial expression, tone of voice data

[0484] Output: Parsed emotion data

[0485] Step 4:

[0486] The device periodically sends the collected basic information, activity data, and emotion data to the server in JSON format.

[0487] Input: Basic information, activity data, emotion data

[0488] Output: Data sent to the server

[0489] Step 5:

[0490] The server receives the submitted data and stores it in a database, which centralizes the user's entire data set.

[0491] Input: Data received from the terminal

[0492] Output: Consolidated data stored in a database

[0493] Step 6:

[0494] Machine learning algorithms on the server use information from the database to predict a user's future health status, for example assessing their risk of heart disease based on their lifestyle habits and emotional state.

[0495] Input: Integrated data stored in a database

[0496] Output: predicted health state

[0497] Step 7:

[0498] The emotion engine analyzes collected facial expression and tone of voice data to understand the user's current emotional state.

[0499] Input: Facial expression, tone of voice data

[0500] Output: Current emotional state

[0501] Step 8:

[0502] The server then recommends personalized products to the user based on their predicted health and emotional state, for example, recommending relaxation products if the user is feeling stressed.

[0503] Input: predicted health status, current emotional state

[0504] Output: A list of recommended products

[0505] Step 9:

[0506] The server sends the recommended product list to the smart glasses.

[0507] Input: Recommended product list

[0508] Output: Product information sent to smart glasses

[0509] Step 10:

[0510] The smart glasses will display the recommended products in the user's field of view, allowing the user to visually confirm and select the products as needed.

[0511] Input: Product information sent from the server

[0512] Output: Product information displayed on smart glasses

[0513] This allows users to receive personalized product recommendations based on their health and emotional state, making it easier to find more suitable products.

[0514] 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.

[0515] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0516] 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.

[0517] [Second embodiment]

[0518] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0519] 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.

[0520] 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).

[0521] 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.

[0522] 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.

[0523] 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).

[0524] 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.

[0525] 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.

[0526] 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.

[0527] 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.

[0528] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0529] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0530] The present invention is a system that collects basic information and activity data of a user, analyzes the data on a server, predicts future conditions, and makes specific suggestions for actions to the user.

[0531] Basic system configuration

[0532] 1. Terminal

[0533] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[0534] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[0535] The collected data is periodically sent to a server.

[0536] 2. Server

[0537] The server receives the data sent from the terminal and stores it in a database.

[0538] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits.

[0539] The prediction results are visualized and presented to the user in an easy-to-understand format.

[0540] 3. Users

[0541] Users can check the forecast results through the device's dashboard, which are displayed in the form of graphs and statistical data.

[0542] Based on the prediction results, users will receive specific action suggestions. For example, if there is an increased risk of health problems, the system will suggest changing exercise habits or improving diet.

[0543] Program processing

[0544] Data Collection Phase

[0545] Terminal

[0546] The user enters basic information as the initial setting, including height, weight, educational background, smoking habits, and exercise habits.

[0547] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[0548] Data transmission phase

[0549] Terminal

[0550] The collected basic information and activity data is periodically sent to a server, usually in a format such as JSON.

[0551] Data Management Phase

[0552] server

[0553] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[0554] Maintain data consistency by integrating with past data.

[0555] Prediction Phase

[0556] server

[0557] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, assessing their health risk if they continue their current lifestyle.

[0558] The prediction results are analyzed and actions are suggested to the user as necessary.

[0559] Visualization phase

[0560] server

[0561] Based on the predictions, graphs and statistics are generated, including predictions of heart disease risk and weight change.

[0562] Terminal

[0563] Predictions are displayed on a dashboard, allowing users to visually review them and adjust their actions as needed.

[0564] Specific examples

[0565] Example 1: Predicting health risks

[0566] Terminal

[0567] Users enter the results of their past health checkups into the app, such as data on blood pressure and cholesterol levels.

[0568] server

[0569] The server stores this information in a database and integrates it with existing lifestyle data.

[0570] Use machine learning algorithms to predict future heart disease risk.

[0571] Terminal

[0572] The predicted risk of heart disease is displayed as a graph on the dashboard. For example, it may say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years."

[0573] Based on this, users receive suggestions for actions to improve their exercise habits and diet, and review their lifestyle.

[0574] Example 2: Predicting weight change

[0575] Terminal

[0576] The user inputs the details of their daily diet and the amount of exercise they do.

[0577] server

[0578] The server analyzes the input data and predicts future weight changes.

[0579] Terminal

[0580] The predicted results are displayed on the dashboard in the form of, for example, "If you continue your current lifestyle, your weight will increase by 5 kg in three months."

[0581] Users can use this information to create dietary and exercise plans.

[0582] Such a system allows users to understand in real time how their lifestyle habits will affect their future and guide them towards healthier lifestyles.

[0583] The processing flow will be explained below.

[0584] Step 1:

[0585] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[0586] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[0587] Step 2:

[0588] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[0589] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[0590] Step 3:

[0591] The device sends the collected basic information and activity data to the server.

[0592] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[0593] Step 4:

[0594] The server receives the transmitted data and stores it in a database.

[0595] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL) in the appropriate format.

[0596] Step 5:

[0597] The server applies machine learning algorithms to analyze the accumulated data.

[0598] Specifically, it combines past and present data and runs machine learning models such as regression analysis and clustering using, for example, Scikit-learn or TensorFlow.

[0599] Step 6:

[0600] The server predicts the user's future state based on the analysis results.

[0601] Specifically, future health risks and weight changes are calculated based on the output of the machine learning model.

[0602] Step 7:

[0603] The server generates data for visualizing the prediction results.

[0604] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[0605] Step 8:

[0606] The graphs and statistical data generated by the server are sent to the terminal.

[0607] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[0608] Step 9:

[0609] The device displays the prediction results on a dashboard.

[0610] Specifically, the received data is displayed as graphs and statistical data on the user interface using HTML and JavaScript.

[0611] Step 10:

[0612] The user sees the forecast results on the dashboard.

[0613] Specifically, the system looks at graphs of predicted health risks and weight changes to determine the necessary improvement actions.

[0614] Step 11:

[0615] The terminal notifies the user of specific suggested actions.

[0616] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" via push notifications and in-app messages.

[0617] This detailed processing step allows the system to predict the user's future health status and provide information for taking specific actions.

[0618] Example 1

[0619] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0620] In modern society, personal health management and lifestyle improvement are extremely important issues. However, many currently available health management systems lack the ability to effectively collect and analyze user data and predict future risks. Furthermore, the feedback users receive is limited to general information and does not translate into specific recommendations for action. This makes self-management a time-consuming process for users, and makes it difficult for them to find appropriate improvement measures.

[0621] 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.

[0622] In this invention, the server includes means for accumulating the transmitted data and storing it in a database while maintaining consistency, means for analyzing the accumulated data and predicting the user's future state using a machine learning algorithm, and means for visualizing the prediction results as graphs or statistical data and presenting them to the user, thereby enabling the user to receive specific behavioral suggestions based on their own lifestyle habits.

[0623] "Basic user information" refers to basic data about an individual, such as height, weight, educational background, smoking habits, and exercise habits.

[0624] "Activity data" is data that records specific actions taken in the user's daily life, including the number of steps taken, heart rate, and sleep time.

[0625] The term "means" refers to a function or module for executing each of the processing steps described above.

[0626] A "server" is a computer system that receives, stores, analyzes, predicts, and presents results of data.

[0627] A "database" is a system for centrally managing user data accumulated by a server.

[0628] A "machine learning algorithm" is a computational method for learning patterns and trends from data and predicting future states.

[0629] "Prediction results" are information about future states derived from the user's current and past data.

[0630] "Visualization" is a method of displaying prediction results in a way that is easy for users to understand, such as in the form of graphs or statistical data.

[0631] "Action suggestions" are specific actions or improvements recommended to users based on the prediction results.

[0632] A "dashboard" is an interface displayed on a user's device that visually presents collected data and prediction results.

[0633] "Notification" is a function that allows the server to notify the user's device of suggested actions and prediction results.

[0634] The present invention is a system that collects basic information and activity data of a user, analyzes it on a server, predicts future conditions, and suggests specific actions to the user. This system uses the following hardware and software.

[0635] 1. Terminal

[0636] The device provides a user interface for the user to enter basic information. For example, information such as height, weight, educational background, smoking habits, and exercise habits can be entered using forms and check boxes. Furthermore, the device connects to an activity tracker or smartwatch to automatically collect the user's daily activity data. The collected basic information and activity data are periodically sent to a server. This transmission is usually done in a format such as JSON.

[0637] Specific examples

[0638] Users enter information such as their height (170cm), weight (70kg), and non-smoking status into a form on the device. The device also receives data from a smartwatch and collects activity data such as the number of steps taken each day and heart rate. The collected data is sent to a server every night.

[0639] 2. Server

[0640] The server receives basic information and activity data sent from the device and stores it in a database. Data integrity is maintained by integrating existing data and updating it with new data. The server analyzes the accumulated data using machine learning algorithms to predict the user's future state. To do this, it utilizes Python libraries such as "pandas," "scikit-learn," and "Matplotlib."

[0641] Specific examples

[0642] The server uses Python's "pandas" to store the received data in a data frame, and then uses "scikit-learn"'s random forest model to predict future heart disease risk. The predicted results are visualized as a graph using "Matplotlib."

[0643] 3. Users

[0644] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data, allowing users to understand the results visually. Users can also receive specific action suggestions based on the prediction results. For example, if health risks increase, the system will suggest actions such as reviewing exercise habits or improving diet.

[0645] Specific examples

[0646] The dashboard displays a graph of predicted results, such as, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years." Based on these results, users receive suggestions to improve their exercise habits and eat healthier meals.

[0647] In this way, this system collects basic information and activity data from users, analyzes this data on the server, and predicts future conditions, allowing the system to suggest specific actions to users. This allows users to understand in real time how their lifestyle habits will affect the future, and to take specific actions to maintain a healthy lifestyle.

[0648] Example prompt sentence:

[0649] "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years. We suggest that you review your exercise habits and improve your diet."

[0650] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0651] Step 1: Data Entry Phase

[0652] Terminal

[0653] Specific operation: The user uses the device's user interface to enter basic information, such as height, weight, educational background, smoking habits, and exercise habits, using the device's forms and check boxes.

[0654] Input and Output: As input, basic information of the user (e.g., height 170 cm, weight 70 kg, non-smoker, exercise 3 times a week) is received. As output, this data is stored on the device.

[0655] Step 2: Data collection phase

[0656] Terminal

[0657] Specific operation: The device works in conjunction with an activity tracker or smartwatch to automatically collect the user's daily activity data (number of steps, heart rate, sleep time, etc.).

[0658] Input and Output: As input, it receives real-time data from an activity tracker or smartwatch (e.g., 10,000 steps per day, heart rate 75 bpm, 7 hours of sleep). As output, it stores the collected activity data on the device.

[0659] Step 3: Data transmission phase

[0660] Terminal

[0661] How it works: The device periodically sends the collected basic information and activity data to the server. The data is usually sent in a format such as JSON.

[0662] Input and Output: As input, we use the saved basic information and activity data (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, these data are sent to the server.

[0663] Step 4: Data management phase

[0664] server

[0665] Specific operation: The server receives the data sent from the device and stores it in a database. It maintains data integrity by integrating it with existing data and updating it with new data.

[0666] Input and output: As input, it receives data sent from the device (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, it stores these data in a database.

[0667] Step 5: Data analysis and prediction phase

[0668] server

[0669] How it works: The server analyzes the accumulated data and uses machine learning algorithms to predict the user's future state. It stores the data in a data frame using Python's "pandas," preprocesses the data using "scikit-learn," and makes predictions using algorithms such as the random forest model.

[0670] Input and Output: The input is data stored in a database (e.g., health data from the past few months). The output is a prediction result (e.g., "20% increase in risk of heart disease within five years").

[0671] Step 6: Visualization phase

[0672] server

[0673] How it works: The server generates graphs and statistical data based on the prediction results, using libraries such as "Matplotlib" and "Seaborn."

[0674] Input and Output: As input, a prediction result (e.g., "20% increase in risk of heart disease within 5 years") is used. As output, a graph or statistical data (e.g., line graph, bar graph) is generated.

[0675] Terminal

[0676] Specific operation: The device displays the generated graphs and statistical data on the dashboard.

[0677] Input and Output: As input, it receives graphs and statistical data sent from the server. As output, it displays these data on the dashboard.

[0678] Step 7: Action proposal phase

[0679] server

[0680] Specific actions: Based on the prediction results, the server generates specific action suggestions for the user, such as suggestions for improving exercise habits or diet.

[0681] Input and Output: The input is a prediction result (e.g., "High risk of heart disease"). The output is an action suggestion (e.g., "Add 30 minutes of walking each day").

[0682] Terminal

[0683] Specific operation: The device notifies and displays the suggested actions to the user.

[0684] Input and Output: As input, it receives action suggestions sent from the server. As output, it displays the action suggestions to the user in push notifications and on the dashboard.

[0685] (Application example 1)

[0686] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0687] With increasing health awareness, many people are trying to manage and improve their lifestyles and health status. However, choosing healthy meals in daily life is not easy. In particular, when using food delivery services, there is a lack of specific guidance on reducing health risks and selecting appropriate meal plans. Therefore, there is a need for a system that can suggest optimal meal plans based on the user's basic information and activity data.

[0688] 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.

[0689] In this invention, the server includes means for inputting basic information and activity data of a user, means for transmitting the basic information and activity data to the server, means for storing and analyzing the transmitted data, means for predicting the user's future state from the analysis results, means for presenting the prediction results to the user and suggesting actions, and means for proposing an optimal meal plan to the user based on the basic information and activity data, thereby enabling the user to select an appropriate meal plan taking into account their health condition and lifestyle habits.

[0690] "Basic information" refers to personal data such as the user's health condition, educational background, and lifestyle habits.

[0691] "Activity data" refers to data related to the user's physical activity, such as the number of steps taken, heart rate, and sleep time.

[0692] A "server" is a system for receiving, storing, and analyzing data sent by users.

[0693] "Future state" is the future state of a user's health and lifestyle, predicted using machine learning algorithms based on current data.

[0694] The means for suggesting "actions" is a function that presents the user with a specific action plan based on the prediction results.

[0695] The "means for suggesting meal plans" is a function that provides optimal meal options based on the user's basic information and activity data.

[0696] A "dashboard" is an interface that visually displays prediction results and statistical data to users.

[0697] "Graphs and statistical data" refers to information that visually represents the predicted results of the user's health risks and future conditions.

[0698] The present invention is a system that collects and analyzes basic information and activity data of a user to predict future conditions and propose an optimal meal plan to the user. The system includes the following components:

[0699] Basic system configuration

[0700] 1. Terminal

[0701] The device provides a user interface for users to enter basic information (health status, educational background, lifestyle habits, etc.). This includes forms and check boxes. The device connects to devices such as activity trackers and smartwatches to automatically collect daily activity data (number of steps, heart rate, sleep time, etc.). The collected data is periodically sent to a server.

