system

Abstract

We provide the system. [Solution] Methods for collecting biometric data of the elderly, A means for transmitting collected biometric data to a data processing device at a remote location, A means for preprocessing received biometric data in a data processing device and analyzing the health status of elderly people using a health status assessment model, A means for generating health promotion suggestions for the elderly based on the results of a health status analysis, Means of providing the generated suggestions to the elderly, Methods for collecting feedback data from elderly individuals and using them to improve the accuracy of the model, 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 the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In an aging society, the health management of the elderly is an important issue. In conventional methods, it is often relied on regular health checks and diagnoses at medical institutions, making it difficult for daily health management and rapid detection of abnormalities. In addition, the burden on caregivers is large, and efficient care provision is required. Furthermore, there is a lack of appropriate support aimed at preventing the solitary death of the elderly and improving the quality of life. In response to such problems, it is desired to provide a system that can efficiently and effectively address them.

Means for Solving the Problems

[0005] This invention solves the problem by providing a system equipped with means for collecting biometric data of elderly individuals. Specifically, the collected biometric data is transmitted to a remote data processing device, where it is pre-processed, and then the health status of the elderly is analyzed using a health status evaluation model. Based on the results of this analysis, the system is equipped with means for generating and providing health promotion suggestions to the elderly. Furthermore, if an abnormality is detected, an alarm is generated to enable a rapid response. In addition, by collecting feedback data from the elderly and using it to improve the accuracy of the model, the system enhances individual health management capabilities, reduces the burden on caregivers, and enables efficient care provision.

[0006] "Biometric data" refers to information indicating the health status of elderly individuals, and includes data such as walking distance, heart rate, and sleep patterns.

[0007] A "data processing device" is a device installed in a remote location for receiving, pre-processing, and analyzing biological data.

[0008] A "health status assessment model" is an algorithm used to evaluate the health status of elderly individuals based on biometric data, and to identify abnormalities and areas for improvement.

[0009] A "suggestion" is a recommendation generated based on the results of a health status analysis, intended to guide elderly individuals toward health promotion and lifestyle improvement.

[0010] "Feedback data" refers to data that shows information such as the implementation status and impressions of suggestions received by elderly people, and is used to improve the accuracy of the model.

[0011] An "alert" is a notification or message that is issued when an abnormality is detected in the health condition of an elderly person, and is intended to encourage a prompt response. [Brief explanation of the drawing]

[0012] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, a numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system aimed at managing the health of the elderly and improving their quality of life in a long-lived society. This system continuously collects daily biometric data from the elderly using devices including wearable devices and smartphones. This data includes walking distance, heart rate, and sleep patterns, and serves as a comprehensive indicator of the elderly's health status.

[0034] The terminal sends this data to a data processing unit in the cloud, i.e., a server, at regular intervals. After preprocessing the received data, the server uses a health status assessment model to analyze the health status of the elderly person from the collected data. This allows it to assess whether their health is good, requires improvement, or is in a state requiring attention.

[0035] Based on this analysis, the server generates personalized health promotion suggestions for elderly individuals. For example, if the walking distance is shorter than usual, a message such as "We recommend taking a slightly longer walk" is generated. Also, if a heart rate is detected to be above the normal range, a suggestion including a warning such as "We recommend resting to lower your heart rate" is generated.

[0036] These suggestions are communicated to elderly individuals via their devices. The elderly users review the suggestions and provide feedback, indicating changes in their lifestyle and health status to the system. This feedback is stored in a database on the server and used to improve the model, enabling more accurate health management.

[0037] Furthermore, the server has a function that immediately generates an alarm if it detects an abnormality in the health condition of an elderly person, and notifies caregivers and other relevant parties. This enables a swift response and can prevent serious incidents. Through this series of operations, a system is realized that efficiently manages the health of the elderly and improves the quality of care.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The device collects biometric data in real time from wearable devices and smartphones used by elderly individuals. This data includes steps taken, heart rate, body temperature, activity level, and sleep patterns.

[0041] Step 2:

[0042] The device encrypts the collected biometric data at regular intervals and transmits it to the server via the internet.

[0043] Step 3:

[0044] Before analyzing the received biometric data, the server performs data preprocessing such as noise reduction and correction of missing values.

[0045] Step 4:

[0046] The server uses pre-processed data to run a health status assessment model and evaluate the current health status of older adults. This determines whether they are healthy, require attention, or require emergency response.

[0047] Step 5:

[0048] The server generates personalized health promotion suggestions for older adults based on their health status assessment. These suggestions include specific daily action plans.

[0049] Step 6:

[0050] The terminal notifies the elderly person of suggestions sent from the server via a user interface. The elderly person can receive this information visually or audibly.

[0051] Step 7:

[0052] Users can review the proposals and send feedback on their implementation status and other information via their devices.

[0053] Step 8:

[0054] The server collects feedback data from elderly users and records it in a database. This data is then used to improve the model and enhance the accuracy of future suggestions.

[0055] Step 9:

[0056] The server monitors data in real time and, if it detects abnormal values ​​or sudden changes in health, quickly generates an alarm and sends a warning to caregivers or designated contacts.

[0057] (Example 1)

[0058] 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."

[0059] Elderly individuals may experience a decline in their quality of life due to delays in responding appropriately to changes in their health. Furthermore, they face challenges in obtaining concrete guidance for health improvement because opportunities to receive appropriate suggestions based on their individual health conditions are limited. Therefore, there is a need to maintain and improve health through continuous, real-time monitoring of health conditions and appropriate guidance.

[0060] 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.

[0061] In this invention, the server includes means for pre-processing biometric information and analyzing it using a health status analysis model, means for generating health promotion recommendations, and means for issuing an alarm when an abnormality is detected. This enables real-time monitoring of the health status of elderly individuals, the provision of individually customized health promotion suggestions, and rapid detection and response to abnormalities.

[0062] "Biometric information" refers to data that indicates an individual's physical condition, and includes information such as heart rate, steps taken, and sleep patterns.

[0063] A "sensing device" is an electronic device used to detect physical or physiological changes and acquire biological information.

[0064] An "information processing device" is a computer system that has the function of receiving, analyzing, and processing data, and outputting the results.

[0065] A "health status analysis model" is an algorithm or machine learning model used to evaluate an individual's health status based on their biometric information.

[0066] "Recommendations" refer to specific health improvement measures and action plans provided to users based on the analysis results.

[0067] "Response information" refers to data used to provide feedback on actions taken and impressions received by users based on recommendations from the system.

[0068] An "alert" is a notification or alert intended to draw the attention of users or relevant parties when an abnormal situation occurs.

[0069] This invention provides a system for effectively managing the health status of elderly individuals, utilizing wearable devices and terminals such as smartphones. The terminal acquires biometric information from the elderly user, including heart rate, walking distance, and sleep patterns. This data is collected by the terminal using short-range communication technologies such as Bluetooth.

[0070] The server functions as an information processing device located in the cloud, receiving data sent from terminals. The received data is first preprocessed, including data cleaning, to impute missing values ​​and remove outliers. Next, a health status analysis model is used to evaluate the health status of individual data points. Machine learning algorithms are used in the analysis to achieve highly accurate health assessments.

[0071] Based on the health assessment results, the server utilizes a generative AI model to generate personalized health promotion suggestions for the user. For example, "Recent data shows your heart rate is a bit high. We recommend setting aside time to relax during the day." The generated suggestions are then pushed to the user via their device.

[0072] Elderly users adjust their behavior based on the suggestions they receive. The effects and feedback they experience after taking action are sent to the server via their device. This feedback is used to further improve the health status analysis model.

[0073] A concrete example of a prompt message is, "Analyze the sleep data of elderly individuals and propose solutions for improvement if sleep is insufficient." This allows the system to efficiently and flexibly support users' health management and improve their quality of life.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The device acquires biometric information from the elderly user. Specifically, a wearable device measures heart rate, steps, and sleep patterns in real time, and this data is transmitted to the device. The input is the measured biometric data, and the output is the temporary storage of this data within the device.

[0077] Step 2:

[0078] The device sends biometric information collected at regular intervals to a server. Wi-Fi or mobile data networks are used for data communication. The input is the biometric information stored on the device, and the output is the transfer of this information to a server in the cloud. Encryption protocols are used to ensure data security during this process.

[0079] Step 3:

[0080] The server preprocesses the received biometric data. This preprocessing includes data cleaning, specifically, missing value imputation and anomaly detection using anomaly detection algorithms. The input is raw data, and the output is cleaned, well-formed data.

[0081] Step 4:

[0082] The server inputs pre-processed data into a health status analysis model to evaluate the health status of elderly individuals. Using a generative AI model, it analyzes health risks and daily health status from the data. The input is well-formed biometric data, and the output is indices and evaluation scores representing the results of the health status assessment.

[0083] Step 5:

[0084] The server generates individually customized health promotion suggestions based on the evaluation results. The generating AI model suggests improvements using the prompt message "Provide appropriate action suggestions for the current heart rate value." The input is the result of the health evaluation, and the output is the suggestion message.

[0085] Step 6:

[0086] The device notifies the user of health promotion suggestions received from the server. Interesting information is delivered to the user in real time via smartphone push notifications and smartwatch vibration functions. The input is the suggestion message, and the output is the notification of this message to the user.

[0087] Step 7:

[0088] After performing the suggested action, the user inputs the results and feedback into the device. This includes changes in physical condition and reactions to the suggestion. The input is the user's feedback information, and the output is sending this information to the server.

[0089] Step 8:

[0090] The server collects user feedback and stores it in a database. This information contributes to further improving the health status analysis model and is used to more accurately assess the health status of older adults. The input is feedback data, and the output is a new dataset for model improvement.

[0091] (Application Example 1)

[0092] 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."

[0093] The challenge lies in effectively managing the health status of the elderly, promptly detecting abnormalities, and providing personalized suggestions to promote their health. Furthermore, it is crucial to improve the accuracy of health management models based on feedback from the elderly, thereby reducing the burden on caregivers and creating an environment where they can live their daily lives with peace of mind.

[0094] 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.

[0095] In this invention, the server includes a device for collecting and transmitting biometric data of elderly individuals, a device for preprocessing the received biometric data and analyzing it using a health indicator evaluation model, a device for generating and providing suggestions based on the analysis results of the health status, a device for collecting response data and improving model accuracy, and a device for monitoring the health status and sending notifications when an anomaly is detected. This makes it possible to grasp the health status of elderly individuals in real time, enabling early detection and appropriate countermeasures.

[0096] "Elderly people" refers to people in an aging society who are particularly concerned with health management.

[0097] "Biometric data" refers to data collected to monitor the health status of older adults, such as heart rate, walking distance, and sleep patterns.

[0098] "Device" refers to hardware or software components used to realize a specific function in an invention.

[0099] An "information processing device" refers to a system that includes a central processing unit for analyzing collected biological data and evaluating health status.

[0100] A "health indicator evaluation model" refers to a mathematical model using algorithms or artificial intelligence that is used to analyze the health status of older adults.

[0101] "Suggestions" refer to specific instructions or advice for promoting health, generated based on the results of an analysis of one's health status.

[0102] "Response data" refers to the information that elderly people provide in response to suggestions, and is used to improve the accuracy of the model.

[0103] "Monitoring" refers to the process of observing the health status of elderly people in real time and detecting any abnormalities.

[0104] "Notification" refers to a warning or informational message sent to the elderly person or their caregiver when an abnormality is detected.

[0105] The system for implementing this invention utilizes various devices and software to collect, analyze, and suggest health data for the elderly. The elderly wear wearable devices during their daily lives. These devices continuously acquire biometric data such as heart rate, walking distance, and sleep patterns. This acquired data is transmitted in real time to a cloud server via a smartphone. The smartphone is used for data transfer and some data preprocessing.

[0106] Upon receiving data, the server first performs preprocessing and then conducts a detailed analysis using a health indicator evaluation model. This model includes machine learning algorithms built on Python and utilizes libraries such as TENSORFLOW®. Based on the results of the data analysis, a generative AI model generates health promotion suggestions tailored to older adults. These suggestions include specific recommendations regarding lifestyle improvements, exercise, nutrition, and rest.

[0107] Suggestions are sent to the elderly person's smartphone and notified. The user can review them and provide feedback. This feedback is stored on the server and used to improve the accuracy of the suggestion model. If an anomaly is detected, a notification is immediately sent from the server to the caregiver, enabling emergency response. This allows for real-time monitoring of the elderly person's health status and enables specific and prompt responses as needed.

[0108] For example, if a wearable device detects that you are experiencing a prolonged period of lighter sleep than your normal sleep pattern, the app will display advice to avoid staying up late and recommend relaxing music. An example of a prompt might be, "Analyze the heart rate data collected by your Fitbit device and send a remote notification via Firebase if your heart rate falls outside the healthy range."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The device acquires biometric data from wearable devices worn by elderly individuals. This biometric data includes heart rate, walking distance, and sleep patterns. The acquired biometric data is collected at regular intervals and temporarily stored on a smartphone.

[0112] Step 2:

[0113] The device transmits the collected biometric data to a server in the cloud via the internet. The transmitted data includes the latest timestamp and personal identification information. This allows the server to ensure the freshness and relevance of the data.

[0114] Step 3:

[0115] The server first preprocesses the received biometric data. This preprocessing involves noise reduction and filtering of outliers to generate a dataset useful for analysis. At this stage, the input is the received biometric data, and the output is the clean, preprocessed data.

[0116] Step 4:

[0117] The server inputs pre-processed data into a health indicator evaluation model to analyze the health status of elderly individuals. This model is a machine learning algorithm built using TensorFlow, which evaluates health status based on multiple data points. The output includes health status scores and classification results.

[0118] Step 5:

[0119] The server uses a generative AI model based on the analysis results to generate specific suggestions for promoting health. These suggestions include personalized advice on improving lifestyle habits. The generated suggestions are designed to mitigate potential health risks that the user may face.

