system

Abstract

We provide the system. [Solution] A means for collecting health-related information from wearable devices and information processing devices, A means for integrating collected health-related information, correcting outliers, and imputing missing values, A means of predicting health risks using generative artificial intelligence technology and statistical models based on integrated health-related information, A means of generating personalized preventive measures in response to predicted health risks and presenting them through visual and notification functions, Means for data encryption and access control for the protection and management of health information, A means of monitoring the health status of the entire urban population and providing information for collective health management, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, the prevention of lifestyle diseases and chronic diseases is emphasized, but there is a problem that the prediction of health risks for individual users and the provision of preventive measures based on such predictions are insufficient. Conventional health management systems only provide general health advice and cannot present specific intervention measures considering individual health conditions. Also, the privacy protection of the collected health data is not sufficient, and providing a system that can be used with confidence is also an issue.

Means for Solving the Problems

[0005] This invention provides a means for integrating health-related data collected from wearable devices and information terminals, correcting for outliers and imputing missing values, and then using generative AI technology and statistical models to perform personalized health risk predictions. Based on these predictions, it is possible to prevent the onset of lifestyle-related diseases and chronic illnesses by generating specific preventive measures regarding exercise, nutrition, and sleep that are appropriate for each user. Furthermore, by including data encryption and management means, the invention ensures the privacy of user data and guarantees a system that can be used with peace of mind.

[0006] A "wearable device" is an electronic device that can be worn on a user's body for everyday use and that can collect health-related data in real time.

[0007] An "information terminal" is an electronic device that has the ability to acquire, process, and display digital data, and functions as an interface with the user.

[0008] "Health-related data" refers to various pieces of information related to a user's health status and lifestyle, such as exercise, heart rate, sleep patterns, weight, and blood pressure.

[0009] "Integration" is the process of centrally managing data collected from different sources and making it usable.

[0010] "Generative AI technology" refers to techniques that use machine learning and deep learning to generate predictive models and decision-making models.

[0011] A "statistical model" is a mathematical model used to analyze data using statistical methods and to make specific predictions or inferences based on the results.

[0012] "Health risk prediction" is the process of predicting the likelihood of a specific health condition or disease occurring based on data.

[0013] "Personalized preventative measures" refer to specific health maintenance suggestions and behavioral guidance that are specially designed based on each user's health status, lifestyle, and risk assessment.

[0014] "Data encryption" is a technology that transforms digital information using a specific encryption method in order to protect it from unauthorized access.

[0015] "Management measures" refer to methods and systems for properly handling and storing collected data. [Brief explanation of the drawing]

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

Embodiments for Carrying out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the 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 processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0037] This invention provides users with personalized preventative measures for health management based on a wide variety of health-related data acquired from wearable devices and information terminals. The following means are necessary to implement the invention.

[0038] First, the device has the function of collecting health data from the user, which is achieved through sensors built into wearable devices or smartphones. This data includes steps taken, heart rate, sleep patterns, body temperature, blood pressure, etc. It also acquires electronic health records, such as blood test results, provided by medical institutions as needed.

[0039] Next, the server receives the collected data and uses data integration means to integrate and preprocess it. It detects and corrects outliers, imputes missing values, and processes the data so that it is suitable for analysis.

[0040] Subsequently, the server uses the compiled health-related data, employing generative AI technology and statistical models to predict specific health risks for each user. For example, the risk of developing lifestyle-related diseases such as cardiovascular disease and diabetes is assessed. This assessment is based on a model trained on historical datasets, enabling highly accurate predictions.

[0041] Furthermore, the server generates appropriate preventative measures for each user based on the predicted risk. These preventative measures include specific recommendations related to exercise, diet, and sleep. For example, high-risk users may receive suggestions for specific exercise plans and dietary restrictions.

[0042] The generated preventative measures are presented to the user via the device. The device's user interface is intuitive and designed to be easily understood and implemented by the user. Notification and reminder features are used to support the user in forming healthy habits.

[0043] Finally, the server encrypts all collected health-related data and controls data access to protect the data. This ensures user privacy and allows users to use the system with peace of mind.

[0044] Thus, in order to implement the invention, all stages, from data collection and risk prediction to suggesting preventive measures and protecting data privacy, must be carried out in coordination. For example, a user who is predicted to be at risk of cardiovascular disease may be notified of a recommendation to do more than 150 minutes of aerobic exercise per week and advised to limit salt intake in their diet. With such specific instructions, users can take actions to improve their health and reduce their risk of lifestyle-related diseases.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The device collects user health-related data through wearable devices and smartphones. This data is acquired in real time and includes steps taken, heart rate, sleep duration, and calorie consumption. Furthermore, through collaboration with medical institutions, it can receive electronic health records with the user's permission.

[0048] Step 2:

[0049] The server receives health-related data sent from the terminal. Since the received data may be in different formats, it is first converted to a standardized format. Next, the collected data is cleaned to detect and correct outliers, and missing values ​​are imputed using past data or average values.

[0050] Step 3:

[0051] The server uses generated AI and statistical models based on the cleaned data to predict the user's future health risks. This process individually assesses the risk of developing specific diseases (e.g., cardiovascular disease, diabetes) through analysis of the user's historical data and similar past cases. This makes it possible to quantitatively understand the user's future health status.

[0052] Step 4:

[0053] The server generates personalized preventative measures tailored to the predicted health risks. These measures may include recommendations for exercise frequency and amount, dietary changes, and improvements to sleep patterns. For specific risks, it may also recommend consulting a doctor or undergoing additional tests.

[0054] Step 5:

[0055] The device notifies the user of preventative measures generated from the server. These notifications are delivered via an interactive interface, providing visual and audio feedback. Users can use this information to adjust their daily behavior. The device also provides a reminder function, periodically informing the user of actions that should be taken.

[0056] Step 6:

[0057] The server implements data encryption and access control throughout the entire system to protect user data privacy. It also establishes a process to provide users with transparent information about what data is collected and how it is used, and to obtain their consent for its use.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In modern society, sophisticated health management tailored to individual lifestyles and health conditions is required. However, effectively collecting and analyzing diverse health-related data and providing personalized preventive measures is not easy, and an efficient system is needed. Furthermore, ensuring user privacy while providing reliable health risk assessments and concrete preventive measures is a challenge.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for acquiring information on the user's physical activity and physiological state, means for integrating the acquired information, detecting and adjusting for anomalies, and estimating missing values, and means for predicting health risks using machine learning techniques and statistical inference generated based on the integrated information. This enables the user to receive a more accurate assessment of health risks and personalized preventive measures.

[0063] "Information about the user's physical activity and physiological state" refers to data such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure, which are collected to understand an individual's health status.

[0064] "Means of acquisition" refers to technologies for collecting users' health-related data in real time through information gathering devices such as wearable devices and smartphones.

[0065] "Means for integrating, detecting and adjusting for anomalies, and estimating missing values" refers to the process of combining health-related information collected from multiple data sources, supplementing data gaps, and preparing it for analysis.

[0066] "Machine learning techniques and statistical inference" are methods for learning patterns from past data and predicting future outcomes based on new data.

[0067] "Methods for predicting health risks" refer to the process of using machine learning techniques and statistical models to assess the likelihood of future illness based on an individual's health status.

[0068] "Personalized preventative measures" are specific recommendations regarding exercise, diet, and lifestyle improvements that are provided to address the user's specific health risks.

[0069] A "server" is a central system that analyzes and predicts the collected data and provides results to users.

[0070] An "information terminal" is an electronic device used to display information to a user and send notifications, and includes smartphones and tablet computers.

[0071] "Data encryption and access control measures" refer to security technologies that encrypt collected data and prevent unauthorized access in order to protect user privacy.

[0072] This system is realized by collecting health-related data using information terminals and wearable devices, and performing advanced analysis based on that data, in order to personalize users' health management.

[0073] The devices used are primarily wearable devices and smartphones. These devices use built-in sensors to acquire information about physical activity and physiological states, such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure. This data is transmitted to a server in real time via Bluetooth or Wi-Fi.

[0074] The server integrates the received data, detecting and correcting outliers and estimating missing values. The integrated information is then used in a process to predict health risks, employing machine learning techniques and statistical inference. The generated AI model learns from previously collected datasets to achieve precise risk assessments. High-performance cloud computing services are typically used for this process.

[0075] Based on predicted health risks, the server generates personalized preventative measures for each user. These include exercise plans, nutritional guidance, and sleep improvement suggestions, and the generated preventative measures are sent to the device in an intuitive and easy-to-understand format.

[0076] Users receive notifications about preventative measures through their information terminals and have the opportunity to improve their lifestyles by following the provided guidelines. The terminal's user interface is designed to be integrated into daily routines, utilizing pop-up notifications and reminder functions.

[0077] A crucial aspect of the data in this system is data confidentiality and the protection of user privacy. The collected information is securely managed on the servers using advanced encryption technology to prevent unauthorized access and provide a safe environment for users.

[0078] As a concrete example, the following prompt could be used as input to a generative AI model: "Please propose a health risk assessment and preventive measures for a 40-year-old male user who takes fewer than 5,000 steps per day on average and performs less than 30 minutes of aerobic exercise once a week." Based on this prompt, the AI ​​would analyze relevant data and provide the user with a specific and effective health management plan.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The device collects user health-related data. Using wearable devices and smartphones, it obtains information such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure. The input to this process is raw data from sensors, and the output is a set of collected data. This dataset is then ready to be transmitted to the next processing step via Bluetooth or Wi-Fi.

[0082] Step 2:

[0083] The server receives health-related data sent from the terminal. It then detects anomalous data points and corrects them using algorithms. If there is missing data, it estimates and fills in its values ​​using statistical methods. The input is the raw data from the terminal, and the output is the cleaned and imputed dataset.

[0084] Step 3:

[0085] The server applies a generative AI model using prepared data to predict health risks. It assesses the risk of specific diseases and health conditions (e.g., cardiovascular disease, diabetes) and generates results. The input is a pre-processed dataset, and the output is a user-specific risk assessment. The AI ​​model is trained on a vast amount of historical data, enabling it to predict risks with high accuracy.

[0086] Step 4:

[0087] The server generates personalized preventative measures based on predicted health risks. These preventative measures include specific recommendations regarding exercise, diet, and sleep. The input is a health risk assessment, and the output is a set of recommendations for the user. This content is customized to the user's lifestyle.

[0088] Step 5:

[0089] The generated preventative measures are presented to the user via the device. The device visually displays the information and sends important health recommendations to the user as pop-up notifications and reminders. The input is a set of recommendations from the server, and the output is an intuitive interface that the user can easily understand. Based on this, the user can decide on and take healthy behaviors.

[0090] Step 6:

[0091] The server encrypts all collected health-related data and implements access control to protect user privacy. Input is the user's health-related data, and output is encrypted and securely stored data. This process allows users to provide data and use the system with confidence.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] While managing health risks using individual health data has become widespread in modern society, there is a challenge in the lack of sufficient collective health management methods to improve the health of the entire population of a city. Beyond individual health advice, there is a need to establish methods for understanding the health status of the entire city and promoting the health of all residents.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for collecting health-related information from wearable devices and information processing devices, means for integrating the collected health-related information, correcting outliers and filling in missing values, and means for monitoring the health status of the entire urban population and providing information for collective health management. This makes it possible to provide a comprehensive healthcare system aimed at promoting the health of the entire population, as well as individual health management.

[0097] A "wearable device" is an electronic device that a user can wear on their body and that has the function of measuring and collecting health-related information.

[0098] An "information processing device" is an electronic device that can receive data and perform calculations, and it plays a role in managing health-related information.

[0099] "Health-related information" refers to data about an individual's physical condition and lifestyle, and specifically includes indicators such as heart rate, steps taken, sleep patterns, blood pressure, and body temperature.

[0100] "Integration" refers to the process of combining and organizing data obtained from different formats or sources into a single format.

[0101] "Correction of outliers" refers to the process of detecting values ​​in the collected data that deviate from the normal range, removing their influence, and adjusting the data to a format suitable for analysis.

[0102] "Missing value imputation" is a technique for filling in data that is not recorded or is missing in a dataset, in order to construct a complete dataset.

[0103] "Generative artificial intelligence technology" is a technology that uses computer programs and algorithms to learn patterns based on data and make predictions and recommendations.

[0104] "Health risk" is an assessment indicator that shows the probability of an individual developing a specific disease or experiencing a deterioration in their health.

[0105] "Personalized preventive measures" refer to specific advice and action plans designed specifically for an individual to maintain and improve their health.

[0106] "Presenting information visually and through notification features" refers to features that display information using the device screen or use sound and vibration to inform the user of important information.

[0107] "Data encryption" is a technology that transforms data to protect its confidentiality and safeguard it from unauthorized access.

[0108] "Access control" refers to a security management technique that restricts access to specific data or systems to only authorized users.

[0109] "Monitoring the health status of the entire urban population" is a process of comprehensively monitoring and analyzing the health status of all people living in a given city.

[0110] "Providing information for collective health management" refers to providing data and analysis results to assess health conditions at the city or community level and to formulate policies and initiatives aimed at improving the health of the entire population.

[0111] The system implementing the present invention collects health-related information via a wearable device and an information processing device, and performs centralized processing on a server.

[0112] The server receives data from wearable devices and information processing devices using Bluetooth or Wi-Fi technology. The wearable devices used incorporate heart rate sensors and accelerometers, and have the function of continuously measuring the user's daily activity metrics. The smartphone, acting as the information processing device, functions as the interface with the user and has applications installed for displaying data and providing notifications.

[0113] The received health-related information is stored in the server's database and preprocessed using the Pandas library. This automatically corrects for outliers and imputes missing values, preparing a dataset suitable for advanced analysis. Subsequently, a generative AI model using TENSORFLOW® predicts health risks for individual users. This model is trained on historical data and can predict, for example, the risk of cardiovascular disease with high accuracy.

[0114] Personalized preventative measures are generated for each user based on predicted risks. Specific advice on exercise metrics and nutritional content is provided through the application. This allows users to understand their own health status and take appropriate health management actions.

[0115] Furthermore, the server generates data that contributes to the formulation of public policies based on the collective health status of the entire city. The data collected from residents is comprehensively analyzed and used for smart city health initiatives.

[0116] For example, if a user's heart rate remains higher than normal for an extended period, notifications regarding appropriate breathing techniques and stress management will be sent to their smartphone. An example of a prompt message might be, "Based on the user's heart rate and step count data, generate relevant health risks and optimal preventative measures." The generating AI model then performs the analysis according to these instructions.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The device collects health-related information from the user's wearable device. Inputs include sensor data such as heart rate, steps, and sleep patterns, which are then transferred to a smartphone via Bluetooth or Wi-Fi. Outputs are the initial, unprocessed data stored in the device.

[0120] Step 2:

[0121] The device transmits collected health-related information to the server. The input is unprocessed health data within the device, and the output is raw data received by the server. An internet connection is used for data transmission.

[0122] Step 3:

[0123] The server stores the received health-related information in a database. The input is raw data sent from the terminal, and the output is a queryable database state. This ensures data persistence.

[0124] Step 4:

[0125] The server uses the Pandas library to preprocess the data. The input is raw data read from the database, and outlier correction and missing value imputation are performed automatically. The output is a well-prepared dataset ready for analysis.

[0126] Step 5:

[0127] The server uses TensorFlow to apply a generative AI model and predict individual health risks from a prepared dataset. The input is prepared health data, and the AI ​​model analyzes this data to output the probability of health risk.