[0702] 2. Server

[0703] The server receives the data sent from the device and stores it in a database. It uses machine learning algorithms to analyze the accumulated data and predict the user's future condition. For example, it can assess future health risks based on current lifestyle habits. The prediction results are visualized and presented to the user in an easy-to-understand format.

[0704] 3. Users

[0705] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data. Based on the prediction results, users are given an optimal meal plan. For example, if there is an increased risk of health problems, the system will suggest calorie restriction or other dietary improvements.

[0706] Program processing

[0707] Data Collection Phase

[0708] The device provides an interface for users to input basic information as an initial setting, including height, weight, educational background, smoking habits, exercise habits, etc. The device also connects to an activity tracker or smartwatch to collect activity data such as steps taken, heart rate, and sleep time in real time.

[0709] Data transmission phase

[0710] The device periodically sends the collected basic information and activity data to a server, usually in a format such as JSON.

[0711] Data Management Phase

[0712] The server receives the data and stores it in a database. It integrates it with existing data and updates it with new data. To maintain data consistency, it is managed together with past data.

[0713] Prediction Phase

[0714] The server uses machine learning algorithms (such as Sci-kit Learn's Linear Regression) to analyze the user's current and past data and predict their future condition. For example, it assesses the health risks if the user continues their current lifestyle. Based on this prediction, it proposes an optimal diet plan for the user.

[0715] Visualization phase

[0716] The server generates graphs and statistical data based on the predictions, including predictions of heart disease risk and weight change. The device displays the predictions on a dashboard, allowing users to visually check the results and adjust their behavior as needed.

[0717] Specific examples

[0718] Example 1: Predicting health risks

[0719] The device provides an interface for users to input past health checkup results into the app, including data such as blood pressure and cholesterol levels. The server stores this information in a database and integrates it with existing lifestyle data. Machine learning algorithms are used to predict future heart disease risk. The device displays the predicted heart disease risk as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within three years."

[0720] Example 2: Meal plan suggestions

[0721] The device provides an interface for users to input their daily dietary information. The server analyzes the input data and predicts future health risks. Based on the results, the server provides the user with an optimal meal plan. For example, the server may suggest, "We will provide you with a meal plan that takes into account calorie restriction and appropriate nutritional balance."

[0722] Example prompts to input to the generative AI model

[0723] "If you continue your current lifestyle habits, your health risks will increase by 15% after three months. To improve this, we recommend the following diet plan."

[0724] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0725] Step 1:

[0726] The device provides an interface where the user can input basic information (health status, educational background, lifestyle habits, etc.). The input data includes height, weight, smoking habits, exercise habits, etc. This allows the user's basic information to be collected. The input data is formatted for storage in a database using a format such as JSON.

[0727] Step 2:

[0728] The terminal connects to devices such as activity monitors and smartwatches to collect daily activity data (number of steps, heart rate, sleep time, etc.) in real time. This data is collected, formatted in JSON format or other formats, and prepared for transmission to the next processing step, either in batch processing or at specified intervals.

[0729] Step 3:

[0730] The device periodically sends the collected basic information and activity data to the server using HTTP or HTTPS, with the Content-Type header set to application / json. The device then verifies that the data reaches the server without any errors.

[0731] Step 4:

[0732] The server receives data sent from the device and stores it in a database. Using a database such as SQLite or MySQL, the received data is integrated with the existing database. A timestamp is added to the new data and it is managed together with past data.

[0733] Step 5:

[0734] The server applies machine learning algorithms to the basic information and activity data stored in the database. Using Scikit-Learn's Linear Regression model, it matches the input data with the training data to generate a predictive model. This model is then used to predict the user's future health status and activity patterns.

[0735] Step 6:

[0736] The server generates an optimal meal plan based on the prediction results. The generated meal plan is optimized taking into account the user's calorie intake, nutritional balance, and past dietary information. The predictions and suggestions are integrated and generated as JSON format data to be provided to the user.

[0737] Step 7:

[0738] The device displays the prediction results and meal plans obtained from the server on a dashboard. Libraries such as Matplotlib and Chart.js are used to visualize the results as graphs and statistical data, allowing users to intuitively understand the predicted health risks and recommended meal plans.

[0739] Step 8:

[0740] Users can check the prediction results and suggestions displayed on the dashboard and adjust their diet and lifestyle accordingly. For example, they may see a prompt such as, "If you continue your current lifestyle, your health risk will increase by 15% in three months. To improve this, we recommend the following meal plan."

[0741] 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.

[0742] This system collects basic information, activity data, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[0743] Basic system configuration

[0744] 1. Terminal

[0745] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[0746] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[0747] The device uses a camera, microphone, and text input to collect the user's emotional data (facial expressions, tone of voice, and text input).

[0748] The collected data is periodically sent to a server.

[0749] 2. Server

[0750] The server receives the basic information, activity data, and emotion data sent from the terminal and stores them in a database.

[0751] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits and emotional state.

[0752] The prediction results are visualized and presented to the user in an easy-to-understand format.

[0753] 3. Emotion Engine

[0754] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state.

[0755] The emotion engine's analysis results are used to personalize suggested actions for the user, for example, relaxation suggestions when the user is feeling stressed.

[0756] 4. Users

[0757] Users can view the prediction results and their emotional state through a dashboard on their device, which is displayed in the form of graphs and statistical data.

[0758] Based on the prediction results and emotional state, users receive specific action suggestions to improve their lifestyle habits.

[0759] Program processing

[0760] Data Collection Phase

[0761] Terminal

[0762] The user enters basic information as the initial setting, including height, weight, education, smoking habits, and exercise frequency.

[0763] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[0764] It uses the camera, microphone, and text input to collect user emotional data.

[0765] Data transmission phase

[0766] Terminal

[0767] The collected basic information, activity data, and emotion data are periodically sent to a server, usually in a format such as JSON.

[0768] Data Management Phase

[0769] server

[0770] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[0771] Maintain data consistency by integrating with past data.

[0772] Prediction Phase

[0773] server

[0774] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, by considering their lifestyle habits and emotional state together to assess future health risks.

[0775] The prediction results are analyzed and actions are suggested to the user as necessary.

[0776] Sentiment Analysis Phase

[0777] Emotion Engine

[0778] Recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and text input, for example, using image processing and natural language processing techniques.

[0779] Visualization phase

[0780] server

[0781] Based on the predictions and your emotional state, graphs and statistics are generated, including predictions of heart disease risk, weight change, and stress levels.

[0782] Terminal

[0783] The predictions and sentiment analysis results are displayed on a dashboard, allowing users to visually check them and adjust their actions as needed.

[0784] Specific examples

[0785] Example 1: Predicting health risks

[0786] Terminal

[0787] Users input their past health check results and daily emotional state (e.g., daily stress level and mood) into the app.

[0788] server

[0789] The server stores this information in a database and integrates it with existing lifestyle data.

[0790] It uses machine learning algorithms to predict future heart disease risk, and an emotion engine to analyze a user's stress state.

[0791] Terminal

[0792] The predicted heart disease risk and emotional state are displayed as a graph on the dashboard, for example, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years."

[0793] Based on this, users receive action suggestions to improve their exercise habits, diet, and stress management methods, and review their lives.

[0794] Example 2: Predicting weight change

[0795] Terminal

[0796] The user inputs their daily diet and exercise, as well as their emotional state for that day (e.g., happy, sad, angry).

[0797] server

[0798] The server analyzes the input data and predicts future weight changes and psychological states. It also uses an emotion engine to analyze the user's emotional state regarding food and exercise.

[0799] Terminal

[0800] The prediction results are displayed on a dashboard in the form of, for example, "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect your diet and exercise.

[0801] Users can use this information to plan their diet and exercise, and manage their emotions, thereby improving their lives more effectively.

[0802] Such a system allows users to understand in real time how their lifestyle habits and emotions affect their future, and to take concrete actions to build healthy lifestyles.

[0803] The processing flow will be explained below.

[0804] Step 1:

[0805] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[0806] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[0807] Step 2:

[0808] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[0809] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[0810] Step 3:

[0811] The device collects user emotional data using the camera, microphone, and text input.

[0812] Specifically, it uses facial recognition technology to analyze facial expressions, voice recognition technology to analyze tone of voice, and natural language processing to analyze emotions from text input.

[0813] Step 4:

[0814] The device transmits the collected basic information, activity data, and emotion data to the server.

[0815] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[0816] Step 5:

[0817] The server receives the transmitted data and stores it in a database.

[0818] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL) in the appropriate format.

[0819] Step 6:

[0820] The server applies machine learning algorithms to analyze the accumulated data.

[0821] Specifically, it combines past and present data and runs machine learning models such as regression analysis and clustering using, for example, Scikit-learn or TensorFlow.

[0822] Step 7:

[0823] The server applies an emotion engine to analyze the user's emotion data.

[0824] Specifically, the emotion engine analyzes the user's facial expressions, tone of voice, and text input and stores them in a database.

[0825] Step 8:

[0826] The server predicts the user's future state based on the results of machine learning and the emotion engine.

[0827] Specifically, the results of both analyses will be integrated to generate future health risks and action recommendations.

[0828] Step 9:

[0829] The server generates data for visualizing the prediction results.

[0830] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[0831] Step 10:

[0832] The graphs and statistical data generated by the server are sent to the terminal.

[0833] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[0834] Step 11:

[0835] The device displays prediction results and sentiment analysis results on a dashboard.

[0836] Specifically, the received data is displayed as graphs and statistical data on the user interface using HTML and JavaScript.

[0837] Step 12:

[0838] The user sees the forecast results on the dashboard.

[0839] Specifically, the system looks at graphs of predicted health risks, weight changes, and emotional states to determine the necessary improvement actions.

[0840] Step 13:

[0841] The terminal notifies the user of specific suggested actions.

[0842] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" and "incorporate relaxation techniques to relieve stress" via push notifications and in-app messages.

[0843] Through this detailed processing step, the system allows users to understand their own health and emotional state in real time, predict future risks, and receive specific action suggestions.

[0844] Example 2

[0845] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0846] While conventional systems were capable of analyzing a user's basic information and activity information, they had the problem of not being able to make personalized suggestions that took into account the user's emotional state. This led to problems such as users overlooking health risks due to stress or emotional changes, or not being able to take effective actions. In addition, because the analysis results and suggested actions were displayed individually, it was difficult for users to grasp their overall health status.

[0847] 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.

[0848] In this invention, the server includes a means for inputting the user's basic information and activity information, a means for inputting the user's emotional state, and a means for accumulating and analyzing the transmitted data. This enables the user's basic information, activity information, and emotional state data to be analyzed in an integrated manner, enabling personalized behavioral suggestions. Furthermore, by displaying the analysis results and emotional state as graphs and statistical data on the display device of the user's terminal, the user can easily visually grasp changes in their own health condition and emotions. As a result, the user can more effectively manage health risks and work to improve their lifestyle habits.

[0849] "Basic user information" refers to personal information such as height, weight, educational background, smoking habits, and exercise frequency entered by the user.

[0850] "Activity information" refers to data on daily activities such as steps taken, heart rate, and sleep time collected from activity monitors and smartwatches.

[0851] "Emotional state" is data about emotions collected from a user's facial expressions, tone of voice, and text input.

[0852] "Input means" refers to the interface through which a user inputs data, such as a form, checkboxes, camera, or microphone.

[0853] "Means for transmitting" refers to the communication protocol or communication module used to transmit collected data to the server.

[0854] "Means of storage and analysis" refers to the server's function of storing received data in a database and analyzing the data using machine learning algorithms and data analysis tools.

[0855] "Means for predicting a user's future health risks and lifestyle changes" refers to the process of using a machine learning model to predict a user's future health risks and lifestyle changes based on the user's past and current data.

[0856] "Means for suggesting actions" refers to functions, such as notifications and alerts, that suggest specific actions to the user based on the prediction results.

[0857] "Display device" refers to a screen or display that allows a user to visually confirm analysis results and suggestions.

[0858] This system collects basic information, activity information, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[0859] Basic system configuration

[0860] 1. Terminal

[0861] The device provides a user interface for users to input basic information, including forms and checkboxes. It also connects with devices such as activity trackers and smartwatches to collect activity information in real time. It also uses a camera, microphone, and text input to collect the user's emotional state. The collected data is periodically sent to a server.

[0862] 2. Server

[0863] The server receives basic information, activity information, and emotion data sent from the device and stores them in a database. It also uses machine learning algorithms to analyze the accumulated data and predict the user's future state. The prediction results are visualized and provided to the user in an easy-to-understand format.

[0864] 3. Emotion Engine

[0865] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state, using image processing and natural language processing techniques, and the results of the analysis are used to personalize suggested actions for the user.

[0866] 4. Users

[0867] Users can check their prediction results and emotional state through the device's dashboard. The prediction results are displayed in the form of graphs and statistical data. Based on the prediction results and emotional state, users can receive specific action suggestions to improve their lifestyle habits.

[0868] Specific actions

[0869] Example 1: Predicting health risks

[0870] Users enter their past health checkup results and daily emotional state into the app. The server stores this information in a database and integrates it with existing lifestyle data. A machine learning algorithm is used to predict future heart disease risk. An emotion engine is also used to analyze the user's stress level. The device displays the predicted heart disease risk and emotional state as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years." Based on this, users receive action suggestions for improving their exercise habits, diet, and stress management methods.

[0871] Example 2: Predicting weight change

[0872] The user inputs their daily diet and exercise routine, as well as their emotional state for that day. The server analyzes the input data and predicts future weight changes and their psychological state. It also uses an emotion engine to analyze the user's emotional state regarding diet and exercise. The device displays the predicted results on a dashboard, such as "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect diet and exercise. Users can use this information to create dietary restrictions and exercise plans, and manage their emotions.

[0873] Example prompt

[0874] "Use the user's lifestyle data to predict future health risks and suggest specific actions to improve them."

[0875] "Analyze user sentiment data and provide personalized health recommendations based on it."

[0876] The system allows users to understand in real time how their lifestyle habits and emotions affect their future, and take concrete actions to build healthy lifestyle habits.

[0877] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0878] Step 1:

[0879] Enter basic information

[0880] The device provides a screen where the user can enter basic information (height, weight, educational background, smoking habits, exercise frequency, etc.). The user enters this information into a form. The input data is temporarily stored in local storage or device memory. This allows the basic information to be collected.

[0881] Input: User's height, weight, education, smoking habits, and exercise frequency

[0882] Output: Basic information data stored in the device

[0883] Step 2:

[0884] Collection of activity information

[0885] The device collects real-time activity information (number of steps, heart rate, sleep time, etc.) from activity monitors and smartwatches via Bluetooth or Wi-Fi. This data is updated at regular intervals and stored internally on the device.

[0886] Input: Activity information obtained from activity trackers and smartwatches

[0887] Output: Activity information data stored in the device

[0888] Step 3:

[0889] Collecting emotional states

[0890] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and collects this as emotional data. In addition, text data entered by the user is also collected as emotional data.