[0120] Step 6:

[0121] The server sends the generated suggestions to the terminal, which then notifies the user. The notification includes text-based advice and displays messages encouraging the user to take care of their health.

[0122] Step 7:

[0123] The user reviews the received proposal and enters feedback into the device. The feedback indicates the implementation status of the proposal and the user's satisfaction with the response, and the device sends this feedback to the server.

[0124] Step 8:

[0125] The server stores the received feedback in a database and uses it to improve future health indicator assessment models. In this step, the feedback is used as new training data to retrain the model.

[0126] 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.

[0127] This invention combines an emotion engine with a system that supports health management for the elderly, enabling suggestions that take into account the user's psychological state. The system's basic elements are the collection of biometric data, data transmission, health status analysis, suggestion generation, suggestion delivery, and feedback collection. By newly introducing an emotion engine, the appropriateness of the suggestions is improved.

[0128] The device acquires user voice and facial expressions in addition to conventional biometric data. This allows the emotion engine to collect data to analyze the user's emotions. The collected data is encrypted and sent to a cloud server.

[0129] The server analyzes the received biometric and emotional data. First, it preprocesses the biometric data, and then assesses the health status of the elderly based on a health status assessment model. In addition to the results of this assessment, it uses an emotional engine to analyze the user's emotional state. The emotional engine estimates the user's psychological state, such as whether they are stressed or relaxed.

[0130] Based on the results of this sentiment analysis, the server generates health promotion suggestions that take into account not only the user's physical condition but also their emotional state. For example, if the user is feeling stressed, suggestions will be generated recommending activities that promote relaxation or rest. If the user is in good health and relaxed, suggestions including active exercise will be made.

[0131] The generated suggestions are notified to the elderly via a device and received visually or audibly. The user takes action in response to the suggestion and provides feedback on the implementation status and changes in their physical condition. This feedback is used to evaluate changes in emotions and the effectiveness of the suggestion.

[0132] The server stores this feedback in a database and uses it to refine the model in the future. In this way, a system incorporating an emotion engine can comprehensively manage both the health and emotions of older adults, making it possible to support health promotion more effectively.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The device collects biometric data from elderly individuals (such as walking distance, heart rate, and body temperature) in real time via a wearable device or smartphone. It also uses a built-in microphone and camera to record voice tone and facial expressions, collecting user emotional data.

[0136] Step 2:

[0137] The device formats the collected biometric and emotional data appropriately, encrypts it for data protection, and then sends it to the server.

[0138] Step 3:

[0139] The server receives data transmitted from the terminal and performs preprocessing such as noise reduction and missing value imputation of biometric data. At the same time, it proceeds with the analysis of emotional data and begins processing to identify the user's emotions.

[0140] Step 4:

[0141] The server inputs pre-processed biometric data into a health status assessment model to evaluate the health status of elderly individuals. The assessment results are classified into one of three categories: healthy, requiring attention, or requiring immediate action.

[0142] Step 5:

[0143] The server uses an emotion engine to recognize the user's emotional state from their voice and facial expressions. It identifies their mental state, such as whether they are stressed or relaxed.

[0144] Step 6:

[0145] The server integrates health assessment results and emotion recognition results to generate health promotion suggestions optimized for the psychological and physical state of the elderly. For example, it recommends relaxation when stress levels are high, and exercise when the person is relaxed.

[0146] Step 7:

[0147] The device notifies elderly individuals of health promotion suggestions provided by the server. Elderly individuals can receive these notifications visually or audibly and incorporate them into their own actions.

[0148] Step 8:

[0149] Users act according to the provided suggestions and input feedback into the device regarding their progress, changes in their physical condition, and changes in their emotions. This information serves as important feedback to the system.

[0150] Step 9:

[0151] The server analyzes the received feedback data and stores it in a database. This data is then used to improve future models and enhance the accuracy of suggestions. As a result, the system dynamically evolves, enabling more personalized health and emotional management.

[0152] (Example 2)

[0153] 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".

[0154] When providing health management for the elderly, simply evaluating their health status based on physiological data is insufficient to provide the most appropriate health promotion plan for each individual. Furthermore, proposals that do not consider the psychological aspects of the elderly lack individuality and may even have counterproductive effects. Therefore, it is necessary to comprehensively collect and analyze physiological and psychological data to provide more personalized health promotion plans and improve the quality of life for the elderly.

[0155] 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.

[0156] In this invention, the server includes means for extracting physiological and psychological information, means for determining the user's health status using an information processing device, and means for evaluating the user's psychological state using an emotion analysis device. This makes it possible to comprehensively assess the user's health and psychological state and provide optimal health promotion recommendations.

[0157] "Physiological information" refers to data that indicates the physical and physiological state of the human body, such as heart rate, blood pressure, and body temperature.

[0158] "Psychological information" refers to data about emotions and mental states that can be gleaned from things like voice and facial expressions.

[0159] An "information processing device" is a device that processes received data and performs evaluations based on a predetermined algorithm.

[0160] A "health assessment model" is a mathematical or machine learning framework for analyzing physiological information and scoring the health status of an individual.

[0161] An "emotional analysis device" is a system that uses psychological information to analyze a subject's emotions and mental state.

[0162] A "health promotion plan" is a plan that proposes daily life behaviors optimized according to the health and psychological state of the target individual.

[0163] A "warning" is a notification or alert that occurs when an anomaly is detected, and is intended to draw the attention of the person concerned or the administrator.

[0164] "Physical activity" refers to exercise and everyday physical movements that contribute to maintaining and improving health.

[0165] "Nutritional improvement" refers to efforts to balance nutrition through reviewing eating habits.

[0166] "Recommendation of rest" is a suggestion to encourage taking appropriate rest to recover from physical and mental fatigue.

[0167] This invention combines emotion analysis technology with a system that supports the health management of the elderly to generate personalized suggestions based on the user's health and psychological state. Specific embodiments for carrying out this invention are described below.

[0168] The device uses a wearable device equipped with various sensors to measure heart rate, blood pressure, and body temperature in order to acquire the user's physiological information. This typically utilizes commonly available sensors (e.g., wearable health devices). The device also incorporates a microphone and camera to collect psychological information by capturing the user's voice and facial expressions. This provides the necessary data to understand the user's emotional state.

[0169] The server uses an information processing device to analyze physiological information sent by the user. This device uses a health assessment model based on machine learning frameworks such as "TensorFlow" to preprocess the received data and then evaluate the user's health status. Similarly, psychological information is processed by an "emotion analyzer" to identify the user's psychological state. The "emotion analyzer" uses "NLP (Natural Language Processing)" technology to analyze the user's emotions based on voice and facial expression data.

[0170] The server generates health promotion suggestions based on the evaluation results of the user's physical and mental state. Specifically, if the user is feeling stressed, it recommends "breathing exercises for relaxation," and if the user is relaxed, it suggests "trying a new exercise program."

[0171] The generated health improvement suggestions are communicated to the user via a terminal and provided through voice or visual display. The user adjusts their daily life according to these suggestions and provides feedback on their implementation and perceived changes. This feedback is stored in a database used for further system improvement and adjustment.

[0172] The following is an example of a prompt:

[0173] Please create a program that incorporates an emotion engine into a health management system for the elderly. This system will analyze voice and facial expression data to assess the user's emotional state and generate personalized health promotion suggestions. For example, if the user is feeling stressed, the program should suggest meditation; if they are relaxed, it should suggest jogging.

[0174] In this way, the system concretizes means of providing support tailored to the individual needs of older adults through health and emotional analysis.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The device acquires the user's physiological information, collecting input data such as heart rate, blood pressure, and body temperature. This is done using a wearable device for real-time physical measurement. The collected physiological information is then stored as digital data on the device.

[0178] Step 2:

[0179] The device acquires the user's voice and facial expressions, collecting audio and image data as input. This process is performed using the microphone and camera built into the device. As output, the audio data is converted into an audio file, and the facial expression data is converted into an image file.

[0180] Step 3:

[0181] The terminal encrypts the collected physiological and psychological information and prepares it for transmission to the server. An encryption protocol is used to ensure data security. An encrypted data packet is generated as output.

[0182] Step 4:

[0183] The server receives encrypted data and performs decryption. It uses the received data as input to initiate the decryption process, and the output is the reconstruction of the original physiological and psychological information.

[0184] Step 5:

[0185] The server preprocesses the physiological information. Signal processing techniques are applied to reduce noise and standardize the data. The output is shaped physiological data.

[0186] Step 6:

[0187] The server analyzes pre-processed physiological data using a health assessment model. It applies the formatted physiological data as input to the model and outputs a health risk score.

[0188] Step 7:

[0189] The server processes psychological information using an emotion analysis device. It analyzes voice data and facial expression data as input and outputs an evaluation of the emotional status (e.g., stress, relaxation).

[0190] Step 8:

[0191] The server integrates the results of health status assessments and emotional status assessments to generate optimal health improvement plans for the user. A generative AI model is used for generation, and specific health improvement suggestions are output.

[0192] Step 9:

[0193] The device receives health promotion suggestions sent from the server and provides them to the user. The output is a notification to the user via audio or visual display.

[0194] Step 10:

[0195] Users take action based on the provided health promotion plan and provide feedback on the results. They report their progress and changes in their physical condition as input, and output this data to the server.

[0196] Step 11:

[0197] The server stores user feedback in a database to help improve the model's accuracy. Based on this feedback, the system is adjusted. The output is an improved evaluation model and generation process.

[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 the "server," and the smart device 14 will be referred to as the "terminal."

[0200] In managing the health of the elderly, there is a need for comprehensive health promotion that considers not only physiological data but also psychological state. However, conventional systems have difficulty making suggestions that take into account the user's emotional state, resulting in a lack of support tailored to individual circumstances. Therefore, in managing the health of the elderly, there is a need for a system that can make suggestions that consider not only physical status but also emotional state.

[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] This invention includes a server that encrypts and analyzes physiological and emotional data after receiving it, a server that integrates the analysis of the health and emotional state of elderly individuals using a health status assessment model and an emotional analysis model, and a server that generates and notifies appropriate suggestions regarding health promotion and psychological state improvement. This makes it possible to comprehensively manage both the health and emotional aspects of elderly individuals and provide accurate health promotion advice tailored to their individual conditions.

[0203] "Physiological data" refers to information that indicates the physical condition of elderly individuals, including numerical indicators such as heart rate, blood pressure, and body temperature.

[0204] "Emotional data" refers to information that indicates the psychological state of elderly individuals, and includes signals obtained from facial expressions, voice tone, and behavioral patterns.

[0205] A "health status assessment model" is an algorithm or computational model used to analyze physiological data and assess health status and potential health risks.

[0206] An "emotion analysis model" is an algorithm or computational model used to analyze emotional data and determine a user's psychological health status.

[0207] "Health promotion suggestions" are specific activities and lifestyle guidance recommended for improving and maintaining the health of the elderly, based on the analysis results.

[0208] "Suggestions for improving psychological state" are guidance that, based on the results of emotion analysis, indicates recommended behaviors and habits to improve or maintain the mental health of older adults.

[0209] "Feedback data" refers to information provided by users after they have taken action based on a suggestion, and is used to record the effectiveness of the suggestion and changes in the user's state.

[0210] The system for implementing this invention mainly consists of three elements: a data collection terminal, a server, and a user. The data collection terminal collects physiological and emotional data from elderly individuals, and this is achieved by using a smart device equipped with a heart rate sensor, camera, and microphone. The obtained data is encrypted and transmitted to a server in the cloud.

[0211] The server plays a central role in analyzing the received data. Operating using machine learning frameworks such as TensorFlow, the server preprocesses physiological data, analyzes the health status of older adults using a health status assessment model, and analyzes their emotional state using an emotion analysis model. Based on the data analysis results, the server generates suggestions for health promotion and psychological improvement tailored to older adults.

[0212] After generating suggestions, the server collects the information and sends it to a terminal, which then notifies the elderly person. The collection terminal communicates the suggestions to the user visually or audibly. Text-to-speech or other speech generation technologies may be used in this process. Furthermore, feedback from the elderly person is sent to the server, and the collected feedback data is used to improve the model's accuracy.

[0213] For example, if an elderly person is experiencing stress, the server might suggest meditation or music therapy to promote relaxation. An example of a prompt used when implementing such a suggestion might be, "Recommend a meditation session best suited for relaxation." This allows for comprehensive management of both the health and emotional well-being of elderly individuals, providing appropriate, individualized support.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The device collects physiological and emotional data. Specifically, it measures heart rate with a heart rate sensor, captures facial expressions with a camera, and records voice with a microphone. The obtained data is then prepared to be sent to the server as raw data.

[0217] Step 2:

[0218] The raw data transmitted from the terminal is received by the server and first decrypted. Next, data preprocessing such as noise reduction and standardization is performed. The input consists of physiological data and emotional data, and the output is preprocessed data.

[0219] Step 3:

[0220] The server calculates health indicators using a health status assessment model based on preprocessed data. Preprocessed physiological data is used as input, and a health assessment score is generated as output. This score is used as an indicator of health status.

[0221] Step 4:

[0222] The server uses an emotion analysis model to estimate the user's emotional state from pre-processed emotion data. Using pre-processed emotion data as input, it outputs a numerical value or category indicating the emotional state. For example, it might output a user as "stressed" or "relaxed."

[0223] Step 5:

[0224] The server uses a generative AI model to generate suggestions for health promotion or psychological improvement based on health assessment scores and emotional states. The inputs are health scores and emotional states, and the output is specific suggestions, such as "a suggestion for a meditation session to relax."

[0225] Step 6:

[0226] The generated suggestions are resent from the server to the terminal, which then notifies the user. The terminal may display the suggestions visually on the screen or provide them verbally through speech synthesis. This allows the user to take concrete action.

