system

Abstract

Provide a system. 【Solution means】 Means for collecting biometric information from a sensor device for real-time monitoring of the health status of the elderly, Means for acquiring video data from a camera device, Means for analyzing these data using a machine learning model to detect anomalies, Means for generating and notifying an alert when an anomaly is detected, Means for communicating with the user by voice or text using natural language processing, Means for proposing a customized care plan based on the behavior pattern, Means including an artificial intelligence conversation agent that responds to voice instructions, Visual display means on a mobile information terminal for visualizing real-time health data, A system including. A system including.

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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 and safety assurance of the elderly are important issues. In conventional health monitoring systems, it is difficult to detect abnormalities in real time, and communication with the outside and the provision of individual care plans are limited. Furthermore, the burden on caregivers and the alleviation of the loneliness of the elderly have not been fully achieved. There is a demand for a system that comprehensively improves these aspects and enables a more secure and active life.

Means for Solving the Problems

[0005] This invention provides a means for collecting biometric information of elderly individuals using sensor devices and acquiring video data through camera devices. This data is analyzed in real time using machine learning models, enabling rapid detection of abnormalities. Furthermore, it has means for immediately generating alerts and notifying relevant parties in the event of an abnormality. In addition, it utilizes natural language processing technology to enable voice or text communication with elderly individuals and proposes individualized care plans based on their behavioral patterns. This enables real-time health management and safety assurance for elderly individuals, reduces the burden on caregivers, and improves the quality of life for the elderly themselves.

[0006] The term "elderly" generally refers to people aged 65 or older, a group for whom health management and safety are considered particularly important due to the effects of aging.

[0007] "Monitoring" is the process or method of continuously observing the state or changes of a specific object and taking appropriate action as needed.

[0008] A "sensor device" is a device that acquires specific information from the physical environment and is used to collect biometric information such as heart rate and body temperature.

[0009] A "camera device" is a device used to acquire video or image data, and is used for identifying movements and facial expressions.

[0010] "Data analysis" is the process of analyzing collected data using statistical methods and algorithms to extract meaningful information.

[0011] A "machine learning model" is an algorithm or system that learns patterns and regularities based on data and uses them to make predictions and classifications on new data.

[0012] "Anomaly detection" refers to a technology or method that automatically detects phenomena that deviate from normal states or patterns and reports or handles them appropriately.

[0013] An "alert" is a signal or notification issued to draw attention or caution, and its role is to inform relevant parties when a system detects an anomaly.

[0014] "Natural language processing" is a technology that uses computers to understand, generate, and analyze human language, and is used when interacting with users through speech or text.

[0015] A "care plan" is an individually formulated plan for health management and lifestyle support, and is used to provide the most suitable measures for each individual based on remote monitoring data. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, a processor with a reference numeral (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.

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

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

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

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

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0037] This invention relates to a system for monitoring the health status of elderly individuals in real time and rapidly detecting abnormalities. This system consists of multiple components for acquiring, analyzing, and managing biometric information and video data.

[0038] First, sensor devices continuously acquire biometric information such as the elderly person's heart rate and body temperature. These devices are often worn directly on the body and are designed to transmit data to a central server via Wi-Fi or Bluetooth. Camera devices are also used to monitor the elderly person's movements and facial expressions, and the video data is similarly transmitted to the server.

[0039] Next, the server receives this raw data and analyzes it using a machine learning model. The model identifies patterns in normal health data and detects any deviations as anomalies. If an anomaly is detected, the server automatically generates an alert and sends a notification to the registered caregiver or family member's device. This notification is sent via push notification or email.

[0040] Furthermore, users can interact with AI chatbots and voice assistants on a daily basis. The device uses natural language processing technology to understand voice commands from the user and provide reminders and health status feedback. This feature aims to provide an environment where elderly people can use the system without feeling isolated.

[0041] Furthermore, the server analyzes continuous behavioral patterns and generates individualized care plans. These care plans are customized based on the user's past behavioral data and provide guidance that helps maintain the user's health and prevent dementia. The terminal clearly notifies the user of this information, promoting daily health maintenance activities.

[0042] This combination enables the present invention to realize a system that can consistently monitor the health of elderly people and take necessary actions quickly and efficiently.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The sensor device acquires biometric information such as the heart rate and body temperature of elderly individuals and transmits the data to a server. The server then records the timestamp of the received data and the device ID.

[0046] Step 2:

[0047] The camera device captures video data of the elderly person's movements and facial expressions and streams it to a server. The server saves this data frame by frame and prepares it for analysis.

[0048] Step 3:

[0049] The server converts biometric information and video data into JSON format and organizes them as a time series. This prepares the data for the analysis process.

[0050] Step 4:

[0051] The server applies a machine learning model to analyze the data in real time. Here, a range of normal values ​​is defined, and a means is used to detect outliers that fall outside of this range.

[0052] Step 5:

[0053] If an anomaly is detected, the server immediately generates an alert and sends a notification to the devices of caregivers and family members that have been registered in advance.

[0054] Step 6:

[0055] When a user begins interacting with an AI chatbot or voice assistant, the device converts the speech into text and uses natural language processing to understand the user's request.

[0056] Step 7:

[0057] The device provides users with reminder functions and health information feedback, and responds to questions in voice or text.

[0058] Step 8:

[0059] The server analyzes the data it collects over a long period to evaluate behavioral patterns. Based on this, it generates a care plan optimized for the user and sends it to the device. The device then notifies the user of this information, promoting health maintenance.

[0060] (Example 1)

[0061] 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."

[0062] In managing the health of the elderly, real-time, detailed monitoring and prompt responses are required. However, current systems have challenges in data accuracy, the speed of anomaly detection, and smooth communication with users. Furthermore, they lack sufficient functionality to flexibly propose care tailored to individual health conditions, making it difficult to maintain a safe and secure life. Therefore, a new system is needed that consistently monitors the health status of the elderly and provides individualized and effective care.

[0063] 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.

[0064] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video data from camera devices, and means for analyzing this data using a machine learning model and detecting anomalies. This makes it possible to monitor the health status of elderly people in real time and in detail, and to quickly generate and notify alerts when an anomaly is detected. Furthermore, personalized health management can be performed more effectively through the proposal of customized care plans based on behavioral patterns and communication with the user using natural language processing.

[0065] A "sensor device" is a device worn on the body to collect biometric information such as heart rate, body temperature, and blood pressure in elderly individuals in real time.

[0066] A "camera device" is a device used to monitor the movements and facial expressions of elderly people and to acquire video data.

[0067] A "machine learning model" is a computational algorithm used to analyze collected biometric and video data and detect abnormalities that fall outside the normal range.

[0068] "Means for generating and notifying alerts" refers to a system that automatically creates warnings when an anomaly is detected and notifies registered caregivers and family members.

[0069] "Natural language processing" is a technology that enables computers to understand human language and interact with users in either speech or text format.

[0070] A "customized care plan" is a specific plan created based on the user's individual behavioral patterns and health condition, outlining the necessary steps for maintaining their health and providing care.

[0071] An "AI chatbot or voice assistant" is a program that interacts with users using voice or text to provide health information and set reminders.

[0072] This invention is a system for monitoring the health status of elderly people in real time and rapidly detecting abnormalities. Its components include a sensor device, a camera device, a machine learning model, a notification function, a natural language processing function, and a customized care plan function.

[0073] First, the sensor device acquires biometric information such as the user's heart rate and body temperature in real time. This device is designed to be worn on the user's body and transmit data to a server via Wi-Fi or Bluetooth. This makes it possible to continuously monitor the user's health status.

[0074] Next, the camera device records the user's movements and facial expressions. The video data is also transferred to a server and used to understand the user's physical activity and emotional state.

[0075] The data received by the server is analyzed using a machine learning model. This model incorporates algorithms that identify data patterns of normal health conditions and quickly detect anomalies. If an anomaly is detected, the server generates an alert and, on behalf of the user, notifies the devices of registered caregivers and family members.