[0128] Step 6:

[0129] The server generates optimal preventative measures for the user based on predicted health risks. The input is the probability of health risk, and the output is information such as specific exercise plans and nutritional advice. Individual preventative measures are designed using prompts from the generating AI model.

[0130] Step 7:

[0131] The server sends the generated preventative measures to the terminal, which then displays the information visually. The input is specific preventative measures, and the output is notifications and information displayed on the terminal. The user then uses this information to manage their health.

[0132] Step 8:

[0133] The server securely processes all transactions using data encryption technology and manages access control. Inputs are unencrypted health-related data, while outputs are encrypted data accessible only to users with access rights.

[0134] Step 9:

[0135] The server provides urban authorities with statistical analysis results to support collective health management. The input is integrated data for the entire population, and the output is policy recommendations and improvement proposals based on the overall health status of the city. This can then be used to develop health policies for smart cities.

[0136] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0137] This invention is a system that predicts health risks based on the user's health-related data, recognizes the user's emotional state, and reflects the results in preventative measures. The aim is to achieve more personalized and appropriate health management. The system is implemented as follows:

[0138] First, the device collects the user's daily physical data using wearable devices and information terminals. This includes heart rate, steps taken, and sleep data. It also captures emotional states from voice and facial expression data acquired by microphones and cameras. Based on this data, the device gains a detailed understanding of the user's current health and emotional state.

[0139] Next, the server receives health and emotional data collected from the terminals and first corrects for outliers and imputes missing values. This process enables analysis based on highly accurate data. Then, using generative artificial intelligence technology and statistical models, health risks are predicted. The predicted risks are evaluated for diseases such as cardiovascular disease and diabetes.

[0140] The server further analyzes the user's emotional state using an emotion engine. Here, it evaluates the user's voice tone, facial expressions, and biometric responses from sensors to determine their current emotion. For example, if stress or anxiety levels are high, this is taken into account when adjusting risk assessments and preventative measures.

[0141] Next, based on the obtained risk assessment and emotional state, the server generates personalized preventative measures. These measures include specific advice on exercise and diet, as well as suggestions to support the user's mental health. For example, a user experiencing high stress levels might be advised on the importance of relaxation exercises and rest.

[0142] The device notifies users of generated preventative measures and presents them through the user interface. It adjusts the tone and timing of notifications based on the user's emotional state, providing information in a way that is more likely to be taken action. This user-friendly interface supports users in their daily health management.

[0143] Finally, the server implements data encryption and strict access controls to ensure the protection of data across the entire system. This allows users to be assured that their health and emotional data is handled securely and to use the system with peace of mind.

[0144] This system allows users to access not only physical health management but also approaches necessary for improving their emotional state, leading to an overall improvement in their well-being. For example, during periods of heightened anxiety, the system may suggest special relaxation techniques and adjust the schedule to ensure the user has the necessary time to relax.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The device collects the user's daily health-related data using wearable devices and smartphones. This includes physical data such as steps taken, heart rate, and sleep duration. It also uses the device's microphone and camera to capture the user's voice and facial expression data, collecting initial data on their emotional state.

[0148] Step 2:

[0149] The server receives health-related and emotional data transmitted from terminals. This data is first centralized, and then anomalies are detected and corrected, and missing values ​​are imputed to ensure data integrity. This prepares clean data suitable for analysis.

[0150] Step 3:

[0151] The server uses generative AI technology and statistical models to analyze integrated health-related data and predict specific health risks. This is a process of quantitatively assessing the risk of developing diseases such as hypertension and diabetes.

[0152] Step 4:

[0153] The server uses an emotion engine to recognize the user's emotional state from acquired voice and facial expression data. For example, it analyzes stress levels and changes in emotional state from voice tone and facial expressions to identify the current emotional state.

[0154] Step 5:

[0155] The server comprehensively considers predicted health risks and perceived emotional states to generate personalized preventative measures tailored to the user. These measures include advice on managing physical health and suggestions for relaxation techniques and meditation exercises to support emotional well-being.

[0156] Step 6:

[0157] The device notifies the user of the generated preventative measures. The user interface is user-friendly and designed to be easily understood and implemented. Furthermore, the timing and content of notifications are appropriately adjusted to take the user's emotional state into consideration.

[0158] Step 7:

[0159] The server encrypts collected health and emotional data to protect the entire system's data, ensuring user privacy. Strict access control is also maintained to prevent misuse of data.

[0160] This process allows users to comprehensively understand their own health status and take preventative measures, thereby maintaining their health both physically and emotionally.

[0161] (Example 2)

[0162] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0163] In recent years, as the importance of health management and mental healthcare has increased, providing personalized approaches to users has become crucial. However, traditional systems have struggled to integrate health and emotional data and propose optimal preventative measures for individual users. Furthermore, there has been the challenge of insufficient data privacy guarantees.

[0164] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0165] In this invention, the server includes means for integrating biometric and emotional data collected from users, means for correcting outliers and imputing missing values ​​in the integrated data, means for evaluating health risks using generative machine learning techniques and analytical models based on the stored data, means for analyzing the user's emotional state and reflecting the results in the health risk assessment, and means for providing encryption and control functions for the purpose of protecting personal information data. This makes it possible to provide users with highly accurate risk assessments and personalized preventive measures.

[0166] "Biometric data collected from users" refers to information about the user's body, such as heart rate, steps taken, and sleep patterns, obtained through wearable devices and information terminals.

[0167] "Emotional data" refers to information used to capture a user's current emotional state, based on their voice tone, facial expressions, and physiological responses obtained from sensors.

[0168] "Correction of outliers" is the process of correcting values ​​in the collected data that are deemed inaccurate to within the normal range.

[0169] "Missing value imputation" is the process of filling in missing information in a dataset based on known data.

[0170] "Generative machine learning technology" is a technique that generates algorithms and models used for data analysis and prediction, and then uses the patterns obtained in that process to make predictions.

[0171] An "analytical model" is a mathematical or statistical method used to derive specific results or conclusions through the analysis and processing of data.

[0172] "Assessing health risks" means analyzing and estimating the likelihood of a specific health problem occurring based on the user's health status.

[0173] "Personalized preventative measures" refer to providing health management and preventative suggestions that are best suited to each user's individual health condition and lifestyle.

[0174] "Encryption" is a technology that protects data by transforming it using a specific algorithm in order to store it securely and prevent unauthorized access by third parties.

[0175] A "control function" is a function that manages and restricts access and operations so that the system operates as intended.

[0176] This invention is a system that comprehensively analyzes a user's health-related data and emotional state to provide personalized health management strategies. The embodiments thereof are described below.

[0177] First, the device collects biometric and emotional data through wearable devices and information terminals worn by the user. This data includes heart rate, steps taken, and sleep patterns. Emotional data is collected and analyzed using the device's microphone and camera to capture the user's voice and facial expressions.

[0178] Next, the server receives the data sent from the terminal. This data is stored in a data storage system, where outliers are corrected and missing values ​​are imputed. This is done using data preprocessing algorithms, which are often implemented in programming languages ​​such as Python or R.

[0179] The server then uses a generative AI model to predict health risks. Specific software used might include TensorFlow or PyTorch. The server uses these models to assess, for example, the probability of developing cardiovascular disease or diabetes. An example of a prompt might be, "Based on the user's most recent health data, predict the risk of developing a disease in the next week."

[0180] Furthermore, the server uses an emotion engine to analyze the collected voice and facial expression data. This analysis evaluates the user's emotional state (e.g., high stress or anxiety) and reflects this in the health risk assessment.

[0181] Ultimately, the server generates personalized preventative measures based on the analysis results. For example, users with high heart rates and stress levels might be recommended yoga or relaxation exercises. These preventative measures are communicated to the user via their device and visually displayed through the user interface. The notifications are tailored to the user's emotional state and presented in an easy-to-follow format.

[0182] Finally, the server uses data encryption technology to ensure the privacy of user data. By using this system, users can be assured that their data is securely protected. In this way, the system can support users in both their physical and emotional aspects, thereby improving overall health management.

[0183] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0184] Step 1:

[0185] The device collects biometric and emotional data from wearable devices and information terminals as input. Specifically, it acquires data such as heart rate, steps, and sleep patterns from device sensors, and voice and facial expression data using microphones and cameras. This data is stored in a database within the device. The output is a set of raw health and emotional data.

[0186] Step 2:

[0187] The device transmits collected biometric and emotional data to the server. The input is a collection of data stored on the device. The data is encrypted when transmitted to the server. This data transfer allows the server to receive all relevant data and prepare it for continuous analysis.

[0188] Step 3:

[0189] The server uses the received data as input to correct for outliers and impute missing values. Outliers are detected using statistical methods, and abnormal elements are identified and corrected. For example, if the heart rate is abnormally high, it is brought closer to the mean. Missing data is imputed based on the data's trend. The output is a corrected and complete dataset.

[0190] Step 4:

[0191] The server uses a generated AI model, taking corrected data as input, to predict health risks. This process employs machine learning algorithms (e.g., neural networks) to assess health risks based on prompts. For example, a prompt might read, "Predict the risk of cardiovascular disease based on the user's blood pressure data." The output is either a risk score or a predicted health risk category.

[0192] Step 5:

[0193] The server uses an emotion engine to determine emotional states by taking emotional data as input. Specifically, it performs voice analysis and facial recognition to quantify stress and anxiety levels. This process evaluates the user's mental state and incorporates it into the health risk assessment results. The output is an indicator of emotional state.

[0194] Step 6:

[0195] The server uses health risk predictions and emotional state indicators as input to generate personalized preventative measures. At this stage, it suggests optimal lifestyle improvement advice (e.g., exercise, nutrition, wellness activities) to the user based on the data. The output is a specific health management plan.

[0196] Step 7:

[0197] The device takes a personalized health management plan as input and notifies the user through a user-friendly interface. Notifications are delivered in real time and are adjusted to take into account the user's emotional state. The output is the display of the notification content on the device.

[0198] (Application Example 2)

[0199] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0200] In modern society, people face stress, anxiety, and the need to maintain their health. However, it is not easy to simultaneously and appropriately manage individual health and emotional states and provide individually customized health management measures based on these factors. In particular, there is a lack of systems that comprehensively support these aspects while considering the impact of a user's emotional state on their health.

[0201] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0202] In this invention, the server includes means for collecting health-related information from wearable devices and computing terminals; means for integrating the collected health-related information and correcting outliers and imputing missing values; means for predicting health risks using generative artificial intelligence technology and statistical models based on the integrated health-related information; and means for analyzing the user's emotions based on collected emotional state data and adjusting the health risk predictions considering the emotional state. This makes it possible to provide personalized health management that takes into account the diverse health and emotional states of the user.

[0203] A "wearable device" is an electronic device that a user wears on their body and has the function of collecting physiological data on a daily basis.

[0204] A "computing terminal" is a digital device used for collecting and processing data, and includes personal computers and smartphones.

[0205] "Health-related information" refers to data that includes the user's physiological indicators such as heart rate, steps taken, and sleep patterns.

[0206] "Correcting outliers" is the process of correcting clearly incorrect values ​​in collected data to bring them back within an appropriate range.

[0207] "Missing value imputation" is the process of filling in the missing information in a dataset with reasonable estimates.

[0208] "Generative artificial intelligence technology" refers to algorithms that have the ability to learn patterns from large amounts of data and perform predictions and classifications.

[0209] A "statistical model" is a mathematical framework used to analyze data and understand the relationships between different factors.

[0210] "Health risk" refers to a prediction of the likelihood of a specific disease or health problem occurring in the future.

[0211] "Emotional state data" refers to information about a user's emotions, estimated based on changes in voice tone and facial expressions.

[0212] "Health management measures" refer to specific actions and recommendations provided to maintain or improve the user's health.

[0213] "Notifying by voice or visual means conveying information to the user through speech synthesis, images, text, etc."

[0214] "Data encryption" is a technology that transforms information using a specific algorithm to protect it from unauthorized access.

[0215] "Management measures" refer to the process of securely handling user data and controlling access as needed.

[0216] The system implementing the invention monitors the user's health and emotional state in real time and provides customized health management measures based on this data. This system combines wearable devices and computing terminals and uses the following hardware and software for communication and processing.

[0217] Users wear wearable devices to collect physical activity and physiological data on a daily basis. This data is sent to a computing terminal, where outliers are corrected and missing values ​​are imputed. The computing terminal then uses a generative AI model to predict health risks based on the integrated health-related information. TensorFlow is used in the generative AI model to enhance its ability to learn patterns from the data and predict risks.

[0218] The server uses voice tone and facial expression data from sensors to analyze the emotional state from the collected data. If the user's emotional state affects the assessment of health risks, it generates preventive measures that take this into account. Specifically, if the user is experiencing stress, it suggests relaxation activities and provides advice tailored to their health condition.

[0219] The device notifies the user of the generated preventative measures via voice or visual means. The system uses encryption technology to protect information and ensure the security of the user's health and emotional state data. A specific example of its use is a system that suggests meditation or light exercise if the user's heart rate is high and their emotional state data indicates stress.

[0220] An example of a prompt to input into a generating AI model is: "Please tell me an approach to designing a robot assistant system that monitors a user's health and emotional state in real time and suggests appropriate preventative measures."

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The device collects user health-related information from wearable devices. Inputs include physiological indicators such as heart rate, steps, and sleep data, while output is the recording and transmission of this data to the computing device. The device uses wireless communication, such as Bluetooth, to acquire this data and monitors the individual's health status in real time through data streaming.

[0224] Step 2:

[0225] The server receives health-related information transmitted from terminals and performs integrated processing within the database. The input is a set of physiological data, and the output is consistent data with outliers corrected and missing values ​​imputed. The server detects abnormal heart rate values ​​and replaces them within the legend range using an algorithm. Furthermore, it maintains data integrity by adding estimated values ​​for missing values.

[0226] Step 3:

[0227] The server applies generative AI models and statistical models to harmonized data to predict health risks. The input is harmonized health-related information, and the output is a predicted value for the risk of a specific disease. The server runs the model using TensorFlow and calculates cardiovascular risk and diabetes risk as probabilities based on patterns learned from large amounts of data.

[0228] Step 4:

[0229] The device uses a camera and microphone to collect data on the user's emotional state and transmits it to a server. Inputs are voice data and facial expression data, while output is real-time analyzed emotional information. The device utilizes voice tone analysis and image processing technologies to capture emotional states such as anger, anxiety, and happiness.

[0230] Step 5:

[0231] The server synthesizes the user's health risks and emotional state to generate individually customized preventative measures. Input is predicted health risk and emotional data, while output is preventative measures including relaxation methods and lifestyle improvements. The server uses a generative AI to determine the best advice and generate motivating suggestions for risk reduction.

[0232] Step 6:

[0233] The user terminal notifies the user of the generated preventative measures via voice or visual means. The input is text data of the preventative measures, and the output is a visual or auditory notification delivered to the user. The terminal displays reminders in an actionable format and provides advice in a friendly tone using speech synthesis.

[0234] Step 7:

[0235] The server implements data encryption and access control to securely manage all health and emotional data. Inputs are users' personal data, and outputs are stored in a securely protected data store. The server applies encryption procedures such as AES and allows access only from specific authorized devices.