[0227] Step 7:

[0228] The user takes action based on the provided suggestions, inputs the results and feedback on their device, and sends them to the server. The feedback is stored and analyzed on the server to improve the accuracy of the model. The user's execution results are obtained as input, and feedback data is obtained as output.

[0229] 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.

[0230] Data generation model 58 is a 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] This invention is a system aimed at managing the health of the elderly and improving their quality of life in a long-lived society. This system continuously collects daily biometric data from the elderly using devices including wearable devices and smartphones. This data includes walking distance, heart rate, and sleep patterns, and serves as a comprehensive indicator of the elderly's health status.

[0246] The terminal sends this data to a data processing unit in the cloud, i.e., a server, at regular intervals. After preprocessing the received data, the server uses a health status assessment model to analyze the health status of the elderly person from the collected data. This allows it to assess whether their health is good, requires improvement, or is in a state requiring attention.

[0247] Based on this analysis, the server generates personalized health promotion suggestions for elderly individuals. For example, if the walking distance is shorter than usual, a message such as "We recommend taking a slightly longer walk" is generated. Also, if a heart rate is detected to be above the normal range, a suggestion including a warning such as "We recommend resting to lower your heart rate" is generated.

[0248] These suggestions are communicated to elderly individuals via their devices. The elderly users review the suggestions and provide feedback, indicating changes in their lifestyle and health status to the system. This feedback is stored in a database on the server and used to improve the model, enabling more accurate health management.

[0249] Furthermore, the server has a function that immediately generates an alarm if it detects an abnormality in the health condition of an elderly person, and notifies caregivers and other relevant parties. This enables a swift response and can prevent serious incidents. Through this series of operations, a system is realized that efficiently manages the health of the elderly and improves the quality of care.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The device collects biometric data in real time from wearable devices and smartphones used by elderly individuals. This data includes steps taken, heart rate, body temperature, activity level, and sleep patterns.

[0253] Step 2:

[0254] The device encrypts the collected biometric data at regular intervals and transmits it to the server via the internet.

[0255] Step 3:

[0256] Before analyzing the received biometric data, the server performs data preprocessing such as noise reduction and correction of missing values.

[0257] Step 4:

[0258] The server uses pre-processed data to run a health status assessment model and evaluate the current health status of older adults. This determines whether they are healthy, require attention, or require emergency response.

[0259] Step 5:

[0260] The server generates personalized health promotion suggestions for older adults based on their health status assessment. These suggestions include specific daily action plans.

[0261] Step 6:

[0262] The terminal notifies the elderly person of suggestions sent from the server via a user interface. The elderly person can receive this information visually or audibly.

[0263] Step 7:

[0264] Users can review the proposals and send feedback on their implementation status and other information via their devices.

[0265] Step 8:

[0266] The server collects feedback data from elderly users and records it in a database. This data is then used to improve the model and enhance the accuracy of future suggestions.

[0267] Step 9:

[0268] The server monitors data in real time and, if it detects abnormal values ​​or sudden changes in health, quickly generates an alarm and sends a warning to caregivers or designated contacts.

[0269] (Example 1)

[0270] 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."

[0271] Elderly individuals may experience a decline in their quality of life due to delays in responding appropriately to changes in their health. Furthermore, they face the challenge of obtaining concrete guidance for health improvement because opportunities to receive appropriate suggestions based on their individual health conditions are limited. Therefore, there is a need to maintain and improve health by continuously and in real time monitoring their health status and providing appropriate guidance.

[0272] 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.

[0273] In this invention, the server includes means for pre-processing biometric information and analyzing it using a health status analysis model, means for generating health promotion recommendations, and means for issuing an alarm when an abnormality is detected. This enables real-time monitoring of the health status of elderly individuals, the provision of individually customized health promotion suggestions, and rapid detection and response to abnormalities.

[0274] "Biometric information" refers to data that indicates an individual's physical condition, and includes information such as heart rate, steps taken, and sleep patterns.

[0275] A "sensing device" is an electronic device used to detect physical or physiological changes and acquire biological information.

[0276] An "information processing device" is a computer system that has the function of receiving, analyzing, and processing data, and outputting the results.

[0277] A "health status analysis model" is an algorithm or machine learning model used to evaluate an individual's health status based on their biometric information.

[0278] "Recommendations" refer to specific health improvement measures and action plans provided to users based on the analysis results.

[0279] "Response information" refers to data used to provide feedback on actions taken and impressions received by users based on recommendations from the system.

[0280] An "alert" is a notification or alert intended to draw the attention of users or relevant parties when an abnormal situation occurs.

[0281] This invention provides a system for effectively managing the health status of elderly individuals, utilizing wearable devices and terminals such as smartphones. The terminal acquires biometric information from the elderly user, including heart rate, walking distance, and sleep patterns. This data is collected by the terminal using short-range communication technologies such as Bluetooth.

[0282] The server functions as an information processing device located in the cloud, receiving data sent from terminals. The received data is first preprocessed, including data cleaning, to impute missing values ​​and remove outliers. Next, a health status analysis model is used to evaluate the health status of individual data points. Machine learning algorithms are used in the analysis to achieve highly accurate health assessments.

[0283] Based on the results of the health assessment, the server utilizes the generative AI model to generate personalized health promotion proposals for the user. For example, it could be something like "Based on recent data, your heart rate is on the high side. We recommend setting aside some time to relax during the day." The generated proposals are push-notified to the user via the terminal.

[0284] The elderly user, as the user, adjusts their behavior based on the notified proposals. The effects and feedback felt after the behavior are sent to the server through the terminal. This feedback is utilized for further improvement of the health status analysis model.

[0285] As an example of a specific prompt sentence, "Analyze the sleep data of the elderly and propose improvement measures if there are deficiencies" can be cited. Thus, the system can efficiently and flexibly support the user's health management and aim to improve the quality of life.

[0286] The flow of the specific process in Example 1 will be described using FIG. 11.

[0287] Step 1:

[0288] The terminal acquires biometric information from the elderly user. Specifically, the wearable device measures the heart rate, number of steps, and sleep pattern in real time, and this data is transferred to the terminal. The input is the measured biometric data, and the output is to temporarily store this in the terminal.

[0289] Step 2:

[0290] The terminal sends the biometric information collected at regular intervals to the server. Wi-Fi or a mobile data network is used for data communication. The input is the biometric information accumulated in the terminal, and the output is to transfer this to the server on the cloud. At this time, an encryption protocol is used to ensure the security of the data.

[0291] Step 3:

[0292] The server preprocesses the received biometric data. This preprocessing includes data cleaning, specifically, missing value imputation and anomaly detection using anomaly detection algorithms. The input is raw data, and the output is cleaned, well-formed data.

[0293] Step 4:

[0294] The server inputs pre-processed data into a health status analysis model to evaluate the health status of elderly individuals. Using a generative AI model, it analyzes health risks and daily health status from the data. The input is well-formed biometric data, and the output is indices and evaluation scores representing the results of the health status assessment.

[0295] Step 5:

[0296] The server generates individually customized health promotion suggestions based on the evaluation results. The generating AI model suggests improvements using the prompt message "Provide appropriate action suggestions for the current heart rate value." The input is the result of the health evaluation, and the output is the suggestion message.

[0297] Step 6:

[0298] The device notifies the user of health promotion suggestions received from the server. Interesting information is delivered to the user in real time via smartphone push notifications and smartwatch vibration functions. The input is the suggestion message, and the output is the notification of this message to the user.

[0299] Step 7:

[0300] After performing the suggested action, the user inputs the results and feedback into the device. This includes changes in physical condition and reactions to the suggestion. The input is the user's feedback information, and the output is sending this information to the server.

[0301] Step 8:

[0302] The server accumulates the feedback from users and stores it in the database. This information contributes to further improvement of the health state analysis model and is used to more precisely evaluate the health state of the elderly. The input is the feedback data, and the output is a new dataset for model improvement.

[0303] (Application Example 1)

[0304] 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".

[0305] The problem is to effectively manage the health state of the elderly, quickly detect abnormalities, and provide individually optimized proposals for promoting health. Also, it is important to improve the accuracy of the health management model based on the feedback from the elderly, reduce the burden on caregivers, and provide an environment where they can live their daily lives with peace of mind.

[0306] 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.

[0307] In this invention, the server includes a device for collecting and transmitting the biological data of the elderly, a device for preprocessing the received biological data and analyzing it using a health index evaluation model, a device for generating and providing proposals based on the analysis results of the health state, a device for collecting response data and improving the model accuracy, and a device for monitoring the health state and transmitting a notification when an abnormality is detected. Thereby, it becomes possible to grasp the health state of the elderly in real time and take early discovery and appropriate measures.

[0308] The "elderly" refers to people in the age group where health management is particularly important in an aging society.

[0309] The "biological data" refers to data collected for monitoring the health state of the elderly, such as heart rate, walking distance, sleep pattern, etc.

[0310] "Device" refers to hardware or software components used to realize a specific function in an invention.

[0311] An "information processing device" refers to a system that includes a central processing unit for analyzing collected biological data and evaluating health status.

[0312] A "health indicator evaluation model" refers to a mathematical model using algorithms or artificial intelligence that is used to analyze the health status of older adults.

[0313] "Suggestions" refer to specific instructions or advice for promoting health, generated based on the results of an analysis of one's health status.

[0314] "Response data" refers to the information that elderly people provide in response to suggestions, and is used to improve the accuracy of the model.

[0315] "Monitoring" refers to the process of observing the health status of elderly people in real time and detecting any abnormalities.

[0316] "Notification" refers to a warning or informational message sent to the elderly person or their caregiver when an abnormality is detected.

[0317] The system for implementing this invention utilizes various devices and software to collect, analyze, and suggest health data for the elderly. The elderly wear wearable devices during their daily lives. These devices continuously acquire biometric data such as heart rate, walking distance, and sleep patterns. This acquired data is transmitted in real time to a cloud server via a smartphone. The smartphone is used for data transfer and some data preprocessing.

[0318] Upon receiving data, the server first performs preprocessing and then conducts a detailed analysis using a health indicator evaluation model. This model includes machine learning algorithms built on Python and utilizes libraries such as TensorFlow. Based on the results of the data analysis, a generative AI model generates health promotion suggestions tailored to older adults. These suggestions include specific recommendations regarding lifestyle improvements, exercise, nutrition, and rest.

[0319] Suggestions are sent to the elderly person's smartphone and notified. The user can review them and provide feedback. This feedback is stored on the server and used to improve the accuracy of the suggestion model. If an anomaly is detected, a notification is immediately sent from the server to the caregiver, enabling emergency response. This allows for real-time monitoring of the elderly person's health status and enables specific and prompt responses as needed.

[0320] For example, if a wearable device detects that you are experiencing a prolonged period of lighter sleep than your normal sleep pattern, the app will display advice to avoid staying up late and recommend relaxing music. An example of a prompt might be, "Analyze the heart rate data collected by your Fitbit device and send a remote notification via Firebase if your heart rate falls outside the healthy range."

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The device acquires biometric data from wearable devices worn by elderly individuals. This biometric data includes heart rate, walking distance, and sleep patterns. The acquired biometric data is collected at regular intervals and temporarily stored on a smartphone.

[0324] Step 2:

[0325] The device transmits the collected biometric data to a server in the cloud via the internet. The transmitted data includes the latest timestamp and personal identification information. This allows the server to ensure the freshness and relevance of the data.

[0326] Step 3:

[0327] The server first preprocesses the received biometric data. This preprocessing involves noise reduction and filtering of outliers to generate a dataset useful for analysis. At this stage, the input is the received biometric data, and the output is the clean, preprocessed data.

[0328] Step 4:

[0329] The server inputs pre-processed data into a health indicator evaluation model to analyze the health status of elderly individuals. This model is a machine learning algorithm built using TensorFlow, which evaluates health status based on multiple data points. The output includes health status scores and classification results.

[0330] Step 5:

[0331] The server uses a generative AI model based on the analysis results to generate specific suggestions for promoting health. These suggestions include personalized advice on improving lifestyle habits. The generated suggestions are designed to mitigate potential health risks that the user may face.

[0332] Step 6:

[0333] The server sends the generated suggestions to the terminal, which then notifies the user. The notification includes text-based advice and displays messages encouraging the user to take care of their health.

[0334] Step 7:

[0335] The user reviews the received proposal and enters feedback into the device. The feedback indicates the implementation status of the proposal and the user's satisfaction with the response, and the device sends this feedback to the server.

[0336] Step 8:

[0337] The server stores the received feedback in a database and uses it to improve future health indicator assessment models. In this step, the feedback is used as new training data to retrain the model.

[0338] 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.

[0339] This invention combines an emotion engine with a system that supports health management for the elderly, enabling suggestions that take into account the user's psychological state. The system's basic elements are the collection of biometric data, data transmission, health status analysis, suggestion generation, suggestion delivery, and feedback collection. By newly introducing an emotion engine, the appropriateness of the suggestions is improved.

[0340] The device acquires user voice and facial expressions in addition to conventional biometric data. This allows the emotion engine to collect data to analyze the user's emotions. The collected data is encrypted and sent to a cloud server.

[0341] The server analyzes the received biometric and emotional data. First, it preprocesses the biometric data, and then assesses the health status of the elderly based on a health status assessment model. In addition to the results of this assessment, it uses an emotional engine to analyze the user's emotional state. The emotional engine estimates the user's psychological state, such as whether they are stressed or relaxed.

[0342] Based on the results of this sentiment analysis, the server generates health promotion suggestions that take into account not only the user's physical condition but also their emotional state. For example, if the user is feeling stressed, suggestions will be generated recommending activities that promote relaxation or rest. If the user is in good health and relaxed, suggestions including active exercise will be made.

[0343] The generated suggestions are notified to the elderly via a device and received visually or audibly. The user takes action in response to the suggestion and provides feedback on the implementation status and changes in their physical condition. This feedback is used to evaluate changes in emotions and the effectiveness of the suggestion.