[0891] Input: facial expression data obtained from a camera or microphone, voice data, and text data entered by the user

[0892] Output: Emotion data stored in the device

[0893] Step 4:

[0894] Data transmission

[0895] The device periodically transmits the collected basic information, activity information, and emotion data to a server, structured in a standard format such as JSON, using a secure communication protocol.

[0896] Input: Basic information, activity information, and emotional data stored on the device

[0897] Output: Various data sent to the server

[0898] Step 5:

[0899] Receiving and storing data

[0900] The server receives the data sent from the device. The received data is stored in a dedicated database (e.g., MySQL, MongoDB), and is updated by integrating it with past data.

[0901] Input: Basic information, activity information, and emotional data sent from the device

[0902] Output: Various data stored in the server database

[0903] Step 6:

[0904] Running the prediction algorithm

[0905] The server analyzes the received data using machine learning models (e.g., TensorFlow, PyTorch), and predicts future health risks and weight changes based on the user's lifestyle and emotional state.

[0906] Input: Basic information, activity information, and emotion data stored in the database

[0907] Output: Predicted health risks and weight change data

[0908] Step 7:

[0909] Performing sentiment analysis

[0910] The emotion engine analyzes facial expressions, voice, and text data sent from the device, and uses image processing technology (e.g., OpenCV) and natural language processing technology (e.g., NLTK, spaCy) to identify the device's emotional state.

[0911] Input: facial expression data, voice data, text data

[0912] Output: Recognized emotional state data

[0913] Step 8:

[0914] Visualizing the results

[0915] The server generates graphs and statistical data based on the prediction results and emotional states (e.g., Matplotlib, D3.js), which makes it easier for users to understand visually.

[0916] Input: predicted health risk, weight change data, emotional state data

[0917] Output: Visualized graphs and statistical data

[0918] Step 9:

[0919] Viewing the Dashboard

[0920] The device displays the analysis results and prediction data sent from the server as a dashboard, allowing users to check their own predictions and sentiment analysis results.

[0921] Input: Analysis results and prediction data sent from the server

[0922] Output: Analysis results and forecast data displayed on a dashboard

[0923] Step 10:

[0924] action suggestion

[0925] The device will suggest specific actions based on the predictions and your emotional state, such as "take 10 minutes of deep breathing exercises to relax."

[0926] Input: Prediction result, emotional state

[0927] Output: Specific action suggestions provided to the user

[0928] Through each of the above steps, users can understand in real time how their lifestyle habits and emotions affect their future and take concrete action.

[0929] (Application example 2)

[0930] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0931] Conventional online shopping sites lack personalized product recommendations that take into account the user's health and emotional state. In particular, they are unable to provide appropriate product suggestions to reduce stress and health risks, making it difficult for users to find the products they truly need. In addition, understanding a user's emotional state in real time and recommending products accordingly is a challenge.

[0932] 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.

[0933] In this invention, the server includes a means for inputting basic information and activity data of a user, a means for analyzing the emotional state of the user using an emotion engine, a means for recommending personalized products to the user based on the basic information, activity data, and emotional state, and a means for displaying the recommendation results on the smart glasses, thereby enabling reliable product recommendations based on the user's health condition and emotional state.

[0934] (Word definition)

[0935] "Basic information of a user" refers to basic information related to an individual, such as the user's height, weight, age, lifestyle, and health condition.

[0936] "Activity data" is data related to the user's daily activities, and includes, for example, the number of steps taken, the amount of exercise, the heart rate, and the amount of sleep.

[0937] "Server" means a computer system on a network that stores and analyzes collected data.

[0938] An "emotion engine" is an algorithm or software that recognizes a user's emotional state by analyzing data such as facial expressions, tone of voice, and text input collected from sensors such as cameras and microphones.

[0939] The "prediction means" is a means for predicting the user's future state using a machine learning algorithm based on the collected basic information, activity data, and emotion data.

[0940] A "means for recommending personalized products" is a means for selecting and recommending products suitable for individual users by taking into consideration the user's basic information, activity data, and emotional state.

[0941] "Smart glasses" are eyeglass-type wearable devices with a built-in display device that can display information directly in the user's field of vision.

[0942] The "result display means" is a means for visually displaying prediction results and product recommendation results on the user's device.

[0943] The system for realizing this application example is configured as follows.

[0944] First, the core hardware of the system consists of a server, smart glasses, an activity tracker, a smartwatch, a camera, and a microphone. The server is responsible for storing data, analyzing it, and sending the results, while the smart glasses are responsible for displaying the data. The activity tracker and smartwatch collect the user's activity data, and the camera and microphone collect emotion data.

[0945] The system includes the following main software components:

[0946] 1. Data collection software: Collects basic user information, activity data, and emotional data using a camera and microphone.

[0947] 2. Data transmission software: periodically transmits collected data to the server.

[0948] 3. Database software: stores and manages the transmitted data.

[0949] 4. Machine learning algorithms: These run on the server and analyze the collected data to predict the user's future state.

[0950] 5. Sentiment Engine: A software component for performing sentiment analysis.

[0951] 6. Product recommendation software: Selects and recommends the most suitable products based on the user's health and emotional state.

[0952] 7. Display software: Visually display the product recommendation results on the smart glasses.

[0953] Data collection

[0954] The user wears the smart glasses and inputs basic information and activity data. The activity tracker or smartwatch automatically collects the user's daily activity data (e.g., number of steps, heart rate, and sleep time). The camera and microphone also analyze the user's facial expressions and tone of voice to collect their emotional state. The collected data is periodically sent to a server and stored in a database.

[0955] Data analysis

[0956] The server uses machine learning algorithms to analyze the accumulated basic information, activity data, and emotional data. The analysis results are used to predict the user's future health and emotional state. Furthermore, an emotion engine analyzes the user's real-time emotional state and makes product recommendations based on this.

[0957] Product recommendation

[0958] The server selects personalized products for the user based on the prediction results and the emotional state, and sends the recommendation results to the smart glasses via the product recommendation software.

[0959] display

[0960] The smart glasses visually display recommended products, allowing users to easily obtain product information based on their health and emotional state.

[0961] For example, when a user is feeling stressed, the emotion engine analyzes the user's stress level and recommends relaxation products and calming clothing. The results are displayed on the smart glasses, allowing the user to check in real time which products are suitable for their emotional state.

[0962] (Example of a prompt)

[0963] When the user feels stressed, a prompt is displayed that takes into account health risks: "Recommend relaxation products based on my health condition and emotions."

[0964] This enables personalized product recommendations based on the user's health and emotional state, contributing to improving the user's lifestyle habits.

[0965] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0966] Step 1:

[0967] The user puts on the smart glasses and inputs basic information, such as height, weight, age, lifestyle habits, and health status, into the application form. This information is then stored on the device.

[0968] Input: Basic information such as height, weight, age, lifestyle habits, and health condition

[0969] Output: Saved basic information data

[0970] Step 2:

[0971] Activity trackers and smartwatches collect users' activity data in real time, including the number of steps taken, heart rate, and sleep time. This data is also sent to the device and stored.

[0972] Input: User's daily activity data (number of steps, heart rate, sleep time, etc.)

[0973] Output: Saved activity data

[0974] Step 3:

[0975] The smart glasses' cameras and microphones capture the user's facial expressions and tone of voice to collect emotional data, which is then analyzed in real time by an emotion engine.

[0976] Input: Facial expression, tone of voice data

[0977] Output: Parsed emotion data

[0978] Step 4:

[0979] The device periodically sends the collected basic information, activity data, and emotion data to the server in JSON format.

[0980] Input: Basic information, activity data, emotion data

[0981] Output: Data sent to the server

[0982] Step 5:

[0983] The server receives the submitted data and stores it in a database, which centralizes the user's entire data set.

[0984] Input: Data received from the terminal

[0985] Output: Consolidated data stored in a database

[0986] Step 6:

[0987] Machine learning algorithms on the server use information from the database to predict a user's future health status, for example assessing their risk of heart disease based on their lifestyle habits and emotional state.

[0988] Input: Integrated data stored in a database

[0989] Output: predicted health state

[0990] Step 7:

[0991] The emotion engine analyzes collected facial expression and tone of voice data to understand the user's current emotional state.

[0992] Input: Facial expression, tone of voice data

[0993] Output: Current emotional state

[0994] Step 8:

[0995] The server then recommends personalized products to the user based on their predicted health and emotional state, for example, recommending relaxation products if the user is feeling stressed.

[0996] Input: predicted health status, current emotional state

[0997] Output: A list of recommended products

[0998] Step 9:

[0999] The server sends the recommended product list to the smart glasses.

[1000] Input: Recommended product list

[1001] Output: Product information sent to smart glasses

[1002] Step 10:

[1003] The smart glasses will display the recommended products in the user's field of view, allowing the user to visually confirm and select the products as needed.

[1004] Input: Product information sent from the server

[1005] Output: Product information displayed on smart glasses

[1006] This allows users to receive personalized product recommendations based on their health and emotional state, making it easier to find more suitable products.

[1007] 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.

[1008] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1009] 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.

[1010] [Third embodiment]

[1011] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1012] 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.

[1013] 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).

[1014] 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.

[1015] 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.

[1016] 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).

[1017] 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.

[1018] 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.

[1019] 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.

[1020] 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.

[1021] 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.

[1022] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1023] The present invention is a system that collects basic information and activity data of a user, analyzes the data on a server, predicts future conditions, and makes specific suggestions for actions to the user.

[1024] Basic system configuration

[1025] 1. Terminal

[1026] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[1027] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[1028] The collected data is periodically sent to a server.

[1029] 2. Server

[1030] The server receives the data sent from the terminal and stores it in a database.

[1031] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits.

[1032] The prediction results are visualized and presented to the user in an easy-to-understand format.

[1033] 3. Users

[1034] Users can check the forecast results through the device's dashboard, which are displayed in the form of graphs and statistical data.

[1035] Based on the prediction results, users will receive specific action suggestions. For example, if there is an increased risk of health problems, the system will suggest changing exercise habits or improving diet.

[1036] Program processing

[1037] Data Collection Phase

[1038] Terminal

[1039] The user enters basic information as the initial setting, including height, weight, educational background, smoking habits, and exercise habits.

[1040] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[1041] Data transmission phase

[1042] Terminal

[1043] The collected basic information and activity data is periodically sent to a server, usually in a format such as JSON.

[1044] Data Management Phase

[1045] server

[1046] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[1047] Maintain data consistency by integrating with past data.

[1048] Prediction Phase

[1049] server

[1050] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, assessing their health risk if they continue their current lifestyle.

[1051] The prediction results are analyzed and actions are suggested to the user as necessary.

[1052] Visualization phase

[1053] server

[1054] Based on the predictions, graphs and statistics are generated, including predictions of heart disease risk and weight change.

[1055] Terminal

[1056] Predictions are displayed on a dashboard, allowing users to visually review them and adjust their actions as needed.

[1057] Specific examples

[1058] Example 1: Predicting health risks

[1059] Terminal

[1060] Users enter the results of their past health checkups into the app, such as data on blood pressure and cholesterol levels.

[1061] server

[1062] The server stores this information in a database and integrates it with existing lifestyle data.

[1063] Use machine learning algorithms to predict future heart disease risk.

[1064] Terminal

[1065] The predicted risk of heart disease is displayed as a graph on the dashboard. For example, it may say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years."

[1066] Based on this, users receive suggestions for actions to improve their exercise habits and diet, and review their lifestyle.

[1067] Example 2: Predicting weight change

[1068] Terminal

[1069] The user inputs the details of their daily diet and the amount of exercise they do.

[1070] server

[1071] The server analyzes the input data and predicts future weight changes.

[1072] Terminal

[1073] The predicted results are displayed on the dashboard in the form of, for example, "If you continue your current lifestyle, your weight will increase by 5 kg in three months."

[1074] Users can use this information to create dietary and exercise plans.

[1075] Such a system allows users to understand in real time how their lifestyle habits will affect their future and guide them towards healthier lifestyles.

[1076] The processing flow will be explained below.

[1077] Step 1:

[1078] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[1079] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[1080] Step 2:

[1081] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[1082] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[1083] Step 3:

[1084] The device sends the collected basic information and activity data to the server.

[1085] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[1086] Step 4:

[1087] The server receives the transmitted data and stores it in a database.

[1088] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL) in the appropriate format.

[1089] Step 5:

[1090] The server applies machine learning algorithms to analyze the accumulated data.

[1091] Specifically, it combines past and present data and runs machine learning models such as regression analysis and clustering using, for example, Scikit-learn or TensorFlow.

[1092] Step 6:

[1093] The server predicts the user's future state based on the analysis results.

[1094] Specifically, future health risks and weight changes are calculated based on the output of the machine learning model.

[1095] Step 7:

[1096] The server generates data for visualizing the prediction results.

[1097] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[1098] Step 8:

[1099] The graphs and statistical data generated by the server are sent to the terminal.

[1100] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[1101] Step 9:

[1102] The device displays the prediction results on a dashboard.

[1103] Specifically, the received data is displayed as graphs and statistical data on the user interface using HTML and JavaScript.

[1104] Step 10:

[1105] The user sees the forecast results on the dashboard.

[1106] Specifically, the system looks at graphs of predicted health risks and weight changes to determine the necessary improvement actions.

[1107] Step 11:

[1108] The terminal notifies the user of specific suggested actions.

[1109] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" via push notifications and in-app messages.

[1110] This detailed processing step allows the system to predict the user's future health status and provide information for taking specific actions.

[1111] Example 1

[1112] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1113] In modern society, personal health management and lifestyle improvement are extremely important issues. However, many currently available health management systems lack the ability to effectively collect and analyze user data and predict future risks. Furthermore, the feedback users receive is limited to general information and does not translate into specific recommendations for action. This makes self-management a time-consuming process for users, and makes it difficult for them to find appropriate improvement measures.

[1114] 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.

[1115] In this invention, the server includes means for accumulating the transmitted data and storing it in a database while maintaining consistency, means for analyzing the accumulated data and predicting the user's future state using a machine learning algorithm, and means for visualizing the prediction results as graphs or statistical data and presenting them to the user, thereby enabling the user to receive specific behavioral suggestions based on their own lifestyle habits.

[1116] "Basic user information" refers to basic data about an individual, such as height, weight, educational background, smoking habits, and exercise habits.

[1117] "Activity data" is data that records specific actions taken in the user's daily life, including the number of steps taken, heart rate, and sleep time.

[1118] The term "means" refers to a function or module for executing each of the processing steps described above.

[1119] A "server" is a computer system that receives, stores, analyzes, predicts, and presents results of data.

[1120] A "database" is a system for centrally managing user data accumulated by a server.

[1121] A "machine learning algorithm" is a computational method for learning patterns and trends from data and predicting future states.

[1122] "Prediction results" are information about future states derived from the user's current and past data.

[1123] "Visualization" is a method of displaying prediction results in a way that is easy for users to understand, such as in the form of graphs or statistical data.

[1124] "Action suggestions" are specific actions or improvements recommended to users based on the prediction results.

[1125] A "dashboard" is an interface displayed on a user's device that visually presents collected data and prediction results.

[1126] "Notification" is a function that allows the server to notify the user's device of suggested actions and prediction results.