[0076] Furthermore, the device communicates with the user via text or voice using natural language processing technology. This feature allows users to receive feedback on their health status. It's also possible to use an AI chatbot to give instructions such as, "Set a reminder for today's exercise."

[0077] In addition, the server creates individualized care plans based on past data. This recommends specific actions for maintaining the user's health and preventing dementia. This care plan is naturally integrated into the user's daily life, promoting efficient health management.

[0078] A concrete example of a prompt message is "Tell me how to analyze health data of elderly people and detect abnormalities," which can be input to the generating AI model.

[0079] This system provides users with consistent health monitoring and support to live an independent life with peace of mind.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The sensor device acquires biometric information such as the heart rate and body temperature of elderly individuals. The input is real-time biometric data. This data is transmitted to a server using communication methods such as Wi-Fi or Bluetooth. Specifically, the device periodically converts the biometric data into digital signals and stores them in a database connected to the server via wireless communication.

[0083] Step 2:

[0084] The camera device records the movements and facial expressions of elderly individuals and collects the resulting video data. The input is physical video information. This data is then converted into digital data and sent to a server. Specifically, the camera captures the user's image, converts the image into a compressed format, and then transfers it to the server for storage in a visual database.

[0085] Step 3:

[0086] The server receives collected biometric and video data and stores it in a database. The input consists of digital data transmitted from sensor and camera devices. The server temporarily stores this data in the database, preparing it for use in the next analysis step. Specifically, the server verifies the data format and adjusts it to a state suitable for analysis.

[0087] Step 4:

[0088] The server uses a machine learning model to analyze biometric and video data. The input is the collected data. As part of the data processing, the machine learning model compares normal and abnormal patterns to detect anomalies. The output is the result of the anomaly detection. For example, if the model detects an abnormal increase in heart rate, an anomaly flag is immediately set.

[0089] Step 5:

[0090] If an anomaly is detected, the server generates an alert and sends a notification to the caregiver's or family member's device. The input is the result of the anomaly detection. Based on this, an alert message is created and sent via push notification or email. Specifically, a notification stating, "Grandma's heart rate is abnormal," is sent to the device.

[0091] Step 6:

[0092] The device uses natural language processing (NLP) capabilities to communicate with the user via voice or text. Input includes voice instructions and questions from the user. The NLP engine analyzes the content and provides appropriate feedback and information. For example, if the user asks, "How am I feeling today?", the device might respond, "Your heart rate and body temperature are within the normal range."

[0093] Step 7:

[0094] The server performs continuous data analysis and generates individualized care plans. Input includes past biometric data and behavioral patterns. Based on the analysis results, it creates a care plan that proposes specific health maintenance and preventative measures. For example, if a user has low exercise levels, it might generate a plan recommending a 15-minute walk daily, which is then notified to the user via their device.

[0095] (Application Example 1)

[0096] 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."

[0097] In managing the health of the elderly, it is crucial to detect abnormalities in real time and respond quickly. However, conventional systems have shortcomings in data collection and analysis, resulting in challenges in the accuracy of abnormality detection and rapid notification. Furthermore, if the elderly are not tech-savvy, there are communication barriers with the system, making it difficult to alleviate feelings of isolation and manage their health appropriately.

[0098] 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.

[0099] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring video data from a camera device, means for analyzing this data using a machine learning model to detect anomalies, means for generating and notifying alerts when an anomaly is detected, means for responding to voice commands using an artificial intelligence conversational agent, and means for visual display on a mobile information terminal that visualizes real-time health data. This enables highly accurate monitoring of health status, rapid notification of anomalies, and the provision of a sense of security through an easy-to-use interface for the elderly.

[0100] A "sensor device" is a device that continuously acquires biometric information such as a user's heart rate and body temperature, and provides this data to other devices or systems.

[0101] A "camera device" is a device used to capture the user's movements and facial expressions, and is capable of collecting video data.

[0102] A "machine learning model" is a set of algorithms and methods used to analyze collected data and detect anomalies that deviate from normal patterns.

[0103] "Means for detecting anomalies" are technical methods or systems designed to identify data that deviates from normal conditions and to recognize problems.

[0104] A "means for generating and notifying alerts" is a mechanism for promptly informing relevant individuals or organizations when an anomaly is detected.

[0105] An "artificial intelligence conversational agent" is software or a system that uses natural language processing technology to interpret voice commands from a user and provide appropriate responses.

[0106] A "portable information terminal" is an electronic device that an individual can carry with them and use to display and process various types of information.

[0107] The system for implementing this invention aims to monitor the health status of elderly people in real time and to quickly detect abnormalities. This includes sensor devices, camera devices, a cloud server, and a personal digital assistant (PDCA) terminal.

[0108] The server receives biometric information such as heart rate and body temperature collected by sensor devices via Bluetooth or Wi-Fi. It also captures video data of movement and facial expressions from camera devices, and this data is sent to the cloud. The server analyzes this raw data using a machine learning model based on Python, detecting deviations from normal health patterns as anomalies.

[0109] When an anomaly is detected, an alert is sent to the user's mobile device via push notification, for example, through Firebase. The artificial intelligence conversational agent installed on the device uses natural language processing technology to interpret voice commands from the user and set reminders or provide feedback on their health status.

[0110] Furthermore, the system analyzes the user's past behavioral data to generate an individualized care plan. This care plan provides guidance for elderly individuals to maintain their daily health. For example, it recommends changes to daily exercise levels and diet, and displays this information visually on a mobile device.

[0111] For example, when a user's heart rate significantly exceeds their normal level, they can receive an alert saying, "Your heart rate is higher than normal. Please check and take any necessary action." Another example of a prompt message for the generating AI model is, "Generate a sample push notification message to send when an abnormal heart rate is detected."

[0112] In this way, the system can consistently support the health management of the elderly and enable the early detection of abnormalities.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The sensor device continuously acquires the user's heart rate and body temperature and transmits it to the server via Bluetooth. This data collection provides biometric input. The server saves the received data to storage in real time. At this time, the data's timestamp and device ID are also recorded.

[0116] Step 2:

[0117] The camera device captures the user's movements and facial expressions as video data and transmits it to the server via Wi-Fi. This video data serves as input for analyzing the user's behavior. The server converts the video data into a predefined format and saves it. This conversion process allows for efficient subsequent analysis.

[0118] Step 3:

[0119] The server feeds the collected biometric and video data into a machine learning model built in Python. The machine learning model executes an anomaly detection algorithm and analyzes the input data. If an anomaly pattern is detected in the data, this information is output as alert data.

[0120] Step 4:

[0121] Based on alert data detecting an anomaly, the server generates a push notification. This notification includes information about the anomaly and how to address it. The generated notification is sent to the user's device using a cloud messaging service. The user's device displays the received notification on the screen and notifies the user with sound and vibration.

[0122] Step 5:

[0123] The server analyzes the user's past behavioral data and runs a program to generate an individualized care plan. This care plan generation utilizes machine learning predictive models and rule-based systems. The generated care plan is visually displayed on the user's device, providing specific guidance for improving their lifestyle.

[0124] Step 6:

[0125] The device uses an artificial intelligence conversational agent to interpret and respond to user voice commands in real time. It takes the user's voice as input, analyzes their intent using natural language processing, and generates an appropriate response. The generated response is output as voice or displayed as text, enabling interaction with the user.

[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 is a system for monitoring the health and emotional state of elderly individuals in real time, and comprises a combination of sensor devices, camera devices, an emotion engine, and other analysis and notification means.

[0128] First, sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time, depending on the environment. Meanwhile, camera devices capture video data of the elderly individuals' facial expressions and movements and transmit it to the server. This allows for the simultaneous collection of both physical and behavioral data.

[0129] Next, this system incorporates an emotion engine that analyzes biometric and video data collected by the server to estimate the user's emotional state. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into states such as "happiness," "sadness," and "anger." This makes it possible to monitor the mental health of elderly individuals.