[0344] The server stores this feedback in a database and uses it to refine the model in the future. In this way, a system incorporating an emotion engine can comprehensively manage both the health and emotions of older adults, making it possible to support health promotion more effectively.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] The device collects biometric data from elderly individuals (such as walking distance, heart rate, and body temperature) in real time via a wearable device or smartphone. It also uses a built-in microphone and camera to record voice tone and facial expressions, collecting user emotional data.

[0348] Step 2:

[0349] The device formats the collected biometric and emotional data appropriately, encrypts it for data protection, and then sends it to the server.

[0350] Step 3:

[0351] The server receives data transmitted from the terminal and performs preprocessing such as noise reduction and missing value imputation of biometric data. At the same time, it proceeds with the analysis of emotional data and begins processing to identify the user's emotions.

[0352] Step 4:

[0353] The server inputs pre-processed biometric data into a health status assessment model to evaluate the health status of elderly individuals. The assessment results are classified into one of three categories: healthy, requiring attention, or requiring immediate action.

[0354] Step 5:

[0355] The server uses an emotion engine to recognize the user's emotional state from their voice and facial expressions. It identifies their mental state, such as whether they are stressed or relaxed.

[0356] Step 6:

[0357] The server integrates health assessment results and emotion recognition results to generate health promotion suggestions optimized for the psychological and physical state of the elderly. For example, it recommends relaxation when stress levels are high, and exercise when the person is relaxed.

[0358] Step 7:

[0359] The device notifies elderly individuals of health promotion suggestions provided by the server. Elderly individuals can receive these notifications visually or audibly and incorporate them into their own actions.

[0360] Step 8:

[0361] Users act according to the provided suggestions and input feedback into the device regarding their progress, changes in their physical condition, and changes in their emotions. This information serves as important feedback to the system.

[0362] Step 9:

[0363] The server analyzes the received feedback data and stores it in a database. This data is then used to improve future models and enhance the accuracy of suggestions. As a result, the system dynamically evolves, enabling more personalized health and emotional management.

[0364] (Example 2)

[0365] 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".

[0366] When providing health management for the elderly, simply evaluating their health status based on physiological data is insufficient to provide the most appropriate health promotion plan for each individual. Furthermore, proposals that do not consider the psychological aspects of the elderly lack individuality and may even have counterproductive effects. Therefore, it is necessary to comprehensively collect and analyze physiological and psychological data to provide more personalized health promotion plans and improve the quality of life for the elderly.

[0367] 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.

[0368] In this invention, the server includes means for extracting physiological and psychological information, means for determining the user's health status using an information processing device, and means for evaluating the user's psychological state using an emotion analysis device. This makes it possible to comprehensively assess the user's health and psychological state and provide optimal health promotion recommendations.

[0369] "Physiological information" refers to data that indicates the physical and physiological state of the human body, such as heart rate, blood pressure, and body temperature.

[0370] "Psychological information" refers to data about emotions and mental states that can be gleaned from things like voice and facial expressions.

[0371] An "information processing device" is a device that processes received data and performs evaluations based on a predetermined algorithm.

[0372] A "health assessment model" is a mathematical or machine learning framework for analyzing physiological information and scoring the health status of an individual.

[0373] An "emotional analysis device" is a system that uses psychological information to analyze a subject's emotions and mental state.

[0374] A "health promotion plan" is a plan that proposes daily life behaviors optimized according to the health and psychological state of the target individual.

[0375] A "warning" is a notification or alert that occurs when an anomaly is detected, and is intended to draw the attention of the person concerned or the administrator.

[0376] "Physical activity" refers to exercise and everyday physical movements that contribute to maintaining and improving health.

[0377] "Nutritional improvement" refers to efforts to balance nutrition through reviewing eating habits.

[0378] "Recommendation of rest" is a suggestion to encourage taking appropriate rest to recover from physical and mental fatigue.

[0379] This invention combines emotion analysis technology with a system that supports the health management of the elderly to generate personalized suggestions based on the user's health and psychological state. Specific embodiments for carrying out this invention are described below.

[0380] The device uses a wearable device equipped with various sensors to measure heart rate, blood pressure, and body temperature in order to acquire the user's physiological information. This typically utilizes commonly available sensors (e.g., wearable health devices). The device also incorporates a microphone and camera to collect psychological information by capturing the user's voice and facial expressions. This provides the necessary data to understand the user's emotional state.

[0381] The server uses an information processing device to analyze physiological information sent by the user. This device uses a health assessment model based on machine learning frameworks such as "TensorFlow" to preprocess the received data and then evaluate the user's health status. Similarly, psychological information is processed by an "emotion analyzer" to identify the user's psychological state. The "emotion analyzer" uses "NLP (Natural Language Processing)" technology to analyze the user's emotions based on voice and facial expression data.

[0382] The server generates health promotion suggestions based on the evaluation results of the user's physical and mental state. Specifically, if the user is feeling stressed, it recommends "breathing exercises for relaxation," and if the user is relaxed, it suggests "trying a new exercise program."

[0383] The generated health improvement suggestions are communicated to the user via a terminal and provided through voice or visual display. The user adjusts their daily life according to these suggestions and provides feedback on their implementation and perceived changes. This feedback is stored in a database used for further system improvement and adjustment.

[0384] The following is an example of a prompt:

[0385] Please create a program that incorporates an emotion engine into a health management system for the elderly. This system will analyze voice and facial expression data to assess the user's emotional state and generate personalized health promotion suggestions. For example, if the user is feeling stressed, the program should suggest meditation; if they are relaxed, it should suggest jogging.

[0386] In this way, the system concretizes means of providing support tailored to the individual needs of older adults through health and emotional analysis.

[0387] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0388] Step 1:

[0389] The device acquires the user's physiological information, collecting input data such as heart rate, blood pressure, and body temperature. This is done using a wearable device for real-time physical measurement. The collected physiological information is then stored as digital data on the device.

[0390] Step 2:

[0391] The device acquires the user's voice and facial expressions, collecting audio and image data as input. This process is performed using the microphone and camera built into the device. As output, the audio data is converted into an audio file, and the facial expression data is converted into an image file.

[0392] Step 3:

[0393] The terminal encrypts the collected physiological and psychological information and prepares it for transmission to the server. An encryption protocol is used to ensure data security. An encrypted data packet is generated as output.

[0394] Step 4:

[0395] The server receives encrypted data and performs decryption. It uses the received data as input to initiate the decryption process, and the output is the reconstruction of the original physiological and psychological information.

[0396] Step 5:

[0397] The server preprocesses the physiological information. Signal processing techniques are applied to reduce noise and standardize the data. The output is shaped physiological data.

[0398] Step 6:

[0399] The server analyzes pre-processed physiological data using a health assessment model. It applies the formatted physiological data as input to the model and outputs a health risk score.

[0400] Step 7:

[0401] The server processes psychological information using an emotion analysis device. It analyzes voice data and facial expression data as input and outputs an evaluation of the emotional status (e.g., stress, relaxation).

[0402] Step 8:

[0403] The server integrates the results of health status assessments and emotional status assessments to generate optimal health improvement plans for the user. A generative AI model is used for generation, and specific health improvement suggestions are output.

[0404] Step 9:

[0405] The device receives health promotion suggestions sent from the server and provides them to the user. The output is a notification to the user via audio or visual display.

[0406] Step 10:

[0407] Users take action based on the provided health promotion plan and provide feedback on the results. They report their progress and changes in their physical condition as input, and output this data to the server.

[0408] Step 11:

[0409] The server stores user feedback in a database to help improve the model's accuracy. Based on this feedback, the system is adjusted. The output is an improved evaluation model and generation process.

[0410] (Application Example 2)

[0411] 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 as the "terminal".

[0412] In managing the health of the elderly, there is a need for comprehensive health promotion that considers not only physiological data but also psychological state. However, conventional systems have difficulty making suggestions that take into account the user's emotional state, resulting in a lack of support tailored to individual circumstances. Therefore, in managing the health of the elderly, there is a need for a system that can make suggestions that consider not only physical status but also emotional state.

[0413] 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.

[0414] This invention includes a server that encrypts and analyzes physiological and emotional data after receiving it, a server that integrates the analysis of the health and emotional state of elderly individuals using a health status assessment model and an emotional analysis model, and a server that generates and notifies appropriate suggestions regarding health promotion and psychological state improvement. This makes it possible to comprehensively manage both the health and emotional aspects of elderly individuals and provide accurate health promotion advice tailored to their individual conditions.

[0415] "Physiological data" refers to information that indicates the physical condition of elderly individuals, including numerical indicators such as heart rate, blood pressure, and body temperature.

[0416] "Emotional data" refers to information that indicates the psychological state of elderly individuals, and includes signals obtained from facial expressions, voice tone, and behavioral patterns.

[0417] A "health status assessment model" is an algorithm or computational model used to analyze physiological data and assess health status and potential health risks.

[0418] An "emotion analysis model" is an algorithm or computational model used to analyze emotional data and determine a user's psychological health status.

[0419] "Health promotion suggestions" are specific activities and lifestyle guidance recommended for improving and maintaining the health of the elderly, based on the analysis results.

[0420] "Suggestions for improving psychological state" are guidance that, based on the results of emotion analysis, indicates recommended behaviors and habits to improve or maintain the mental health of older adults.

[0421] "Feedback data" refers to information provided by users after they have taken action based on a suggestion, and is used to record the effectiveness of the suggestion and changes in the user's state.

[0422] The system for implementing this invention mainly consists of three elements: a data collection terminal, a server, and a user. The data collection terminal collects physiological and emotional data from elderly individuals, and this is achieved by using a smart device equipped with a heart rate sensor, camera, and microphone. The obtained data is encrypted and transmitted to a server in the cloud.

[0423] The server plays a central role in analyzing the received data. Operating using machine learning frameworks such as TensorFlow, the server preprocesses physiological data, analyzes the health status of older adults using a health status assessment model, and analyzes their emotional state using an emotion analysis model. Based on the data analysis results, the server generates suggestions for health promotion and psychological improvement tailored to older adults.

[0424] After generating suggestions, the server collects the information and sends it to a terminal, which then notifies the elderly person. The collection terminal communicates the suggestions to the user visually or audibly. Text-to-speech or other speech generation technologies may be used in this process. Furthermore, feedback from the elderly person is sent to the server, and the collected feedback data is used to improve the model's accuracy.

[0425] For example, if an elderly person is experiencing stress, the server might suggest meditation or music therapy to promote relaxation. An example of a prompt used when implementing such a suggestion might be, "Recommend a meditation session best suited for relaxation." This allows for comprehensive management of both the health and emotional well-being of elderly individuals, providing appropriate, individualized support.

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] The device collects physiological and emotional data. Specifically, it measures heart rate with a heart rate sensor, captures facial expressions with a camera, and records voice with a microphone. The obtained data is then prepared to be sent to the server as raw data.

[0429] Step 2:

[0430] The raw data transmitted from the terminal is received by the server and first decrypted. Next, data preprocessing such as noise reduction and standardization is performed. The input consists of physiological data and emotional data, and the output is preprocessed data.

[0431] Step 3:

[0432] The server calculates health indicators using a health status assessment model based on preprocessed data. Preprocessed physiological data is used as input, and a health assessment score is generated as output. This score is used as an indicator of health status.

[0433] Step 4:

[0434] The server uses an emotion analysis model to estimate the user's emotional state from pre-processed emotion data. Using pre-processed emotion data as input, it outputs a numerical value or category indicating the emotional state. For example, it might output a user as "stressed" or "relaxed."

[0435] Step 5:

[0436] The server uses a generative AI model to generate suggestions for health promotion or psychological improvement based on health assessment scores and emotional states. The inputs are health scores and emotional states, and the output is specific suggestions, such as "a suggestion for a meditation session to relax."

[0437] Step 6:

[0438] The generated suggestions are resent from the server to the terminal, which then notifies the user. The terminal may display the suggestions visually on the screen or provide them verbally through speech synthesis. This allows the user to take concrete action.

[0439] Step 7:

[0440] The user takes action based on the provided suggestions, inputs the results and feedback on their device, and sends them to the server. The feedback is stored and analyzed on the server to improve the accuracy of the model. The user's execution results are obtained as input, and feedback data is obtained as output.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] [Third Embodiment]

[0445] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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).

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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".

[0457] This invention is a system aimed at managing the health of the elderly and improving their quality of life in a long-lived society. This system continuously collects daily biometric data from the elderly using devices including wearable devices and smartphones. This data includes walking distance, heart rate, and sleep patterns, and serves as a comprehensive indicator of the elderly's health status.

[0458] The terminal sends this data to a data processing unit in the cloud, i.e., a server, at regular intervals. After preprocessing the received data, the server uses a health status assessment model to analyze the health status of the elderly person from the collected data. This allows it to assess whether their health is good, requires improvement, or is in a state requiring attention.

[0459] Based on this analysis, the server generates personalized health promotion suggestions for elderly individuals. For example, if the walking distance is shorter than usual, a message such as "We recommend taking a slightly longer walk" is generated. Also, if a heart rate is detected to be above the normal range, a suggestion including a warning such as "We recommend resting to lower your heart rate" is generated.

[0460] These suggestions are communicated to elderly individuals via their devices. The elderly users review the suggestions and provide feedback, indicating changes in their lifestyle and health status to the system. This feedback is stored in a database on the server and used to improve the model, enabling more accurate health management.

[0461] Furthermore, the server has a function that immediately generates an alarm if it detects an abnormality in the health condition of an elderly person, and notifies caregivers and other relevant parties. This enables a swift response and can prevent serious incidents. Through this series of operations, a system is realized that efficiently manages the health of the elderly and improves the quality of care.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The device collects biometric data in real time from wearable devices and smartphones used by elderly individuals. This data includes steps taken, heart rate, body temperature, activity level, and sleep patterns.