[1127] The present invention is a system that collects basic information and activity data of a user, analyzes it on a server, predicts future conditions, and suggests specific actions to the user. This system uses the following hardware and software.

[1128] 1. Terminal

[1129] The device provides a user interface for the user to enter basic information. For example, information such as height, weight, educational background, smoking habits, and exercise habits can be entered using forms and check boxes. Furthermore, the device connects to an activity tracker or smartwatch to automatically collect the user's daily activity data. The collected basic information and activity data are periodically sent to a server. This transmission is usually done in a format such as JSON.

[1130] Specific examples

[1131] Users enter information such as their height (170cm), weight (70kg), and non-smoking status into a form on the device. The device also receives data from a smartwatch and collects activity data such as the number of steps taken each day and heart rate. The collected data is sent to a server every night.

[1132] 2. Server

[1133] The server receives basic information and activity data sent from the device and stores it in a database. Data integrity is maintained by integrating existing data and updating it with new data. The server analyzes the accumulated data using machine learning algorithms to predict the user's future state. To do this, it utilizes Python libraries such as "pandas," "scikit-learn," and "Matplotlib."

[1134] Specific examples

[1135] The server uses Python's "pandas" to store the received data in a data frame, and then uses "scikit-learn"'s random forest model to predict future heart disease risk. The predicted results are visualized as a graph using "Matplotlib."

[1136] 3. Users

[1137] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data, allowing users to understand the results visually. Users can also receive specific action suggestions based on the prediction results. For example, if health risks increase, the system will suggest actions such as reviewing exercise habits or improving diet.

[1138] Specific examples

[1139] The dashboard displays a graph of predicted results, such as, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years." Based on these results, users receive suggestions to improve their exercise habits and eat healthier meals.

[1140] In this way, this system collects basic information and activity data from users, analyzes this data on the server, and predicts future conditions, allowing the system to suggest specific actions to users. This allows users to understand in real time how their lifestyle habits will affect the future, and to take specific actions to maintain a healthy lifestyle.

[1141] Example prompt sentence:

[1142] "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years. We suggest that you review your exercise habits and improve your diet."

[1143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1144] Step 1: Data Entry Phase

[1145] Terminal

[1146] Specific operation: The user uses the device's user interface to enter basic information, such as height, weight, educational background, smoking habits, and exercise habits, using the device's forms and check boxes.

[1147] Input and Output: As input, basic information of the user (e.g., height 170 cm, weight 70 kg, non-smoker, exercise 3 times a week) is received. As output, this data is stored on the device.

[1148] Step 2: Data collection phase

[1149] Terminal

[1150] Specific operation: The device works in conjunction with an activity tracker or smartwatch to automatically collect the user's daily activity data (number of steps, heart rate, sleep time, etc.).

[1151] Input and Output: As input, it receives real-time data from an activity tracker or smartwatch (e.g., 10,000 steps per day, heart rate 75 bpm, 7 hours of sleep). As output, it stores the collected activity data on the device.

[1152] Step 3: Data transmission phase

[1153] Terminal

[1154] How it works: The device periodically sends the collected basic information and activity data to the server. The data is usually sent in a format such as JSON.

[1155] Input and Output: As input, we use the saved basic information and activity data (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, these data are sent to the server.

[1156] Step 4: Data management phase

[1157] server

[1158] Specific operation: The server receives the data sent from the device and stores it in a database. It maintains data integrity by integrating it with existing data and updating it with new data.

[1159] Input and output: As input, it receives data sent from the device (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, it stores these data in a database.

[1160] Step 5: Data analysis and prediction phase

[1161] server

[1162] How it works: The server analyzes the accumulated data and uses machine learning algorithms to predict the user's future state. It stores the data in a data frame using Python's "pandas," preprocesses the data using "scikit-learn," and makes predictions using algorithms such as the random forest model.

[1163] Input and Output: The input is data stored in a database (e.g., health data from the past few months). The output is a prediction result (e.g., "20% increase in risk of heart disease within five years").

[1164] Step 6: Visualization phase

[1165] server

[1166] How it works: The server generates graphs and statistical data based on the prediction results, using libraries such as "Matplotlib" and "Seaborn."

[1167] Input and Output: As input, a prediction result (e.g., "20% increase in risk of heart disease within 5 years") is used. As output, a graph or statistical data (e.g., line graph, bar graph) is generated.

[1168] Terminal

[1169] Specific operation: The device displays the generated graphs and statistical data on the dashboard.

[1170] Input and Output: As input, it receives graphs and statistical data sent from the server. As output, it displays these data on the dashboard.

[1171] Step 7: Action proposal phase

[1172] server

[1173] Specific actions: Based on the prediction results, the server generates specific action suggestions for the user, such as suggestions for improving exercise habits or diet.

[1174] Input and Output: The input is a prediction result (e.g., "High risk of heart disease"). The output is an action suggestion (e.g., "Add 30 minutes of walking each day").

[1175] Terminal

[1176] Specific operation: The device notifies and displays the suggested actions to the user.

[1177] Input and Output: As input, it receives action suggestions sent from the server. As output, it displays the action suggestions to the user in push notifications and on the dashboard.

[1178] (Application example 1)

[1179] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1180] With increasing health awareness, many people are trying to manage and improve their lifestyles and health status. However, choosing healthy meals in daily life is not easy. In particular, when using food delivery services, there is a lack of specific guidance on reducing health risks and selecting appropriate meal plans. Therefore, there is a need for a system that can suggest optimal meal plans based on the user's basic information and activity data.

[1181] 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.

[1182] In this invention, the server includes means for inputting basic information and activity data of a user, means for transmitting the basic information and activity data to the server, means for storing and analyzing the transmitted data, means for predicting the user's future state from the analysis results, means for presenting the prediction results to the user and suggesting actions, and means for proposing an optimal meal plan to the user based on the basic information and activity data, thereby enabling the user to select an appropriate meal plan taking into account their health condition and lifestyle habits.

[1183] "Basic information" refers to personal data such as the user's health condition, educational background, and lifestyle habits.

[1184] "Activity data" refers to data related to the user's physical activity, such as the number of steps taken, heart rate, and sleep time.

[1185] A "server" is a system for receiving, storing, and analyzing data sent by users.

[1186] "Future state" is the future state of a user's health and lifestyle, predicted using machine learning algorithms based on current data.

[1187] The means for suggesting "actions" is a function that presents the user with a specific action plan based on the prediction results.

[1188] The "means for suggesting meal plans" is a function that provides optimal meal options based on the user's basic information and activity data.

[1189] A "dashboard" is an interface that visually displays prediction results and statistical data to users.

[1190] "Graphs and statistical data" refers to information that visually represents the predicted results of the user's health risks and future conditions.

[1191] The present invention is a system that collects and analyzes basic information and activity data of a user to predict future conditions and propose an optimal meal plan to the user. The system includes the following components:

[1192] Basic system configuration

[1193] 1. Terminal

[1194] The device provides a user interface for users to enter basic information (health status, educational background, lifestyle habits, etc.). This includes forms and check boxes. The device connects to devices such as activity trackers and smartwatches to automatically collect daily activity data (number of steps, heart rate, sleep time, etc.). The collected data is periodically sent to a server.

[1195] 2. Server

[1196] The server receives the data sent from the device and stores it in a database. It uses machine learning algorithms to analyze the accumulated data and predict the user's future condition. For example, it can assess future health risks based on current lifestyle habits. The prediction results are visualized and presented to the user in an easy-to-understand format.

[1197] 3. Users

[1198] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data. Based on the prediction results, users are given an optimal meal plan. For example, if there is an increased risk of health problems, the system will suggest calorie restriction or other dietary improvements.

[1199] Program processing

[1200] Data Collection Phase

[1201] The device provides an interface for users to input basic information as an initial setting, including height, weight, educational background, smoking habits, exercise habits, etc. The device also connects to an activity tracker or smartwatch to collect activity data such as steps taken, heart rate, and sleep time in real time.

[1202] Data transmission phase

[1203] The device periodically sends the collected basic information and activity data to a server, usually in a format such as JSON.

[1204] Data Management Phase

[1205] The server receives the data and stores it in a database. It integrates it with existing data and updates it with new data. To maintain data consistency, it is managed together with past data.

[1206] Prediction Phase

[1207] The server uses machine learning algorithms (such as Sci-kit Learn's Linear Regression) to analyze the user's current and past data and predict their future condition. For example, it assesses the health risks if the user continues their current lifestyle. Based on this prediction, it proposes an optimal diet plan for the user.

[1208] Visualization phase

[1209] The server generates graphs and statistical data based on the predictions, including predictions of heart disease risk and weight change. The device displays the predictions on a dashboard, allowing users to visually check the results and adjust their behavior as needed.

[1210] Specific examples

[1211] Example 1: Predicting health risks

[1212] The device provides an interface for users to input past health checkup results into the app, including data such as blood pressure and cholesterol levels. The server stores this information in a database and integrates it with existing lifestyle data. Machine learning algorithms are used to predict future heart disease risk. The device displays the predicted heart disease risk as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within three years."

[1213] Example 2: Meal plan suggestions

[1214] The device provides an interface for users to input their daily dietary information. The server analyzes the input data and predicts future health risks. Based on the results, the server provides the user with an optimal meal plan. For example, the server may suggest, "We will provide you with a meal plan that takes into account calorie restriction and appropriate nutritional balance."

[1215] Example prompts to input to the generative AI model

[1216] "If you continue your current lifestyle habits, your health risks will increase by 15% after three months. To improve this, we recommend the following diet plan."

[1217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1218] Step 1:

[1219] The device provides an interface where the user can input basic information (health status, educational background, lifestyle habits, etc.). The input data includes height, weight, smoking habits, exercise habits, etc. This allows the user's basic information to be collected. The input data is formatted for storage in a database using a format such as JSON.

[1220] Step 2:

[1221] The terminal connects to devices such as activity monitors and smartwatches to collect daily activity data (number of steps, heart rate, sleep time, etc.) in real time. This data is collected, formatted in JSON format or other formats, and prepared for transmission to the next processing step, either in batch processing or at specified intervals.

[1222] Step 3:

[1223] The device periodically sends the collected basic information and activity data to the server using HTTP or HTTPS, with the Content-Type header set to application / json. The device then verifies that the data reaches the server without any errors.

[1224] Step 4:

[1225] The server receives data sent from the device and stores it in a database. Using a database such as SQLite or MySQL, the received data is integrated with the existing database. A timestamp is added to the new data and it is managed together with past data.

[1226] Step 5:

[1227] The server applies machine learning algorithms to the basic information and activity data stored in the database. Using Scikit-Learn's Linear Regression model, it matches the input data with the training data to generate a predictive model. This model is then used to predict the user's future health status and activity patterns.

[1228] Step 6:

[1229] The server generates an optimal meal plan based on the prediction results. The generated meal plan is optimized taking into account the user's calorie intake, nutritional balance, and past dietary information. The predictions and suggestions are integrated and generated as JSON format data to be provided to the user.

[1230] Step 7:

[1231] The device displays the prediction results and meal plans obtained from the server on a dashboard. Libraries such as Matplotlib and Chart.js are used to visualize the results as graphs and statistical data, allowing users to intuitively understand the predicted health risks and recommended meal plans.

[1232] Step 8:

[1233] Users can check the prediction results and suggestions displayed on the dashboard and adjust their diet and lifestyle accordingly. For example, they may see a prompt such as, "If you continue your current lifestyle, your health risk will increase by 15% in three months. To improve this, we recommend the following meal plan."

[1234] 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.

[1235] This system collects basic information, activity data, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[1236] Basic system configuration

[1237] 1. Terminal

[1238] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[1239] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[1240] The device uses a camera, microphone, and text input to collect the user's emotional data (facial expressions, tone of voice, and text input).

[1241] The collected data is periodically sent to a server.

[1242] 2. Server

[1243] The server receives the basic information, activity data, and emotion data sent from the terminal and stores them in a database.

[1244] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits and emotional state.

[1245] The prediction results are visualized and presented to the user in an easy-to-understand format.

[1246] 3. Emotion Engine

[1247] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state.

[1248] The emotion engine's analysis results are used to personalize suggested actions for the user, for example, relaxation suggestions when the user is feeling stressed.

[1249] 4. Users

[1250] Users can view the prediction results and their emotional state through a dashboard on their device, which is displayed in the form of graphs and statistical data.

[1251] Based on the prediction results and emotional state, users receive specific action suggestions to improve their lifestyle habits.

[1252] Program processing

[1253] Data Collection Phase

[1254] Terminal

[1255] The user enters basic information as the initial setting, including height, weight, education, smoking habits, and exercise frequency.

[1256] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[1257] It uses the camera, microphone, and text input to collect user emotional data.

[1258] Data transmission phase

[1259] Terminal

[1260] The collected basic information, activity data, and emotion data are periodically sent to a server, usually in a format such as JSON.

[1261] Data Management Phase

[1262] server

[1263] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[1264] Maintain data consistency by integrating with past data.

[1265] Prediction Phase

[1266] server

[1267] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, by considering their lifestyle habits and emotional state together to assess future health risks.

[1268] The prediction results are analyzed and actions are suggested to the user as necessary.

[1269] Sentiment Analysis Phase

[1270] Emotion Engine

[1271] Recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and text input, for example, using image processing and natural language processing techniques.

[1272] Visualization phase

[1273] server

[1274] Based on the predictions and your emotional state, graphs and statistics are generated, including predictions of heart disease risk, weight change, and stress levels.

[1275] Terminal

[1276] The predictions and sentiment analysis results are displayed on a dashboard, allowing users to visually check them and adjust their actions as needed.

[1277] Specific examples

[1278] Example 1: Predicting health risks

[1279] Terminal

[1280] Users input their past health check results and daily emotional state (e.g., daily stress level and mood) into the app.

[1281] server

[1282] The server stores this information in a database and integrates it with existing lifestyle data.

[1283] It uses machine learning algorithms to predict future heart disease risk, and an emotion engine to analyze a user's stress state.

[1284] Terminal

[1285] The predicted heart disease risk and emotional state are displayed as a graph on the dashboard, for example, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years."

[1286] Based on this, users receive action suggestions to improve their exercise habits, diet, and stress management methods, and review their lives.

[1287] Example 2: Predicting weight change

[1288] Terminal

[1289] The user inputs their daily diet and exercise, as well as their emotional state for that day (e.g., happy, sad, angry).

[1290] server

[1291] The server analyzes the input data and predicts future weight changes and psychological states. It also uses an emotion engine to analyze the user's emotional state regarding food and exercise.

[1292] Terminal

[1293] The prediction results are displayed on a dashboard in the form of, for example, "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect your diet and exercise.

[1294] Users can use this information to plan their diet and exercise, and manage their emotions, thereby improving their lives more effectively.

[1295] Such a system allows users to understand in real time how their lifestyle habits and emotions affect their future, and to take concrete actions to build healthy lifestyles.

[1296] The processing flow will be explained below.