[0130] When abnormal conditions or specific emotions are detected, the server generates an alert. For example, if a sudden change in heart rate or a prolonged state of "sadness" is detected, a notification is immediately sent to the device of the registered caregiver or family member. This notification enables rapid intervention and promotes preventative action.

[0131] Furthermore, when users interact with AI chatbots and voice assistants, the analysis results from the emotion engine enable more personalized conversations. For example, if the system determines that a user is stressed, it may offer relaxing topics or suggest deep breathing reminders.

[0132] Furthermore, the server learns the user's behavioral and emotional patterns over a long period of time and creates an individualized care plan. This provides customized health management tailored to the user's physical and mental needs. Finally, the device notifies the user of this information to help improve their daily life.

[0133] Thus, this invention aims to improve the quality of life for the elderly by monitoring both their health and emotions, and through anomaly detection and appropriate interaction.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] The sensor device continuously measures the heart rate and body temperature of elderly individuals and transmits the data to a server.

[0137] Step 2:

[0138] A camera device captures the faces and movements of elderly individuals and transmits the resulting video data to a server. This data is used to capture the elderly individuals' daily activities and changes in their facial expressions.

[0139] Step 3:

[0140] The system receives biometric and video data collected by the server and converts it into a pre-configured format. Simultaneously, it organizes the data with timestamps in preparation for analysis.

[0141] Step 4:

[0142] The server uses machine learning models to perform data analysis. Based on biometric information, it detects abnormal heart rate and body temperature, and uses an emotion engine to analyze changes in the facial expressions of elderly people from video data to determine their emotional state.

[0143] Step 5:

[0144] If an anomaly or a specific emotional state (e.g., "sadness" or "anger") is detected, the server generates an alert and sends a notification to the relevant parties' terminals. This notification includes information about the anomaly and the emotional state.

[0145] Step 6:

[0146] When a user makes a request to an AI chatbot or voice assistant, the device converts the user's voice into text and interprets the request using natural language processing.

[0147] Step 7:

[0148] Based on information obtained from the emotion engine, the device adjusts the conversation content according to the user's emotions and provides personalized follow-up messages and reminders.

[0149] Step 8:

[0150] The server analyzes long-term data and learns the behavioral and emotional patterns of elderly individuals to create personalized care plans, which are then sent to the user's device. This provides specific suggestions to support the user's health promotion activities.

[0151] (Example 2)

[0152] 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".

[0153] In modern society, real-time monitoring of the physical and emotional health of the elderly is a crucial challenge. However, conventional technologies have struggled to comprehensively grasp these conditions and respond quickly. In particular, health management systems for the elderly that take into account changes in emotional state are still insufficient. This invention aims to provide a system that comprehensively monitors not only physical health but also emotional aspects, and that can respond quickly when abnormalities occur.

[0154] 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.

[0155] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring facial expression and motion data from a camera device, and means for data analysis, including an emotion engine that estimates the user's emotional state using this data. This makes it possible to comprehensively monitor the physical and emotional health status of elderly people, detect abnormalities, and respond quickly.

[0156] A "sensor device" is a device used to collect biometric information such as heart rate and body temperature of elderly people in real time.

[0157] A "camera device" is a device used to acquire video data of elderly people's facial expressions and movements.

[0158] An "emotion engine" is software or hardware that analyzes collected video data and biometric information to estimate the user's emotional state.

[0159] "Means of data analysis" refers to technical means of analyzing collected data and executing a process to detect abnormal conditions and emotional patterns.

[0160] An "alert" is a notification that is generated when an abnormal condition or a specific emotional state is detected.

[0161] An "external terminal" is a device owned by a registered caregiver or family member that can receive notifications such as alerts.

[0162] "Natural language processing" is a technology that enables communication with users through voice or text, and includes processing to understand and respond to users' emotions and requests.

[0163] An "individualized care plan" is a set of suggestions created based on the behavioral and emotional patterns of elderly individuals, aimed at optimizing the user's health and mental state.

[0164] This invention is a system for monitoring the health and emotional state of elderly individuals in real time. The system comprises a combination of a sensor device, a camera device, an emotion engine, and other data analysis and notification means.

[0165] Sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time and stored in a database. Camera devices capture the elderly individuals' facial expressions and movements as video data, which is also transmitted to the server.

[0166] The server uses an emotion engine to analyze collected biometric and video data. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into categories such as "happiness," "sadness," and "anger." The analyzed emotion data is used to monitor the user's mental health.

[0167] If an anomaly is detected, the server generates an alert and sends that information to the terminal. For example, if there is a sudden change in heart rate or a prolonged feeling of "sadness," caregivers and family members will be notified in real time. This allows for prompt action to be taken.

[0168] When users interact with AI chatbots or voice assistants, the conversation becomes more personalized based on analysis results from the emotion engine. This allows for the provision of topics and suggestions tailored to the user. For example, if the system determines that the user is experiencing high stress levels, it may offer relaxing topics or suggest taking deep breaths.

[0169] Furthermore, the server learns the user's long-term behavioral and emotional patterns and creates an individualized care plan. This care plan is designed to provide customized health management tailored to the user's physical and mental needs.

[0170] Specific example:

[0171] If a user continues to experience feelings of sadness, the system will send a notification to the caregiver's device stating, "Continuous sadness has been detected. Confirmation is required."

[0172] Examples of prompts for a generative AI model:

[0173] "Please analyze the emotional state of elderly individuals based on the following data: heart rate, facial expression data, and voice tone."

[0174] "Based on the results of the emotion analysis, please suggest appropriate relaxation methods to the user."

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

[0176] Step 1:

[0177] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals. The input is the elderly person's physical data, and the output is the biometric information acquired by the sensor device. This biometric information is transmitted to a server using wireless communication and recorded in a database.

[0178] Step 2:

[0179] The camera device monitors the facial expressions and movements of elderly individuals and acquires video data. The input is video from the elderly individuals, and the output is video data. The video data is transmitted to and stored on a server, similar to sensor devices.

[0180] Step 3:

[0181] The server receives heart rate and body temperature data and performs time-series analysis. The input is biometric data, and data analysis is performed to detect rapid fluctuations and abnormal patterns. The output is the result of the abnormality detection. Specifically, if the heart rate exceeds the normal range, an alert state is triggered.

[0182] Step 4:

[0183] The emotion engine analyzes video data and estimates emotions from facial expressions. The input is video data, and the output is the estimated emotional state. Classifications such as "happiness," "sadness," and "anger" are performed, and analysis results are generated. Specifically, the movements of facial muscles are matched with specific emotional patterns.

[0184] Step 5:

[0185] The server generates an alert upon receiving abnormal biometric data or specific emotional states. Inputs include the detection results of the anomaly and the emotional analysis results, while output is alert information. This alert information is sent to the device and notified to registered caregivers and family members. Specifically, push notifications are sent to the device, enabling a quick response.

[0186] Step 6:

[0187] When users interact with AI chatbots or voice assistants, the conversation is personalized based on the results of sentiment analysis. The input is the user's emotional state, and the output is personalized conversation content. Specifically, if the system determines that the user is stressed, it will suggest ways to relax.

[0188] Step 7:

[0189] The server learns the user's behavioral and emotional patterns based on long-term data and creates an individualized care plan. The input is historical data, and the output is a customized care plan. This provides optimized health management and support for daily life for each user.

[0190] (Application Example 2)

[0191] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0192] In an aging society, managing the health of the elderly is a crucial issue. In particular, it is necessary to consider not only the physical health but also the emotional well-being of the elderly. While conventional systems focus on monitoring physical health, they have struggled to track emotional states in real time and provide appropriate responses. Furthermore, while rapid responses are required in the event of abnormal conditions or changes in emotional state, automatically providing specific care suggestions has been difficult. This has hindered improvements in the quality of life for the elderly.