[0236] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0237] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0238] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0239] [Second Embodiment]

[0240] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0241] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0242] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0243] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0244] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0245] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0246] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0247] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0248] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0249] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0250] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0251] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0252] This invention provides users with personalized preventative measures for health management based on a wide variety of health-related data acquired from wearable devices and information terminals. The following means are necessary to implement the invention.

[0253] First, the device has the function of collecting health data from the user, which is achieved through sensors built into wearable devices or smartphones. This data includes steps taken, heart rate, sleep patterns, body temperature, blood pressure, etc. It also acquires electronic health records, such as blood test results, provided by medical institutions as needed.

[0254] Next, the server receives the collected data and uses data integration means to integrate and preprocess it. It detects and corrects outliers, imputes missing values, and processes the data so that it is suitable for analysis.

[0255] Subsequently, the server uses the compiled health-related data, employing generative AI technology and statistical models to predict specific health risks for each user. For example, the risk of developing lifestyle-related diseases such as cardiovascular disease and diabetes is assessed. This assessment is based on a model trained on historical datasets, enabling highly accurate predictions.

[0256] Furthermore, the server generates appropriate preventative measures for each user based on the predicted risk. These preventative measures include specific recommendations related to exercise, diet, and sleep. For example, high-risk users may receive suggestions for specific exercise plans and dietary restrictions.

[0257] The generated preventative measures are presented to the user via the device. The device's user interface is intuitive and designed to be easily understood and implemented by the user. Notification and reminder features are used to support the user in forming healthy habits.

[0258] Finally, the server encrypts all collected health-related data and controls data access to protect the data. This ensures user privacy and allows users to use the system with peace of mind.

[0259] Thus, in order to implement the invention, all stages, from data collection and risk prediction to suggesting preventive measures and protecting data privacy, must be carried out in coordination. For example, a user who is predicted to be at risk of cardiovascular disease may be notified of a recommendation to do more than 150 minutes of aerobic exercise per week and advised to limit salt intake in their diet. With such specific instructions, users can take actions to improve their health and reduce their risk of lifestyle-related diseases.

[0260] The following describes the processing flow.

[0261] Step 1:

[0262] The device collects user health-related data through wearable devices and smartphones. This data is acquired in real time and includes steps taken, heart rate, sleep duration, and calorie consumption. Furthermore, through collaboration with medical institutions, it can receive electronic health records with the user's permission.

[0263] Step 2:

[0264] The server receives health-related data sent from the terminal. Since the received data may be in different formats, it is first converted to a standardized format. Next, the collected data is cleaned to detect and correct outliers, and missing values ​​are imputed using past data or average values.

[0265] Step 3:

[0266] The server uses generated AI and statistical models based on the cleaned data to predict the user's future health risks. This process individually assesses the risk of developing specific diseases (e.g., cardiovascular disease, diabetes) through analysis of the user's historical data and similar past cases. This makes it possible to quantitatively understand the user's future health status.

[0267] Step 4:

[0268] The server generates personalized preventative measures tailored to the predicted health risks. These measures may include recommendations for exercise frequency and amount, dietary changes, and improvements to sleep patterns. For specific risks, it may also recommend consulting a doctor or undergoing additional tests.

[0269] Step 5:

[0270] The device notifies the user of preventative measures generated from the server. These notifications are delivered via an interactive interface, providing visual and audio feedback. Users can use this information to adjust their daily behavior. The device also provides a reminder function, periodically informing the user of actions that should be taken.

[0271] Step 6:

[0272] The server implements data encryption and access control throughout the entire system to protect user data privacy. It also establishes a process to provide users with transparent information about what data is collected and how it is used, and to obtain their consent for its use.

[0273] (Example 1)

[0274] Next, we will describe Example 1. 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."

[0275] In modern society, sophisticated health management tailored to individual lifestyles and health conditions is required. However, effectively collecting and analyzing diverse health-related data and providing personalized preventive measures is not easy, and an efficient system is needed. Furthermore, ensuring user privacy while providing reliable health risk assessments and concrete preventive measures is a challenge.

[0276] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0277] In this invention, the server includes means for acquiring information regarding the user's physical activities and physiological state, means for integrating the acquired information, detecting and adjusting for abnormalities, and estimating missing values, and means for predicting health risks using machine learning techniques and statistical inferences generated based on the integrated information. As a result, it becomes possible to provide users with a more accurate assessment of health risks and individualized preventive measures.

[0278] "Information regarding the user's physical activities and physiological state" refers to data such as the number of steps, heart rate, sleep pattern, body temperature, blood pressure, etc., which are acquired to understand an individual's health status.

[0279] "Means for acquiring" is a technology for collecting the user's health-related data in real time through information collection devices such as wearable devices and smartphones.

[0280] "Means for integrating, detecting and adjusting for abnormalities, and estimating missing values" is a process for combining health-related information collected from multiple data sources, complementing data defects, and arranging it in a form suitable for analysis.

[0281] "Machine learning techniques and statistical inferences" are methods for learning patterns from past data and predicting future results based on new data.

[0282] "Means for predicting health risks" is a process for evaluating the likelihood of future diseases based on an individual's health status using machine learning techniques and statistical models.

[0283] "Individualized preventive measures" are specific recommendations regarding exercise, diet, and improvement of lifestyle habits provided in response to a user's specific health risks.

[0284] "Server" is a central system for analyzing and predicting the collected data and providing the results to the user.

[0285] An "information terminal" is an electronic device that displays information to users and sends notifications, including smartphones and tablet computers.

[0286] "Data encryption and access control means" is a security technology that encrypts the collected data and prevents unauthorized access in order to protect user privacy.

[0287] This system is realized by utilizing information terminals and wearable devices to collect health-related data and performing advanced analysis based on this data in order to individualize user health management.

[0288] As terminals, mainly wearable devices and smartphones are used. These devices use built-in sensors to obtain information on physical activities and physiological states such as the number of steps, heart rate, sleep pattern, body temperature, and blood pressure. This data is sent to the server in real time via Bluetooth or Wi-Fi.

[0289] The server integrates the received data, detects and adjusts abnormal values, and estimates missing values. The integrated information is transferred to a process of predicting health risks by making full use of machine learning techniques and statistical inference. The generated AI model learns based on the data set collected in the past and realizes precise risk assessment. High-performance cloud computing services are usually used for this processing.

[0290] Based on the predicted health risks, the server generates preventive measures optimized for each user. This includes exercise plans, nutritional guidance, and sleep improvement suggestions, and the generated preventive measures are sent to the terminal in an intuitive and easily understandable form.

[0291] Users receive notifications about preventative measures through their information terminals and have the opportunity to improve their lifestyles by following the provided guidelines. The terminal's user interface is designed to be integrated into daily routines, utilizing pop-up notifications and reminder functions.

[0292] A crucial aspect of the data in this system is data confidentiality and the protection of user privacy. The collected information is securely managed on the servers using advanced encryption technology to prevent unauthorized access and provide a safe environment for users.

[0293] As a concrete example, the following prompt could be used as input to a generative AI model: "Please propose a health risk assessment and preventive measures for a 40-year-old male user who takes fewer than 5,000 steps per day on average and performs less than 30 minutes of aerobic exercise once a week." Based on this prompt, the AI ​​would analyze relevant data and provide the user with a specific and effective health management plan.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The device collects user health-related data. Using wearable devices and smartphones, it obtains information such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure. The input to this process is raw data from sensors, and the output is a set of collected data. This dataset is then ready to be transmitted to the next processing step via Bluetooth or Wi-Fi.

[0297] Step 2:

[0298] The server receives health-related data sent from the terminal. It then detects anomalous data points and corrects them using algorithms. If there is missing data, it estimates and fills in its values ​​using statistical methods. The input is the raw data from the terminal, and the output is the cleaned and imputed dataset.

[0299] Step 3:

[0300] The server applies a generative AI model using prepared data to predict health risks. It assesses the risk of specific diseases and health conditions (e.g., cardiovascular disease, diabetes) and generates results. The input is a pre-processed dataset, and the output is a user-specific risk assessment. The AI ​​model is trained on a vast amount of historical data, enabling it to predict risks with high accuracy.

[0301] Step 4:

[0302] The server generates personalized preventative measures based on predicted health risks. These preventative measures include specific recommendations regarding exercise, diet, and sleep. The input is a health risk assessment, and the output is a set of recommendations for the user. This content is customized to the user's lifestyle.

[0303] Step 5:

[0304] The generated preventative measures are presented to the user via the device. The device visually displays the information and sends important health recommendations to the user as pop-up notifications and reminders. The input is a set of recommendations from the server, and the output is an intuitive interface that the user can easily understand. Based on this, the user can decide on and take healthy behaviors.

[0305] Step 6:

[0306] To protect user privacy, the server encrypts all collected health-related data and implements access control. The input is the user's health-related data, and the output is encrypted and securely stored data storage. This process enables users to provide data with confidence and utilize the system.

[0307] (Application Example 1)

[0308] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] In modern society, the management of health risks using individual health data has become widespread, but there is an issue that the collective health management methods for improving the health of all residents in a city are not sufficient. There is a need to establish a method not only for providing health advice to individuals but also for grasping the overall health status of the city and promoting the health of all residents.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0311] In this invention, the server includes means for collecting health-related information from wearable devices and information processing devices, means for integrating the collected health-related information and performing correction of abnormal values and supplementation of missing values, and means for monitoring the health status of the entire urban population and providing information for collective health management. This enables the provision of a comprehensive healthcare system aimed at promoting the health of all residents as well as individual health management.

[0312] A "wearable device" is an electronic device that a user can wear on the body and has a function of measuring and collecting health-related information.

[0313] An "information processing device" is an electronic device that can receive data and perform arithmetic processing and plays a role in managing health-related information.

[0314] "Health-related information" refers to data about an individual's physical condition and lifestyle, and specifically includes indicators such as heart rate, steps taken, sleep patterns, blood pressure, and body temperature.

[0315] "Integration" refers to the process of combining and organizing data obtained from different formats or sources into a single format.

[0316] "Correction of outliers" refers to the process of detecting values ​​in the collected data that deviate from the normal range, removing their influence, and adjusting the data to a format suitable for analysis.

[0317] "Missing value imputation" is a technique for filling in data that is not recorded or is missing in a dataset, in order to construct a complete dataset.

[0318] "Generative artificial intelligence technology" is a technology that uses computer programs and algorithms to learn patterns based on data and make predictions and recommendations.

[0319] "Health risk" is an assessment indicator that shows the probability of an individual developing a specific disease or experiencing a deterioration in their health.

[0320] "Personalized preventive measures" refer to specific advice and action plans designed specifically for an individual to maintain and improve their health.

[0321] "Presenting information visually and through notification features" refers to features that display information using the device screen or use sound and vibration to inform the user of important information.

[0322] "Data encryption" is a technology that transforms data to protect its confidentiality and safeguard it from unauthorized access.

[0323] "Access control" refers to a security management technique that restricts access to specific data or systems to only authorized users.

[0324] "Monitoring the health status of the entire urban population" is a process of comprehensively monitoring and analyzing the health status of all people living in a given city.

[0325] "Providing information for collective health management" refers to providing data and analysis results to assess health conditions at the city or community level and to formulate policies and initiatives aimed at improving the health of the entire population.

[0326] The system implementing the present invention collects health-related information via a wearable device and an information processing device, and performs centralized processing on a server.

[0327] The server receives data from wearable devices and information processing devices using Bluetooth or Wi-Fi technology. The wearable devices used incorporate heart rate sensors and accelerometers, and have the function of continuously measuring the user's daily activity metrics. The smartphone, acting as the information processing device, functions as the interface with the user and has applications installed for displaying data and providing notifications.

[0328] The received health-related information is stored in the server's database and preprocessed using the Pandas library. This automatically corrects for outliers and imputes missing values, preparing the dataset for advanced analysis. Then, a generative AI model using TensorFlow predicts the health risks for individual users. This model is trained on historical data and can predict, for example, the risk of cardiovascular disease with high accuracy.

[0329] Personalized preventative measures are generated for each user based on predicted risks. Specific advice on exercise metrics and nutritional content is provided through the application. This allows users to understand their own health status and take appropriate health management actions.

[0330] Furthermore, the server generates data that contributes to the formulation of public policies based on the collective health status of the entire city. The data collected from residents is comprehensively analyzed and used for smart city health initiatives.

[0331] For example, if a user's heart rate remains higher than normal for an extended period, notifications regarding appropriate breathing techniques and stress management will be sent to their smartphone. An example of a prompt message might be, "Based on the user's heart rate and step count data, generate relevant health risks and optimal preventative measures." The generating AI model then performs the analysis according to these instructions.

[0332] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0333] Step 1:

[0334] The device collects health-related information from the user's wearable device. Inputs include sensor data such as heart rate, steps, and sleep patterns, which are then transferred to a smartphone via Bluetooth or Wi-Fi. Outputs are the initial, unprocessed data stored in the device.

[0335] Step 2:

[0336] The device transmits collected health-related information to the server. The input is unprocessed health data within the device, and the output is raw data received by the server. An internet connection is used for data transmission.

[0337] Step 3:

[0338] The server stores the received health-related information in a database. The input is raw data sent from the terminal, and the output is a queryable database state. This ensures data persistence.

[0339] Step 4:

[0340] The server uses the Pandas library to preprocess the data. The input is raw data read from the database, and outlier correction and missing value imputation are performed automatically. The output is a well-prepared dataset ready for analysis.

[0341] Step 5:

[0342] The server uses TensorFlow to apply a generative AI model and predict individual health risks from a prepared dataset. The input is prepared health data, and the AI ​​model analyzes this data to output the probability of health risk.

[0343] Step 6:

[0344] The server generates optimal preventative measures for the user based on predicted health risks. The input is the probability of health risk, and the output is information such as specific exercise plans and nutritional advice. Individual preventative measures are designed using prompts from the generating AI model.

[0345] Step 7:

[0346] The server sends the generated preventative measures to the terminal, which then displays the information visually. The input is specific preventative measures, and the output is notifications and information displayed on the terminal. The user then uses this information to manage their health.

[0347] Step 8:

[0348] The server securely processes all transactions using data encryption technology and manages access control. Inputs are unencrypted health-related data, while outputs are encrypted data accessible only to users with access rights.

[0349] Step 9:

[0350] The server provides urban authorities with statistical analysis results to support collective health management. The input is integrated data for the entire population, and the output is policy recommendations and improvement proposals based on the overall health status of the city. This can then be used to develop health policies for smart cities.

[0351] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0352] This invention is a system that predicts health risks based on the user's health-related data, recognizes the user's emotional state, and reflects the results in preventative measures. The aim is to achieve more personalized and appropriate health management. The system is implemented as follows:

[0353] First, the device collects the user's daily physical data using wearable devices and information terminals. This includes heart rate, steps taken, and sleep data. It also captures emotional states from voice and facial expression data acquired by microphones and cameras. Based on this data, the device gains a detailed understanding of the user's current health and emotional state.

[0354] Next, the server receives health and emotional data collected from the terminals and first corrects for outliers and imputes missing values. This process enables analysis based on highly accurate data. Then, using generative artificial intelligence technology and statistical models, health risks are predicted. The predicted risks are evaluated for diseases such as cardiovascular disease and diabetes.

[0355] The server further analyzes the user's emotional state using an emotion engine. Here, it evaluates the user's voice tone, facial expressions, and biometric responses from sensors to determine their current emotion. For example, if stress or anxiety levels are high, this is taken into account when adjusting risk assessments and preventative measures.