[0465] Step 2:

[0466] The device encrypts the collected biometric data at regular intervals and transmits it to the server via the internet.

[0467] Step 3:

[0468] Before analyzing the received biometric data, the server performs data preprocessing such as noise reduction and correction of missing values.

[0469] Step 4:

[0470] The server uses pre-processed data to run a health status assessment model and evaluate the current health status of older adults. This determines whether they are healthy, require attention, or require emergency response.

[0471] Step 5:

[0472] The server generates personalized health promotion suggestions for older adults based on their health status assessment. These suggestions include specific daily action plans.

[0473] Step 6:

[0474] The terminal notifies the elderly person of suggestions sent from the server via a user interface. The elderly person can receive this information visually or audibly.

[0475] Step 7:

[0476] Users can review the proposals and send feedback on their implementation status and other information via their devices.

[0477] Step 8:

[0478] The server collects feedback data from elderly users and records it in a database. This data is then used to improve the model and enhance the accuracy of future suggestions.

[0479] Step 9:

[0480] The server monitors data in real time and, if it detects abnormal values ​​or sudden changes in health, quickly generates an alarm and sends a warning to caregivers or designated contacts.

[0481] (Example 1)

[0482] 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."

[0483] Elderly individuals may experience a decline in their quality of life due to delays in responding appropriately to changes in their health. Furthermore, they face the challenge of obtaining concrete guidance for health improvement because opportunities to receive appropriate suggestions based on their individual health conditions are limited. Therefore, there is a need to maintain and improve health by continuously and in real time monitoring their health status and providing appropriate guidance.

[0484] 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.

[0485] In this invention, the server includes means for pre-processing biometric information and analyzing it using a health status analysis model, means for generating health promotion recommendations, and means for issuing an alarm when an abnormality is detected. This enables real-time monitoring of the health status of elderly individuals, the provision of individually customized health promotion suggestions, and rapid detection and response to abnormalities.

[0486] "Biometric information" refers to data that indicates an individual's physical condition, and includes information such as heart rate, steps taken, and sleep patterns.

[0487] A "sensing device" is an electronic device used to detect physical or physiological changes and acquire biological information.

[0488] An "information processing device" is a computer system that has the function of receiving, analyzing, and processing data, and outputting the results.

[0489] A "health status analysis model" is an algorithm or machine learning model used to evaluate an individual's health status based on their biometric information.

[0490] "Recommendations" refer to specific health improvement measures and action plans provided to users based on the analysis results.

[0491] "Response information" refers to data used to provide feedback on actions taken and impressions received by users based on recommendations from the system.

[0492] An "alert" is a notification or alert intended to draw the attention of users or relevant parties when an abnormal situation occurs.

[0493] This invention provides a system for effectively managing the health status of elderly individuals, utilizing wearable devices and terminals such as smartphones. The terminal acquires biometric information from the elderly user, including heart rate, walking distance, and sleep patterns. This data is collected by the terminal using short-range communication technologies such as Bluetooth.

[0494] The server functions as an information processing device located in the cloud, receiving data sent from terminals. The received data is first preprocessed, including data cleaning, to impute missing values ​​and remove outliers. Next, a health status analysis model is used to evaluate the health status of individual data points. Machine learning algorithms are used in the analysis to achieve highly accurate health assessments.

[0495] Based on the health assessment results, the server utilizes a generative AI model to generate personalized health promotion suggestions for the user. For example, "Recent data shows your heart rate is a bit high. We recommend setting aside time to relax during the day." The generated suggestions are then pushed to the user via their device.

[0496] Elderly users adjust their behavior based on the suggestions they receive. The effects and feedback they experience after taking action are sent to the server via their device. This feedback is used to further improve the health status analysis model.

[0497] A concrete example of a prompt message is, "Analyze the sleep data of elderly individuals and propose solutions for improvement if sleep is insufficient." This allows the system to efficiently and flexibly support users' health management and improve their quality of life.

[0498] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0499] Step 1:

[0500] The device acquires biometric information from the elderly user. Specifically, a wearable device measures heart rate, steps, and sleep patterns in real time, and this data is transmitted to the device. The input is the measured biometric data, and the output is the temporary storage of this data within the device.

[0501] Step 2:

[0502] The device sends biometric information collected at regular intervals to a server. Wi-Fi or mobile data networks are used for data communication. The input is the biometric information stored on the device, and the output is the transfer of this information to a server in the cloud. Encryption protocols are used to ensure data security during this process.

[0503] Step 3:

[0504] The server preprocesses the received biometric data. This preprocessing includes data cleaning, specifically, missing value imputation and anomaly detection using anomaly detection algorithms. The input is raw data, and the output is cleaned, well-formed data.

[0505] Step 4:

[0506] The server inputs pre-processed data into a health status analysis model to evaluate the health status of elderly individuals. Using a generative AI model, it analyzes health risks and daily health status from the data. The input is well-formed biometric data, and the output is indices and evaluation scores representing the results of the health status assessment.

[0507] Step 5:

[0508] The server generates individually customized health promotion suggestions based on the evaluation results. The generating AI model suggests improvements using the prompt message "Provide appropriate action suggestions for the current heart rate value." The input is the result of the health evaluation, and the output is the suggestion message.

[0509] Step 6:

[0510] The device notifies the user of health promotion suggestions received from the server. Interesting information is delivered to the user in real time via smartphone push notifications and smartwatch vibration functions. The input is the suggestion message, and the output is the notification of this message to the user.

[0511] Step 7:

[0512] After performing the suggested action, the user inputs the results and feedback into the device. This includes changes in physical condition and reactions to the suggestion. The input is the user's feedback information, and the output is sending this information to the server.

[0513] Step 8:

[0514] The server collects user feedback and stores it in a database. This information contributes to further improving the health status analysis model and is used to more accurately assess the health status of older adults. The input is feedback data, and the output is a new dataset for model improvement.

[0515] (Application Example 1)

[0516] 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."

[0517] The challenge lies in effectively managing the health status of the elderly, promptly detecting abnormalities, and providing personalized suggestions to promote their health. Furthermore, it is crucial to improve the accuracy of health management models based on feedback from the elderly, thereby reducing the burden on caregivers and creating an environment where they can live their daily lives with peace of mind.

[0518] 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.

[0519] In this invention, the server includes a device for collecting and transmitting biometric data of elderly individuals, a device for preprocessing the received biometric data and analyzing it using a health indicator evaluation model, a device for generating and providing suggestions based on the analysis results of the health status, a device for collecting response data and improving model accuracy, and a device for monitoring the health status and sending notifications when an anomaly is detected. This makes it possible to grasp the health status of elderly individuals in real time, enabling early detection and appropriate countermeasures.

[0520] "Elderly people" refers to people in an aging society who are particularly concerned with health management.

[0521] "Biometric data" refers to data collected to monitor the health status of older adults, such as heart rate, walking distance, and sleep patterns.

[0522] "Device" refers to hardware or software components used to realize a specific function in an invention.

[0523] An "information processing device" refers to a system that includes a central processing unit for analyzing collected biological data and evaluating health status.

[0524] A "health indicator evaluation model" refers to a mathematical model using algorithms or artificial intelligence that is used to analyze the health status of older adults.

[0525] "Suggestions" refer to specific instructions or advice for promoting health, generated based on the results of an analysis of one's health status.

[0526] "Response data" refers to the information that elderly people provide in response to suggestions, and is used to improve the accuracy of the model.

[0527] "Monitoring" refers to the process of observing the health status of elderly people in real time and detecting any abnormalities.

[0528] "Notification" refers to a warning or informational message sent to the elderly person or their caregiver when an abnormality is detected.

[0529] The system for implementing this invention utilizes various devices and software to collect, analyze, and suggest health data for the elderly. The elderly wear wearable devices during their daily lives. These devices continuously acquire biometric data such as heart rate, walking distance, and sleep patterns. This acquired data is transmitted in real time to a cloud server via a smartphone. The smartphone is used for data transfer and some data preprocessing.

[0530] Upon receiving data, the server first performs preprocessing and then conducts a detailed analysis using a health indicator evaluation model. This model includes machine learning algorithms built on Python and utilizes libraries such as TensorFlow. Based on the results of the data analysis, a generative AI model generates health promotion suggestions tailored to older adults. These suggestions include specific recommendations regarding lifestyle improvements, exercise, nutrition, and rest.

[0531] Suggestions are sent to the elderly person's smartphone and notified. The user can review them and provide feedback. This feedback is stored on the server and used to improve the accuracy of the suggestion model. If an anomaly is detected, a notification is immediately sent from the server to the caregiver, enabling emergency response. This allows for real-time monitoring of the elderly person's health status and enables specific and prompt responses as needed.

[0532] For example, if a wearable device detects that you are experiencing a prolonged period of lighter sleep than your normal sleep pattern, the app will display advice to avoid staying up late and recommend relaxing music. An example of a prompt might be, "Analyze the heart rate data collected by your Fitbit device and send a remote notification via Firebase if your heart rate falls outside the healthy range."

[0533] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0534] Step 1:

[0535] The device acquires biometric data from wearable devices worn by elderly individuals. This biometric data includes heart rate, walking distance, and sleep patterns. The acquired biometric data is collected at regular intervals and temporarily stored on a smartphone.

[0536] Step 2:

[0537] The device transmits the collected biometric data to a server in the cloud via the internet. The transmitted data includes the latest timestamp and personal identification information. This allows the server to ensure the freshness and relevance of the data.

[0538] Step 3:

[0539] The server first preprocesses the received biometric data. This preprocessing involves noise reduction and filtering of outliers to generate a dataset useful for analysis. At this stage, the input is the received biometric data, and the output is the clean, preprocessed data.

[0540] Step 4:

[0541] The server inputs pre-processed data into a health indicator evaluation model to analyze the health status of elderly individuals. This model is a machine learning algorithm built using TensorFlow, which evaluates health status based on multiple data points. The output includes health status scores and classification results.

[0542] Step 5:

[0543] The server uses a generative AI model based on the analysis results to generate specific suggestions for promoting health. These suggestions include personalized advice on improving lifestyle habits. The generated suggestions are designed to mitigate potential health risks that the user may face.

[0544] Step 6:

[0545] The server sends the generated suggestions to the terminal, which then notifies the user. The notification includes text-based advice and displays messages encouraging the user to take care of their health.

[0546] Step 7:

[0547] The user reviews the received proposal and enters feedback into the device. The feedback indicates the implementation status of the proposal and the user's satisfaction with the response, and the device sends this feedback to the server.

[0548] Step 8:

[0549] The server stores the received feedback in a database and uses it to improve future health indicator assessment models. In this step, the feedback is used as new training data to retrain the model.

[0550] 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.

[0551] This invention combines an emotion engine with a system that supports health management for the elderly, enabling suggestions that take into account the user's psychological state. The system's basic elements are the collection of biometric data, data transmission, health status analysis, suggestion generation, suggestion delivery, and feedback collection. By newly introducing an emotion engine, the appropriateness of the suggestions is improved.

[0552] The device acquires user voice and facial expressions in addition to conventional biometric data. This allows the emotion engine to collect data to analyze the user's emotions. The collected data is encrypted and sent to a cloud server.

[0553] The server analyzes the received biometric and emotional data. First, it preprocesses the biometric data, and then assesses the health status of the elderly based on a health status assessment model. In addition to the results of this assessment, it uses an emotional engine to analyze the user's emotional state. The emotional engine estimates the user's psychological state, such as whether they are stressed or relaxed.

[0554] Based on the results of this sentiment analysis, the server generates health promotion suggestions that take into account not only the user's physical condition but also their emotional state. For example, if the user is feeling stressed, suggestions will be generated recommending activities that promote relaxation or rest. If the user is in good health and relaxed, suggestions including active exercise will be made.

[0555] The generated suggestions are notified to the elderly via a device and received visually or audibly. The user takes action in response to the suggestion and provides feedback on the implementation status and changes in their physical condition. This feedback is used to evaluate changes in emotions and the effectiveness of the suggestion.

[0556] The server stores this feedback in a database and uses it to refine the model in the future. In this way, a system incorporating an emotion engine can comprehensively manage both the health and emotions of older adults, making it possible to support health promotion more effectively.

[0557] The following describes the processing flow.

[0558] Step 1:

[0559] The device collects biometric data from elderly individuals (such as walking distance, heart rate, and body temperature) in real time via a wearable device or smartphone. It also uses a built-in microphone and camera to record voice tone and facial expressions, collecting user emotional data.

[0560] Step 2:

[0561] The device formats the collected biometric and emotional data appropriately, encrypts it for data protection, and then sends it to the server.

[0562] Step 3:

[0563] The server receives data transmitted from the terminal and performs preprocessing such as noise reduction and missing value imputation of biometric data. At the same time, it proceeds with the analysis of emotional data and begins processing to identify the user's emotions.

[0564] Step 4:

[0565] The server inputs pre-processed biometric data into a health status assessment model to evaluate the health status of elderly individuals. The assessment results are classified into one of three categories: healthy, requiring attention, or requiring immediate action.

[0566] Step 5:

[0567] The server uses an emotion engine to recognize the user's emotional state from their voice and facial expressions. It identifies their mental state, such as whether they are stressed or relaxed.

[0568] Step 6:

[0569] The server integrates health assessment results and emotion recognition results to generate health promotion suggestions optimized for the psychological and physical state of the elderly. For example, it recommends relaxation when stress levels are high, and exercise when the person is relaxed.

[0570] Step 7:

[0571] The device notifies elderly individuals of health promotion suggestions provided by the server. Elderly individuals can receive these notifications visually or audibly and incorporate them into their own actions.

[0572] Step 8:

[0573] Users act according to the provided suggestions and input feedback into the device regarding their progress, changes in their physical condition, and changes in their emotions. This information serves as important feedback to the system.