[0193] 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.

[0194] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video information from video acquisition devices, means for analyzing this data using machine learning models to detect abnormal states or emotional states, means for generating and notifying alerts when abnormal states or specific emotional states are detected, means for using natural language processing to engage in voice or text-based dialogue with humans, and means for presenting customized care plans based on the user's behavior and emotions. This enables real-time monitoring of the health and emotional state of elderly individuals and allows for the provision of rapid and personalized care plans.

[0195] A "sensor device" is a device used to collect biological information from the body in real time, and is particularly responsible for acquiring data such as heart rate and body temperature.

[0196] A "video acquisition device" is a device used to record a subject's facial expressions and movements, and has the function of transmitting video data to a server in real time.

[0197] A "machine learning model" is an algorithm that uses collected biometric information and video data to analyze and identify abnormal states and emotional states.

[0198] "Abnormal state alert generation" is a process that notifies users of information when sudden changes in heart rate or body temperature, or specific emotional states, are detected.

[0199] "Natural language processing" is a technology that uses human language to understand and analyze speech and text, thereby facilitating smooth communication.

[0200] A "customized care plan" is a means of proposing an optimized care plan based on the individual health and emotional state of the user.

[0201] The system of the present invention consists mainly of a sensor device, a video acquisition device, and a machine learning model for monitoring the health and emotional state of elderly people in real time. The sensor device acquires biometric information such as the heart rate and body temperature of elderly people in real time and transmits it to a server. The video acquisition device records the facial expressions and movements of elderly people and similarly transmits them to the server.

[0202] The server analyzes this data using machine learning models to identify abnormal conditions and emotional states. Based on the results of this analysis, the server makes recommendations. For example, if the heart rate increases sharply or if the detected emotions differ from normal, it generates an alarm and immediately sends it to the caregiver.

[0203] The server also uses natural language processing to engage in voice or text-based conversations with the user and present personalized care plans tailored to the elderly person's condition. These care plans are designed to support the elderly person's daily life and maintain their mental and physical health.

[0204] Specifically, the server analyzes heart rate and facial expression data, and if it determines that the user is stressed, it offers relaxation suggestions in a conversational format. For example, it can send a reminder to take deep breaths. For this purpose, it sometimes uses prompts constructed by a generative AI model.

[0205] An example of a prompt message is: "Based on the current heart rate and facial expression data of the elderly, identify possible emotional states and recommend an appropriate action plan."

[0206] As a result, this invention can improve the quality of life for the elderly and help maintain a safe and secure life.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals in real time. This data is transmitted to a server using wireless communication. The input is heart rate and body temperature data, and the output is raw biometric data that is transferred to the server.

[0210] Step 2:

[0211] The video acquisition device records the facial expressions and movements of elderly individuals as video data and transmits it to a server. The input is video data, and the output is unprocessed video data sent to the server.

[0212] Step 3:

[0213] The server inputs the received biometric information and video data into a machine learning model for data analysis. Specifically, the AI ​​model analyzes fluctuations in heart rate and body temperature, as well as changes in facial expression. The input consists of biometric information and video data, and the output is the analysis results regarding health status and emotional state.

[0214] Step 4:

[0215] The server detects abnormal states and emotional states based on the analysis results. If an abnormality is detected, it generates an alert. The input is the analysis results, and the output is the alert information.

[0216] Step 5:

[0217] The server sends the generated alert information to the caregiver's or family member's device and provides instructions if an emergency response is needed. The input is the alert information, and the output is a notification message.

[0218] Step 6:

[0219] The server uses natural language processing to present the user with customized care plans in voice or text. Based on the analyzed emotional state, it suggests relaxation methods and appropriate activities. Input consists of the analysis results and prompts generated by the AI ​​model, while output is the text or voice data presented as the care plan.

[0220] Step 7:

[0221] The user selects actions to improve their daily life based on the presented care plan. The input is the presented care plan, and the output is the actions selected by the user.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] This invention relates to a system for monitoring the health status of elderly individuals in real time and rapidly detecting abnormalities. This system consists of multiple components for acquiring, analyzing, and managing biometric information and video data.

[0239] First, sensor devices continuously acquire biometric information such as the elderly person's heart rate and body temperature. These devices are often worn directly on the body and are designed to transmit data to a central server via Wi-Fi or Bluetooth. Camera devices are also used to monitor the elderly person's movements and facial expressions, and the video data is similarly transmitted to the server.

[0240] Next, the server receives this raw data and analyzes it using a machine learning model. The model identifies patterns in normal health data and detects any deviations as anomalies. If an anomaly is detected, the server automatically generates an alert and sends a notification to the registered caregiver or family member's device. This notification is sent via push notification or email.

[0241] Furthermore, users can interact with AI chatbots and voice assistants on a daily basis. The device uses natural language processing technology to understand voice commands from the user and provide reminders and health status feedback. This feature aims to provide an environment where elderly people can use the system without feeling isolated.

[0242] Furthermore, the server analyzes continuous behavioral patterns and generates individualized care plans. These care plans are customized based on the user's past behavioral data and provide guidance that helps maintain the user's health and prevent dementia. The terminal clearly notifies the user of this information, promoting daily health maintenance activities.

[0243] This combination enables the present invention to realize a system that can consistently monitor the health of elderly people and take necessary actions quickly and efficiently.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The sensor device acquires biometric information such as the heart rate and body temperature of elderly individuals and transmits the data to a server. The server then records the timestamp of the received data and the device ID.

[0247] Step 2:

[0248] The camera device captures video data of the elderly person's movements and facial expressions and streams it to a server. The server saves this data frame by frame and prepares it for analysis.

[0249] Step 3:

[0250] The server converts biometric information and video data into JSON format and organizes them as a time series. This prepares the data for the analysis process.

[0251] Step 4:

[0252] The server applies a machine learning model to analyze the data in real time. Here, a range of normal values ​​is defined, and a means is used to detect outliers that fall outside of this range.

[0253] Step 5:

[0254] If an anomaly is detected, the server immediately generates an alert and sends a notification to the devices of caregivers and family members that have been registered in advance.

[0255] Step 6:

[0256] When a user begins interacting with an AI chatbot or voice assistant, the device converts the speech into text and uses natural language processing to understand the user's request.

[0257] Step 7:

[0258] The device provides users with reminder functions and health information feedback, and responds to questions in voice or text.

[0259] Step 8:

[0260] The server analyzes the data it collects over a long period to evaluate behavioral patterns. Based on this, it generates a care plan optimized for the user and sends it to the device. The device then notifies the user of this information, promoting health maintenance.

[0261] (Example 1)

[0262] 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".

[0263] In managing the health of the elderly, real-time, detailed monitoring and prompt responses are required. However, current systems have challenges in data accuracy, the speed of anomaly detection, and smooth communication with users. Furthermore, they lack sufficient functionality to flexibly propose care tailored to individual health conditions, making it difficult to maintain a safe and secure life. Therefore, a new system is needed that consistently monitors the health status of the elderly and provides individualized and effective care.

[0264] 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.

[0265] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video data from camera devices, and means for analyzing this data using a machine learning model and detecting anomalies. This makes it possible to monitor the health status of elderly people in real time and in detail, and to quickly generate and notify alerts when an anomaly is detected. Furthermore, personalized health management can be performed more effectively through the proposal of customized care plans based on behavioral patterns and communication with the user using natural language processing.

[0266] A "sensor device" is a device worn on the body to collect biometric information such as heart rate, body temperature, and blood pressure in elderly individuals in real time.

[0267] A "camera device" is a device used to monitor the movements and facial expressions of elderly people and to acquire video data.

[0268] A "machine learning model" is a computational algorithm used to analyze collected biometric and video data and detect abnormalities that fall outside the normal range.

[0269] "Means for generating and notifying alerts" refers to a system that automatically creates warnings when an anomaly is detected and notifies registered caregivers and family members.