[0356] Next, based on the obtained risk assessment and emotional state, the server generates personalized preventative measures. These measures include specific advice on exercise and diet, as well as suggestions to support the user's mental health. For example, a user experiencing high stress levels might be advised on the importance of relaxation exercises and rest.

[0357] The device notifies users of generated preventative measures and presents them through the user interface. It adjusts the tone and timing of notifications based on the user's emotional state, providing information in a way that is more likely to be taken action. This user-friendly interface supports users in their daily health management.

[0358] Finally, the server implements data encryption and strict access controls to ensure the protection of data across the entire system. This allows users to be assured that their health and emotional data is handled securely and to use the system with peace of mind.

[0359] This system allows users to access not only physical health management but also approaches necessary for improving their emotional state, leading to an overall improvement in their well-being. For example, during periods of heightened anxiety, the system may suggest special relaxation techniques and adjust the schedule to ensure the user has the necessary time to relax.

[0360] The following describes the processing flow.

[0361] Step 1:

[0362] The device collects the user's daily health-related data using wearable devices and smartphones. This includes physical data such as steps taken, heart rate, and sleep duration. It also uses the device's microphone and camera to capture the user's voice and facial expression data, collecting initial data on their emotional state.

[0363] Step 2:

[0364] The server receives health-related and emotional data transmitted from terminals. This data is first centralized, and then anomalies are detected and corrected, and missing values ​​are imputed to ensure data integrity. This prepares clean data suitable for analysis.

[0365] Step 3:

[0366] The server uses generative AI technology and statistical models to analyze integrated health-related data and predict specific health risks. This is a process of quantitatively assessing the risk of developing diseases such as hypertension and diabetes.

[0367] Step 4:

[0368] The server uses an emotion engine to recognize the user's emotional state from acquired voice and facial expression data. For example, it analyzes stress levels and changes in emotional state from voice tone and facial expressions to identify the current emotional state.

[0369] Step 5:

[0370] The server comprehensively considers predicted health risks and perceived emotional states to generate personalized preventative measures tailored to the user. These measures include advice on managing physical health and suggestions for relaxation techniques and meditation exercises to support emotional well-being.

[0371] Step 6:

[0372] The device notifies the user of the generated preventative measures. The user interface is user-friendly and designed to be easily understood and implemented. Furthermore, the timing and content of notifications are appropriately adjusted to take the user's emotional state into consideration.

[0373] Step 7:

[0374] The server encrypts collected health and emotional data to protect the entire system's data, ensuring user privacy. Strict access control is also maintained to prevent misuse of data.

[0375] This process allows users to comprehensively understand their own health status and take preventative measures, thereby maintaining their health both physically and emotionally.

[0376] (Example 2)

[0377] Next, we will describe Example 2. 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".

[0378] In recent years, as the importance of health management and mental healthcare has increased, providing personalized approaches to users has become crucial. However, traditional systems have struggled to integrate health and emotional data and propose optimal preventative measures for individual users. Furthermore, there has been the challenge of insufficient data privacy guarantees.

[0379] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0380] In this invention, the server includes means for integrating biometric and emotional data collected from users, means for correcting outliers and imputing missing values ​​in the integrated data, means for evaluating health risks using generative machine learning techniques and analytical models based on the stored data, means for analyzing the user's emotional state and reflecting the results in the health risk assessment, and means for providing encryption and control functions for the purpose of protecting personal information data. This makes it possible to provide users with highly accurate risk assessments and personalized preventive measures.

[0381] "Biometric data collected from users" refers to information about the user's body, such as heart rate, steps taken, and sleep patterns, obtained through wearable devices and information terminals.

[0382] "Emotional data" refers to information used to capture a user's current emotional state, based on their voice tone, facial expressions, and physiological responses obtained from sensors.

[0383] "Correction of outliers" is the process of correcting values ​​in the collected data that are deemed inaccurate to within the normal range.

[0384] "Missing value imputation" is the process of filling in missing information in a dataset based on known data.

[0385] "Generative machine learning technology" is a technique that generates algorithms and models used for data analysis and prediction, and then uses the patterns obtained in that process to make predictions.

[0386] An "analytical model" is a mathematical or statistical method used to derive specific results or conclusions through the analysis and processing of data.

[0387] "Assessing health risks" means analyzing and estimating the likelihood of a specific health problem occurring based on the user's health status.

[0388] "Personalized preventative measures" refer to providing health management and preventative suggestions that are best suited to each user's individual health condition and lifestyle.

[0389] "Encryption" is a technology that protects data by transforming it using a specific algorithm in order to store it securely and prevent unauthorized access by third parties.

[0390] A "control function" is a function that manages and restricts access and operations so that the system operates as intended.

[0391] This invention is a system that comprehensively analyzes a user's health-related data and emotional state to provide personalized health management strategies. The embodiments thereof are described below.

[0392] First, the device collects biometric and emotional data through wearable devices and information terminals worn by the user. This data includes heart rate, steps taken, and sleep patterns. Emotional data is collected and analyzed using the device's microphone and camera to capture the user's voice and facial expressions.

[0393] Next, the server receives the data sent from the terminal. This data is stored in a data storage system, where outliers are corrected and missing values ​​are imputed. This is done using data preprocessing algorithms, which are often implemented in programming languages ​​such as Python or R.

[0394] The server then uses a generative AI model to predict health risks. Specific software used might include TensorFlow or PyTorch. The server uses these models to assess, for example, the probability of developing cardiovascular disease or diabetes. An example of a prompt might be, "Based on the user's most recent health data, predict the risk of developing a disease in the next week."

[0395] Furthermore, the server uses an emotion engine to analyze the collected voice and facial expression data. This analysis evaluates the user's emotional state (e.g., high stress or anxiety) and reflects this in the health risk assessment.

[0396] Ultimately, the server generates personalized preventative measures based on the analysis results. For example, users with high heart rates and stress levels might be recommended yoga or relaxation exercises. These preventative measures are communicated to the user via their device and visually displayed through the user interface. The notifications are tailored to the user's emotional state and presented in an easy-to-follow format.

[0397] Finally, the server uses data encryption technology to ensure the privacy of user data. By using this system, users can be assured that their data is securely protected. In this way, the system can support users in both their physical and emotional aspects, thereby improving overall health management.

[0398] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0399] Step 1:

[0400] The device collects biometric and emotional data from wearable devices and information terminals as input. Specifically, it acquires data such as heart rate, steps, and sleep patterns from device sensors, and voice and facial expression data using microphones and cameras. This data is stored in a database within the device. The output is a set of raw health and emotional data.

[0401] Step 2:

[0402] The device transmits collected biometric and emotional data to the server. The input is a collection of data stored on the device. The data is encrypted when transmitted to the server. This data transfer allows the server to receive all relevant data and prepare it for continuous analysis.

[0403] Step 3:

[0404] The server uses the received data as input to correct for outliers and impute missing values. Outliers are detected using statistical methods, and abnormal elements are identified and corrected. For example, if the heart rate is abnormally high, it is brought closer to the mean. Missing data is imputed based on the data's trend. The output is a corrected and complete dataset.

[0405] Step 4:

[0406] The server uses a generated AI model, taking corrected data as input, to predict health risks. This process employs machine learning algorithms (e.g., neural networks) to assess health risks based on prompts. For example, a prompt might read, "Predict the risk of cardiovascular disease based on the user's blood pressure data." The output is either a risk score or a predicted health risk category.

[0407] Step 5:

[0408] The server uses an emotion engine to determine emotional states by taking emotional data as input. Specifically, it performs voice analysis and facial recognition to quantify stress and anxiety levels. This process evaluates the user's mental state and incorporates it into the health risk assessment results. The output is an indicator of emotional state.

[0409] Step 6:

[0410] The server uses health risk predictions and emotional state indicators as input to generate personalized preventative measures. At this stage, it suggests optimal lifestyle improvement advice (e.g., exercise, nutrition, wellness activities) to the user based on the data. The output is a specific health management plan.

[0411] Step 7:

[0412] The device takes a personalized health management plan as input and notifies the user through a user-friendly interface. Notifications are delivered in real time and are adjusted to take into account the user's emotional state. The output is the display of the notification content on the device.

[0413] (Application Example 2)

[0414] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0415] In modern society, people face stress, anxiety, and the need to maintain their health. However, it is not easy to simultaneously and appropriately manage individual health and emotional states and provide individually customized health management measures based on these factors. In particular, there is a lack of systems that comprehensively support these aspects while considering the impact of a user's emotional state on their health.

[0416] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0417] In this invention, the server includes means for collecting health-related information from wearable devices and computing terminals; means for integrating the collected health-related information and correcting outliers and imputing missing values; means for predicting health risks using generative artificial intelligence technology and statistical models based on the integrated health-related information; and means for analyzing the user's emotions based on collected emotional state data and adjusting the health risk predictions considering the emotional state. This makes it possible to provide personalized health management that takes into account the diverse health and emotional states of the user.

[0418] A "wearable device" is an electronic device that a user wears on their body and has the function of collecting physiological data on a daily basis.

[0419] A "computing terminal" is a digital device used for collecting and processing data, and includes personal computers and smartphones.

[0420] "Health-related information" refers to data that includes the user's physiological indicators such as heart rate, steps taken, and sleep patterns.

[0421] "Correcting outliers" is the process of correcting clearly incorrect values ​​in collected data to bring them back within an appropriate range.

[0422] "Missing value imputation" is the process of filling in the missing information in a dataset with reasonable estimates.

[0423] "Generative artificial intelligence technology" refers to algorithms that have the ability to learn patterns from large amounts of data and perform predictions and classifications.

[0424] A "statistical model" is a mathematical framework used to analyze data and understand the relationships between different factors.

[0425] "Health risk" refers to a prediction of the likelihood of a specific disease or health problem occurring in the future.

[0426] "Emotional state data" refers to information about a user's emotions, estimated based on changes in voice tone and facial expressions.

[0427] "Health management measures" refer to specific actions and recommendations provided to maintain or improve the user's health.

[0428] "Notifying by voice or visual means conveying information to the user through speech synthesis, images, text, etc."

[0429] "Data encryption" is a technology that transforms information using a specific algorithm to protect it from unauthorized access.

[0430] "Management measures" refer to the process of securely handling user data and controlling access as needed.

[0431] The system implementing the invention monitors the user's health and emotional state in real time and provides customized health management measures based on this data. This system combines wearable devices and computing terminals and uses the following hardware and software for communication and processing.

[0432] Users wear wearable devices to collect physical activity and physiological data on a daily basis. This data is sent to a computing terminal, where outliers are corrected and missing values ​​are imputed. The computing terminal then uses a generative AI model to predict health risks based on the integrated health-related information. TensorFlow is used in the generative AI model to enhance its ability to learn patterns from the data and predict risks.

[0433] The server uses voice tone and facial expression data from sensors to analyze the emotional state from the collected data. If the user's emotional state affects the assessment of health risks, it generates preventive measures that take this into account. Specifically, if the user is experiencing stress, it suggests relaxation activities and provides advice tailored to their health condition.

[0434] The device notifies the user of the generated preventative measures via voice or visual means. The system uses encryption technology to protect information and ensure the security of the user's health and emotional state data. A specific example of its use is a system that suggests meditation or light exercise if the user's heart rate is high and their emotional state data indicates stress.

[0435] An example of a prompt to input into a generating AI model is: "Please tell me an approach to designing a robot assistant system that monitors a user's health and emotional state in real time and suggests appropriate preventative measures."

[0436] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0437] Step 1:

[0438] The device collects user health-related information from wearable devices. Inputs include physiological indicators such as heart rate, steps, and sleep data, while output is the recording and transmission of this data to the computing device. The device uses wireless communication, such as Bluetooth, to acquire this data and monitors the individual's health status in real time through data streaming.

[0439] Step 2:

[0440] The server receives health-related information transmitted from terminals and performs integrated processing within the database. The input is a set of physiological data, and the output is consistent data with outliers corrected and missing values ​​imputed. The server detects abnormal heart rate values ​​and replaces them within the legend range using an algorithm. Furthermore, it maintains data integrity by adding estimated values ​​for missing values.

[0441] Step 3:

[0442] The server applies generative AI models and statistical models to harmonized data to predict health risks. The input is harmonized health-related information, and the output is a predicted value for the risk of a specific disease. The server runs the model using TensorFlow and calculates cardiovascular risk and diabetes risk as probabilities based on patterns learned from large amounts of data.

[0443] Step 4:

[0444] The device uses a camera and microphone to collect data on the user's emotional state and transmits it to a server. Inputs are voice data and facial expression data, while output is real-time analyzed emotional information. The device utilizes voice tone analysis and image processing technologies to capture emotional states such as anger, anxiety, and happiness.

[0445] Step 5:

[0446] The server synthesizes the user's health risks and emotional state to generate individually customized preventative measures. Input is predicted health risk and emotional data, while output is preventative measures including relaxation methods and lifestyle improvements. The server uses a generative AI to determine the best advice and generate motivating suggestions for risk reduction.

[0447] Step 6:

[0448] The user terminal notifies the user of the generated preventative measures via voice or visual means. The input is text data of the preventative measures, and the output is a visual or auditory notification delivered to the user. The terminal displays reminders in an actionable format and provides advice in a friendly tone using speech synthesis.

[0449] Step 7:

[0450] The server implements data encryption and access control to securely manage all health and emotional data. Inputs are users' personal data, and outputs are stored in a securely protected data store. The server applies encryption procedures such as AES and allows access only from specific authorized devices.

[0451] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0452] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0453] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0454] [Third Embodiment]

[0455] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0456] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0457] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0458] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0459] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0460] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0461] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0462] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0463] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0464] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0465] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0466] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0467] This invention provides users with personalized preventative measures for health management based on a wide variety of health-related data acquired from wearable devices and information terminals. The following means are necessary to implement the invention.

[0468] First, the device has the function of collecting health data from the user, which is achieved through sensors built into wearable devices or smartphones. This data includes steps taken, heart rate, sleep patterns, body temperature, blood pressure, etc. It also acquires electronic health records, such as blood test results, provided by medical institutions as needed.

[0469] Next, the server receives the collected data and uses data integration means to integrate and preprocess it. It detects and corrects outliers, imputes missing values, and processes the data so that it is suitable for analysis.

[0470] Subsequently, the server uses the compiled health-related data, employing generative AI technology and statistical models to predict specific health risks for each user. For example, the risk of developing lifestyle-related diseases such as cardiovascular disease and diabetes is assessed. This assessment is based on a model trained on historical datasets, enabling highly accurate predictions.

[0471] Furthermore, the server generates appropriate preventative measures for each user based on the predicted risk. These preventative measures include specific recommendations related to exercise, diet, and sleep. For example, high-risk users may receive suggestions for specific exercise plans and dietary restrictions.

[0472] The generated preventative measures are presented to the user via the device. The device's user interface is intuitive and designed to be easily understood and implemented by the user. Notification and reminder features are used to support the user in forming healthy habits.

[0473] Finally, the server encrypts all collected health-related data and controls data access to protect the data. This ensures user privacy and allows users to use the system with peace of mind.

[0474] Thus, in order to implement the invention, all stages, from data collection and risk prediction to suggesting preventive measures and protecting data privacy, must be carried out in coordination. For example, a user who is predicted to be at risk of cardiovascular disease may be notified of a recommendation to do more than 150 minutes of aerobic exercise per week and advised to limit salt intake in their diet. With such specific instructions, users can take actions to improve their health and reduce their risk of lifestyle-related diseases.