[1297] Step 1:

[1298] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[1299] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[1300] Step 2:

[1301] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[1302] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[1303] Step 3:

[1304] The device collects user emotional data using the camera, microphone, and text input.

[1305] Specifically, it uses facial recognition technology to analyze facial expressions, voice recognition technology to analyze tone of voice, and natural language processing to analyze emotions from text input.

[1306] Step 4:

[1307] The device transmits the collected basic information, activity data, and emotion data to the server.

[1308] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[1309] Step 5:

[1310] The server receives the transmitted data and stores it in a database.

[1311] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL) in the appropriate format.

[1312] Step 6:

[1313] The server applies machine learning algorithms to analyze the accumulated data.

[1314] Specifically, it combines past and present data and runs machine learning models such as regression analysis and clustering using, for example, Scikit-learn or TensorFlow.

[1315] Step 7:

[1316] The server applies an emotion engine to analyze the user's emotion data.

[1317] Specifically, the emotion engine analyzes the user's facial expressions, tone of voice, and text input and stores them in a database.

[1318] Step 8:

[1319] The server predicts the user's future state based on the results of machine learning and the emotion engine.

[1320] Specifically, the results of both analyses will be integrated to generate future health risks and action recommendations.

[1321] Step 9:

[1322] The server generates data for visualizing the prediction results.

[1323] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[1324] Step 10:

[1325] The graphs and statistical data generated by the server are sent to the terminal.

[1326] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[1327] Step 11:

[1328] The device displays prediction results and sentiment analysis results on a dashboard.

[1329] Specifically, the received data is displayed as graphs and statistical data on the user interface using HTML and JavaScript.

[1330] Step 12:

[1331] The user sees the forecast results on the dashboard.

[1332] Specifically, the system looks at graphs of predicted health risks, weight changes, and emotional states to determine the necessary improvement actions.

[1333] Step 13:

[1334] The terminal notifies the user of specific suggested actions.

[1335] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" and "incorporate relaxation techniques to relieve stress" via push notifications and in-app messages.

[1336] Through this detailed processing step, the system allows users to understand their own health and emotional state in real time, predict future risks, and receive specific action suggestions.

[1337] Example 2

[1338] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1339] While conventional systems were capable of analyzing a user's basic information and activity information, they had the problem of not being able to make personalized suggestions that took into account the user's emotional state. This led to problems such as users overlooking health risks due to stress or emotional changes, or not being able to take effective actions. In addition, because the analysis results and suggested actions were displayed individually, it was difficult for users to grasp their overall health status.

[1340] 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.

[1341] In this invention, the server includes a means for inputting the user's basic information and activity information, a means for inputting the user's emotional state, and a means for accumulating and analyzing the transmitted data. This enables the user's basic information, activity information, and emotional state data to be analyzed in an integrated manner, enabling personalized behavioral suggestions. Furthermore, by displaying the analysis results and emotional state as graphs and statistical data on the display device of the user's terminal, the user can easily visually grasp changes in their own health condition and emotions. As a result, the user can more effectively manage health risks and work to improve their lifestyle habits.

[1342] "Basic user information" refers to personal information such as height, weight, educational background, smoking habits, and exercise frequency entered by the user.

[1343] "Activity information" refers to data on daily activities such as steps taken, heart rate, and sleep time collected from activity monitors and smartwatches.

[1344] "Emotional state" is data about emotions collected from a user's facial expressions, tone of voice, and text input.

[1345] "Input means" refers to the interface through which a user inputs data, such as a form, checkboxes, camera, or microphone.

[1346] "Means for transmitting" refers to the communication protocol or communication module used to transmit collected data to the server.

[1347] "Means of storage and analysis" refers to the server's function of storing received data in a database and analyzing the data using machine learning algorithms and data analysis tools.

[1348] "Means for predicting a user's future health risks and lifestyle changes" refers to the process of using a machine learning model to predict a user's future health risks and lifestyle changes based on the user's past and current data.

[1349] "Means for suggesting actions" refers to functions, such as notifications and alerts, that suggest specific actions to the user based on the prediction results.

[1350] "Display device" refers to a screen or display that allows a user to visually confirm analysis results and suggestions.

[1351] This system collects basic information, activity information, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[1352] Basic system configuration

[1353] 1. Terminal

[1354] The device provides a user interface for users to input basic information, including forms and checkboxes. It also connects with devices such as activity trackers and smartwatches to collect activity information in real time. It also uses a camera, microphone, and text input to collect the user's emotional state. The collected data is periodically sent to a server.

[1355] 2. Server

[1356] The server receives basic information, activity information, and emotion data sent from the device and stores them in a database. It also uses machine learning algorithms to analyze the accumulated data and predict the user's future state. The prediction results are visualized and provided to the user in an easy-to-understand format.

[1357] 3. Emotion Engine

[1358] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state, using image processing and natural language processing techniques, and the results of the analysis are used to personalize suggested actions for the user.

[1359] 4. Users

[1360] Users can check their prediction results and emotional state through the device's dashboard. The prediction results are displayed in the form of graphs and statistical data. Based on the prediction results and emotional state, users can receive specific action suggestions to improve their lifestyle habits.

[1361] Specific actions

[1362] Example 1: Predicting health risks

[1363] Users enter their past health checkup results and daily emotional state into the app. The server stores this information in a database and integrates it with existing lifestyle data. A machine learning algorithm is used to predict future heart disease risk. An emotion engine is also used to analyze the user's stress level. The device displays the predicted heart disease risk and emotional state as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years." Based on this, users receive action suggestions for improving their exercise habits, diet, and stress management methods.

[1364] Example 2: Predicting weight change

[1365] The user inputs their daily diet and exercise routine, as well as their emotional state for that day. The server analyzes the input data and predicts future weight changes and their psychological state. It also uses an emotion engine to analyze the user's emotional state regarding diet and exercise. The device displays the predicted results on a dashboard, such as "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect diet and exercise. Users can use this information to create dietary restrictions and exercise plans, and manage their emotions.

[1366] Example prompt

[1367] "Use the user's lifestyle data to predict future health risks and suggest specific actions to improve them."

[1368] "Analyze user sentiment data and provide personalized health recommendations based on it."

[1369] The system allows users to understand in real time how their lifestyle habits and emotions affect their future, and take concrete actions to build healthy lifestyle habits.

[1370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1371] Step 1:

[1372] Enter basic information

[1373] The device provides a screen where the user can enter basic information (height, weight, educational background, smoking habits, exercise frequency, etc.). The user enters this information into a form. The input data is temporarily stored in local storage or device memory. This allows the basic information to be collected.

[1374] Input: User's height, weight, education, smoking habits, and exercise frequency

[1375] Output: Basic information data stored in the device

[1376] Step 2:

[1377] Collection of activity information

[1378] The device collects real-time activity information (number of steps, heart rate, sleep time, etc.) from activity monitors and smartwatches via Bluetooth or Wi-Fi. This data is updated at regular intervals and stored internally on the device.

[1379] Input: Activity information obtained from activity trackers and smartwatches

[1380] Output: Activity information data stored in the device

[1381] Step 3:

[1382] Collecting emotional states

[1383] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and collects this as emotional data. In addition, text data entered by the user is also collected as emotional data.

[1384] Input: facial expression data obtained from a camera or microphone, voice data, and text data entered by the user

[1385] Output: Emotion data stored in the device

[1386] Step 4:

[1387] Data transmission

[1388] The device periodically transmits the collected basic information, activity information, and emotion data to a server, structured in a standard format such as JSON, using a secure communication protocol.

[1389] Input: Basic information, activity information, and emotional data stored on the device

[1390] Output: Various data sent to the server

[1391] Step 5:

[1392] Receiving and storing data

[1393] The server receives the data sent from the device. The received data is stored in a dedicated database (e.g., MySQL, MongoDB), and is updated by integrating it with past data.

[1394] Input: Basic information, activity information, and emotional data sent from the device

[1395] Output: Various data stored in the server database

[1396] Step 6:

[1397] Running the prediction algorithm

[1398] The server analyzes the received data using machine learning models (e.g., TensorFlow, PyTorch), and predicts future health risks and weight changes based on the user's lifestyle and emotional state.

[1399] Input: Basic information, activity information, and emotion data stored in the database

[1400] Output: Predicted health risks and weight change data

[1401] Step 7:

[1402] Performing sentiment analysis

[1403] The emotion engine analyzes facial expressions, voice, and text data sent from the device, and uses image processing technology (e.g., OpenCV) and natural language processing technology (e.g., NLTK, spaCy) to identify the device's emotional state.

[1404] Input: facial expression data, voice data, text data

[1405] Output: Recognized emotional state data

[1406] Step 8:

[1407] Visualizing the results

[1408] The server generates graphs and statistical data based on the prediction results and emotional states (e.g., Matplotlib, D3.js), which makes it easier for users to understand visually.

[1409] Input: predicted health risk, weight change data, emotional state data

[1410] Output: Visualized graphs and statistical data

[1411] Step 9:

[1412] Viewing the Dashboard

[1413] The device displays the analysis results and prediction data sent from the server as a dashboard, allowing users to check their own predictions and sentiment analysis results.

[1414] Input: Analysis results and prediction data sent from the server

[1415] Output: Analysis results and forecast data displayed on a dashboard

[1416] Step 10:

[1417] action suggestion

[1418] The device will suggest specific actions based on the predictions and your emotional state, such as "take 10 minutes of deep breathing exercises to relax."

[1419] Input: Prediction result, emotional state

[1420] Output: Specific action suggestions provided to the user

[1421] Through each of the above steps, users can understand in real time how their lifestyle habits and emotions affect their future and take concrete action.

[1422] (Application example 2)

[1423] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1424] Conventional online shopping sites lack personalized product recommendations that take into account the user's health and emotional state. In particular, they are unable to provide appropriate product suggestions to reduce stress and health risks, making it difficult for users to find the products they truly need. In addition, understanding a user's emotional state in real time and recommending products accordingly is a challenge.

[1425] 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.

[1426] In this invention, the server includes a means for inputting basic information and activity data of a user, a means for analyzing the emotional state of the user using an emotion engine, a means for recommending personalized products to the user based on the basic information, activity data, and emotional state, and a means for displaying the recommendation results on the smart glasses, thereby enabling reliable product recommendations based on the user's health condition and emotional state.

[1427] (Word definition)

[1428] "Basic information of a user" refers to basic information related to an individual, such as the user's height, weight, age, lifestyle, and health condition.

[1429] "Activity data" is data related to the user's daily activities, and includes, for example, the number of steps taken, the amount of exercise, the heart rate, and the amount of sleep.

[1430] "Server" means a computer system on a network that stores and analyzes collected data.

[1431] An "emotion engine" is an algorithm or software that recognizes a user's emotional state by analyzing data such as facial expressions, tone of voice, and text input collected from sensors such as cameras and microphones.

[1432] The "prediction means" is a means for predicting the user's future state using a machine learning algorithm based on the collected basic information, activity data, and emotion data.

[1433] A "means for recommending personalized products" is a means for selecting and recommending products suitable for individual users by taking into consideration the user's basic information, activity data, and emotional state.

[1434] "Smart glasses" are eyeglass-type wearable devices with a built-in display device that can display information directly in the user's field of vision.

[1435] The "result display means" is a means for visually displaying prediction results and product recommendation results on the user's device.

[1436] The system for realizing this application example is configured as follows.

[1437] First, the core hardware of the system consists of a server, smart glasses, an activity tracker, a smartwatch, a camera, and a microphone. The server is responsible for storing data, analyzing it, and sending the results, while the smart glasses are responsible for displaying the data. The activity tracker and smartwatch collect the user's activity data, and the camera and microphone collect emotion data.

[1438] The system includes the following main software components:

[1439] 1. Data collection software: Collects basic user information, activity data, and emotional data using a camera and microphone.

[1440] 2. Data transmission software: periodically transmits collected data to the server.

[1441] 3. Database software: stores and manages the transmitted data.

[1442] 4. Machine learning algorithms: These run on the server and analyze the collected data to predict the user's future state.

[1443] 5. Sentiment Engine: A software component for performing sentiment analysis.

[1444] 6. Product recommendation software: Selects and recommends the most suitable products based on the user's health and emotional state.

[1445] 7. Display software: Visually display the product recommendation results on the smart glasses.

[1446] Data collection

[1447] The user wears the smart glasses and inputs basic information and activity data. The activity tracker or smartwatch automatically collects the user's daily activity data (e.g., number of steps, heart rate, and sleep time). The camera and microphone also analyze the user's facial expressions and tone of voice to collect their emotional state. The collected data is periodically sent to a server and stored in a database.

[1448] Data analysis

[1449] The server uses machine learning algorithms to analyze the accumulated basic information, activity data, and emotional data. The analysis results are used to predict the user's future health and emotional state. Furthermore, an emotion engine analyzes the user's real-time emotional state and makes product recommendations based on this.

[1450] Product recommendation

[1451] The server selects personalized products for the user based on the prediction results and the emotional state, and sends the recommendation results to the smart glasses via the product recommendation software.

[1452] display

[1453] The smart glasses visually display recommended products, allowing users to easily obtain product information based on their health and emotional state.

[1454] For example, when a user is feeling stressed, the emotion engine analyzes the user's stress level and recommends relaxation products and calming clothing. The results are displayed on the smart glasses, allowing the user to check in real time which products are suitable for their emotional state.

[1455] (Example of a prompt)

[1456] When the user feels stressed, a prompt is displayed that takes into account health risks: "Recommend relaxation products based on my health condition and emotions."

[1457] This enables personalized product recommendations based on the user's health and emotional state, contributing to improving the user's lifestyle habits.

[1458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1459] Step 1:

[1460] The user puts on the smart glasses and inputs basic information, such as height, weight, age, lifestyle habits, and health status, into the application form. This information is then stored on the device.

[1461] Input: Basic information such as height, weight, age, lifestyle habits, and health condition

[1462] Output: Saved basic information data

[1463] Step 2:

[1464] Activity trackers and smartwatches collect users' activity data in real time, including the number of steps taken, heart rate, and sleep time. This data is also sent to the device and stored.

[1465] Input: User's daily activity data (number of steps, heart rate, sleep time, etc.)

[1466] Output: Saved activity data

[1467] Step 3:

[1468] The smart glasses' cameras and microphones capture the user's facial expressions and tone of voice to collect emotional data, which is then analyzed in real time by an emotion engine.

[1469] Input: Facial expression, tone of voice data

[1470] Output: Parsed emotion data

[1471] Step 4:

[1472] The device periodically sends the collected basic information, activity data, and emotion data to the server in JSON format.

[1473] Input: Basic information, activity data, emotion data

[1474] Output: Data sent to the server

[1475] Step 5:

[1476] The server receives the submitted data and stores it in a database, which centralizes the user's entire data set.

[1477] Input: Data received from the terminal

[1478] Output: Consolidated data stored in a database

[1479] Step 6:

[1480] Machine learning algorithms on the server use information from the database to predict a user's future health status, for example assessing their risk of heart disease based on their lifestyle habits and emotional state.

[1481] Input: Integrated data stored in a database

[1482] Output: predicted health state

[1483] Step 7:

[1484] The emotion engine analyzes collected facial expression and tone of voice data to understand the user's current emotional state.