[0270] "Natural language processing" is a technology that enables computers to understand human language and interact with users in either speech or text format.

[0271] A "customized care plan" is a specific plan created based on the user's individual behavioral patterns and health condition, outlining the necessary steps for maintaining their health and providing care.

[0272] An "AI chatbot or voice assistant" is a program that interacts with users using voice or text to provide health information and set reminders.

[0273] This invention is a system for monitoring the health status of elderly people in real time and rapidly detecting abnormalities. Its components include a sensor device, a camera device, a machine learning model, a notification function, a natural language processing function, and a customized care plan function.

[0274] First, the sensor device acquires biometric information such as the user's heart rate and body temperature in real time. This device is designed to be worn on the user's body and transmit data to a server via Wi-Fi or Bluetooth. This makes it possible to continuously monitor the user's health status.

[0275] Next, the camera device records the user's movements and facial expressions. The video data is also transferred to a server and used to understand the user's physical activity and emotional state.

[0276] The data received by the server is analyzed using a machine learning model. This model incorporates algorithms that identify data patterns of normal health conditions and quickly detect anomalies. If an anomaly is detected, the server generates an alert and, on behalf of the user, notifies the devices of registered caregivers and family members.

[0277] Furthermore, the device communicates with the user via text or voice using natural language processing technology. This feature allows users to receive feedback on their health status. It's also possible to use an AI chatbot to give instructions such as, "Set a reminder for today's exercise."

[0278] In addition, the server creates individualized care plans based on past data. This recommends specific actions for maintaining the user's health and preventing dementia. This care plan is naturally integrated into the user's daily life, promoting efficient health management.

[0279] A concrete example of a prompt message is "Tell me how to analyze health data of elderly people and detect abnormalities," which can be input to the generating AI model.

[0280] This system provides users with consistent health monitoring and support to live an independent life with peace of mind.

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The sensor device acquires biological information such as the heart rate and body temperature of the elderly. The input is real-time biological data. This is transmitted to the server using communication means such as Wi-Fi or Bluetooth. Specifically, the biological data periodically measured by the device is converted into a digital signal and stored in a database connected to the server via wireless communication.

[0284] Step 2:

[0285] The camera device records the actions and expressions of the elderly and collects the video data. The input is physical video information. It is converted into digital data and transmitted to the server. As a specific operation, the camera captures the user's video, converts the video into a compressed format, and then transfers it to the server for storage in the visual database.

[0286] Step 3:

[0287] The server receives the collected biological information and video data and stores them in the database. The input is the digital data transmitted from the sensor device and the camera device. The server temporarily stores these in the database and prepares them for use in the next analysis step. As a specific operation, the server checks the data format and adjusts it to an analyzable state.

[0288] Step 4:

[0289] The server analyzes the biological information and video data using a machine learning model. The input is the collected data. As data processing, the machine learning model compares normal patterns and abnormal patterns to detect abnormalities. As output, the result of abnormality detection is obtained. As a specific example, when the model detects an abnormal increase in the heart rate, an abnormal flag is immediately set.

[0290] Step 5:

[0291] If an anomaly is detected, the server generates an alert and sends a notification to the caregiver's or family member's device. The input is the result of the anomaly detection. Based on this, an alert message is created and sent via push notification or email. Specifically, a notification stating, "Grandma's heart rate is abnormal," is sent to the device.

[0292] Step 6:

[0293] The device uses natural language processing (NLP) capabilities to communicate with the user via voice or text. Input includes voice instructions and questions from the user. The NLP engine analyzes the content and provides appropriate feedback and information. For example, if the user asks, "How am I feeling today?", the device might respond, "Your heart rate and body temperature are within the normal range."

[0294] Step 7:

[0295] The server performs continuous data analysis and generates individualized care plans. Input includes past biometric data and behavioral patterns. Based on the analysis results, it creates a care plan that proposes specific health maintenance and preventative measures. For example, if a user has low exercise levels, it might generate a plan recommending a 15-minute walk daily, which is then notified to the user via their device.

[0296] (Application Example 1)

[0297] 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 glasses 214 will be referred to as the "terminal."

[0298] In managing the health of the elderly, it is crucial to detect abnormalities in real time and respond quickly. However, conventional systems have shortcomings in data collection and analysis, resulting in challenges in the accuracy of abnormality detection and rapid notification. Furthermore, if the elderly are not tech-savvy, there are communication barriers with the system, making it difficult to alleviate feelings of isolation and manage their health appropriately.

[0299] 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.

[0300] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring video data from a camera device, means for analyzing this data using a machine learning model to detect anomalies, means for generating and notifying alerts when an anomaly is detected, means for responding to voice commands using an artificial intelligence conversational agent, and means for visual display on a mobile information terminal that visualizes real-time health data. This enables highly accurate monitoring of health status, rapid notification of anomalies, and the provision of a sense of security through an easy-to-use interface for the elderly.

[0301] A "sensor device" is a device that continuously acquires biometric information such as a user's heart rate and body temperature, and provides this data to other devices or systems.

[0302] A "camera device" is a device used to capture the user's movements and facial expressions, and is capable of collecting video data.

[0303] A "machine learning model" is a set of algorithms and methods used to analyze collected data and detect anomalies that deviate from normal patterns.

[0304] "Means for detecting anomalies" are technical methods or systems designed to identify data that deviates from normal conditions and to recognize problems.

[0305] The "means for generating and notifying alerts" is a mechanism for promptly communicating the discovery of an abnormality to the relevant individuals or organizations.

[0306] The "artificial intelligence conversation agent" is software or a system that uses natural language processing technology to interpret voice instructions from the user and provide appropriate responses.

[0307] The "portable information terminal" is an electronic device that an individual can carry around and use to display and process various information.

[0308] The system for implementing this invention aims to monitor the health status of the elderly in real-time and quickly detect abnormalities. This includes a sensor device, a camera device, a cloud server, and a portable information terminal.

[0309] The server receives biometric information such as heart rate and body temperature collected by the sensor device via Bluetooth or Wi-Fi. The camera device captures video data of movements and expressions, and these data are transmitted to the cloud. The server analyzes these raw data using a machine learning model based on Python and detects cases that deviate from the normal health pattern as abnormalities.

[0310] When an abnormality is detected, an alert is sent as a push notification to the user's portable information terminal, for example, via Firebase. The artificial intelligence conversation agent installed on the terminal uses natural language processing technology to interpret voice instructions from the user and perform functions such as setting reminders and providing feedback on the health status.

[0311] Furthermore, the system conducts an analysis based on the user's past behavior data and generates an individual care plan. This care plan provides guidance for the elderly to carry out daily health maintenance activities. For example, it recommends the daily exercise amount and a review of the diet, and visually displays these contents on the portable information terminal.

[0312] For example, when a user's heart rate significantly exceeds their normal level, they can receive an alert saying, "Your heart rate is higher than normal. Please check and take any necessary action." Another example of a prompt message for the generating AI model is, "Generate a sample push notification message to send when an abnormal heart rate is detected."

[0313] In this way, the system can consistently support the health management of the elderly and enable the early detection of abnormalities.

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] The sensor device continuously acquires the user's heart rate and body temperature and transmits it to the server via Bluetooth. This data collection provides biometric input. The server saves the received data to storage in real time. At this time, the data's timestamp and device ID are also recorded.

[0317] Step 2:

[0318] The camera device captures the user's movements and facial expressions as video data and transmits it to the server via Wi-Fi. This video data serves as input for analyzing the user's behavior. The server converts the video data into a predefined format and saves it. This conversion process allows for efficient subsequent analysis.

[0319] Step 3:

[0320] The server feeds the collected biometric and video data into a machine learning model built in Python. The machine learning model executes an anomaly detection algorithm and analyzes the input data. If an anomaly pattern is detected in the data, this information is output as alert data.