[0475] The following describes the processing flow.

[0476] Step 1:

[0477] The device collects user health-related data through wearable devices and smartphones. This data is acquired in real time and includes steps taken, heart rate, sleep duration, and calorie consumption. Furthermore, through collaboration with medical institutions, it can receive electronic health records with the user's permission.

[0478] Step 2:

[0479] The server receives health-related data sent from the terminal. Since the received data may be in different formats, it is first converted to a standardized format. Next, the collected data is cleaned to detect and correct outliers, and missing values ​​are imputed using past data or average values.

[0480] Step 3:

[0481] The server uses generated AI and statistical models based on the cleaned data to predict the user's future health risks. This process individually assesses the risk of developing specific diseases (e.g., cardiovascular disease, diabetes) through analysis of the user's historical data and similar past cases. This makes it possible to quantitatively understand the user's future health status.

[0482] Step 4:

[0483] The server generates personalized preventative measures tailored to the predicted health risks. These measures may include recommendations for exercise frequency and amount, dietary changes, and improvements to sleep patterns. For specific risks, it may also recommend consulting a doctor or undergoing additional tests.

[0484] Step 5:

[0485] The device notifies the user of preventative measures generated from the server. These notifications are delivered via an interactive interface, providing visual and audio feedback. Users can use this information to adjust their daily behavior. The device also provides a reminder function, periodically informing the user of actions that should be taken.

[0486] Step 6:

[0487] The server implements data encryption and access control throughout the entire system to protect user data privacy. It also establishes a process to provide users with transparent information about what data is collected and how it is used, and to obtain their consent for its use.

[0488] (Example 1)

[0489] Next, we will describe Example 1. 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."

[0490] In modern society, sophisticated health management tailored to individual lifestyles and health conditions is required. However, effectively collecting and analyzing diverse health-related data and providing personalized preventive measures is not easy, and an efficient system is needed. Furthermore, ensuring user privacy while providing reliable health risk assessments and concrete preventive measures is a challenge.

[0491] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0492] In this invention, the server includes means for acquiring information on the user's physical activity and physiological state, means for integrating the acquired information, detecting and adjusting for anomalies, and estimating missing values, and means for predicting health risks using machine learning techniques and statistical inference generated based on the integrated information. This enables the user to receive a more accurate assessment of health risks and personalized preventive measures.

[0493] "Information about the user's physical activity and physiological state" refers to data such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure, which are collected to understand an individual's health status.

[0494] "Means of acquisition" refers to technologies for collecting users' health-related data in real time through information gathering devices such as wearable devices and smartphones.

[0495] "Means for integrating, detecting and adjusting for anomalies, and estimating missing values" refers to the process of combining health-related information collected from multiple data sources, supplementing data gaps, and preparing it for analysis.

[0496] "Machine learning techniques and statistical inference" are methods for learning patterns from past data and predicting future outcomes based on new data.

[0497] "Methods for predicting health risks" refer to the process of using machine learning techniques and statistical models to assess the likelihood of future illness based on an individual's health status.

[0498] "Personalized preventative measures" are specific recommendations regarding exercise, diet, and lifestyle improvements that are provided to address the user's specific health risks.

[0499] A "server" is a central system that analyzes and predicts the collected data and provides results to users.

[0500] An "information terminal" is an electronic device used to display information to a user and send notifications, and includes smartphones and tablet computers.

[0501] "Data encryption and access control measures" refer to security technologies that encrypt collected data and prevent unauthorized access in order to protect user privacy.

[0502] This system is realized by collecting health-related data using information terminals and wearable devices, and performing advanced analysis based on that data, in order to personalize users' health management.

[0503] The devices used are primarily wearable devices and smartphones. These devices use built-in sensors to acquire information about physical activity and physiological states, such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure. This data is transmitted to a server in real time via Bluetooth or Wi-Fi.

[0504] The server integrates the received data, detecting and correcting outliers and estimating missing values. The integrated information is then used in a process to predict health risks, employing machine learning techniques and statistical inference. The generated AI model learns from previously collected datasets to achieve precise risk assessments. High-performance cloud computing services are typically used for this process.

[0505] Based on predicted health risks, the server generates personalized preventative measures for each user. These include exercise plans, nutritional guidance, and sleep improvement suggestions, and the generated preventative measures are sent to the device in an intuitive and easy-to-understand format.

[0506] Users receive notifications about preventative measures through their information terminals and have the opportunity to improve their lifestyles by following the provided guidelines. The terminal's user interface is designed to be integrated into daily routines, utilizing pop-up notifications and reminder functions.

[0507] A crucial aspect of the data in this system is data confidentiality and the protection of user privacy. The collected information is securely managed on the servers using advanced encryption technology to prevent unauthorized access and provide a safe environment for users.

[0508] As a concrete example, the following prompt could be used as input to a generative AI model: "Please propose a health risk assessment and preventive measures for a 40-year-old male user who takes fewer than 5,000 steps per day on average and performs less than 30 minutes of aerobic exercise once a week." Based on this prompt, the AI ​​would analyze relevant data and provide the user with a specific and effective health management plan.

[0509] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0510] Step 1:

[0511] The device collects user health-related data. Using wearable devices and smartphones, it obtains information such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure. The input to this process is raw data from sensors, and the output is a set of collected data. This dataset is then ready to be transmitted to the next processing step via Bluetooth or Wi-Fi.

[0512] Step 2:

[0513] The server receives health-related data sent from the terminal. It then detects anomalous data points and corrects them using algorithms. If there is missing data, it estimates and fills in its values ​​using statistical methods. The input is the raw data from the terminal, and the output is the cleaned and imputed dataset.

[0514] Step 3:

[0515] The server applies a generative AI model using prepared data to predict health risks. It assesses the risk of specific diseases and health conditions (e.g., cardiovascular disease, diabetes) and generates results. The input is a pre-processed dataset, and the output is a user-specific risk assessment. The AI ​​model is trained on a vast amount of historical data, enabling it to predict risks with high accuracy.

[0516] Step 4:

[0517] The server generates personalized preventative measures based on predicted health risks. These preventative measures include specific recommendations regarding exercise, diet, and sleep. The input is a health risk assessment, and the output is a set of recommendations for the user. This content is customized to the user's lifestyle.

[0518] Step 5:

[0519] The generated preventative measures are presented to the user via the device. The device visually displays the information and sends important health recommendations to the user as pop-up notifications and reminders. The input is a set of recommendations from the server, and the output is an intuitive interface that the user can easily understand. Based on this, the user can decide on and take healthy behaviors.

[0520] Step 6:

[0521] The server encrypts all collected health-related data and implements access control to protect user privacy. Input is the user's health-related data, and output is encrypted and securely stored data. This process allows users to provide data and use the system with confidence.

[0522] (Application Example 1)

[0523] Next, we will explain Application Example 1. In the following explanation, 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."

[0524] While managing health risks using individual health data has become widespread in modern society, there is a challenge in the lack of sufficient collective health management methods to improve the health of the entire population of a city. Beyond individual health advice, there is a need to establish methods for understanding the health status of the entire city and promoting the health of all residents.

[0525] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0526] In this invention, the server includes means for collecting health-related information from wearable devices and information processing devices, means for integrating the collected health-related information, correcting outliers and filling in missing values, and means for monitoring the health status of the entire urban population and providing information for collective health management. This makes it possible to provide a comprehensive healthcare system aimed at promoting the health of the entire population, as well as individual health management.

[0527] A "wearable device" is an electronic device that a user can wear on their body and that has the function of measuring and collecting health-related information.

[0528] An "information processing device" is an electronic device that can receive data and perform calculations, and it plays a role in managing health-related information.

[0529] "Health-related information" refers to data about an individual's physical condition and lifestyle, and specifically includes indicators such as heart rate, steps taken, sleep patterns, blood pressure, and body temperature.

[0530] "Integration" refers to the process of combining and organizing data obtained from different formats or sources into a single format.

[0531] "Correction of outliers" refers to the process of detecting values ​​in the collected data that deviate from the normal range, removing their influence, and adjusting the data to a format suitable for analysis.

[0532] "Missing value imputation" is a technique for filling in data that is not recorded or is missing in a dataset, in order to construct a complete dataset.

[0533] "Generative artificial intelligence technology" is a technology that uses computer programs and algorithms to learn patterns based on data and make predictions and recommendations.

[0534] "Health risk" is an assessment indicator that shows the probability of an individual developing a specific disease or experiencing a deterioration in their health.

[0535] "Personalized preventive measures" refer to specific advice and action plans designed specifically for an individual to maintain and improve their health.

[0536] "Presenting information visually and through notification features" refers to features that display information using the device screen or use sound and vibration to inform the user of important information.

[0537] "Data encryption" is a technology that transforms data to protect its confidentiality and safeguard it from unauthorized access.

[0538] "Access control" refers to a security management technique that restricts access to specific data or systems to only authorized users.

[0539] "Monitoring the health status of the entire urban population" is a process of comprehensively monitoring and analyzing the health status of all people living in a given city.

[0540] "Providing information for collective health management" refers to providing data and analysis results to assess health conditions at the city or community level and to formulate policies and initiatives aimed at improving the health of the entire population.

[0541] The system implementing the present invention collects health-related information via a wearable device and an information processing device, and performs centralized processing on a server.

[0542] The server receives data from wearable devices and information processing devices using Bluetooth or Wi-Fi technology. The wearable devices used incorporate heart rate sensors and accelerometers, and have the function of continuously measuring the user's daily activity metrics. The smartphone, acting as the information processing device, functions as the interface with the user and has applications installed for displaying data and providing notifications.

[0543] The received health-related information is stored in the server's database and preprocessed using the Pandas library. This automatically corrects for outliers and imputes missing values, preparing the dataset for advanced analysis. Then, a generative AI model using TensorFlow predicts the health risks for individual users. This model is trained on historical data and can predict, for example, the risk of cardiovascular disease with high accuracy.

[0544] Personalized preventative measures are generated for each user based on predicted risks. Specific advice on exercise metrics and nutritional content is provided through the application. This allows users to understand their own health status and take appropriate health management actions.

[0545] Furthermore, the server generates data that contributes to the formulation of public policies based on the collective health status of the entire city. The data collected from residents is comprehensively analyzed and used for smart city health initiatives.

[0546] For example, if a user's heart rate remains higher than normal for an extended period, notifications regarding appropriate breathing techniques and stress management will be sent to their smartphone. An example of a prompt message might be, "Based on the user's heart rate and step count data, generate relevant health risks and optimal preventative measures." The generating AI model then performs the analysis according to these instructions.

[0547] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0548] Step 1:

[0549] The device collects health-related information from the user's wearable device. Inputs include sensor data such as heart rate, steps, and sleep patterns, which are then transferred to a smartphone via Bluetooth or Wi-Fi. Outputs are the initial, unprocessed data stored in the device.

[0550] Step 2:

[0551] The device transmits collected health-related information to the server. The input is unprocessed health data within the device, and the output is raw data received by the server. An internet connection is used for data transmission.

[0552] Step 3:

[0553] The server stores the received health-related information in a database. The input is raw data sent from the terminal, and the output is a queryable database state. This ensures data persistence.

[0554] Step 4:

[0555] The server uses the Pandas library to preprocess the data. The input is raw data read from the database, and outlier correction and missing value imputation are performed automatically. The output is a well-prepared dataset ready for analysis.

[0556] Step 5:

[0557] The server uses TensorFlow to apply a generative AI model and predict individual health risks from a prepared dataset. The input is prepared health data, and the AI ​​model analyzes this data to output the probability of health risk.

[0558] Step 6:

[0559] The server generates optimal preventative measures for the user based on predicted health risks. The input is the probability of health risk, and the output is information such as specific exercise plans and nutritional advice. Individual preventative measures are designed using prompts from the generating AI model.

[0560] Step 7:

[0561] The server sends the generated preventative measures to the terminal, which then displays the information visually. The input is specific preventative measures, and the output is notifications and information displayed on the terminal. The user then uses this information to manage their health.

[0562] Step 8:

[0563] The server securely processes all transactions using data encryption technology and manages access control. Inputs are unencrypted health-related data, while outputs are encrypted data accessible only to users with access rights.

[0564] Step 9:

[0565] The server provides urban authorities with statistical analysis results to support collective health management. The input is integrated data for the entire population, and the output is policy recommendations and improvement proposals based on the overall health status of the city. This can then be used to develop health policies for smart cities.

[0566] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0567] This invention is a system that predicts health risks based on the user's health-related data, recognizes the user's emotional state, and reflects the results in preventative measures. The aim is to achieve more personalized and appropriate health management. The system is implemented as follows:

[0568] First, the device collects the user's daily physical data using wearable devices and information terminals. This includes heart rate, steps taken, and sleep data. It also captures emotional states from voice and facial expression data acquired by microphones and cameras. Based on this data, the device gains a detailed understanding of the user's current health and emotional state.

[0569] Next, the server receives health and emotional data collected from the terminals and first corrects for outliers and imputes missing values. This process enables analysis based on highly accurate data. Then, using generative artificial intelligence technology and statistical models, health risks are predicted. The predicted risks are evaluated for diseases such as cardiovascular disease and diabetes.

[0570] The server further analyzes the user's emotional state using an emotion engine. Here, it evaluates the user's voice tone, facial expressions, and biometric responses from sensors to determine their current emotion. For example, if stress or anxiety levels are high, this is taken into account when adjusting risk assessments and preventative measures.

[0571] Next, based on the obtained risk assessment and emotional state, the server generates personalized preventative measures. These measures include specific advice on exercise and diet, as well as suggestions to support the user's mental health. For example, a user experiencing high stress levels might be advised on the importance of relaxation exercises and rest.

[0572] The device notifies users of generated preventative measures and presents them through the user interface. It adjusts the tone and timing of notifications based on the user's emotional state, providing information in a way that is more likely to be taken action. This user-friendly interface supports users in their daily health management.

[0573] Finally, the server implements data encryption and strict access controls to ensure the protection of data across the entire system. This allows users to be assured that their health and emotional data is handled securely and to use the system with peace of mind.

[0574] This system allows users to access not only physical health management but also approaches necessary for improving their emotional state, leading to an overall improvement in their well-being. For example, during periods of heightened anxiety, the system may suggest special relaxation techniques and adjust the schedule to ensure the user has the necessary time to relax.

[0575] The following describes the processing flow.

[0576] Step 1:

[0577] The device collects the user's daily health-related data using wearable devices and smartphones. This includes physical data such as steps taken, heart rate, and sleep duration. It also uses the device's microphone and camera to capture the user's voice and facial expression data, collecting initial data on their emotional state.

[0578] Step 2:

[0579] The server receives health-related and emotional data transmitted from terminals. This data is first centralized, and then anomalies are detected and corrected, and missing values ​​are imputed to ensure data integrity. This prepares clean data suitable for analysis.

[0580] Step 3:

[0581] The server uses generative AI technology and statistical models to analyze integrated health-related data and predict specific health risks. This is a process of quantitatively assessing the risk of developing diseases such as hypertension and diabetes.

[0582] Step 4:

[0583] The server uses an emotion engine to recognize the user's emotional state from acquired voice and facial expression data. For example, it analyzes stress levels and changes in emotional state from voice tone and facial expressions to identify the current emotional state.