[0574] Step 9:

[0575] The server analyzes the received feedback data and stores it in a database. This data is then used to improve future models and enhance the accuracy of suggestions. As a result, the system dynamically evolves, enabling more personalized health and emotional management.

[0576] (Example 2)

[0577] 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."

[0578] When providing health management for the elderly, simply evaluating their health status based on physiological data is insufficient to provide the most appropriate health promotion plan for each individual. Furthermore, proposals that do not consider the psychological aspects of the elderly lack individuality and may even have counterproductive effects. Therefore, it is necessary to comprehensively collect and analyze physiological and psychological data to provide more personalized health promotion plans and improve the quality of life for the elderly.

[0579] 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.

[0580] In this invention, the server includes means for extracting physiological and psychological information, means for determining the user's health status using an information processing device, and means for evaluating the user's psychological state using an emotion analysis device. This makes it possible to comprehensively assess the user's health and psychological state and provide optimal health promotion recommendations.

[0581] "Physiological information" refers to data that indicates the physical and physiological state of the human body, such as heart rate, blood pressure, and body temperature.

[0582] "Psychological information" refers to data about emotions and mental states that can be gleaned from things like voice and facial expressions.

[0583] An "information processing device" is a device that processes received data and performs evaluations based on a predetermined algorithm.

[0584] A "health assessment model" is a mathematical or machine learning framework for analyzing physiological information and scoring the health status of an individual.

[0585] An "emotional analysis device" is a system that uses psychological information to analyze a subject's emotions and mental state.

[0586] A "health promotion plan" is a plan that proposes daily life behaviors optimized according to the health and psychological state of the target individual.

[0587] A "warning" is a notification or alert that occurs when an anomaly is detected, and is intended to draw the attention of the person concerned or the administrator.

[0588] "Physical activity" refers to exercise and everyday physical movements that contribute to maintaining and improving health.

[0589] "Nutritional improvement" refers to efforts to balance nutrition through reviewing eating habits.

[0590] "Recommendation of rest" is a suggestion to encourage taking appropriate rest to recover from physical and mental fatigue.

[0591] This invention combines emotion analysis technology with a system that supports the health management of the elderly to generate personalized suggestions based on the user's health and psychological state. Specific embodiments for carrying out this invention are described below.

[0592] The device uses a wearable device equipped with various sensors to measure heart rate, blood pressure, and body temperature in order to acquire the user's physiological information. This typically utilizes commonly available sensors (e.g., wearable health devices). The device also incorporates a microphone and camera to collect psychological information by capturing the user's voice and facial expressions. This provides the necessary data to understand the user's emotional state.

[0593] The server uses an information processing device to analyze physiological information sent by the user. This device uses a health assessment model based on machine learning frameworks such as "TensorFlow" to preprocess the received data and then evaluate the user's health status. Similarly, psychological information is processed by an "emotion analyzer" to identify the user's psychological state. The "emotion analyzer" uses "NLP (Natural Language Processing)" technology to analyze the user's emotions based on voice and facial expression data.

[0594] The server generates health promotion suggestions based on the evaluation results of the user's physical and mental state. Specifically, if the user is feeling stressed, it recommends "breathing exercises for relaxation," and if the user is relaxed, it suggests "trying a new exercise program."

[0595] The generated health improvement suggestions are communicated to the user via a terminal and provided through voice or visual display. The user adjusts their daily life according to these suggestions and provides feedback on their implementation and perceived changes. This feedback is stored in a database used for further system improvement and adjustment.

[0596] The following is an example of a prompt:

[0597] Please create a program that incorporates an emotion engine into a health management system for the elderly. This system will analyze voice and facial expression data to assess the user's emotional state and generate personalized health promotion suggestions. For example, if the user is feeling stressed, the program should suggest meditation; if they are relaxed, it should suggest jogging.

[0598] In this way, the system concretizes means of providing support tailored to the individual needs of older adults through health and emotional analysis.

[0599] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0600] Step 1:

[0601] The device acquires the user's physiological information, collecting input data such as heart rate, blood pressure, and body temperature. During this process, a wearable device is used to perform real-time physical measurements. The collected physiological information is then stored as digital data on the device.

[0602] Step 2:

[0603] The device acquires the user's voice and facial expressions, collecting audio and image data as input. This process is performed using the microphone and camera built into the device. As output, the audio data is converted into an audio file, and the facial expression data is converted into an image file.

[0604] Step 3:

[0605] The terminal encrypts the collected physiological and psychological information and prepares it for transmission to the server. An encryption protocol is used to ensure data security. An encrypted data packet is generated as output.

[0606] Step 4:

[0607] The server receives encrypted data and performs decryption. It uses the received data as input to initiate the decryption process, and the output is the reconstruction of the original physiological and psychological information.

[0608] Step 5:

[0609] The server preprocesses the physiological information. Signal processing techniques are applied to reduce noise and standardize the data. The output is shaped physiological data.

[0610] Step 6:

[0611] The server analyzes pre-processed physiological data using a health assessment model. It applies the formatted physiological data as input to the model and outputs a health risk score.

[0612] Step 7:

[0613] The server processes psychological information using an emotion analysis device. It analyzes voice data and facial expression data as input and outputs an evaluation of the emotional status (e.g., stress, relaxation).

[0614] Step 8:

[0615] The server integrates the results of health status assessments and emotional status assessments to generate optimal health improvement plans for the user. A generative AI model is used for generation, and specific health improvement suggestions are output.

[0616] Step 9:

[0617] The device receives health promotion suggestions sent from the server and provides them to the user. The output is a notification to the user via audio or visual display.

[0618] Step 10:

[0619] Users take action based on the provided health promotion plan and provide feedback on the results. They report their progress and changes in their physical condition as input, and output this data to the server.

[0620] Step 11:

[0621] The server stores user feedback in a database to help improve the model's accuracy. Based on this feedback, the system is adjusted. The output is an improved evaluation model and generation process.

[0622] (Application Example 2)

[0623] 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."

[0624] In managing the health of the elderly, there is a need for comprehensive health promotion that considers not only physiological data but also psychological state. However, conventional systems have difficulty making suggestions that take into account the user's emotional state, resulting in a lack of support tailored to individual circumstances. Therefore, in managing the health of the elderly, there is a need for a system that can make suggestions that consider not only physical status but also emotional state.

[0625] 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.

[0626] This invention includes a server that encrypts and analyzes physiological and emotional data after receiving it, a server that integrates the analysis of the health and emotional state of elderly individuals using a health status assessment model and an emotional analysis model, and a server that generates and notifies appropriate suggestions regarding health promotion and psychological state improvement. This makes it possible to comprehensively manage both the health and emotional aspects of elderly individuals and provide accurate health promotion advice tailored to their individual conditions.

[0627] "Physiological data" refers to information that indicates the physical condition of elderly individuals, including numerical indicators such as heart rate, blood pressure, and body temperature.

[0628] "Emotional data" refers to information that indicates the psychological state of elderly individuals, and includes signals obtained from facial expressions, voice tone, and behavioral patterns.

[0629] A "health status assessment model" is an algorithm or computational model used to analyze physiological data and assess health status and potential health risks.

[0630] An "emotion analysis model" is an algorithm or computational model used to analyze emotional data and determine a user's psychological health status.

[0631] "Health promotion suggestions" are specific activities and lifestyle guidance recommended for improving and maintaining the health of the elderly, based on the analysis results.

[0632] "Suggestions for improving psychological state" are guidance that, based on the results of emotion analysis, indicates recommended behaviors and habits to improve or maintain the mental health of older adults.

[0633] "Feedback data" refers to information provided by users after they have taken action based on a suggestion, and is used to record the effectiveness of the suggestion and changes in the user's state.

[0634] The system for implementing this invention mainly consists of three elements: a data collection terminal, a server, and a user. The data collection terminal collects physiological and emotional data from elderly individuals, and this is achieved by using a smart device equipped with a heart rate sensor, camera, and microphone. The obtained data is encrypted and transmitted to a server in the cloud.

[0635] The server plays a central role in analyzing the received data. Operating using machine learning frameworks such as TensorFlow, the server preprocesses physiological data, analyzes the health status of older adults using a health status assessment model, and analyzes their emotional state using an emotion analysis model. Based on the data analysis results, the server generates suggestions for health promotion and psychological improvement tailored to older adults.

[0636] After generating suggestions, the server collects the information and sends it to a terminal, which then notifies the elderly person. The collection terminal communicates the suggestions to the user visually or audibly. Text-to-speech or other speech generation technologies may be used in this process. Furthermore, feedback from the elderly person is sent to the server, and the collected feedback data is used to improve the model's accuracy.

[0637] For example, if an elderly person is experiencing stress, the server might suggest meditation or music therapy to promote relaxation. An example of a prompt used when implementing such a suggestion might be, "Recommend a meditation session best suited for relaxation." This allows for comprehensive management of both the health and emotional well-being of elderly individuals, providing appropriate, individualized support.

[0638] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0639] Step 1:

[0640] The device collects physiological and emotional data. Specifically, it measures heart rate with a heart rate sensor, captures facial expressions with a camera, and records voice with a microphone. The obtained data is then prepared to be sent to the server as raw data.

[0641] Step 2:

[0642] The raw data transmitted from the terminal is received by the server and first decrypted. Next, data preprocessing such as noise reduction and standardization is performed. The input consists of physiological data and emotional data, and the output is preprocessed data.

[0643] Step 3:

[0644] The server calculates health indicators using a health status assessment model based on preprocessed data. Preprocessed physiological data is used as input, and a health assessment score is generated as output. This score is used as an indicator of health status.

[0645] Step 4:

[0646] The server uses an emotion analysis model to estimate the user's emotional state from pre-processed emotion data. Using pre-processed emotion data as input, it outputs a numerical value or category indicating the emotional state. For example, it might output a user as "stressed" or "relaxed."

[0647] Step 5:

[0648] The server uses a generative AI model to generate suggestions for health promotion or psychological improvement based on health assessment scores and emotional states. The inputs are health scores and emotional states, and the output is specific suggestions, such as "a suggestion for a meditation session to relax."

[0649] Step 6:

[0650] The generated suggestions are resent from the server to the terminal, which then notifies the user. The terminal may display the suggestions visually on the screen or provide them verbally through speech synthesis. This allows the user to take concrete action.

[0651] Step 7:

[0652] The user takes action based on the provided suggestions, inputs the results and feedback on their device, and sends them to the server. The feedback is stored and analyzed on the server to improve the accuracy of the model. The user's execution results are obtained as input, and feedback data is obtained as output.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] [Fourth Embodiment]

[0657] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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).

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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".

[0670] This invention is a system aimed at managing the health of the elderly and improving their quality of life in a long-lived society. This system continuously collects daily biometric data from the elderly using devices including wearable devices and smartphones. This data includes walking distance, heart rate, and sleep patterns, and serves as a comprehensive indicator of the elderly's health status.

[0671] The terminal sends this data to a data processing unit in the cloud, i.e., a server, at regular intervals. After preprocessing the received data, the server uses a health status assessment model to analyze the health status of the elderly person from the collected data. This allows it to assess whether their health is good, requires improvement, or is in a state requiring attention.

[0672] Based on this analysis, the server generates personalized health promotion suggestions for elderly individuals. For example, if the walking distance is shorter than usual, a message such as "We recommend taking a slightly longer walk" is generated. Also, if a heart rate is detected to be above the normal range, a suggestion including a warning such as "We recommend resting to lower your heart rate" is generated.

[0673] These suggestions are communicated to elderly individuals via their devices. The elderly users review the suggestions and provide feedback, indicating changes in their lifestyle and health status to the system. This feedback is stored in a database on the server and used to improve the model, enabling more accurate health management.

[0674] Furthermore, the server has a function that immediately generates an alarm if it detects an abnormality in the health condition of an elderly person, and notifies caregivers and other relevant parties. This enables a swift response and can prevent serious incidents. Through this series of operations, a system is realized that efficiently manages the health of the elderly and improves the quality of care.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The device collects biometric data in real time from wearable devices and smartphones used by elderly individuals. This data includes steps taken, heart rate, body temperature, activity level, and sleep patterns.

[0678] Step 2:

[0679] The device encrypts the collected biometric data at regular intervals and transmits it to the server via the internet.

[0680] Step 3:

[0681] Before analyzing the received biometric data, the server performs data preprocessing such as noise reduction and correction of missing values.

[0682] Step 4:

[0683] The server uses pre-processed data to run a health status assessment model and evaluate the current health status of older adults. This determines whether they are healthy, require attention, or require emergency response.

[0684] Step 5:

[0685] The server generates personalized health promotion suggestions for older adults based on their health status assessment. These suggestions include specific daily action plans.

[0686] Step 6:

[0687] The terminal notifies the elderly person of suggestions sent from the server via a user interface. The elderly person can receive this information visually or audibly.

[0688] Step 7:

[0689] Users can review the proposals and send feedback on their implementation status and other information via their devices.

[0690] Step 8:

[0691] The server collects feedback data from elderly users and records it in a database. This data is then used to improve the model and enhance the accuracy of future suggestions.

[0692] Step 9:

[0693] The server monitors data in real time and, if it detects abnormal values ​​or sudden changes in health, quickly generates an alarm and sends a warning to caregivers or designated contacts.

[0694] (Example 1)

[0695] 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".

[0696] Elderly individuals may experience a decline in their quality of life due to delays in responding appropriately to changes in their health. Furthermore, they face the challenge of obtaining concrete guidance for health improvement because opportunities to receive appropriate suggestions based on their individual health conditions are limited. Therefore, there is a need to maintain and improve health by continuously and in real time monitoring their health status and providing appropriate guidance.

[0697] 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.

[0698] In this invention, the server includes means for pre-processing biometric information and analyzing it using a health status analysis model, means for generating health promotion recommendations, and means for issuing an alarm when an abnormality is detected. This enables real-time monitoring of the health status of elderly individuals, the provision of individually customized health promotion suggestions, and rapid detection and response to abnormalities.