[0321] Step 4:

[0322] Based on alert data detecting an anomaly, the server generates a push notification. This notification includes information about the anomaly and how to address it. The generated notification is sent to the user's device using a cloud messaging service. The user's device displays the received notification on the screen and notifies the user with sound and vibration.

[0323] Step 5:

[0324] The server analyzes the user's past behavioral data and runs a program to generate an individualized care plan. This care plan generation utilizes machine learning predictive models and rule-based systems. The generated care plan is visually displayed on the user's device, providing specific guidance for improving their lifestyle.

[0325] Step 6:

[0326] The device uses an artificial intelligence conversational agent to interpret and respond to user voice commands in real time. It takes the user's voice as input, analyzes their intent using natural language processing, and generates an appropriate response. The generated response is output as voice or displayed as text, enabling interaction with the user.

[0327] 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.

[0328] This invention is a system for monitoring the health and emotional state of elderly individuals in real time, and comprises a combination of sensor devices, camera devices, an emotion engine, and other analysis and notification means.

[0329] First, sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time, depending on the environment. Meanwhile, camera devices capture video data of the elderly individuals' facial expressions and movements and transmit it to the server. This allows for the simultaneous collection of both physical and behavioral data.

[0330] Next, this system incorporates an emotion engine that analyzes biometric and video data collected by the server to estimate the user's emotional state. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into states such as "happiness," "sadness," and "anger." This makes it possible to monitor the mental health of elderly individuals.

[0331] When abnormal conditions or specific emotions are detected, the server generates an alert. For example, if a sudden change in heart rate or a prolonged state of "sadness" is detected, a notification is immediately sent to the device of the registered caregiver or family member. This notification enables rapid intervention and promotes preventative action.

[0332] Furthermore, when users interact with AI chatbots and voice assistants, the analysis results from the emotion engine enable more personalized conversations. For example, if the system determines that a user is stressed, it may offer relaxing topics or suggest deep breathing reminders.

[0333] Furthermore, the server learns the user's behavioral and emotional patterns over a long period of time and creates an individualized care plan. This provides customized health management tailored to the user's physical and mental needs. Finally, the device notifies the user of this information to help improve their daily life.

[0334] Thus, this invention aims to improve the quality of life for the elderly by monitoring both their health and emotions, and through anomaly detection and appropriate interaction.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The sensor device continuously measures the heart rate and body temperature of elderly individuals and transmits the data to a server.

[0338] Step 2:

[0339] A camera device captures the faces and movements of elderly individuals and transmits the resulting video data to a server. This data is used to capture the elderly individuals' daily activities and changes in their facial expressions.

[0340] Step 3:

[0341] The system receives biometric and video data collected by the server and converts it into a pre-configured format. Simultaneously, it organizes the data with timestamps in preparation for analysis.

[0342] Step 4:

[0343] The server uses machine learning models to perform data analysis. Based on biometric information, it detects abnormal heart rate and body temperature, and uses an emotion engine to analyze changes in the facial expressions of elderly people from video data to determine their emotional state.

[0344] Step 5:

[0345] If an anomaly or a specific emotional state (e.g., "sadness" or "anger") is detected, the server generates an alert and sends a notification to the relevant parties' terminals. This notification includes information about the anomaly and the emotional state.

[0346] Step 6:

[0347] When a user makes a request to an AI chatbot or voice assistant, the device converts the user's voice into text and interprets the request using natural language processing.

[0348] Step 7:

[0349] Based on information obtained from the emotion engine, the device adjusts the conversation content according to the user's emotions and provides personalized follow-up messages and reminders.

[0350] Step 8:

[0351] The server analyzes long-term data and learns the behavioral and emotional patterns of elderly individuals to create personalized care plans, which are then sent to the user's device. This provides specific suggestions to support the user's health promotion activities.

[0352] (Example 2)

[0353] 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".

[0354] In modern society, real-time monitoring of the physical and emotional health of the elderly is a crucial challenge. However, conventional technologies have struggled to comprehensively grasp these conditions and respond quickly. In particular, health management systems for the elderly that take into account changes in emotional state are still insufficient. This invention aims to provide a system that comprehensively monitors not only physical health but also emotional aspects, and that can respond quickly when abnormalities occur.

[0355] 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.

[0356] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring facial expression and motion data from a camera device, and means for data analysis, including an emotion engine that estimates the user's emotional state using this data. This makes it possible to comprehensively monitor the physical and emotional health status of elderly people, detect abnormalities, and respond quickly.

[0357] A "sensor device" is a device used to collect biometric information such as heart rate and body temperature of elderly people in real time.

[0358] A "camera device" is a device used to acquire video data of elderly people's facial expressions and movements.

[0359] An "emotion engine" is software or hardware that analyzes collected video data and biometric information to estimate the user's emotional state.

[0360] "Means of data analysis" refers to technical means of analyzing collected data and executing a process to detect abnormal conditions and emotional patterns.

[0361] An "alert" is a notification that is generated when an abnormal condition or a specific emotional state is detected.

[0362] An "external terminal" is a device owned by a registered caregiver or family member that can receive notifications such as alerts.

[0363] "Natural language processing" is a technology that enables communication with users through voice or text, and includes processing to understand and respond to users' emotions and requests.

[0364] An "individualized care plan" is a set of suggestions created based on the behavioral and emotional patterns of elderly individuals, aimed at optimizing the user's health and mental state.

[0365] This invention is a system for monitoring the health and emotional state of elderly individuals in real time. The system comprises a combination of a sensor device, a camera device, an emotion engine, and other data analysis and notification means.

[0366] Sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time and stored in a database. Camera devices capture the elderly individuals' facial expressions and movements as video data, which is also transmitted to the server.

[0367] The server uses an emotion engine to analyze collected biometric and video data. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into categories such as "happiness," "sadness," and "anger." The analyzed emotion data is used to monitor the user's mental health.

[0368] If an anomaly is detected, the server generates an alert and sends that information to the terminal. For example, if there is a sudden change in heart rate or a prolonged feeling of "sadness," caregivers and family members will be notified in real time. This allows for prompt action to be taken.

[0369] When users interact with AI chatbots or voice assistants, the conversation becomes more personalized based on analysis results from the emotion engine. This allows for the provision of topics and suggestions tailored to the user. For example, if the system determines that the user is experiencing high stress levels, it may offer relaxing topics or suggest taking deep breaths.

[0370] Furthermore, the server learns the user's long-term behavioral and emotional patterns and creates an individualized care plan. This care plan is designed to provide customized health management tailored to the user's physical and mental needs.

[0371] Specific example:

[0372] If a user continues to experience feelings of sadness, the system will send a notification to the caregiver's device stating, "Continuous sadness has been detected. Confirmation is required."

[0373] Examples of prompts for a generative AI model:

[0374] "Please analyze the emotional state of elderly individuals based on the following data: heart rate, facial expression data, and voice tone."

[0375] "Based on the results of the emotion analysis, please suggest appropriate relaxation methods to the user."

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals. The input is the elderly person's physical data, and the output is the biometric information acquired by the sensor device. This biometric information is transmitted to a server using wireless communication and recorded in a database.

[0379] Step 2:

[0380] The camera device monitors the facial expressions and movements of elderly individuals and acquires video data. The input is video from the elderly individuals, and the output is video data. The video data is transmitted to and stored on a server, similar to sensor devices.

[0381] Step 3:

[0382] The server receives heart rate and body temperature data and performs time-series analysis. The input is biometric data, and data analysis is performed to detect rapid fluctuations and abnormal patterns. The output is the result of the abnormality detection. Specifically, if the heart rate exceeds the normal range, an alert state is triggered.

[0383] Step 4:

[0384] The emotion engine analyzes video data and estimates emotions from facial expressions. The input is video data, and the output is the estimated emotional state. Classifications such as "happiness," "sadness," and "anger" are performed, and analysis results are generated. Specifically, the movements of facial muscles are matched with specific emotional patterns.