[0584] Step 5:

[0585] The server comprehensively considers predicted health risks and perceived emotional states to generate personalized preventative measures tailored to the user. These measures include advice on managing physical health and suggestions for relaxation techniques and meditation exercises to support emotional well-being.

[0586] Step 6:

[0587] The device notifies the user of the generated preventative measures. The user interface is user-friendly and designed to be easily understood and implemented. Furthermore, the timing and content of notifications are appropriately adjusted to take the user's emotional state into consideration.

[0588] Step 7:

[0589] The server encrypts collected health and emotional data to protect the entire system's data, ensuring user privacy. Strict access control is also maintained to prevent misuse of data.

[0590] This process allows users to comprehensively understand their own health status and take preventative measures, thereby maintaining their health both physically and emotionally.

[0591] (Example 2)

[0592] Next, we will describe Example 2. 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."

[0593] In recent years, as the importance of health management and mental healthcare has increased, providing personalized approaches to users has become crucial. However, traditional systems have struggled to integrate health and emotional data and propose optimal preventative measures for individual users. Furthermore, there has been the challenge of insufficient data privacy guarantees.

[0594] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0595] In this invention, the server includes means for integrating biometric and emotional data collected from users, means for correcting outliers and imputing missing values ​​in the integrated data, means for evaluating health risks using generative machine learning techniques and analytical models based on the stored data, means for analyzing the user's emotional state and reflecting the results in the health risk assessment, and means for providing encryption and control functions for the purpose of protecting personal information data. This makes it possible to provide users with highly accurate risk assessments and personalized preventive measures.

[0596] "Biometric data collected from users" refers to information about the user's body, such as heart rate, steps taken, and sleep patterns, obtained through wearable devices and information terminals.

[0597] "Emotional data" refers to information used to capture a user's current emotional state, based on their voice tone, facial expressions, and physiological responses obtained from sensors.

[0598] "Correction of outliers" is the process of correcting values ​​in the collected data that are deemed inaccurate to within the normal range.

[0599] "Missing value imputation" is the process of filling in missing information in a dataset based on known data.

[0600] "Generative machine learning technology" is a technique that generates algorithms and models used for data analysis and prediction, and then uses the patterns obtained in that process to make predictions.

[0601] An "analytical model" is a mathematical or statistical method used to derive specific results or conclusions through the analysis and processing of data.

[0602] "Assessing health risks" means analyzing and estimating the likelihood of a specific health problem occurring based on the user's health status.

[0603] "Personalized preventative measures" refer to providing health management and preventative suggestions that are best suited to each user's individual health condition and lifestyle.

[0604] "Encryption" is a technology that protects data by transforming it using a specific algorithm in order to store it securely and prevent unauthorized access by third parties.

[0605] A "control function" is a function that manages and restricts access and operations so that the system operates as intended.

[0606] This invention is a system that comprehensively analyzes a user's health-related data and emotional state to provide personalized health management strategies. The embodiments thereof are described below.

[0607] First, the device collects biometric and emotional data through wearable devices and information terminals worn by the user. This data includes heart rate, steps taken, and sleep patterns. Emotional data is collected and analyzed using the device's microphone and camera to capture the user's voice and facial expressions.

[0608] Next, the server receives the data sent from the terminal. This data is stored in a data storage system, where outliers are corrected and missing values ​​are imputed. This is done using data preprocessing algorithms, which are often implemented in programming languages ​​such as Python or R.

[0609] The server then uses a generative AI model to predict health risks. Specific software used might include TensorFlow or PyTorch. The server uses these models to assess, for example, the probability of developing cardiovascular disease or diabetes. An example of a prompt might be, "Based on the user's most recent health data, predict the risk of developing a disease in the next week."

[0610] Furthermore, the server uses an emotion engine to analyze the collected voice and facial expression data. This analysis evaluates the user's emotional state (e.g., high stress or anxiety) and reflects this in the health risk assessment.

[0611] Ultimately, the server generates personalized preventative measures based on the analysis results. For example, users with high heart rates and stress levels might be recommended yoga or relaxation exercises. These preventative measures are communicated to the user via their device and visually displayed through the user interface. The notifications are tailored to the user's emotional state and presented in an easy-to-follow format.

[0612] Finally, the server uses data encryption technology to ensure the privacy of user data. By using this system, users can be assured that their data is securely protected. In this way, the system can support users in both their physical and emotional aspects, thereby improving overall health management.

[0613] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0614] Step 1:

[0615] The device collects biometric and emotional data from wearable devices and information terminals as input. Specifically, it acquires data such as heart rate, steps, and sleep patterns from device sensors, and voice and facial expression data using microphones and cameras. This data is stored in a database within the device. The output is a set of raw health and emotional data.

[0616] Step 2:

[0617] The device transmits collected biometric and emotional data to the server. The input is a collection of data stored on the device. The data is encrypted when transmitted to the server. This data transfer allows the server to receive all relevant data and prepare it for continuous analysis.

[0618] Step 3:

[0619] The server uses the received data as input to correct for outliers and impute missing values. Outliers are detected using statistical methods, and abnormal elements are identified and corrected. For example, if the heart rate is abnormally high, it is brought closer to the mean. Missing data is imputed based on the data's trend. The output is a corrected and complete dataset.

[0620] Step 4:

[0621] The server uses a generated AI model, taking corrected data as input, to predict health risks. This process employs machine learning algorithms (e.g., neural networks) to assess health risks based on prompts. For example, a prompt might read, "Predict the risk of cardiovascular disease based on the user's blood pressure data." The output is either a risk score or a predicted health risk category.

[0622] Step 5:

[0623] The server uses an emotion engine to determine emotional states by taking emotional data as input. Specifically, it performs voice analysis and facial recognition to quantify stress and anxiety levels. This process evaluates the user's mental state and incorporates it into the health risk assessment results. The output is an indicator of emotional state.

[0624] Step 6:

[0625] The server uses health risk predictions and emotional state indicators as input to generate personalized preventative measures. At this stage, it suggests optimal lifestyle improvement advice (e.g., exercise, nutrition, wellness activities) to the user based on the data. The output is a specific health management plan.

[0626] Step 7:

[0627] The device takes a personalized health management plan as input and notifies the user through a user-friendly interface. Notifications are delivered in real time and are adjusted to take into account the user's emotional state. The output is the display of the notification content on the device.

[0628] (Application Example 2)

[0629] Next, we will explain application example 2. In the following explanation, 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."

[0630] In modern society, people face stress, anxiety, and the need to maintain their health. However, it is not easy to simultaneously and appropriately manage individual health and emotional states and provide individually customized health management measures based on these factors. In particular, there is a lack of systems that comprehensively support these aspects while considering the impact of a user's emotional state on their health.

[0631] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0632] In this invention, the server includes means for collecting health-related information from wearable devices and computing terminals; means for integrating the collected health-related information and correcting outliers and imputing missing values; means for predicting health risks using generative artificial intelligence technology and statistical models based on the integrated health-related information; and means for analyzing the user's emotions based on collected emotional state data and adjusting the health risk predictions considering the emotional state. This makes it possible to provide personalized health management that takes into account the diverse health and emotional states of the user.

[0633] A "wearable device" is an electronic device that a user wears on their body and has the function of collecting physiological data on a daily basis.

[0634] A "computing terminal" is a digital device used for collecting and processing data, and includes personal computers and smartphones.

[0635] "Health-related information" refers to data that includes the user's physiological indicators such as heart rate, steps taken, and sleep patterns.

[0636] "Correcting outliers" is the process of correcting clearly incorrect values ​​in collected data to bring them back within an appropriate range.

[0637] "Missing value imputation" is the process of filling in the missing information in a dataset with reasonable estimates.

[0638] "Generative artificial intelligence technology" refers to algorithms that have the ability to learn patterns from large amounts of data and perform predictions and classifications.

[0639] A "statistical model" is a mathematical framework used to analyze data and understand the relationships between different factors.

[0640] "Health risk" refers to a prediction of the likelihood of a specific disease or health problem occurring in the future.

[0641] "Emotional state data" refers to information about a user's emotions, estimated based on changes in voice tone and facial expressions.

[0642] "Health management measures" refer to specific actions and recommendations provided to maintain or improve the user's health.

[0643] "Notifying by voice or visual means conveying information to the user through speech synthesis, images, text, etc."

[0644] "Data encryption" is a technology that transforms information using a specific algorithm to protect it from unauthorized access.

[0645] "Management measures" refer to the process of securely handling user data and controlling access as needed.

[0646] The system implementing the invention monitors the user's health and emotional state in real time and provides customized health management measures based on this data. This system combines wearable devices and computing terminals and uses the following hardware and software for communication and processing.

[0647] Users wear wearable devices to collect physical activity and physiological data on a daily basis. This data is sent to a computing terminal, where outliers are corrected and missing values ​​are imputed. The computing terminal then uses a generative AI model to predict health risks based on the integrated health-related information. TensorFlow is used in the generative AI model to enhance its ability to learn patterns from the data and predict risks.

[0648] The server uses voice tone and facial expression data from sensors to analyze the emotional state from the collected data. If the user's emotional state affects the assessment of health risks, it generates preventive measures that take this into account. Specifically, if the user is experiencing stress, it suggests relaxation activities and provides advice tailored to their health condition.

[0649] The device notifies the user of the generated preventative measures via voice or visual means. The system uses encryption technology to protect information and ensure the security of the user's health and emotional state data. A specific example of its use is a system that suggests meditation or light exercise if the user's heart rate is high and their emotional state data indicates stress.

[0650] An example of a prompt to input into a generating AI model is: "Please tell me an approach to designing a robot assistant system that monitors a user's health and emotional state in real time and suggests appropriate preventative measures."

[0651] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0652] Step 1:

[0653] The device collects user health-related information from wearable devices. Inputs include physiological indicators such as heart rate, steps, and sleep data, while output is the recording and transmission of this data to the computing device. The device uses wireless communication, such as Bluetooth, to acquire this data and monitors the individual's health status in real time through data streaming.

[0654] Step 2:

[0655] The server receives health-related information transmitted from terminals and performs integrated processing within the database. The input is a set of physiological data, and the output is consistent data with outliers corrected and missing values ​​imputed. The server detects abnormal heart rate values ​​and replaces them within the legend range using an algorithm. Furthermore, it maintains data integrity by adding estimated values ​​for missing values.

[0656] Step 3:

[0657] The server applies generative AI models and statistical models to harmonized data to predict health risks. The input is harmonized health-related information, and the output is a predicted value for the risk of a specific disease. The server runs the model using TensorFlow and calculates cardiovascular risk and diabetes risk as probabilities based on patterns learned from large amounts of data.

[0658] Step 4:

[0659] The device uses a camera and microphone to collect data on the user's emotional state and transmits it to a server. Inputs are voice data and facial expression data, while output is real-time analyzed emotional information. The device utilizes voice tone analysis and image processing technologies to capture emotional states such as anger, anxiety, and happiness.

[0660] Step 5:

[0661] The server synthesizes the user's health risks and emotional state to generate individually customized preventative measures. Input is predicted health risk and emotional data, while output is preventative measures including relaxation methods and lifestyle improvements. The server uses a generative AI to determine the best advice and generate motivating suggestions for risk reduction.

[0662] Step 6:

[0663] The user terminal notifies the user of the generated preventative measures via voice or visual means. The input is text data of the preventative measures, and the output is a visual or auditory notification delivered to the user. The terminal displays reminders in an actionable format and provides advice in a friendly tone using speech synthesis.

[0664] Step 7:

[0665] The server implements data encryption and access control to securely manage all health and emotional data. Inputs are users' personal data, and outputs are stored in a securely protected data store. The server applies encryption procedures such as AES and allows access only from specific authorized devices.

[0666] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0667] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0668] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0669] [Fourth Embodiment]

[0670] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0671] As shown in Figure 7, the 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.

[0672] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0673] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0674] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0675] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0676] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0677] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0678] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0679] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0680] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0681] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0682] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0683] This invention provides users with personalized preventative measures for health management based on a wide variety of health-related data acquired from wearable devices and information terminals. The following means are necessary to implement the invention.

[0684] First, the device has the function of collecting health data from the user, which is achieved through sensors built into wearable devices or smartphones. This data includes steps taken, heart rate, sleep patterns, body temperature, blood pressure, etc. It also acquires electronic health records, such as blood test results, provided by medical institutions as needed.

[0685] Next, the server receives the collected data and uses data integration means to integrate and preprocess it. It detects and corrects outliers, imputes missing values, and processes the data so that it is suitable for analysis.

[0686] Subsequently, the server uses the compiled health-related data, employing generative AI technology and statistical models to predict specific health risks for each user. For example, the risk of developing lifestyle-related diseases such as cardiovascular disease and diabetes is assessed. This assessment is based on a model trained on historical datasets, enabling highly accurate predictions.

[0687] Furthermore, the server generates appropriate preventative measures for each user based on the predicted risk. These preventative measures include specific recommendations related to exercise, diet, and sleep. For example, high-risk users may receive suggestions for specific exercise plans and dietary restrictions.

[0688] The generated preventative measures are presented to the user via the device. The device's user interface is intuitive and designed to be easily understood and implemented by the user. Notification and reminder features are used to support the user in forming healthy habits.

[0689] Finally, the server encrypts all collected health-related data and controls data access to protect the data. This ensures user privacy and allows users to use the system with peace of mind.

[0690] Thus, in order to implement the invention, all stages, from data collection and risk prediction to suggesting preventive measures and protecting data privacy, must be carried out in coordination. For example, a user who is predicted to be at risk of cardiovascular disease may be notified of a recommendation to do more than 150 minutes of aerobic exercise per week and advised to limit salt intake in their diet. With such specific instructions, users can take actions to improve their health and reduce their risk of lifestyle-related diseases.

[0691] The following describes the processing flow.

[0692] Step 1:

[0693] The device collects user health-related data through wearable devices and smartphones. This data is acquired in real time and includes steps taken, heart rate, sleep duration, and calorie consumption. Furthermore, through collaboration with medical institutions, it can receive electronic health records with the user's permission.

[0694] Step 2:

[0695] The server receives health-related data sent from the terminal. Since the received data may be in different formats, it is first converted to a standardized format. Next, the collected data is cleaned to detect and correct outliers, and missing values ​​are imputed using past data or average values.

[0696] Step 3:

[0697] The server uses generated AI and statistical models based on the cleaned data to predict the user's future health risks. This process individually assesses the risk of developing specific diseases (e.g., cardiovascular disease, diabetes) through analysis of the user's historical data and similar past cases. This makes it possible to quantitatively understand the user's future health status.

[0698] Step 4:

[0699] The server generates personalized preventative measures tailored to the predicted health risks. These measures may include recommendations for exercise frequency and amount, dietary changes, and improvements to sleep patterns. For specific risks, it may also recommend consulting a doctor or undergoing additional tests.

[0700] Step 5:

[0701] The device notifies the user of preventative measures generated from the server. These notifications are delivered via an interactive interface, providing visual and audio feedback. Users can use this information to adjust their daily behavior. The device also provides a reminder function, periodically informing the user of actions that should be taken.

[0702] Step 6:

[0703] The server implements data encryption and access control throughout the entire system to protect user data privacy. It also establishes a process to provide users with transparent information about what data is collected and how it is used, and to obtain their consent for its use.