[1485] Input: Facial expression, tone of voice data

[1486] Output: Current emotional state

[1487] Step 8:

[1488] The server then recommends personalized products to the user based on their predicted health and emotional state, for example, recommending relaxation products if the user is feeling stressed.

[1489] Input: predicted health status, current emotional state

[1490] Output: A list of recommended products

[1491] Step 9:

[1492] The server sends the recommended product list to the smart glasses.

[1493] Input: Recommended product list

[1494] Output: Product information sent to smart glasses

[1495] Step 10:

[1496] The smart glasses will display the recommended products in the user's field of view, allowing the user to visually confirm and select the products as needed.

[1497] Input: Product information sent from the server

[1498] Output: Product information displayed on smart glasses

[1499] This allows users to receive personalized product recommendations based on their health and emotional state, making it easier to find more suitable products.

[1500] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1501] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1502] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1503] [Fourth embodiment]

[1504] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1505] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1506] 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).

[1507] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1508] 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.

[1509] 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).

[1510] 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.

[1511] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1512] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1513] 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.

[1514] 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.

[1515] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1516] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1517] The present invention is a system that collects basic information and activity data of a user, analyzes the data on a server, predicts future conditions, and makes specific suggestions for actions to the user.

[1518] Basic system configuration

[1519] 1. Terminal

[1520] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[1521] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[1522] The collected data is periodically sent to a server.

[1523] 2. Server

[1524] The server receives the data sent from the terminal and stores it in a database.

[1525] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits.

[1526] The prediction results are visualized and presented to the user in an easy-to-understand format.

[1527] 3. Users

[1528] Users can check the forecast results through the device's dashboard, which are displayed in the form of graphs and statistical data.

[1529] Based on the prediction results, users will receive specific action suggestions. For example, if there is an increased risk of health problems, the system will suggest changing exercise habits or improving diet.

[1530] Program processing

[1531] Data Collection Phase

[1532] Terminal

[1533] The user enters basic information as the initial setting, including height, weight, educational background, smoking habits, and exercise habits.

[1534] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[1535] Data transmission phase

[1536] Terminal

[1537] The collected basic information and activity data is periodically sent to a server, usually in a format such as JSON.

[1538] Data Management Phase

[1539] server

[1540] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[1541] Maintain data consistency by integrating with past data.

[1542] Prediction Phase

[1543] server

[1544] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, assessing their health risk if they continue their current lifestyle.

[1545] The prediction results are analyzed and actions are suggested to the user as necessary.

[1546] Visualization phase

[1547] server

[1548] Based on the predictions, graphs and statistics are generated, including predictions of heart disease risk and weight change.

[1549] Terminal

[1550] Predictions are displayed on a dashboard, allowing users to visually review them and adjust their actions as needed.

[1551] Specific examples

[1552] Example 1: Predicting health risks

[1553] Terminal

[1554] Users enter the results of their past health checkups into the app, such as data on blood pressure and cholesterol levels.

[1555] server

[1556] The server stores this information in a database and integrates it with existing lifestyle data.

[1557] Use machine learning algorithms to predict future heart disease risk.

[1558] Terminal

[1559] The predicted risk of heart disease is displayed as a graph on the dashboard. For example, it may say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years."

[1560] Based on this, users receive suggestions for actions to improve their exercise habits and diet, and review their lifestyle.

[1561] Example 2: Predicting weight change

[1562] Terminal

[1563] The user inputs the details of their daily diet and the amount of exercise they do.

[1564] server

[1565] The server analyzes the input data and predicts future weight changes.

[1566] Terminal

[1567] The predicted results are displayed on the dashboard in the form of, for example, "If you continue your current lifestyle, your weight will increase by 5 kg in three months."

[1568] Users can use this information to create dietary and exercise plans.

[1569] Such a system allows users to understand in real time how their lifestyle habits will affect their future and guide them towards healthier lifestyles.

[1570] The processing flow will be explained below.

[1571] Step 1:

[1572] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[1573] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[1574] Step 2:

[1575] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[1576] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[1577] Step 3:

[1578] The device sends the collected basic information and activity data to the server.

[1579] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[1580] Step 4:

[1581] The server receives the transmitted data and stores it in a database.

[1582] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL) in the appropriate format.

[1583] Step 5:

[1584] The server applies machine learning algorithms to analyze the accumulated data.

[1585] Specifically, it combines past and present data and runs machine learning models such as regression analysis and clustering using, for example, Scikit-learn or TensorFlow.

[1586] Step 6:

[1587] The server predicts the user's future state based on the analysis results.

[1588] Specifically, future health risks and weight changes are calculated based on the output of the machine learning model.

[1589] Step 7:

[1590] The server generates data for visualizing the prediction results.

[1591] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[1592] Step 8:

[1593] The graphs and statistical data generated by the server are sent to the terminal.

[1594] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[1595] Step 9:

[1596] The device displays the prediction results on a dashboard.

[1597] Specifically, the received data is displayed as graphs and statistical data on the user interface using HTML and JavaScript.

[1598] Step 10:

[1599] The user sees the forecast results on the dashboard.

[1600] Specifically, the system looks at graphs of predicted health risks and weight changes to determine the necessary improvement actions.

[1601] Step 11:

[1602] The terminal notifies the user of specific suggested actions.

[1603] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" via push notifications and in-app messages.

[1604] This detailed processing step allows the system to predict the user's future health status and provide information for taking specific actions.

[1605] Example 1

[1606] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1607] In modern society, personal health management and lifestyle improvement are extremely important issues. However, many currently available health management systems lack the ability to effectively collect and analyze user data and predict future risks. Furthermore, the feedback users receive is limited to general information and does not translate into specific recommendations for action. This makes self-management a time-consuming process for users, and makes it difficult for them to find appropriate improvement measures.

[1608] 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.

[1609] In this invention, the server includes means for accumulating the transmitted data and storing it in a database while maintaining consistency, means for analyzing the accumulated data and predicting the user's future state using a machine learning algorithm, and means for visualizing the prediction results as graphs or statistical data and presenting them to the user, thereby enabling the user to receive specific behavioral suggestions based on their own lifestyle habits.

[1610] "Basic user information" refers to basic data about an individual, such as height, weight, educational background, smoking habits, and exercise habits.

[1611] "Activity data" is data that records specific actions taken in the user's daily life, including the number of steps taken, heart rate, and sleep time.

[1612] The term "means" refers to a function or module for executing each of the processing steps described above.

[1613] A "server" is a computer system that receives, stores, analyzes, predicts, and presents results of data.

[1614] A "database" is a system for centrally managing user data accumulated by a server.

[1615] A "machine learning algorithm" is a computational method for learning patterns and trends from data and predicting future states.

[1616] "Prediction results" are information about future states derived from the user's current and past data.

[1617] "Visualization" is a method of displaying prediction results in a way that is easy for users to understand, such as in the form of graphs or statistical data.

[1618] "Action suggestions" are specific actions or improvements recommended to users based on the prediction results.

[1619] A "dashboard" is an interface displayed on a user's device that visually presents collected data and prediction results.

[1620] "Notification" is a function that allows the server to notify the user's device of suggested actions and prediction results.

[1621] The present invention is a system that collects basic information and activity data of a user, analyzes it on a server, predicts future conditions, and suggests specific actions to the user. This system uses the following hardware and software.

[1622] 1. Terminal

[1623] The device provides a user interface for the user to enter basic information. For example, information such as height, weight, educational background, smoking habits, and exercise habits can be entered using forms and check boxes. Furthermore, the device connects to an activity tracker or smartwatch to automatically collect the user's daily activity data. The collected basic information and activity data are periodically sent to a server. This transmission is usually done in a format such as JSON.

[1624] Specific examples

[1625] Users enter information such as their height (170cm), weight (70kg), and non-smoking status into a form on the device. The device also receives data from a smartwatch and collects activity data such as the number of steps taken each day and heart rate. The collected data is sent to a server every night.

[1626] 2. Server

[1627] The server receives basic information and activity data sent from the device and stores it in a database. Data integrity is maintained by integrating existing data and updating it with new data. The server analyzes the accumulated data using machine learning algorithms to predict the user's future state. To do this, it utilizes Python libraries such as "pandas," "scikit-learn," and "Matplotlib."

[1628] Specific examples

[1629] The server uses Python's "pandas" to store the received data in a data frame, and then uses "scikit-learn"'s random forest model to predict future heart disease risk. The predicted results are visualized as a graph using "Matplotlib."

[1630] 3. Users

[1631] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data, allowing users to understand the results visually. Users can also receive specific action suggestions based on the prediction results. For example, if health risks increase, the system will suggest actions such as reviewing exercise habits or improving diet.

[1632] Specific examples

[1633] The dashboard displays a graph of predicted results, such as, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years." Based on these results, users receive suggestions to improve their exercise habits and eat healthier meals.

[1634] In this way, this system collects basic information and activity data from users, analyzes this data on the server, and predicts future conditions, allowing the system to suggest specific actions to users. This allows users to understand in real time how their lifestyle habits will affect the future, and to take specific actions to maintain a healthy lifestyle.

[1635] Example prompt sentence:

[1636] "If you continue your current lifestyle, your risk of heart disease will increase by 20% within five years. We suggest that you review your exercise habits and improve your diet."

[1637] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1638] Step 1: Data Entry Phase

[1639] Terminal

[1640] Specific operation: The user uses the device's user interface to enter basic information, such as height, weight, educational background, smoking habits, and exercise habits, using the device's forms and check boxes.

[1641] Input and Output: As input, basic information of the user (e.g., height 170 cm, weight 70 kg, non-smoker, exercise 3 times a week) is received. As output, this data is stored on the device.

[1642] Step 2: Data collection phase

[1643] Terminal

[1644] Specific operation: The device works in conjunction with an activity tracker or smartwatch to automatically collect the user's daily activity data (number of steps, heart rate, sleep time, etc.).

[1645] Input and Output: As input, it receives real-time data from an activity tracker or smartwatch (e.g., 10,000 steps per day, heart rate 75 bpm, 7 hours of sleep). As output, it stores the collected activity data on the device.

[1646] Step 3: Data transmission phase

[1647] Terminal

[1648] How it works: The device periodically sends the collected basic information and activity data to the server. The data is usually sent in a format such as JSON.

[1649] Input and Output: As input, we use the saved basic information and activity data (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, these data are sent to the server.

[1650] Step 4: Data management phase

[1651] server

[1652] Specific operation: The server receives the data sent from the device and stores it in a database. It maintains data integrity by integrating it with existing data and updating it with new data.

[1653] Input and output: As input, it receives data sent from the device (e.g., {"height":170, "weight":70, "steps":10000, "heart_rate":75, "sleep_hours":7}). As output, it stores these data in a database.

[1654] Step 5: Data analysis and prediction phase

[1655] server

[1656] How it works: The server analyzes the accumulated data and uses machine learning algorithms to predict the user's future state. It stores the data in a data frame using Python's "pandas," preprocesses the data using "scikit-learn," and makes predictions using algorithms such as the random forest model.

[1657] Input and Output: The input is data stored in a database (e.g., health data from the past few months). The output is a prediction result (e.g., "20% increase in risk of heart disease within five years").

[1658] Step 6: Visualization phase

[1659] server

[1660] How it works: The server generates graphs and statistical data based on the prediction results, using libraries such as "Matplotlib" and "Seaborn."

[1661] Input and Output: As input, a prediction result (e.g., "20% increase in risk of heart disease within 5 years") is used. As output, a graph or statistical data (e.g., line graph, bar graph) is generated.

[1662] Terminal

[1663] Specific operation: The device displays the generated graphs and statistical data on the dashboard.

[1664] Input and Output: As input, it receives graphs and statistical data sent from the server. As output, it displays these data on the dashboard.

[1665] Step 7: Action proposal phase

[1666] server

[1667] Specific actions: Based on the prediction results, the server generates specific action suggestions for the user, such as suggestions for improving exercise habits or diet.

[1668] Input and Output: The input is a prediction result (e.g., "High risk of heart disease"). The output is an action suggestion (e.g., "Add 30 minutes of walking each day").

[1669] Terminal

[1670] Specific operation: The device notifies and displays the suggested actions to the user.

[1671] Input and Output: As input, it receives action suggestions sent from the server. As output, it displays the action suggestions to the user in push notifications and on the dashboard.

[1672] (Application example 1)

[1673] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1674] With increasing health awareness, many people are trying to manage and improve their lifestyles and health status. However, choosing healthy meals in daily life is not easy. In particular, when using food delivery services, there is a lack of specific guidance on reducing health risks and selecting appropriate meal plans. Therefore, there is a need for a system that can suggest optimal meal plans based on the user's basic information and activity data.

[1675] 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.

[1676] In this invention, the server includes means for inputting basic information and activity data of a user, means for transmitting the basic information and activity data to the server, means for storing and analyzing the transmitted data, means for predicting the user's future state from the analysis results, means for presenting the prediction results to the user and suggesting actions, and means for proposing an optimal meal plan to the user based on the basic information and activity data, thereby enabling the user to select an appropriate meal plan taking into account their health condition and lifestyle habits.

[1677] "Basic information" refers to personal data such as the user's health condition, educational background, and lifestyle habits.

[1678] "Activity data" refers to data related to the user's physical activity, such as the number of steps taken, heart rate, and sleep time.

[1679] A "server" is a system for receiving, storing, and analyzing data sent by users.

[1680] "Future state" is the future state of a user's health and lifestyle, predicted using machine learning algorithms based on current data.

[1681] The means for suggesting "actions" is a function that presents the user with a specific action plan based on the prediction results.

[1682] The "means for suggesting meal plans" is a function that provides optimal meal options based on the user's basic information and activity data.

[1683] A "dashboard" is an interface that visually displays prediction results and statistical data to users.

[1684] "Graphs and statistical data" refers to information that visually represents the predicted results of the user's health risks and future conditions.

[1685] The present invention is a system that collects and analyzes basic information and activity data of a user to predict future conditions and propose an optimal meal plan to the user. The system includes the following components:

[1686] Basic system configuration

[1687] 1. Terminal

[1688] The device provides a user interface for users to enter basic information (health status, educational background, lifestyle habits, etc.). This includes forms and check boxes. The device connects to devices such as activity trackers and smartwatches to automatically collect daily activity data (number of steps, heart rate, sleep time, etc.). The collected data is periodically sent to a server.

[1689] 2. Server

[1690] The server receives the data sent from the device and stores it in a database. It uses machine learning algorithms to analyze the accumulated data and predict the user's future condition. For example, it can assess future health risks based on current lifestyle habits. The prediction results are visualized and presented to the user in an easy-to-understand format.

[1691] 3. Users

[1692] Users can check the prediction results through the device's dashboard. The results are displayed in the form of graphs and statistical data. Based on the prediction results, users are given an optimal meal plan. For example, if there is an increased risk of health problems, the system will suggest calorie restriction or other dietary improvements.