[0699] "Biometric information" refers to data that indicates an individual's physical condition, and includes information such as heart rate, steps taken, and sleep patterns.

[0700] A "sensing device" is an electronic device used to detect physical or physiological changes and acquire biological information.

[0701] An "information processing device" is a computer system that has the function of receiving, analyzing, and processing data, and outputting the results.

[0702] A "health status analysis model" is an algorithm or machine learning model used to evaluate an individual's health status based on their biometric information.

[0703] "Recommendations" refer to specific health improvement measures and action plans provided to users based on the analysis results.

[0704] "Response information" refers to data used to provide feedback on actions taken and impressions received by users based on recommendations from the system.

[0705] An "alert" is a notification or alert intended to draw the attention of users or relevant parties when an abnormal situation occurs.

[0706] This invention provides a system for effectively managing the health status of elderly individuals, utilizing wearable devices and terminals such as smartphones. The terminal acquires biometric information from the elderly user, including heart rate, walking distance, and sleep patterns. This data is collected by the terminal using short-range communication technologies such as Bluetooth.

[0707] The server functions as an information processing device located in the cloud, receiving data sent from terminals. The received data is first preprocessed, including data cleaning, to impute missing values ​​and remove outliers. Next, a health status analysis model is used to evaluate the health status of individual data points. Machine learning algorithms are used in the analysis to achieve highly accurate health assessments.

[0708] Based on the health assessment results, the server utilizes a generative AI model to generate personalized health promotion suggestions for the user. For example, "Recent data shows your heart rate is a bit high. We recommend setting aside time to relax during the day." The generated suggestions are then pushed to the user via their device.

[0709] Elderly users adjust their behavior based on the suggestions they receive. The effects and feedback they experience after taking action are sent to the server via their device. This feedback is used to further improve the health status analysis model.

[0710] A concrete example of a prompt message is, "Analyze the sleep data of elderly individuals and propose solutions for improvement if sleep is insufficient." This allows the system to efficiently and flexibly support users' health management and improve their quality of life.

[0711] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0712] Step 1:

[0713] The device acquires biometric information from the elderly user. Specifically, a wearable device measures heart rate, steps, and sleep patterns in real time, and this data is transmitted to the device. The input is the measured biometric data, and the output is the temporary storage of this data within the device.

[0714] Step 2:

[0715] The device sends biometric information collected at regular intervals to a server. Wi-Fi or mobile data networks are used for data communication. The input is the biometric information stored on the device, and the output is the transfer of this information to a server in the cloud. Encryption protocols are used to ensure data security during this process.

[0716] Step 3:

[0717] The server preprocesses the received biometric data. This preprocessing includes data cleaning, specifically, missing value imputation and anomaly detection using anomaly detection algorithms. The input is raw data, and the output is cleaned, well-formed data.

[0718] Step 4:

[0719] The server inputs pre-processed data into a health status analysis model to evaluate the health status of elderly individuals. Using a generative AI model, it analyzes health risks and daily health status from the data. The input is well-formed biometric data, and the output is indices and evaluation scores representing the results of the health status assessment.

[0720] Step 5:

[0721] The server generates individually customized health promotion suggestions based on the evaluation results. The generating AI model suggests improvements using the prompt message "Provide appropriate action suggestions for the current heart rate value." The input is the result of the health evaluation, and the output is the suggestion message.

[0722] Step 6:

[0723] The device notifies the user of health promotion suggestions received from the server. Interesting information is delivered to the user in real time via smartphone push notifications and smartwatch vibration functions. The input is the suggestion message, and the output is the notification of this message to the user.

[0724] Step 7:

[0725] After performing the suggested action, the user inputs the results and feedback into the device. This includes changes in physical condition and reactions to the suggestion. The input is the user's feedback information, and the output is sending this information to the server.

[0726] Step 8:

[0727] The server collects user feedback and stores it in a database. This information contributes to further improving the health status analysis model and is used to more accurately assess the health status of older adults. The input is feedback data, and the output is a new dataset for model improvement.

[0728] (Application Example 1)

[0729] 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".

[0730] The challenge lies in effectively managing the health status of the elderly, promptly detecting abnormalities, and providing personalized suggestions to promote their health. Furthermore, it is crucial to improve the accuracy of health management models based on feedback from the elderly, thereby reducing the burden on caregivers and creating an environment where they can live their daily lives with peace of mind.

[0731] 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.

[0732] In this invention, the server includes a device for collecting and transmitting biometric data of elderly individuals, a device for preprocessing the received biometric data and analyzing it using a health indicator evaluation model, a device for generating and providing suggestions based on the analysis results of the health status, a device for collecting response data and improving model accuracy, and a device for monitoring the health status and sending notifications when an anomaly is detected. This makes it possible to grasp the health status of elderly individuals in real time, enabling early detection and appropriate countermeasures.

[0733] "Elderly people" refers to people in an aging society who are particularly concerned with health management.

[0734] "Biometric data" refers to data collected to monitor the health status of older adults, such as heart rate, walking distance, and sleep patterns.

[0735] "Device" refers to hardware or software components used to realize a specific function in an invention.

[0736] An "information processing device" refers to a system that includes a central processing unit for analyzing collected biological data and evaluating health status.

[0737] A "health indicator evaluation model" refers to a mathematical model using algorithms or artificial intelligence that is used to analyze the health status of older adults.

[0738] "Suggestions" refer to specific instructions or advice for promoting health, generated based on the results of an analysis of one's health status.

[0739] "Response data" refers to the information that elderly people provide in response to suggestions, and is used to improve the accuracy of the model.

[0740] "Monitoring" refers to the process of observing the health status of elderly people in real time and detecting any abnormalities.

[0741] "Notification" refers to a warning or informational message sent to the elderly person or their caregiver when an abnormality is detected.

[0742] The system for implementing this invention utilizes various devices and software to collect, analyze, and suggest health data for the elderly. The elderly wear wearable devices during their daily lives. These devices continuously acquire biometric data such as heart rate, walking distance, and sleep patterns. This acquired data is transmitted in real time to a cloud server via a smartphone. The smartphone is used for data transfer and some data preprocessing.

[0743] Upon receiving data, the server first performs preprocessing and then conducts a detailed analysis using a health indicator evaluation model. This model includes machine learning algorithms built on Python and utilizes libraries such as TensorFlow. Based on the results of the data analysis, a generative AI model generates health promotion suggestions tailored to older adults. These suggestions include specific recommendations regarding lifestyle improvements, exercise, nutrition, and rest.

[0744] Suggestions are sent to the elderly person's smartphone and notified. The user can review them and provide feedback. This feedback is stored on the server and used to improve the accuracy of the suggestion model. If an anomaly is detected, a notification is immediately sent from the server to the caregiver, enabling emergency response. This allows for real-time monitoring of the elderly person's health status and enables specific and prompt responses as needed.

[0745] For example, if a wearable device detects that you are experiencing a prolonged period of lighter sleep than your normal sleep pattern, the app will display advice to avoid staying up late and recommend relaxing music. An example of a prompt might be, "Analyze the heart rate data collected by your Fitbit device and send a remote notification via Firebase if your heart rate falls outside the healthy range."

[0746] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0747] Step 1:

[0748] The device acquires biometric data from wearable devices worn by elderly individuals. This biometric data includes heart rate, walking distance, and sleep patterns. The acquired biometric data is collected at regular intervals and temporarily stored on a smartphone.

[0749] Step 2:

[0750] The device transmits the collected biometric data to a server in the cloud via the internet. The transmitted data includes the latest timestamp and personal identification information. This allows the server to ensure the freshness and relevance of the data.

[0751] Step 3:

[0752] The server first preprocesses the received biometric data. This preprocessing involves noise reduction and filtering of outliers to generate a dataset useful for analysis. At this stage, the input is the received biometric data, and the output is the clean, preprocessed data.

[0753] Step 4:

[0754] The server inputs pre-processed data into a health indicator evaluation model to analyze the health status of elderly individuals. This model is a machine learning algorithm built using TensorFlow, which evaluates health status based on multiple data points. The output includes health status scores and classification results.

[0755] Step 5:

[0756] The server uses a generative AI model based on the analysis results to generate specific suggestions for promoting health. These suggestions include personalized advice on improving lifestyle habits. The generated suggestions are designed to mitigate potential health risks that the user may face.

[0757] Step 6:

[0758] The server sends the generated suggestions to the terminal, which then notifies the user. The notification includes text-based advice and displays messages encouraging the user to take care of their health.

[0759] Step 7:

[0760] The user reviews the received proposal and enters feedback into the device. The feedback indicates the implementation status of the proposal and the user's satisfaction with the response, and the device sends this feedback to the server.

[0761] Step 8:

[0762] The server stores the received feedback in a database and uses it to improve future health indicator assessment models. In this step, the feedback is used as new training data to retrain the model.

[0763] 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.

[0764] This invention combines an emotion engine with a system that supports health management for the elderly, enabling suggestions that take into account the user's psychological state. The system's basic elements are the collection of biometric data, data transmission, health status analysis, suggestion generation, suggestion delivery, and feedback collection. By newly introducing an emotion engine, the appropriateness of the suggestions is improved.

[0765] The device acquires user voice and facial expressions in addition to conventional biometric data. This allows the emotion engine to collect data to analyze the user's emotions. The collected data is encrypted and sent to a cloud server.

[0766] The server analyzes the received biometric and emotional data. First, it preprocesses the biometric data, and then assesses the health status of the elderly based on a health status assessment model. In addition to the results of this assessment, it uses an emotional engine to analyze the user's emotional state. The emotional engine estimates the user's psychological state, such as whether they are stressed or relaxed.

[0767] Based on the results of this sentiment analysis, the server generates health promotion suggestions that take into account not only the user's physical condition but also their emotional state. For example, if the user is feeling stressed, suggestions will be generated recommending activities that promote relaxation or rest. If the user is in good health and relaxed, suggestions including active exercise will be made.

[0768] The generated suggestions are notified to the elderly via a device and received visually or audibly. The user takes action in response to the suggestion and provides feedback on the implementation status and changes in their physical condition. This feedback is used to evaluate changes in emotions and the effectiveness of the suggestion.

[0769] The server stores this feedback in a database and uses it to refine the model in the future. In this way, a system incorporating an emotion engine can comprehensively manage both the health and emotions of older adults, making it possible to support health promotion more effectively.

[0770] The following describes the processing flow.

[0771] Step 1:

[0772] The device collects biometric data from elderly individuals (such as walking distance, heart rate, and body temperature) in real time via a wearable device or smartphone. It also uses a built-in microphone and camera to record voice tone and facial expressions, collecting user emotional data.

[0773] Step 2:

[0774] The device formats the collected biometric and emotional data appropriately, encrypts it for data protection, and then sends it to the server.

[0775] Step 3:

[0776] The server receives data transmitted from the terminal and performs preprocessing such as noise reduction and missing value imputation of biometric data. At the same time, it proceeds with the analysis of emotional data and begins processing to identify the user's emotions.

[0777] Step 4:

[0778] The server inputs pre-processed biometric data into a health status assessment model to evaluate the health status of elderly individuals. The assessment results are classified into one of three categories: healthy, requiring attention, or requiring immediate action.

[0779] Step 5:

[0780] The server uses an emotion engine to recognize the user's emotional state from their voice and facial expressions. It identifies their mental state, such as whether they are stressed or relaxed.

[0781] Step 6:

[0782] The server integrates health assessment results and emotion recognition results to generate health promotion suggestions optimized for the psychological and physical state of the elderly. For example, it recommends relaxation when stress levels are high, and exercise when the person is relaxed.

[0783] Step 7:

[0784] The device notifies elderly individuals of health promotion suggestions provided by the server. Elderly individuals can receive these notifications visually or audibly and incorporate them into their own actions.

[0785] Step 8:

[0786] Users act according to the provided suggestions and input feedback into the device regarding their progress, changes in their physical condition, and changes in their emotions. This information serves as important feedback to the system.

[0787] Step 9:

[0788] The server analyzes the received feedback data and stores it in a database. This data is then used to improve future models and enhance the accuracy of suggestions. As a result, the system dynamically evolves, enabling more personalized health and emotional management.

[0789] (Example 2)

[0790] 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".

[0791] When providing health management for the elderly, simply evaluating their health status based on physiological data is insufficient to provide the most appropriate health promotion plan for each individual. Furthermore, proposals that do not consider the psychological aspects of the elderly lack individuality and may even have counterproductive effects. Therefore, it is necessary to comprehensively collect and analyze physiological and psychological data to provide more personalized health promotion plans and improve the quality of life for the elderly.

[0792] 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.

[0793] In this invention, the server includes means for extracting physiological and psychological information, means for determining the user's health status using an information processing device, and means for evaluating the user's psychological state using an emotion analysis device. This makes it possible to comprehensively assess the user's health and psychological state and provide optimal health promotion recommendations.

[0794] "Physiological information" refers to data that indicates the physical and physiological state of the human body, such as heart rate, blood pressure, and body temperature.

[0795] "Psychological information" refers to data about emotions and mental states that can be gleaned from things like voice and facial expressions.

[0796] An "information processing device" is a device that processes received data and performs evaluations based on a predetermined algorithm.

[0797] A "health assessment model" is a mathematical or machine learning framework for analyzing physiological information and scoring the health status of an individual.

[0798] An "emotional analysis device" is a system that uses psychological information to analyze a subject's emotions and mental state.

[0799] A "health promotion plan" is a plan that proposes daily life behaviors optimized according to the health and psychological state of the target individual.

[0800] A "warning" is a notification or alert that occurs when an anomaly is detected, and is intended to draw the attention of the person concerned or the administrator.

[0801] "Physical activity" refers to exercise and everyday physical movements that contribute to maintaining and improving health.

[0802] "Nutritional improvement" refers to efforts to balance nutrition through reviewing eating habits.