[0704] (Example 1)

[0705] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0706] In modern society, sophisticated health management tailored to individual lifestyles and health conditions is required. However, effectively collecting and analyzing diverse health-related data and providing personalized preventive measures is not easy, and an efficient system is needed. Furthermore, ensuring user privacy while providing reliable health risk assessments and concrete preventive measures is a challenge.

[0707] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0708] In this invention, the server includes means for acquiring information on the user's physical activity and physiological state, means for integrating the acquired information, detecting and adjusting for anomalies, and estimating missing values, and means for predicting health risks using machine learning techniques and statistical inference generated based on the integrated information. This enables the user to receive a more accurate assessment of health risks and personalized preventive measures.

[0709] "Information about the user's physical activity and physiological state" refers to data such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure, which are collected to understand an individual's health status.

[0710] "Means of acquisition" refers to technologies for collecting users' health-related data in real time through information gathering devices such as wearable devices and smartphones.

[0711] "Means for integrating, detecting and adjusting for anomalies, and estimating missing values" refers to the process of combining health-related information collected from multiple data sources, supplementing data gaps, and preparing it for analysis.

[0712] "Machine learning techniques and statistical inference" are methods for learning patterns from past data and predicting future outcomes based on new data.

[0713] "Methods for predicting health risks" refer to the process of using machine learning techniques and statistical models to assess the likelihood of future illness based on an individual's health status.

[0714] "Personalized preventative measures" are specific recommendations regarding exercise, diet, and lifestyle improvements that are provided to address the user's specific health risks.

[0715] A "server" is a central system that analyzes and predicts the collected data and provides results to users.

[0716] An "information terminal" is an electronic device used to display information to a user and send notifications, and includes smartphones and tablet computers.

[0717] "Data encryption and access control measures" refer to security technologies that encrypt collected data and prevent unauthorized access in order to protect user privacy.

[0718] This system is realized by collecting health-related data using information terminals and wearable devices, and performing advanced analysis based on that data, in order to personalize users' health management.

[0719] The devices used are primarily wearable devices and smartphones. These devices use built-in sensors to acquire information about physical activity and physiological states, such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure. This data is transmitted to a server in real time via Bluetooth or Wi-Fi.

[0720] The server integrates the received data, detecting and correcting outliers and estimating missing values. The integrated information is then used in a process to predict health risks, employing machine learning techniques and statistical inference. The generated AI model learns from previously collected datasets to achieve precise risk assessments. High-performance cloud computing services are typically used for this process.

[0721] Based on predicted health risks, the server generates personalized preventative measures for each user. These include exercise plans, nutritional guidance, and sleep improvement suggestions, and the generated preventative measures are sent to the device in an intuitive and easy-to-understand format.

[0722] Users receive notifications about preventative measures through their information terminals and have the opportunity to improve their lifestyles by following the provided guidelines. The terminal's user interface is designed to be integrated into daily routines, utilizing pop-up notifications and reminder functions.

[0723] A crucial aspect of the data in this system is data confidentiality and the protection of user privacy. The collected information is securely managed on the servers using advanced encryption technology to prevent unauthorized access and provide a safe environment for users.

[0724] As a concrete example, the following prompt could be used as input to a generative AI model: "Please propose a health risk assessment and preventive measures for a 40-year-old male user who takes fewer than 5,000 steps per day on average and performs less than 30 minutes of aerobic exercise once a week." Based on this prompt, the AI ​​would analyze relevant data and provide the user with a specific and effective health management plan.

[0725] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0726] Step 1:

[0727] The device collects user health-related data. Using wearable devices and smartphones, it obtains information such as steps taken, heart rate, sleep patterns, body temperature, and blood pressure. The input to this process is raw data from sensors, and the output is a set of collected data. This dataset is then ready to be transmitted to the next processing step via Bluetooth or Wi-Fi.

[0728] Step 2:

[0729] The server receives health-related data sent from the terminal. It then detects anomalous data points and corrects them using algorithms. If there is missing data, it estimates and fills in its values ​​using statistical methods. The input is the raw data from the terminal, and the output is the cleaned and imputed dataset.

[0730] Step 3:

[0731] The server applies a generative AI model using prepared data to predict health risks. It assesses the risk of specific diseases and health conditions (e.g., cardiovascular disease, diabetes) and generates results. The input is a pre-processed dataset, and the output is a user-specific risk assessment. The AI ​​model is trained on a vast amount of historical data, enabling it to predict risks with high accuracy.

[0732] Step 4:

[0733] The server generates personalized preventative measures based on predicted health risks. These preventative measures include specific recommendations regarding exercise, diet, and sleep. The input is a health risk assessment, and the output is a set of recommendations for the user. This content is customized to the user's lifestyle.

[0734] Step 5:

[0735] The generated preventative measures are presented to the user via the device. The device visually displays the information and sends important health recommendations to the user as pop-up notifications and reminders. The input is a set of recommendations from the server, and the output is an intuitive interface that the user can easily understand. Based on this, the user can decide on and take healthy behaviors.

[0736] Step 6:

[0737] The server encrypts all collected health-related data and implements access control to protect user privacy. Input is the user's health-related data, and output is encrypted and securely stored data. This process allows users to provide data and use the system with confidence.

[0738] (Application Example 1)

[0739] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0740] While managing health risks using individual health data has become widespread in modern society, there is a challenge in the lack of sufficient collective health management methods to improve the health of the entire population of a city. Beyond individual health advice, there is a need to establish methods for understanding the health status of the entire city and promoting the health of all residents.

[0741] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0742] In this invention, the server includes means for collecting health-related information from wearable devices and information processing devices, means for integrating the collected health-related information, correcting outliers and filling in missing values, and means for monitoring the health status of the entire urban population and providing information for collective health management. This makes it possible to provide a comprehensive healthcare system aimed at promoting the health of the entire population, as well as individual health management.

[0743] A "wearable device" is an electronic device that a user can wear on their body and that has the function of measuring and collecting health-related information.

[0744] An "information processing device" is an electronic device that can receive data and perform calculations, and it plays a role in managing health-related information.

[0745] "Health-related information" refers to data about an individual's physical condition and lifestyle, and specifically includes indicators such as heart rate, steps taken, sleep patterns, blood pressure, and body temperature.

[0746] "Integration" refers to the process of combining and organizing data obtained from different formats or sources into a single format.

[0747] "Correction of outliers" refers to the process of detecting values ​​in the collected data that deviate from the normal range, removing their influence, and adjusting the data to a format suitable for analysis.

[0748] "Missing value imputation" is a technique for filling in data that is not recorded or is missing in a dataset, in order to construct a complete dataset.

[0749] "Generative artificial intelligence technology" is a technology that uses computer programs and algorithms to learn patterns based on data and make predictions and recommendations.

[0750] "Health risk" is an assessment indicator that shows the probability of an individual developing a specific disease or experiencing a deterioration in their health.

[0751] "Personalized preventive measures" refer to specific advice and action plans designed specifically for an individual to maintain and improve their health.

[0752] "Presenting information visually and through notification features" refers to features that display information using the device screen or use sound and vibration to inform the user of important information.

[0753] "Data encryption" is a technology that transforms data to protect its confidentiality and safeguard it from unauthorized access.

[0754] "Access control" refers to a security management technique that restricts access to specific data or systems to only authorized users.

[0755] "Monitoring the health status of the entire urban population" is a process of comprehensively monitoring and analyzing the health status of all people living in a given city.

[0756] "Providing information for collective health management" refers to providing data and analysis results to assess health conditions at the city or community level and to formulate policies and initiatives aimed at improving the health of the entire population.

[0757] The system implementing the present invention collects health-related information via a wearable device and an information processing device, and performs centralized processing on a server.

[0758] The server receives data from wearable devices and information processing devices using Bluetooth or Wi-Fi technology. The wearable devices used incorporate heart rate sensors and accelerometers, and have the function of continuously measuring the user's daily activity metrics. The smartphone, acting as the information processing device, functions as the interface with the user and has applications installed for displaying data and providing notifications.

[0759] The received health-related information is stored in the server's database and preprocessed using the Pandas library. This automatically corrects for outliers and imputes missing values, preparing the dataset for advanced analysis. Then, a generative AI model using TensorFlow predicts the health risks for individual users. This model is trained on historical data and can predict, for example, the risk of cardiovascular disease with high accuracy.

[0760] Personalized preventative measures are generated for each user based on predicted risks. Specific advice on exercise metrics and nutritional content is provided through the application. This allows users to understand their own health status and take appropriate health management actions.

[0761] Furthermore, the server generates data that contributes to the formulation of public policies based on the collective health status of the entire city. The data collected from residents is comprehensively analyzed and used for smart city health initiatives.

[0762] For example, if a user's heart rate remains higher than normal for an extended period, notifications regarding appropriate breathing techniques and stress management will be sent to their smartphone. An example of a prompt message might be, "Based on the user's heart rate and step count data, generate relevant health risks and optimal preventative measures." The generating AI model then performs the analysis according to these instructions.

[0763] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0764] Step 1:

[0765] The device collects health-related information from the user's wearable device. Inputs include sensor data such as heart rate, steps, and sleep patterns, which are then transferred to a smartphone via Bluetooth or Wi-Fi. Outputs are the initial, unprocessed data stored in the device.

[0766] Step 2:

[0767] The device transmits collected health-related information to the server. The input is unprocessed health data within the device, and the output is raw data received by the server. An internet connection is used for data transmission.

[0768] Step 3:

[0769] The server stores the received health-related information in a database. The input is raw data sent from the terminal, and the output is a queryable database state. This ensures data persistence.

[0770] Step 4:

[0771] The server uses the Pandas library to preprocess the data. The input is raw data read from the database, and outlier correction and missing value imputation are performed automatically. The output is a well-prepared dataset ready for analysis.

[0772] Step 5:

[0773] The server uses TensorFlow to apply a generative AI model and predict individual health risks from a prepared dataset. The input is prepared health data, and the AI ​​model analyzes this data to output the probability of health risk.

[0774] Step 6:

[0775] The server generates optimal preventative measures for the user based on predicted health risks. The input is the probability of health risk, and the output is information such as specific exercise plans and nutritional advice. Individual preventative measures are designed using prompts from the generating AI model.

[0776] Step 7:

[0777] The server sends the generated preventative measures to the terminal, which then displays the information visually. The input is specific preventative measures, and the output is notifications and information displayed on the terminal. The user then uses this information to manage their health.

[0778] Step 8:

[0779] The server securely processes all transactions using data encryption technology and manages access control. Inputs are unencrypted health-related data, while outputs are encrypted data accessible only to users with access rights.

[0780] Step 9:

[0781] The server provides urban authorities with statistical analysis results to support collective health management. The input is integrated data for the entire population, and the output is policy recommendations and improvement proposals based on the overall health status of the city. This can then be used to develop health policies for smart cities.

[0782] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0783] This invention is a system that predicts health risks based on the user's health-related data, recognizes the user's emotional state, and reflects the results in preventative measures. The aim is to achieve more personalized and appropriate health management. The system is implemented as follows:

[0784] First, the device collects the user's daily physical data using wearable devices and information terminals. This includes heart rate, steps taken, and sleep data. It also captures emotional states from voice and facial expression data acquired by microphones and cameras. Based on this data, the device gains a detailed understanding of the user's current health and emotional state.

[0785] Next, the server receives health and emotional data collected from the terminals and first corrects for outliers and imputes missing values. This process enables analysis based on highly accurate data. Then, using generative artificial intelligence technology and statistical models, health risks are predicted. The predicted risks are evaluated for diseases such as cardiovascular disease and diabetes.

[0786] The server further analyzes the user's emotional state using an emotion engine. Here, it evaluates the user's voice tone, facial expressions, and biometric responses from sensors to determine their current emotion. For example, if stress or anxiety levels are high, this is taken into account when adjusting risk assessments and preventative measures.

[0787] Next, based on the obtained risk assessment and emotional state, the server generates personalized preventative measures. These measures include specific advice on exercise and diet, as well as suggestions to support the user's mental health. For example, a user experiencing high stress levels might be advised on the importance of relaxation exercises and rest.

[0788] The device notifies users of generated preventative measures and presents them through the user interface. It adjusts the tone and timing of notifications based on the user's emotional state, providing information in a way that is more likely to be taken action. This user-friendly interface supports users in their daily health management.

[0789] Finally, the server implements data encryption and strict access controls to ensure the protection of data across the entire system. This allows users to be assured that their health and emotional data is handled securely and to use the system with peace of mind.

[0790] This system allows users to access not only physical health management but also approaches necessary for improving their emotional state, leading to an overall improvement in their well-being. For example, during periods of heightened anxiety, the system may suggest special relaxation techniques and adjust the schedule to ensure the user has the necessary time to relax.

[0791] The following describes the processing flow.

[0792] Step 1:

[0793] The device collects the user's daily health-related data using wearable devices and smartphones. This includes physical data such as steps taken, heart rate, and sleep duration. It also uses the device's microphone and camera to capture the user's voice and facial expression data, collecting initial data on their emotional state.

[0794] Step 2:

[0795] The server receives health-related and emotional data transmitted from terminals. This data is first centralized, and then anomalies are detected and corrected, and missing values ​​are imputed to ensure data integrity. This prepares clean data suitable for analysis.

[0796] Step 3:

[0797] The server uses generative AI technology and statistical models to analyze integrated health-related data and predict specific health risks. This is a process of quantitatively assessing the risk of developing diseases such as hypertension and diabetes.

[0798] Step 4:

[0799] The server uses an emotion engine to recognize the user's emotional state from acquired voice and facial expression data. For example, it analyzes stress levels and changes in emotional state from voice tone and facial expressions to identify the current emotional state.

[0800] Step 5:

[0801] The server comprehensively considers predicted health risks and perceived emotional states to generate personalized preventative measures tailored to the user. These measures include advice on managing physical health and suggestions for relaxation techniques and meditation exercises to support emotional well-being.

[0802] Step 6:

[0803] The device notifies the user of the generated preventative measures. The user interface is user-friendly and designed to be easily understood and implemented. Furthermore, the timing and content of notifications are appropriately adjusted to take the user's emotional state into consideration.

[0804] Step 7:

[0805] The server encrypts collected health and emotional data to protect the entire system's data, ensuring user privacy. Strict access control is also maintained to prevent misuse of data.

[0806] This process allows users to comprehensively understand their own health status and take preventative measures, thereby maintaining their health both physically and emotionally.

[0807] (Example 2)

[0808] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0809] In recent years, as the importance of health management and mental healthcare has increased, providing personalized approaches to users has become crucial. However, traditional systems have struggled to integrate health and emotional data and propose optimal preventative measures for individual users. Furthermore, there has been the challenge of insufficient data privacy guarantees.

[0810] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0811] In this invention, the server includes means for integrating biometric and emotional data collected from users, means for correcting outliers and imputing missing values ​​in the integrated data, means for evaluating health risks using generative machine learning techniques and analytical models based on the stored data, means for analyzing the user's emotional state and reflecting the results in the health risk assessment, and means for providing encryption and control functions for the purpose of protecting personal information data. This makes it possible to provide users with highly accurate risk assessments and personalized preventive measures.

[0812] "Biometric data collected from users" refers to information about the user's body, such as heart rate, steps taken, and sleep patterns, obtained through wearable devices and information terminals.

[0813] "Emotional data" refers to information used to capture a user's current emotional state, based on their voice tone, facial expressions, and physiological responses obtained from sensors.