[1693] Program processing

[1694] Data Collection Phase

[1695] The device provides an interface for users to input basic information as an initial setting, including height, weight, educational background, smoking habits, exercise habits, etc. The device also connects to an activity tracker or smartwatch to collect activity data such as steps taken, heart rate, and sleep time in real time.

[1696] Data transmission phase

[1697] The device periodically sends the collected basic information and activity data to a server, usually in a format such as JSON.

[1698] Data Management Phase

[1699] The server receives the data and stores it in a database. It integrates it with existing data and updates it with new data. To maintain data consistency, it is managed together with past data.

[1700] Prediction Phase

[1701] The server uses machine learning algorithms (such as Sci-kit Learn's Linear Regression) to analyze the user's current and past data and predict their future condition. For example, it assesses the health risks if the user continues their current lifestyle. Based on this prediction, it proposes an optimal diet plan for the user.

[1702] Visualization phase

[1703] The server generates graphs and statistical data based on the predictions, including predictions of heart disease risk and weight change. The device displays the predictions on a dashboard, allowing users to visually check the results and adjust their behavior as needed.

[1704] Specific examples

[1705] Example 1: Predicting health risks

[1706] The device provides an interface for users to input past health checkup results into the app, including data such as blood pressure and cholesterol levels. The server stores this information in a database and integrates it with existing lifestyle data. Machine learning algorithms are used to predict future heart disease risk. The device displays the predicted heart disease risk as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle, your risk of heart disease will increase by 20% within three years."

[1707] Example 2: Meal plan suggestions

[1708] The device provides an interface for users to input their daily dietary information. The server analyzes the input data and predicts future health risks. Based on the results, the server provides the user with an optimal meal plan. For example, the server may suggest, "We will provide you with a meal plan that takes into account calorie restriction and appropriate nutritional balance."

[1709] Example prompts to input to the generative AI model

[1710] "If you continue your current lifestyle habits, your health risks will increase by 15% after three months. To improve this, we recommend the following diet plan."

[1711] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1712] Step 1:

[1713] The device provides an interface where the user can input basic information (health status, educational background, lifestyle habits, etc.). The input data includes height, weight, smoking habits, exercise habits, etc. This allows the user's basic information to be collected. The input data is formatted for storage in a database using a format such as JSON.

[1714] Step 2:

[1715] The terminal connects to devices such as activity monitors and smartwatches to collect daily activity data (number of steps, heart rate, sleep time, etc.) in real time. This data is collected, formatted in JSON format or other formats, and prepared for transmission to the next processing step, either in batch processing or at specified intervals.

[1716] Step 3:

[1717] The device periodically sends the collected basic information and activity data to the server using HTTP or HTTPS, with the Content-Type header set to application / json. The device then verifies that the data reaches the server without any errors.

[1718] Step 4:

[1719] The server receives data sent from the device and stores it in a database. Using a database such as SQLite or MySQL, the received data is integrated with the existing database. A timestamp is added to the new data and it is managed together with past data.

[1720] Step 5:

[1721] The server applies machine learning algorithms to the basic information and activity data stored in the database. Using Scikit-Learn's Linear Regression model, it matches the input data with the training data to generate a predictive model. This model is then used to predict the user's future health status and activity patterns.

[1722] Step 6:

[1723] The server generates an optimal meal plan based on the prediction results. The generated meal plan is optimized taking into account the user's calorie intake, nutritional balance, and past dietary information. The predictions and suggestions are integrated and generated as JSON format data to be provided to the user.

[1724] Step 7:

[1725] The device displays the prediction results and meal plans obtained from the server on a dashboard. Libraries such as Matplotlib and Chart.js are used to visualize the results as graphs and statistical data, allowing users to intuitively understand the predicted health risks and recommended meal plans.

[1726] Step 8:

[1727] Users can check the prediction results and suggestions displayed on the dashboard and adjust their diet and lifestyle accordingly. For example, they may see a prompt such as, "If you continue your current lifestyle, your health risk will increase by 15% in three months. To improve this, we recommend the following meal plan."

[1728] 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.

[1729] This system collects basic information, activity data, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[1730] Basic system configuration

[1731] 1. Terminal

[1732] The terminal provides a user interface for the user to input basic information (e.g., health status, educational background, lifestyle habits, etc.), which includes forms and check boxes.

[1733] The device works in conjunction with devices such as activity trackers and smartwatches to automatically collect daily activity data (such as number of steps, heart rate, and sleep time).

[1734] The device uses a camera, microphone, and text input to collect the user's emotional data (facial expressions, tone of voice, and text input).

[1735] The collected data is periodically sent to a server.

[1736] 2. Server

[1737] The server receives the basic information, activity data, and emotion data sent from the terminal and stores them in a database.

[1738] The server uses machine learning algorithms to analyze the accumulated data and predict the user's future condition, for example, assessing future health risks based on current lifestyle habits and emotional state.

[1739] The prediction results are visualized and presented to the user in an easy-to-understand format.

[1740] 3. Emotion Engine

[1741] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state.

[1742] The emotion engine's analysis results are used to personalize suggested actions for the user, for example, relaxation suggestions when the user is feeling stressed.

[1743] 4. Users

[1744] Users can view the prediction results and their emotional state through a dashboard on their device, which is displayed in the form of graphs and statistical data.

[1745] Based on the prediction results and emotional state, users receive specific action suggestions to improve their lifestyle habits.

[1746] Program processing

[1747] Data Collection Phase

[1748] Terminal

[1749] The user enters basic information as the initial setting, including height, weight, education, smoking habits, and exercise frequency.

[1750] The device works in conjunction with activity monitors and smartwatches to collect activity data in real time.

[1751] It uses the camera, microphone, and text input to collect user emotional data.

[1752] Data transmission phase

[1753] Terminal

[1754] The collected basic information, activity data, and emotion data are periodically sent to a server, usually in a format such as JSON.

[1755] Data Management Phase

[1756] server

[1757] Receives the submitted data and stores it in a database, merging it with existing data and updating it with new data.

[1758] Maintain data consistency by integrating with past data.

[1759] Prediction Phase

[1760] server

[1761] It uses machine learning algorithms to analyze a user's current and past data and predict their future condition, for example, by considering their lifestyle habits and emotional state together to assess future health risks.

[1762] The prediction results are analyzed and actions are suggested to the user as necessary.

[1763] Sentiment Analysis Phase

[1764] Emotion Engine

[1765] Recognizes the user's emotional state by analyzing their facial expressions, tone of voice, and text input, for example, using image processing and natural language processing techniques.

[1766] Visualization phase

[1767] server

[1768] Based on the predictions and your emotional state, graphs and statistics are generated, including predictions of heart disease risk, weight change, and stress levels.

[1769] Terminal

[1770] The predictions and sentiment analysis results are displayed on a dashboard, allowing users to visually check them and adjust their actions as needed.

[1771] Specific examples

[1772] Example 1: Predicting health risks

[1773] Terminal

[1774] Users input their past health check results and daily emotional state (e.g., daily stress level and mood) into the app.

[1775] server

[1776] The server stores this information in a database and integrates it with existing lifestyle data.

[1777] It uses machine learning algorithms to predict future heart disease risk, and an emotion engine to analyze a user's stress state.

[1778] Terminal

[1779] The predicted heart disease risk and emotional state are displayed as a graph on the dashboard, for example, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years."

[1780] Based on this, users receive action suggestions to improve their exercise habits, diet, and stress management methods, and review their lives.

[1781] Example 2: Predicting weight change

[1782] Terminal

[1783] The user inputs their daily diet and exercise, as well as their emotional state for that day (e.g., happy, sad, angry).

[1784] server

[1785] The server analyzes the input data and predicts future weight changes and psychological states. It also uses an emotion engine to analyze the user's emotional state regarding food and exercise.

[1786] Terminal

[1787] The prediction results are displayed on a dashboard in the form of, for example, "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect your diet and exercise.

[1788] Users can use this information to plan their diet and exercise, and manage their emotions, thereby improving their lives more effectively.

[1789] Such a system allows users to understand in real time how their lifestyle habits and emotions affect their future, and to take concrete actions to build healthy lifestyles.

[1790] The processing flow will be explained below.

[1791] Step 1:

[1792] The user enters basic information such as health status, educational background, and lifestyle habits into the terminal.

[1793] Specifically, data such as "height," "weight," "smoking habits," and "exercise frequency" are entered into a form on the terminal application.

[1794] Step 2:

[1795] The device connects to devices such as activity trackers and smartwatches to collect daily activity data.

[1796] Specifically, data such as steps taken, heart rate, and sleep time is collected from the device via Bluetooth or Wi-Fi.

[1797] Step 3:

[1798] The device collects user emotional data using the camera, microphone, and text input.

[1799] Specifically, it uses facial recognition technology to analyze facial expressions, voice recognition technology to analyze tone of voice, and natural language processing to analyze emotions from text input.

[1800] Step 4:

[1801] The device transmits the collected basic information, activity data, and emotion data to the server.

[1802] Specifically, the data is formatted in JSON format and sent to the server using an HTTP POST request.

[1803] Step 5:

[1804] The server receives the transmitted data and stores it in a database.

[1805] Specifically, it parses the received JSON data and stores it in a database (e.g., MongoDB, MySQL) in the appropriate format.

[1806] Step 6:

[1807] The server applies machine learning algorithms to analyze the accumulated data.

[1808] Specifically, it combines past and present data and runs machine learning models such as regression analysis and clustering using, for example, Scikit-learn or TensorFlow.

[1809] Step 7:

[1810] The server applies an emotion engine to analyze the user's emotion data.

[1811] Specifically, the emotion engine analyzes the user's facial expressions, tone of voice, and text input and stores them in a database.

[1812] Step 8:

[1813] The server predicts the user's future state based on the results of machine learning and the emotion engine.

[1814] Specifically, the results of both analyses will be integrated to generate future health risks and action recommendations.

[1815] Step 9:

[1816] The server generates data for visualizing the prediction results.

[1817] Specifically, use a graph generation library (e.g., D3.js, Chart.js) to format the data to create line graphs and pie charts.

[1818] Step 10:

[1819] The graphs and statistical data generated by the server are sent to the terminal.

[1820] Specifically, the visualization data is formatted in JSON format and sent to the terminal using an HTTP POST request.

[1821] Step 11:

[1822] The device displays prediction results and sentiment analysis results on a dashboard.

[1823] Specifically, the received data is displayed as graphs and statistical data on the user interface using HTML and JavaScript.

[1824] Step 12:

[1825] The user sees the forecast results on the dashboard.

[1826] Specifically, the system looks at graphs of predicted health risks, weight changes, and emotional states to determine the necessary improvement actions.

[1827] Step 13:

[1828] The terminal notifies the user of specific suggested actions.

[1829] Specifically, the app will send action suggestions such as "exercise for 30 minutes three times a week" and "incorporate relaxation techniques to relieve stress" via push notifications and in-app messages.

[1830] Through this detailed processing step, the system allows users to understand their own health and emotional state in real time, predict future risks, and receive specific action suggestions.

[1831] Example 2

[1832] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1833] While conventional systems were capable of analyzing a user's basic information and activity information, they had the problem of not being able to make personalized suggestions that took into account the user's emotional state. This led to problems such as users overlooking health risks due to stress or emotional changes, or not being able to take effective actions. In addition, because the analysis results and suggested actions were displayed individually, it was difficult for users to grasp their overall health status.

[1834] 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.

[1835] In this invention, the server includes a means for inputting the user's basic information and activity information, a means for inputting the user's emotional state, and a means for accumulating and analyzing the transmitted data. This enables the user's basic information, activity information, and emotional state data to be analyzed in an integrated manner, enabling personalized behavioral suggestions. Furthermore, by displaying the analysis results and emotional state as graphs and statistical data on the display device of the user's terminal, the user can easily visually grasp changes in their own health condition and emotions. As a result, the user can more effectively manage health risks and work to improve their lifestyle habits.

[1836] "Basic user information" refers to personal information such as height, weight, educational background, smoking habits, and exercise frequency entered by the user.

[1837] "Activity information" refers to data on daily activities such as steps taken, heart rate, and sleep time collected from activity monitors and smartwatches.

[1838] "Emotional state" is data about emotions collected from a user's facial expressions, tone of voice, and text input.

[1839] "Input means" refers to the interface through which a user inputs data, such as a form, checkboxes, camera, or microphone.

[1840] "Means for transmitting" refers to the communication protocol or communication module used to transmit collected data to the server.

[1841] "Means of storage and analysis" refers to the server's function of storing received data in a database and analyzing the data using machine learning algorithms and data analysis tools.

[1842] "Means for predicting a user's future health risks and lifestyle changes" refers to the process of using a machine learning model to predict a user's future health risks and lifestyle changes based on the user's past and current data.

[1843] "Means for suggesting actions" refers to functions, such as notifications and alerts, that suggest specific actions to the user based on the prediction results.

[1844] "Display device" refers to a screen or display that allows a user to visually confirm analysis results and suggestions.

[1845] This system collects basic information, activity information, and emotional state of a user, predicts the user's future state based on this information, and proposes specific actions. In particular, by combining it with an emotion engine, personalized proposals that take the user's emotions into consideration are realized.

[1846] Basic system configuration

[1847] 1. Terminal

[1848] The device provides a user interface for users to input basic information, including forms and checkboxes. It also connects with devices such as activity trackers and smartwatches to collect activity information in real time. It also uses a camera, microphone, and text input to collect the user's emotional state. The collected data is periodically sent to a server.

[1849] 2. Server

[1850] The server receives basic information, activity information, and emotion data sent from the device and stores them in a database. It also uses machine learning algorithms to analyze the accumulated data and predict the user's future state. The prediction results are visualized and provided to the user in an easy-to-understand format.

[1851] 3. Emotion Engine

[1852] The emotion engine analyzes the user's facial expressions, tone of voice, and text input to recognize their emotional state, using image processing and natural language processing techniques, and the results of the analysis are used to personalize suggested actions for the user.

[1853] 4. Users

[1854] Users can check their prediction results and emotional state through the device's dashboard. The prediction results are displayed in the form of graphs and statistical data. Based on the prediction results and emotional state, users can receive specific action suggestions to improve their lifestyle habits.

[1855] Specific actions

[1856] Example 1: Predicting health risks

[1857] Users enter their past health checkup results and daily emotional state into the app. The server stores this information in a database and integrates it with existing lifestyle data. A machine learning algorithm is used to predict future heart disease risk. An emotion engine is also used to analyze the user's stress level. The device displays the predicted heart disease risk and emotional state as a graph on a dashboard. For example, it might say, "If you continue your current lifestyle and high stress levels, your risk of heart disease will increase by 20% within five years." Based on this, users receive action suggestions for improving their exercise habits, diet, and stress management methods.

[1858] Example 2: Predicting weight change

[1859] The user inputs their daily diet and exercise routine, as well as their emotional state for that day. The server analyzes the input data and predicts future weight changes and their psychological state. It also uses an emotion engine to analyze the user's emotional state regarding diet and exercise. The device displays the predicted results on a dashboard, such as "If you continue your current lifestyle and emotional state, you will gain 5 kg in three months." It also shows how emotions affect diet and exercise. Users can use this information to create dietary restrictions and exercise plans, and manage their emotions.