[0803] "Recommendation of rest" is a suggestion to encourage taking appropriate rest to recover from physical and mental fatigue.

[0804] This invention combines emotion analysis technology with a system that supports the health management of the elderly to generate personalized suggestions based on the user's health and psychological state. Specific embodiments for carrying out this invention are described below.

[0805] The device uses a wearable device equipped with various sensors to measure heart rate, blood pressure, and body temperature in order to acquire the user's physiological information. This typically utilizes commonly available sensors (e.g., wearable health devices). The device also incorporates a microphone and camera to collect psychological information by capturing the user's voice and facial expressions. This provides the necessary data to understand the user's emotional state.

[0806] The server uses an information processing device to analyze physiological information sent by the user. This device uses a health assessment model based on machine learning frameworks such as "TensorFlow" to preprocess the received data and then evaluate the user's health status. Similarly, psychological information is processed by an "emotion analyzer" to identify the user's psychological state. The "emotion analyzer" uses "NLP (Natural Language Processing)" technology to analyze the user's emotions based on voice and facial expression data.

[0807] The server generates health promotion suggestions based on the evaluation results of the user's physical and mental state. Specifically, if the user is feeling stressed, it recommends "breathing exercises for relaxation," and if the user is relaxed, it suggests "trying a new exercise program."

[0808] The generated health improvement suggestions are communicated to the user via a terminal and provided through voice or visual display. The user adjusts their daily life according to these suggestions and provides feedback on their implementation and perceived changes. This feedback is stored in a database used for further system improvement and adjustment.

[0809] The following is an example of a prompt:

[0810] Please create a program that incorporates an emotion engine into a health management system for the elderly. This system will analyze voice and facial expression data to assess the user's emotional state and generate personalized health promotion suggestions. For example, if the user is feeling stressed, the program should suggest meditation; if they are relaxed, it should suggest jogging.

[0811] In this way, the system concretizes means of providing support tailored to the individual needs of older adults through health and emotional analysis.

[0812] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0813] Step 1:

[0814] The device acquires the user's physiological information, collecting input data such as heart rate, blood pressure, and body temperature. During this process, a wearable device is used to perform real-time physical measurements. The collected physiological information is then stored as digital data on the device.

[0815] Step 2:

[0816] The device acquires the user's voice and facial expressions, collecting audio and image data as input. This process is performed using the microphone and camera built into the device. As output, the audio data is converted into an audio file, and the facial expression data is converted into an image file.

[0817] Step 3:

[0818] The terminal encrypts the collected physiological and psychological information and prepares it for transmission to the server. An encryption protocol is used to ensure data security. An encrypted data packet is generated as output.

[0819] Step 4:

[0820] The server receives encrypted data and performs decryption. It uses the received data as input to initiate the decryption process, and the output is the reconstruction of the original physiological and psychological information.

[0821] Step 5:

[0822] The server preprocesses the physiological information. Signal processing techniques are applied to reduce noise and standardize the data. The output is shaped physiological data.

[0823] Step 6:

[0824] The server analyzes pre-processed physiological data using a health assessment model. It applies the formatted physiological data as input to the model and outputs a health risk score.

[0825] Step 7:

[0826] The server processes psychological information using an emotion analysis device. It analyzes voice data and facial expression data as input and outputs an evaluation of the emotional status (e.g., stress, relaxation).

[0827] Step 8:

[0828] The server integrates the results of health status assessments and emotional status assessments to generate optimal health improvement plans for the user. A generative AI model is used for generation, and specific health improvement suggestions are output.

[0829] Step 9:

[0830] The device receives health promotion suggestions sent from the server and provides them to the user. The output is a notification to the user via audio or visual display.

[0831] Step 10:

[0832] Users take action based on the provided health promotion plan and provide feedback on the results. They report their progress and changes in their physical condition as input, and output this data to the server.

[0833] Step 11:

[0834] The server stores user feedback in a database to help improve the model's accuracy. Based on this feedback, the system is adjusted. The output is an improved evaluation model and generation process.

[0835] (Application Example 2)

[0836] 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".

[0837] In managing the health of the elderly, there is a need for comprehensive health promotion that considers not only physiological data but also psychological state. However, conventional systems have difficulty making suggestions that take into account the user's emotional state, resulting in a lack of support tailored to individual circumstances. Therefore, in managing the health of the elderly, there is a need for a system that can make suggestions that consider not only physical status but also emotional state.

[0838] 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.

[0839] This invention includes a server that encrypts and analyzes physiological and emotional data after receiving it, a server that integrates the analysis of the health and emotional state of elderly individuals using a health status assessment model and an emotional analysis model, and a server that generates and notifies appropriate suggestions regarding health promotion and psychological state improvement. This makes it possible to comprehensively manage both the health and emotional aspects of elderly individuals and provide accurate health promotion advice tailored to their individual conditions.

[0840] "Physiological data" refers to information that indicates the physical condition of elderly individuals, including numerical indicators such as heart rate, blood pressure, and body temperature.

[0841] "Emotional data" refers to information that indicates the psychological state of elderly individuals, and includes signals obtained from facial expressions, voice tone, and behavioral patterns.

[0842] A "health status assessment model" is an algorithm or computational model used to analyze physiological data and assess health status and potential health risks.

[0843] An "emotion analysis model" is an algorithm or computational model used to analyze emotional data and determine a user's psychological health status.

[0844] "Health promotion suggestions" are specific activities and lifestyle guidance recommended for improving and maintaining the health of the elderly, based on the analysis results.

[0845] "Suggestions for improving psychological state" are guidance that, based on the results of emotion analysis, indicates recommended behaviors and habits to improve or maintain the mental health of older adults.

[0846] "Feedback data" refers to information provided by users after they have taken action based on a suggestion, and is used to record the effectiveness of the suggestion and changes in the user's state.

[0847] The system for implementing this invention mainly consists of three elements: a data collection terminal, a server, and a user. The data collection terminal collects physiological and emotional data from elderly individuals, and this is achieved by using a smart device equipped with a heart rate sensor, camera, and microphone. The obtained data is encrypted and transmitted to a server in the cloud.

[0848] The server plays a central role in analyzing the received data. Operating using machine learning frameworks such as TensorFlow, the server preprocesses physiological data, analyzes the health status of older adults using a health status assessment model, and analyzes their emotional state using an emotion analysis model. Based on the data analysis results, the server generates suggestions for health promotion and psychological improvement tailored to older adults.

[0849] After generating suggestions, the server collects the information and sends it to a terminal, which then notifies the elderly person. The collection terminal communicates the suggestions to the user visually or audibly. Text-to-speech or other speech generation technologies may be used in this process. Furthermore, feedback from the elderly person is sent to the server, and the collected feedback data is used to improve the model's accuracy.

[0850] For example, if an elderly person is experiencing stress, the server might suggest meditation or music therapy to promote relaxation. An example of a prompt used when implementing such a suggestion might be, "Recommend a meditation session best suited for relaxation." This allows for comprehensive management of both the health and emotional well-being of elderly individuals, providing appropriate, individualized support.

[0851] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0852] Step 1:

[0853] The device collects physiological and emotional data. Specifically, it measures heart rate with a heart rate sensor, captures facial expressions with a camera, and records voice with a microphone. The obtained data is then prepared to be sent to the server as raw data.

[0854] Step 2:

[0855] The raw data transmitted from the terminal is received by the server and first decrypted. Next, data preprocessing such as noise reduction and standardization is performed. The input consists of physiological data and emotional data, and the output is preprocessed data.

[0856] Step 3:

[0857] The server calculates health indicators using a health status assessment model based on preprocessed data. Preprocessed physiological data is used as input, and a health assessment score is generated as output. This score is used as an indicator of health status.

[0858] Step 4:

[0859] The server uses an emotion analysis model to estimate the user's emotional state from pre-processed emotion data. Using pre-processed emotion data as input, it outputs a numerical value or category indicating the emotional state. For example, it might output a user as "stressed" or "relaxed."

[0860] Step 5:

[0861] The server uses a generative AI model to generate suggestions for health promotion or psychological improvement based on health assessment scores and emotional states. The inputs are health scores and emotional states, and the output is specific suggestions, such as "a suggestion for a meditation session to relax."

[0862] Step 6:

[0863] The generated suggestions are resent from the server to the terminal, which then notifies the user. The terminal may display the suggestions visually on the screen or provide them verbally through speech synthesis. This allows the user to take concrete action.

[0864] Step 7:

[0865] The user takes action based on the provided suggestions, inputs the results and feedback on their device, and sends them to the server. The feedback is stored and analyzed on the server to improve the accuracy of the model. The user's execution results are obtained as input, and feedback data is obtained as output.

[0866] 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.

[0867] 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.

[0868] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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."

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] The following is further disclosed regarding the embodiments described above.

[0888] (Claim 1)

[0889] Methods for collecting biometric data of the elderly,

[0890] A means for transmitting collected biometric data to a data processing device at a remote location,

[0891] A means for preprocessing received biometric data in a data processing device and analyzing the health status of elderly people using a health status assessment model,

[0892] A means for generating health promotion suggestions for the elderly based on the results of a health status analysis,

[0893] Means of providing the generated suggestions to the elderly,

[0894] Methods for collecting feedback data from elderly individuals and using them to improve the accuracy of the model,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, comprising means for generating an alarm when an abnormality is detected in a data processing device.

[0898] (Claim 3)

[0899] The system according to claim 1, wherein the generated health promotion suggestions include at least one of exercise, nutrition, and rest.

[0900] "Example 1"

[0901] (Claim 1)

[0902] A means of continuously acquiring a user's biometric information using a biometric information sensing device,

[0903] A means for transferring acquired biometric information to a remotely located information processing device,

[0904] A means for pre-processing biometric information received in an information processing device and analyzing the user's health status using a health status analysis model,

[0905] A means of generating health promotion recommendations for users based on the results of health status analysis,

[0906] A means of notifying users of the generated recommendations,

[0907] A means of obtaining response information from users and using it to improve the accuracy of the analysis model,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, comprising means for issuing an alarm when an abnormality is detected from biological information in an information processing device.

[0911] (Claim 3)

[0912] The system according to claim 1, wherein the generated health promotion recommendations include at least one of physical activity, nutritional intake, and rest.

[0913] "Application Example 1"

[0914] (Claim 1)

[0915] A device for collecting biometric data of elderly people,

[0916] A device that transmits collected biometric data to an information processing device located remotely,

[0917] A device that preprocesses biometric data received in an information processing device and analyzes the health status of elderly people using a health indicator evaluation model,

[0918] A device that generates health promotion suggestions for the elderly based on the results of a health status analysis,

[0919] A device that provides the generated suggestions to the elderly,

[0920] A device used to collect response data from elderly people and improve the accuracy of the model,

[0921] A device that monitors the health status of elderly people and immediately sends a notification when an abnormality is detected,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, comprising a device for transmitting a notification when an abnormality is detected in an information processing device.

[0925] (Claim 3)

[0926] The system according to claim 1, wherein the generated health promotion suggestions include at least one of exercise, nutrition, and rest, and are further individually optimized based on the user's response.

[0927] "Example 2 of combining an emotion engine"

[0928] (Claim 1)

[0929] A means for extracting physiological and psychological information from elderly people,

[0930] Means for transmitting extracted physiological and psychological information to an information processing device,

[0931] A means for preprocessing physiological information received in an information processing device and determining the health status of an elderly person using a health assessment model,

[0932] Furthermore, the system includes a means for processing the received psychological information using an emotion analysis device and evaluating the psychological state of the subject,

[0933] A means of developing optimal health promotion plans for the elderly based on the results of assessments of their physical and psychological condition,

[0934] Means for communicating the developed health promotion plan to the elderly,

[0935] A means for collecting information from elderly individuals regarding the implementation status and changes in their physical condition, and for adjusting the accuracy of the evaluation model and analysis device,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, further comprising means for generating a warning when an abnormality is detected.

[0939] (Claim 3)

[0940] The system according to claim 1, wherein the constructed health promotion plan combines at least one of physical activity, nutritional improvement, and rest recommendations.

[0941] "Application example 2 when combining with an emotional engine"

[0942] (Claim 1)

[0943] Methods for collecting physiological and emotional data from the elderly,

[0944] A means for encrypting and transmitting collected physiological and emotional data to a remote information processing device,

[0945] A means for preprocessing physiological and emotional data received in an information processing device and analyzing the health and emotional state of elderly people using a health status assessment model and an emotion analysis model,

[0946] A means for generating suggestions for health promotion and psychological improvement for the elderly based on the results of health status analysis and emotional status analysis,

[0947] Means for providing the generated proposals to the elderly audibly or visually,

[0948] A means to collect feedback data from elderly individuals related to their performance and changes in physical condition, and to use this data to improve the accuracy of health status assessment models and emotion analysis models.

[0949] A system that includes this.

[0950] (Claim 2)

[0951] The system according to claim 1, comprising means for generating an alarm when an abnormality is detected in an information processing device and notifying the elderly person or caregiver in real time.

[0952] (Claim 3)

[0953] The system according to claim 1, wherein the generated suggestions for promoting health and improving psychological state include at least one of exercise, nutrition, rest, and relaxation activities. [Explanation of Symbols]

[0954] 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. Methods for collecting biometric data of the elderly, A means for transmitting collected biometric data to a data processing device at a remote location, A means for preprocessing received biometric data in a data processing device and analyzing the health status of elderly people using a health status assessment model, A means for generating health promotion suggestions for the elderly based on the results of a health status analysis, Means of providing the generated suggestions to the elderly, Methods for collecting feedback data from elderly individuals and using them to improve the accuracy of the model, A system that includes this.

2. The system according to claim 1, comprising means for generating an alarm when an abnormality is detected in a data processing device.

3. The system according to claim 1, wherein the generated health promotion suggestions include at least one of exercise, nutrition, and rest.

Images