[0385] Step 5:

[0386] The server generates an alert upon receiving abnormal biometric data or specific emotional states. Inputs include the detection results of the anomaly and the emotional analysis results, while output is alert information. This alert information is sent to the device and notified to registered caregivers and family members. Specifically, push notifications are sent to the device, enabling a quick response.

[0387] Step 6:

[0388] When users interact with AI chatbots or voice assistants, the conversation is personalized based on the results of sentiment analysis. The input is the user's emotional state, and the output is personalized conversation content. Specifically, if the system determines that the user is stressed, it will suggest ways to relax.

[0389] Step 7:

[0390] The server learns the user's behavioral and emotional patterns based on long-term data and creates an individualized care plan. The input is historical data, and the output is a customized care plan. This provides optimized health management and support for daily life for each user.

[0391] (Application Example 2)

[0392] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0393] In an aging society, managing the health of the elderly is a crucial issue. In particular, it is necessary to consider not only the physical health but also the emotional well-being of the elderly. While conventional systems focus on monitoring physical health, they have struggled to track emotional states in real time and provide appropriate responses. Furthermore, while rapid responses are required in the event of abnormal conditions or changes in emotional state, automatically providing specific care suggestions has been difficult. This has hindered improvements in the quality of life for the elderly.

[0394] 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.

[0395] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video information from video acquisition devices, means for analyzing this data using machine learning models to detect abnormal states or emotional states, means for generating and notifying alerts when abnormal states or specific emotional states are detected, means for using natural language processing to engage in voice or text-based dialogue with humans, and means for presenting customized care plans based on the user's behavior and emotions. This enables real-time monitoring of the health and emotional state of elderly individuals and allows for the provision of rapid and personalized care plans.

[0396] A "sensor device" is a device used to collect biological information from the body in real time, and is particularly responsible for acquiring data such as heart rate and body temperature.

[0397] A "video acquisition device" is a device used to record a subject's facial expressions and movements, and has the function of transmitting video data to a server in real time.

[0398] A "machine learning model" is an algorithm that uses collected biometric information and video data to analyze and identify abnormal states and emotional states.

[0399] "Abnormal state alert generation" is a process that notifies users of information when sudden changes in heart rate or body temperature, or specific emotional states, are detected.

[0400] "Natural language processing" is a technology that uses human language to understand and analyze speech and text, thereby facilitating smooth communication.

[0401] A "customized care plan" is a means of proposing an optimized care plan based on the individual health and emotional state of the user.

[0402] The system of the present invention consists mainly of a sensor device, a video acquisition device, and a machine learning model for monitoring the health and emotional state of elderly people in real time. The sensor device acquires biometric information such as the heart rate and body temperature of elderly people in real time and transmits it to a server. The video acquisition device records the facial expressions and movements of elderly people and similarly transmits them to the server.

[0403] The server analyzes this data using machine learning models to identify abnormal conditions and emotional states. Based on the results of this analysis, the server makes recommendations. For example, if the heart rate increases sharply or if the detected emotions differ from normal, it generates an alarm and immediately sends it to the caregiver.

[0404] The server also uses natural language processing to engage in voice or text-based conversations with the user and present personalized care plans tailored to the elderly person's condition. These care plans are designed to support the elderly person's daily life and maintain their mental and physical health.

[0405] Specifically, the server analyzes heart rate and facial expression data, and if it determines that the user is stressed, it offers relaxation suggestions in a conversational format. For example, it can send a reminder to take deep breaths. For this purpose, it sometimes uses prompts constructed by a generative AI model.

[0406] An example of a prompt message is: "Based on the current heart rate and facial expression data of the elderly, identify possible emotional states and recommend an appropriate action plan."

[0407] As a result, this invention can improve the quality of life for the elderly and help maintain a safe and secure life.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals in real time. This data is transmitted to a server using wireless communication. The input is heart rate and body temperature data, and the output is raw biometric data that is transferred to the server.

[0411] Step 2:

[0412] The video acquisition device records the facial expressions and movements of elderly individuals as video data and transmits it to a server. The input is video data, and the output is unprocessed video data sent to the server.

[0413] Step 3:

[0414] The server inputs the received biometric information and video data into a machine learning model for data analysis. Specifically, the AI ​​model analyzes fluctuations in heart rate and body temperature, as well as changes in facial expression. The input consists of biometric information and video data, and the output is the analysis results regarding health status and emotional state.

[0415] Step 4:

[0416] The server detects abnormal states and emotional states based on the analysis results. If an abnormality is detected, it generates an alert. The input is the analysis results, and the output is the alert information.

[0417] Step 5:

[0418] The server sends the generated alert information to the caregiver's or family member's device and provides instructions if an emergency response is needed. The input is the alert information, and the output is a notification message.

[0419] Step 6:

[0420] The server uses natural language processing to present the user with customized care plans in voice or text. Based on the analyzed emotional state, it suggests relaxation methods and appropriate activities. Input consists of the analysis results and prompts generated by the AI ​​model, while output is the text or voice data presented as the care plan.

[0421] Step 7:

[0422] The user selects actions to improve their daily life based on the presented care plan. The input is the presented care plan, and the output is the actions selected by the user.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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".

[0439] This invention relates to a system for monitoring the health status of elderly individuals in real time and rapidly detecting abnormalities. This system consists of multiple components for acquiring, analyzing, and managing biometric information and video data.

[0440] First, sensor devices continuously acquire biometric information such as the elderly person's heart rate and body temperature. These devices are often worn directly on the body and are designed to transmit data to a central server via Wi-Fi or Bluetooth. Camera devices are also used to monitor the elderly person's movements and facial expressions, and the video data is similarly transmitted to the server.

[0441] Next, the server receives this raw data and analyzes it using a machine learning model. The model identifies patterns in normal health data and detects any deviations as anomalies. If an anomaly is detected, the server automatically generates an alert and sends a notification to the registered caregiver or family member's device. This notification is sent via push notification or email.

[0442] Furthermore, users can interact with AI chatbots and voice assistants on a daily basis. The device uses natural language processing technology to understand voice commands from the user and provide reminders and health status feedback. This feature aims to provide an environment where elderly people can use the system without feeling isolated.

[0443] Furthermore, the server analyzes continuous behavioral patterns and generates individualized care plans. These care plans are customized based on the user's past behavioral data and provide guidance that helps maintain the user's health and prevent dementia. The terminal clearly notifies the user of this information, promoting daily health maintenance activities.

[0444] This combination enables the present invention to realize a system that can consistently monitor the health of elderly people and take necessary actions quickly and efficiently.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The sensor device acquires biometric information such as the heart rate and body temperature of elderly individuals and transmits the data to a server. The server then records the timestamp of the received data and the device ID.

[0448] Step 2:

[0449] The camera device captures video data of the elderly person's movements and facial expressions and streams it to a server. The server saves this data frame by frame and prepares it for analysis.

[0450] Step 3:

[0451] The server converts biometric information and video data into JSON format and organizes them as a time series. This prepares the data for the analysis process.

[0452] Step 4:

[0453] The server applies a machine learning model to analyze the data in real time. Here, a range of normal values ​​is defined, and a means is used to detect outliers that fall outside of this range.

[0454] Step 5:

[0455] If an anomaly is detected, the server immediately generates an alert and sends a notification to the devices of caregivers and family members that have been registered in advance.

[0456] Step 6:

[0457] When a user begins interacting with an AI chatbot or voice assistant, the device converts the speech into text and uses natural language processing to understand the user's request.

[0458] Step 7:

[0459] The device provides users with reminder functions and health information feedback, and responds to questions in voice or text.

[0460] Step 8:

[0461] The server analyzes the data it collects over a long period to evaluate behavioral patterns. Based on this, it generates a care plan optimized for the user and sends it to the device. The device then notifies the user of this information, promoting health maintenance.

[0462] (Example 1)

[0463] 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."