[1860] Example prompt

[1861] "Use the user's lifestyle data to predict future health risks and suggest specific actions to improve them."

[1862] "Analyze user sentiment data and provide personalized health recommendations based on it."

[1863] The system allows users to understand in real time how their lifestyle habits and emotions affect their future, and take concrete actions to build healthy lifestyle habits.

[1864] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1865] Step 1:

[1866] Enter basic information

[1867] The device provides a screen where the user can enter basic information (height, weight, educational background, smoking habits, exercise frequency, etc.). The user enters this information into a form. The input data is temporarily stored in local storage or device memory. This allows the basic information to be collected.

[1868] Input: User's height, weight, education, smoking habits, and exercise frequency

[1869] Output: Basic information data stored in the device

[1870] Step 2:

[1871] Collection of activity information

[1872] The device collects real-time activity information (number of steps, heart rate, sleep time, etc.) from activity monitors and smartwatches via Bluetooth or Wi-Fi. This data is updated at regular intervals and stored internally on the device.

[1873] Input: Activity information obtained from activity trackers and smartwatches

[1874] Output: Activity information data stored in the device

[1875] Step 3:

[1876] Collecting emotional states

[1877] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and collects this as emotional data. In addition, text data entered by the user is also collected as emotional data.

[1878] Input: facial expression data obtained from a camera or microphone, voice data, and text data entered by the user

[1879] Output: Emotion data stored in the device

[1880] Step 4:

[1881] Data transmission

[1882] The device periodically transmits the collected basic information, activity information, and emotion data to a server, structured in a standard format such as JSON, using a secure communication protocol.

[1883] Input: Basic information, activity information, and emotional data stored on the device

[1884] Output: Various data sent to the server

[1885] Step 5:

[1886] Receiving and storing data

[1887] The server receives the data sent from the device. The received data is stored in a dedicated database (e.g., MySQL, MongoDB), and is updated by integrating it with past data.

[1888] Input: Basic information, activity information, and emotional data sent from the device

[1889] Output: Various data stored in the server database

[1890] Step 6:

[1891] Running the prediction algorithm

[1892] The server analyzes the received data using machine learning models (e.g., TensorFlow, PyTorch), and predicts future health risks and weight changes based on the user's lifestyle and emotional state.

[1893] Input: Basic information, activity information, and emotion data stored in the database

[1894] Output: Predicted health risks and weight change data

[1895] Step 7:

[1896] Performing sentiment analysis

[1897] The emotion engine analyzes facial expressions, voice, and text data sent from the device, and uses image processing technology (e.g., OpenCV) and natural language processing technology (e.g., NLTK, spaCy) to identify the device's emotional state.

[1898] Input: facial expression data, voice data, text data

[1899] Output: Recognized emotional state data

[1900] Step 8:

[1901] Visualizing the results

[1902] The server generates graphs and statistical data based on the prediction results and emotional states (e.g., Matplotlib, D3.js), which makes it easier for users to understand visually.

[1903] Input: predicted health risk, weight change data, emotional state data

[1904] Output: Visualized graphs and statistical data

[1905] Step 9:

[1906] Viewing the Dashboard

[1907] The device displays the analysis results and prediction data sent from the server as a dashboard, allowing users to check their own predictions and sentiment analysis results.

[1908] Input: Analysis results and prediction data sent from the server

[1909] Output: Analysis results and forecast data displayed on a dashboard

[1910] Step 10:

[1911] action suggestion

[1912] The device will suggest specific actions based on the predictions and your emotional state, such as "take 10 minutes of deep breathing exercises to relax."

[1913] Input: Prediction result, emotional state

[1914] Output: Specific action suggestions provided to the user

[1915] Through each of the above steps, users can understand in real time how their lifestyle habits and emotions affect their future and take concrete action.

[1916] (Application example 2)

[1917] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1918] Conventional online shopping sites lack personalized product recommendations that take into account the user's health and emotional state. In particular, they are unable to provide appropriate product suggestions to reduce stress and health risks, making it difficult for users to find the products they truly need. In addition, understanding a user's emotional state in real time and recommending products accordingly is a challenge.

[1919] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1920] In this invention, the server includes a means for inputting basic information and activity data of a user, a means for analyzing the emotional state of the user using an emotion engine, a means for recommending personalized products to the user based on the basic information, activity data, and emotional state, and a means for displaying the recommendation results on the smart glasses, thereby enabling reliable product recommendations based on the user's health condition and emotional state.

[1921] (Word definition)

[1922] "Basic information of a user" refers to basic information related to an individual, such as the user's height, weight, age, lifestyle, and health condition.

[1923] "Activity data" is data related to the user's daily activities, and includes, for example, the number of steps taken, the amount of exercise, the heart rate, and the amount of sleep.

[1924] "Server" means a computer system on a network that stores and analyzes collected data.

[1925] An "emotion engine" is an algorithm or software that recognizes a user's emotional state by analyzing data such as facial expressions, tone of voice, and text input collected from sensors such as cameras and microphones.

[1926] The "prediction means" is a means for predicting the user's future state using a machine learning algorithm based on the collected basic information, activity data, and emotion data.

[1927] A "means for recommending personalized products" is a means for selecting and recommending products suitable for individual users by taking into consideration the user's basic information, activity data, and emotional state.

[1928] "Smart glasses" are eyeglass-type wearable devices with a built-in display device that can display information directly in the user's field of vision.

[1929] The "result display means" is a means for visually displaying prediction results and product recommendation results on the user's device.

[1930] The system for realizing this application example is configured as follows.

[1931] First, the core hardware of the system consists of a server, smart glasses, an activity tracker, a smartwatch, a camera, and a microphone. The server is responsible for storing data, analyzing it, and sending the results, while the smart glasses are responsible for displaying the data. The activity tracker and smartwatch collect the user's activity data, and the camera and microphone collect emotion data.

[1932] The system includes the following main software components:

[1933] 1. Data collection software: Collects basic user information, activity data, and emotional data using a camera and microphone.

[1934] 2. Data transmission software: periodically transmits collected data to the server.

[1935] 3. Database software: stores and manages the transmitted data.

[1936] 4. Machine learning algorithms: These run on the server and analyze the collected data to predict the user's future state.

[1937] 5. Sentiment Engine: A software component for performing sentiment analysis.

[1938] 6. Product recommendation software: Selects and recommends the most suitable products based on the user's health and emotional state.

[1939] 7. Display software: Visually display the product recommendation results on the smart glasses.

[1940] Data collection

[1941] The user wears the smart glasses and inputs basic information and activity data. The activity tracker or smartwatch automatically collects the user's daily activity data (e.g., number of steps, heart rate, and sleep time). The camera and microphone also analyze the user's facial expressions and tone of voice to collect their emotional state. The collected data is periodically sent to a server and stored in a database.

[1942] Data analysis

[1943] The server uses machine learning algorithms to analyze the accumulated basic information, activity data, and emotional data. The analysis results are used to predict the user's future health and emotional state. Furthermore, an emotion engine analyzes the user's real-time emotional state and makes product recommendations based on this.

[1944] Product recommendation

[1945] The server selects personalized products for the user based on the prediction results and the emotional state, and sends the recommendation results to the smart glasses via the product recommendation software.

[1946] display

[1947] The smart glasses visually display recommended products, allowing users to easily obtain product information based on their health and emotional state.

[1948] For example, when a user is feeling stressed, the emotion engine analyzes the user's stress level and recommends relaxation products and calming clothing. The results are displayed on the smart glasses, allowing the user to check in real time which products are suitable for their emotional state.

[1949] (Example of a prompt)

[1950] When the user feels stressed, a prompt is displayed that takes into account health risks: "Recommend relaxation products based on my health condition and emotions."

[1951] This enables personalized product recommendations based on the user's health and emotional state, contributing to improving the user's lifestyle habits.

[1952] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1953] Step 1:

[1954] The user puts on the smart glasses and inputs basic information, such as height, weight, age, lifestyle habits, and health status, into the application form. This information is then stored on the device.

[1955] Input: Basic information such as height, weight, age, lifestyle habits, and health condition

[1956] Output: Saved basic information data

[1957] Step 2:

[1958] Activity trackers and smartwatches collect users' activity data in real time, including the number of steps taken, heart rate, and sleep time. This data is also sent to the device and stored.

[1959] Input: User's daily activity data (number of steps, heart rate, sleep time, etc.)

[1960] Output: Saved activity data

[1961] Step 3:

[1962] The smart glasses' cameras and microphones capture the user's facial expressions and tone of voice to collect emotional data, which is then analyzed in real time by an emotion engine.

[1963] Input: Facial expression, tone of voice data

[1964] Output: Parsed emotion data

[1965] Step 4:

[1966] The device periodically sends the collected basic information, activity data, and emotion data to the server in JSON format.

[1967] Input: Basic information, activity data, emotion data

[1968] Output: Data sent to the server

[1969] Step 5:

[1970] The server receives the submitted data and stores it in a database, which centralizes the user's entire data set.

[1971] Input: Data received from the terminal

[1972] Output: Consolidated data stored in a database

[1973] Step 6:

[1974] Machine learning algorithms on the server use information from the database to predict a user's future health status, for example assessing their risk of heart disease based on their lifestyle habits and emotional state.

[1975] Input: Integrated data stored in a database

[1976] Output: predicted health state

[1977] Step 7:

[1978] The emotion engine analyzes collected facial expression and tone of voice data to understand the user's current emotional state.

[1979] Input: Facial expression, tone of voice data

[1980] Output: Current emotional state

[1981] Step 8:

[1982] The server then recommends personalized products to the user based on their predicted health and emotional state, for example, recommending relaxation products if the user is feeling stressed.

[1983] Input: predicted health status, current emotional state

[1984] Output: A list of recommended products

[1985] Step 9:

[1986] The server sends the recommended product list to the smart glasses.

[1987] Input: Recommended product list

[1988] Output: Product information sent to smart glasses

[1989] Step 10:

[1990] The smart glasses will display the recommended products in the user's field of view, allowing the user to visually confirm and select the products as needed.

[1991] Input: Product information sent from the server

[1992] Output: Product information displayed on smart glasses

[1993] This allows users to receive personalized product recommendations based on their health and emotional state, making it easier to find more suitable products.

[1994] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1995] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1996] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1997] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1998] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1999] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2000] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2001] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2002] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2003] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2004] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2005] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2006] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2007] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2008] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2009] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2010] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2011] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2012] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2013] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2014] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2015] The following is further disclosed regarding the above embodiment.

[2016] (Claim 1)

[2017] a means for inputting user basic information and activity data;

[2018] means for transmitting the basic information and activity data to a server;

[2019] means for storing and analyzing the transmitted data;

[2020] A means for predicting the user's future state from the analysis results;

[2021] means for presenting the prediction result to a user and suggesting an action;

[2022] A system including:

[2023] (Claim 2)

[2024] The system according to claim 1, further comprising means for making suggestions for improving the user's health risks and lifestyle habits based on the basic information and activity data.

[2025] (Claim 3)

[2026] The system according to claim 1, further comprising means for displaying the prediction results as graphs and statistical data on a dashboard of a user's terminal.

[2027] "Example 1"

[2028] (Claim 1)

[2029] a means for inputting user basic information and activity data;

[2030] means for transmitting the basic information and activity data to a server;

[2031] a means for accumulating the transmitted data and storing it in a database while maintaining its integrity;

[2032] A means for analyzing the accumulated data and predicting the user's future state using a machine learning algorithm;

[2033] a means for visualizing the prediction results as graphs or statistical data and presenting them to a user;

[2034] a means for generating a specific action proposal based on the visualized prediction result and notifying the user of the action proposal;

[2035] A system including:

[2036] (Claim 2)

[2037] 2. The system according to claim 1, further comprising means for analyzing the user's health risks based on the basic information and activity data and making suggestions for improving lifestyle habits.

[2038] (Claim 3)

[2039] The system according to claim 1, further comprising means for displaying the prediction results as graphs and statistical data on a dashboard of a user's terminal.

[2040] "Application Example 1"

[2041] (Claim 1)

[2042] a means for inputting user basic information and activity data;

[2043] means for transmitting the basic information and activity data to a server;

[2044] means for storing and analyzing the transmitted data;

[2045] A means for predicting the user's future state from the analysis results;

[2046] means for presenting the prediction result to a user and suggesting an action;

[2047] A means for proposing an optimal meal plan to a user based on the basic information and activity data;

[2048] A system including:

[2049] (Claim 2)

[2050] The system according to claim 1, further comprising means for making suggestions for improving the user's health risks and lifestyle habits based on the basic information and activity data.

[2051] (Claim 3)

[2052] The system according to claim 1, further comprising means for displaying the prediction results as graphs and statistical data on a dashboard of a user's terminal.

[2053] "Example 2: Combining Emotion Engines"

[2054] (Claim 1)

[2055] A means for inputting basic information and activity information of a user;

[2056] means for transmitting the basic information and activity information to a server;

[2057] a means for inputting a user's emotional state;

[2058] means for transmitting the basic information, activity information, and emotional state to a server;

[2059] means for storing and analyzing the transmitted data;

[2060] A means for predicting future health risks and lifestyle changes of the user based on the analysis results;

[2061] means for presenting the prediction result and the emotional state to the user and suggesting an action;

[2062] A system including:

[2063] (Claim 2)

[2064] The system according to claim 1, further comprising means for making suggestions for improving the user's health risks and lifestyle habits based on the basic information, activity information and emotional state.

[2065] (Claim 3)

[2066] 2. The system according to claim 1, further comprising means for displaying the prediction results and emotional state as graphs and statistical data on a display device of a user's terminal.

[2067] "Application example 2 when combining emotion engines"

[2068] (Claim 1)

[2069] a means for inputting user basic information and activity data;

[2070] means for transmitting the basic information and activity data to a server;

[2071] means for storing and analyzing the transmitted data;

[2072] A means for predicting the user's future state from the analysis results;

[2073] means including an emotion engine for analyzing an emotional state of a user;

[2074] means for recommending personalized products to a user based on the prediction result and the user's emotional state;

[2075] means for displaying the recommendation results on smart glasses;

[2076] A system including:

[2077] (Claim 2)

[2078] The system according to claim 1, further comprising means for providing suggestions for improving the user's health risks and lifestyle habits based on the basic information, activity data and emotional state.

[2079] (Claim 3)

[2080] The system of claim 1, further comprising: means for displaying the recommendation result based on the prediction result and the emotional state on the user's smart glasses. [Explanation of symbols]

[2081] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for inputting user basic information and activity data; means for transmitting the basic information and activity data to a server; means for storing and analyzing the transmitted data; A means for predicting the user's future state from the analysis results; means for presenting the prediction result to a user and suggesting an action; A system including:

2. The system according to claim 1 , further comprising means for making suggestions for improving the user's health risks and lifestyle habits based on the basic information and activity data.

3. The system according to claim 1 , further comprising means for displaying the prediction results as graphs and statistical data on a dashboard of a user's terminal.

Images