[0814] "Correction of outliers" is the process of correcting values ​​in the collected data that are deemed inaccurate to within the normal range.

[0815] "Missing value imputation" is the process of filling in missing information in a dataset based on known data.

[0816] "Generative machine learning technology" is a technique that generates algorithms and models used for data analysis and prediction, and then uses the patterns obtained in that process to make predictions.

[0817] An "analytical model" is a mathematical or statistical method used to derive specific results or conclusions through the analysis and processing of data.

[0818] "Assessing health risks" means analyzing and estimating the likelihood of a specific health problem occurring based on the user's health status.

[0819] "Personalized preventative measures" refer to providing health management and preventative suggestions that are best suited to each user's individual health condition and lifestyle.

[0820] "Encryption" is a technology that protects data by transforming it using a specific algorithm in order to store it securely and prevent unauthorized access by third parties.

[0821] A "control function" is a function that manages and restricts access and operations so that the system operates as intended.

[0822] This invention is a system that comprehensively analyzes a user's health-related data and emotional state to provide personalized health management strategies. The embodiments thereof are described below.

[0823] First, the device collects biometric and emotional data through wearable devices and information terminals worn by the user. This data includes heart rate, steps taken, and sleep patterns. Emotional data is collected and analyzed using the device's microphone and camera to capture the user's voice and facial expressions.

[0824] Next, the server receives the data sent from the terminal. This data is stored in a data storage system, where outliers are corrected and missing values ​​are imputed. This is done using data preprocessing algorithms, which are often implemented in programming languages ​​such as Python or R.

[0825] The server then uses a generative AI model to predict health risks. Specific software used might include TensorFlow or PyTorch. The server uses these models to assess, for example, the probability of developing cardiovascular disease or diabetes. An example of a prompt might be, "Based on the user's most recent health data, predict the risk of developing a disease in the next week."

[0826] Furthermore, the server uses an emotion engine to analyze the collected voice and facial expression data. This analysis evaluates the user's emotional state (e.g., high stress or anxiety) and reflects this in the health risk assessment.

[0827] Ultimately, the server generates personalized preventative measures based on the analysis results. For example, users with high heart rates and stress levels might be recommended yoga or relaxation exercises. These preventative measures are communicated to the user via their device and visually displayed through the user interface. The notifications are tailored to the user's emotional state and presented in an easy-to-follow format.

[0828] Finally, the server uses data encryption technology to ensure the privacy of user data. By using this system, users can be assured that their data is securely protected. In this way, the system can support users in both their physical and emotional aspects, thereby improving overall health management.

[0829] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0830] Step 1:

[0831] The device collects biometric and emotional data from wearable devices and information terminals as input. Specifically, it acquires data such as heart rate, steps, and sleep patterns from device sensors, and voice and facial expression data using microphones and cameras. This data is stored in a database within the device. The output is a set of raw health and emotional data.

[0832] Step 2:

[0833] The device transmits collected biometric and emotional data to the server. The input is a collection of data stored on the device. The data is encrypted when transmitted to the server. This data transfer allows the server to receive all relevant data and prepare it for continuous analysis.

[0834] Step 3:

[0835] The server uses the received data as input to correct for outliers and impute missing values. Outliers are detected using statistical methods, and abnormal elements are identified and corrected. For example, if the heart rate is abnormally high, it is brought closer to the mean. Missing data is imputed based on the data's trend. The output is a corrected and complete dataset.

[0836] Step 4:

[0837] The server uses a generated AI model, taking corrected data as input, to predict health risks. This process employs machine learning algorithms (e.g., neural networks) to assess health risks based on prompts. For example, a prompt might read, "Predict the risk of cardiovascular disease based on the user's blood pressure data." The output is either a risk score or a predicted health risk category.

[0838] Step 5:

[0839] The server uses an emotion engine to determine emotional states by taking emotional data as input. Specifically, it performs voice analysis and facial recognition to quantify stress and anxiety levels. This process evaluates the user's mental state and incorporates it into the health risk assessment results. The output is an indicator of emotional state.

[0840] Step 6:

[0841] The server uses health risk predictions and emotional state indicators as input to generate personalized preventative measures. At this stage, it suggests optimal lifestyle improvement advice (e.g., exercise, nutrition, wellness activities) to the user based on the data. The output is a specific health management plan.

[0842] Step 7:

[0843] The device takes a personalized health management plan as input and notifies the user through a user-friendly interface. Notifications are delivered in real time and are adjusted to take into account the user's emotional state. The output is the display of the notification content on the device.

[0844] (Application Example 2)

[0845] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0846] In modern society, people face stress, anxiety, and the need to maintain their health. However, it is not easy to simultaneously and appropriately manage individual health and emotional states and provide individually customized health management measures based on these factors. In particular, there is a lack of systems that comprehensively support these aspects while considering the impact of a user's emotional state on their health.

[0847] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0848] In this invention, the server includes means for collecting health-related information from wearable devices and computing terminals; means for integrating the collected health-related information and correcting outliers and imputing missing values; means for predicting health risks using generative artificial intelligence technology and statistical models based on the integrated health-related information; and means for analyzing the user's emotions based on collected emotional state data and adjusting the health risk predictions considering the emotional state. This makes it possible to provide personalized health management that takes into account the diverse health and emotional states of the user.

[0849] A "wearable device" is an electronic device that a user wears on their body and has the function of collecting physiological data on a daily basis.

[0850] A "computing terminal" is a digital device used for collecting and processing data, and includes personal computers and smartphones.

[0851] "Health-related information" refers to data that includes the user's physiological indicators such as heart rate, steps taken, and sleep patterns.

[0852] "Correcting outliers" is the process of correcting clearly incorrect values ​​in collected data to bring them back within an appropriate range.

[0853] "Missing value imputation" is the process of filling in the missing information in a dataset with reasonable estimates.

[0854] "Generative artificial intelligence technology" refers to algorithms that have the ability to learn patterns from large amounts of data and perform predictions and classifications.

[0855] A "statistical model" is a mathematical framework used to analyze data and understand the relationships between different factors.

[0856] "Health risk" refers to a prediction of the likelihood of a specific disease or health problem occurring in the future.

[0857] "Emotional state data" refers to information about a user's emotions, estimated based on changes in voice tone and facial expressions.

[0858] "Health management measures" refer to specific actions and recommendations provided to maintain or improve the user's health.

[0859] "Notifying by voice or visual means conveying information to the user through speech synthesis, images, text, etc."

[0860] "Data encryption" is a technology that transforms information using a specific algorithm to protect it from unauthorized access.

[0861] "Management measures" refer to the process of securely handling user data and controlling access as needed.

[0862] The system implementing the invention monitors the user's health and emotional state in real time and provides customized health management measures based on this data. This system combines wearable devices and computing terminals and uses the following hardware and software for communication and processing.

[0863] Users wear wearable devices to collect physical activity and physiological data on a daily basis. This data is sent to a computing terminal, where outliers are corrected and missing values ​​are imputed. The computing terminal then uses a generative AI model to predict health risks based on the integrated health-related information. TensorFlow is used in the generative AI model to enhance its ability to learn patterns from the data and predict risks.

[0864] The server uses voice tone and facial expression data from sensors to analyze the emotional state from the collected data. If the user's emotional state affects the assessment of health risks, it generates preventive measures that take this into account. Specifically, if the user is experiencing stress, it suggests relaxation activities and provides advice tailored to their health condition.

[0865] The device notifies the user of the generated preventative measures via voice or visual means. The system uses encryption technology to protect information and ensure the security of the user's health and emotional state data. A specific example of its use is a system that suggests meditation or light exercise if the user's heart rate is high and their emotional state data indicates stress.

[0866] An example of a prompt to input into a generating AI model is: "Please tell me an approach to designing a robot assistant system that monitors a user's health and emotional state in real time and suggests appropriate preventative measures."

[0867] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0868] Step 1:

[0869] The device collects user health-related information from wearable devices. Inputs include physiological indicators such as heart rate, steps, and sleep data, while output is the recording and transmission of this data to the computing device. The device uses wireless communication, such as Bluetooth, to acquire this data and monitors the individual's health status in real time through data streaming.

[0870] Step 2:

[0871] The server receives health-related information transmitted from terminals and performs integrated processing within the database. The input is a set of physiological data, and the output is consistent data with outliers corrected and missing values ​​imputed. The server detects abnormal heart rate values ​​and replaces them within the legend range using an algorithm. Furthermore, it maintains data integrity by adding estimated values ​​for missing values.

[0872] Step 3:

[0873] The server applies generative AI models and statistical models to harmonized data to predict health risks. The input is harmonized health-related information, and the output is a predicted value for the risk of a specific disease. The server runs the model using TensorFlow and calculates cardiovascular risk and diabetes risk as probabilities based on patterns learned from large amounts of data.

[0874] Step 4:

[0875] The device uses a camera and microphone to collect data on the user's emotional state and transmits it to a server. Inputs are voice data and facial expression data, while output is real-time analyzed emotional information. The device utilizes voice tone analysis and image processing technologies to capture emotional states such as anger, anxiety, and happiness.

[0876] Step 5:

[0877] The server synthesizes the user's health risks and emotional state to generate individually customized preventative measures. Input is predicted health risk and emotional data, while output is preventative measures including relaxation methods and lifestyle improvements. The server uses a generative AI to determine the best advice and generate motivating suggestions for risk reduction.

[0878] Step 6:

[0879] The user terminal notifies the user of the generated preventative measures via voice or visual means. The input is text data of the preventative measures, and the output is a visual or auditory notification delivered to the user. The terminal displays reminders in an actionable format and provides advice in a friendly tone using speech synthesis.

[0880] Step 7:

[0881] The server implements data encryption and access control to securely manage all health and emotional data. Inputs are users' personal data, and outputs are stored in a securely protected data store. The server applies encryption procedures such as AES and allows access only from specific authorized devices.

[0882] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0883] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0884] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0885] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0886] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0887] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0888] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0889] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0890] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0891] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0892] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0893] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0894] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0895] 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.

[0896] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0897] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0898] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0899] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0900] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0901] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0902] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0903] The following is further disclosed regarding the embodiments described above.

[0904] (Claim 1)

[0905] A means of collecting health-related data from wearable devices and information terminals,

[0906] A means for integrating collected health-related data, correcting outliers, and imputing missing values,

[0907] A means of predicting health risks using generative artificial intelligence technology and statistical models based on integrated health-related data,

[0908] A means of generating personalized preventive measures in response to predicted health risks,

[0909] A means of visually displaying the generated preventative measures on the device and notifying the user,

[0910] Including data encryption and management measures to protect user data privacy,

[0911] system.

[0912] (Claim 2)

[0913] The system according to claim 1, wherein the aforementioned health risk is used to calculate the probability of a specific disease risk.

[0914] (Claim 3)

[0915] The system according to claim 1, wherein the means for generating the preventive measures provides advice on exercise, nutrition, and sleep.

[0916] "Example 1"

[0917] (Claim 1)

[0918] Means for obtaining information on the user's physical activity and physiological state,

[0919] A means for integrating acquired information, detecting and adjusting for anomalies, and estimating missing values,

[0920] A means of predicting health risks using machine learning techniques and statistical inference generated based on integrated information,

[0921] Means for generating personalized preventive measures to address predicted health risks,

[0922] A means of visually displaying the preventative measures created on an information terminal and notifying the user,

[0923] Includes data encryption and access control measures to protect the confidentiality of user information.

[0924] system.

[0925] (Claim 2)

[0926] The system according to claim 1, wherein the health risk is an assessment of the probability of developing a specific disease.

[0927] (Claim 3)

[0928] The system according to claim 1, wherein the means for generating the preventive measures provides an exercise plan, nutritional guidance, and suggestions for improving sleep.

[0929] "Application Example 1"

[0930] (Claim 1)

[0931] A means for collecting health-related information from wearable devices and information processing devices,

[0932] A means for integrating collected health-related information, correcting outliers, and imputing missing values,

[0933] A means of predicting health risks using generative artificial intelligence technology and statistical models based on integrated health-related information,

[0934] A means of generating personalized preventive measures in response to predicted health risks and presenting them through visual and notification functions,

[0935] Means for data encryption and access control for the protection and management of health information,

[0936] A means of monitoring the health status of the entire urban population and providing information for collective health management,

[0937] A system that includes this.

[0938] (Claim 2)

[0939] The system according to claim 1, wherein the aforementioned health risks calculate the probability of a specific disease risk and provide advice for improving the health of the group, including recommended behaviors.

[0940] (Claim 3)

[0941] The system according to claim 1, wherein the means for generating preventive measures provides individual advice on exercise, nutrition, and sleep, and generates information that contributes to improving health policies for the entire city.

[0942] "Example 2 of combining an emotion engine"

[0943] (Claim 1)

[0944] A device that integrates biometric and emotional data collected from users,

[0945] A device that corrects outliers and imputes missing values ​​in integrated data,

[0946] A device that uses generative machine learning techniques and analytical models based on stored data to assess health risks,

[0947] A device that analyzes the user's emotional state and reflects the results in health risk assessment,

[0948] A device for devising personalized preventive measures based on assessed health risks,

[0949] A device that displays and notifies users of personalized preventive measures on their terminals using an information visualization function,

[0950] A system including devices that provide encryption and control functions for the purpose of protecting personal data.

[0951] (Claim 2)

[0952] The system according to claim 1, wherein the aforementioned health risk is used to calculate the probability of a specific health problem occurring.

[0953] (Claim 3)

[0954] The system according to claim 1, wherein the device for devising the aforementioned preventive measures provides suggestions regarding physical exercise, nutritional intake, and sleep habits.

[0955] "Application example 2 when combining with an emotional engine"

[0956] (Claim 1)

[0957] A means for collecting health-related information from wearable devices and computing terminals,

[0958] A means of integrating collected health-related information, correcting outliers, and imputing missing values,

[0959] A means of predicting health risks using generative artificial intelligence technology and statistical models based on integrated health-related information,

[0960] A means of analyzing a user's emotions based on collected emotional state data and adjusting health risk predictions considering that emotional state,

[0961] A means of generating personalized preventive measures based on predicted health risks and emotional states, and notifying the user of the results via voice or visual means,

[0962] Including data encryption and management measures to protect user data privacy,

[0963] system.

[0964] (Claim 2)

[0965] The system according to claim 1, wherein the aforementioned health risks calculate the probability of a specific disease risk and add coping strategies based on the user's emotional state.

[0966] (Claim 3)

[0967] The system according to claim 1, wherein the means for generating preventive measures provides advice on exercise, nutrition, and rest, and presents relaxation activities tailored to the user's emotional state. [Explanation of Symbols]

[0968] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting health-related information from wearable devices and information processing devices, A means for integrating collected health-related information, correcting outliers, and imputing missing values, A means of predicting health risks using generative artificial intelligence technology and statistical models based on integrated health-related information, A means of generating personalized preventive measures in response to predicted health risks and presenting them through visual and notification functions, Means for data encryption and access control for the protection and management of health information, A means of monitoring the health status of the entire urban population and providing information for collective health management, A system that includes this.

2. The system according to claim 1, wherein the aforementioned health risks calculate the probability of a specific disease risk and provide advice for improving the health of the group, including recommended behaviors.

3. The system according to claim 1, wherein the means for generating preventive measures provides individual advice on exercise, nutrition, and sleep, and generates information that contributes to improving health policies for the entire city.

Images