[0464] In managing the health of the elderly, real-time, detailed monitoring and prompt responses are required. However, current systems have challenges in data accuracy, the speed of anomaly detection, and smooth communication with users. Furthermore, they lack sufficient functionality to flexibly propose care tailored to individual health conditions, making it difficult to maintain a safe and secure life. Therefore, a new system is needed that consistently monitors the health status of the elderly and provides individualized and effective care.

[0465] 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.

[0466] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video data from camera devices, and means for analyzing this data using a machine learning model and detecting anomalies. This makes it possible to monitor the health status of elderly people in real time and in detail, and to quickly generate and notify alerts when an anomaly is detected. Furthermore, personalized health management can be performed more effectively through the proposal of customized care plans based on behavioral patterns and communication with the user using natural language processing.

[0467] A "sensor device" is a device worn on the body to collect biometric information such as heart rate, body temperature, and blood pressure in elderly individuals in real time.

[0468] A "camera device" is a device used to monitor the movements and facial expressions of elderly people and to acquire video data.

[0469] A "machine learning model" is a computational algorithm used to analyze collected biometric and video data and detect abnormalities that fall outside the normal range.

[0470] "Means for generating and notifying alerts" refers to a system that automatically creates warnings when an anomaly is detected and notifies registered caregivers and family members.

[0471] "Natural language processing" is a technology that enables computers to understand human language and interact with users in either speech or text format.

[0472] A "customized care plan" is a specific plan created based on the user's individual behavioral patterns and health condition, outlining the necessary steps for maintaining their health and providing care.

[0473] An "AI chatbot or voice assistant" is a program that interacts with users using voice or text to provide health information and set reminders.

[0474] This invention is a system for monitoring the health status of elderly people in real time and rapidly detecting abnormalities. Its components include a sensor device, a camera device, a machine learning model, a notification function, a natural language processing function, and a customized care plan function.

[0475] First, the sensor device acquires biometric information such as the user's heart rate and body temperature in real time. This device is designed to be worn on the user's body and transmit data to a server via Wi-Fi or Bluetooth. This makes it possible to continuously monitor the user's health status.

[0476] Next, the camera device records the user's movements and facial expressions. The video data is also transferred to a server and used to understand the user's physical activity and emotional state.

[0477] The data received by the server is analyzed using a machine learning model. This model incorporates algorithms that identify data patterns of normal health conditions and quickly detect anomalies. If an anomaly is detected, the server generates an alert and, on behalf of the user, notifies the devices of registered caregivers and family members.

[0478] Furthermore, the device communicates with the user via text or voice using natural language processing technology. This feature allows users to receive feedback on their health status. It's also possible to use an AI chatbot to give instructions such as, "Set a reminder for today's exercise."

[0479] In addition, the server creates individualized care plans based on past data. This recommends specific actions for maintaining the user's health and preventing dementia. This care plan is naturally integrated into the user's daily life, promoting efficient health management.

[0480] A concrete example of a prompt message is "Tell me how to analyze health data of elderly people and detect abnormalities," which can be input to the generating AI model.

[0481] This system provides users with consistent health monitoring and support to live an independent life with peace of mind.

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The sensor device acquires biometric information such as the heart rate and body temperature of elderly individuals. The input is real-time biometric data. This data is transmitted to a server using communication methods such as Wi-Fi or Bluetooth. Specifically, the device periodically converts the biometric data into digital signals and stores them in a database connected to the server via wireless communication.

[0485] Step 2:

[0486] The camera device records the movements and facial expressions of elderly individuals and collects the resulting video data. The input is physical video information. This data is then converted into digital data and sent to a server. Specifically, the camera captures the user's image, converts the image into a compressed format, and then transfers it to the server for storage in a visual database.

[0487] Step 3:

[0488] The server receives collected biometric and video data and stores it in a database. The input consists of digital data transmitted from sensor and camera devices. The server temporarily stores this data in the database, preparing it for use in the next analysis step. Specifically, the server verifies the data format and adjusts it to a state suitable for analysis.

[0489] Step 4:

[0490] The server uses a machine learning model to analyze biometric and video data. The input is the collected data. As part of the data processing, the machine learning model compares normal and abnormal patterns to detect anomalies. The output is the result of the anomaly detection. For example, if the model detects an abnormal increase in heart rate, an anomaly flag is immediately set.

[0491] Step 5:

[0492] If an anomaly is detected, the server generates an alert and sends a notification to the caregiver's or family member's device. The input is the result of the anomaly detection. Based on this, an alert message is created and sent via push notification or email. Specifically, a notification stating, "Grandma's heart rate is abnormal," is sent to the device.

[0493] Step 6:

[0494] The device uses natural language processing (NLP) capabilities to communicate with the user via voice or text. Input includes voice instructions and questions from the user. The NLP engine analyzes the content and provides appropriate feedback and information. For example, if the user asks, "How am I feeling today?", the device might respond, "Your heart rate and body temperature are within the normal range."

[0495] Step 7:

[0496] The server performs continuous data analysis and generates individualized care plans. Input includes past biometric data and behavioral patterns. Based on the analysis results, it creates a care plan that proposes specific health maintenance and preventative measures. For example, if a user has low exercise levels, it might generate a plan recommending a 15-minute walk daily, which is then notified to the user via their device.

[0497] (Application Example 1)

[0498] 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."

[0499] In managing the health of the elderly, it is crucial to detect abnormalities in real time and respond quickly. However, conventional systems have shortcomings in data collection and analysis, resulting in challenges in the accuracy of abnormality detection and rapid notification. Furthermore, if the elderly are not tech-savvy, there are communication barriers with the system, making it difficult to alleviate feelings of isolation and manage their health appropriately.

[0500] 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.

[0501] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring video data from a camera device, means for analyzing this data using a machine learning model to detect anomalies, means for generating and notifying alerts when an anomaly is detected, means for responding to voice commands using an artificial intelligence conversational agent, and means for visual display on a mobile information terminal that visualizes real-time health data. This enables highly accurate monitoring of health status, rapid notification of anomalies, and the provision of a sense of security through an easy-to-use interface for the elderly.

[0502] A "sensor device" is a device that continuously acquires biometric information such as a user's heart rate and body temperature, and provides this data to other devices or systems.

[0503] A "camera device" is a device used to capture the user's movements and facial expressions, and is capable of collecting video data.

[0504] A "machine learning model" is a set of algorithms and methods used to analyze collected data and detect anomalies that deviate from normal patterns.

[0505] "Means for detecting anomalies" are technical methods or systems designed to identify data that deviates from normal conditions and to recognize problems.

[0506] A "means for generating and notifying alerts" is a mechanism for promptly informing relevant individuals or organizations when an anomaly is detected.

[0507] An "artificial intelligence conversational agent" is software or a system that uses natural language processing technology to interpret voice commands from a user and provide appropriate responses.

[0508] A "portable information terminal" is an electronic device that an individual can carry with them and use to display and process various types of information.

[0509] The system for implementing this invention aims to monitor the health status of elderly people in real time and to quickly detect abnormalities. This includes sensor devices, camera devices, a cloud server, and a personal digital assistant (PDCA) terminal.

[0510] The server receives biometric information such as heart rate and body temperature collected by sensor devices via Bluetooth or Wi-Fi. It also captures video data of movement and facial expressions from camera devices, and this data is sent to the cloud. The server analyzes this raw data using a machine learning model based on Python, detecting deviations from normal health patterns as anomalies.

[0511] When an anomaly is detected, an alert is sent to the user's mobile device via push notification, for example, through Firebase. The artificial intelligence conversational agent installed on the device uses natural language processing technology to interpret voice commands from the user and set reminders or provide feedback on their health status.

[0512] Furthermore, the system analyzes the user's past behavioral data to generate an individualized care plan. This care plan provides guidance for elderly individuals to maintain their daily health. For example, it recommends changes to daily exercise levels and diet, and displays this information visually on a mobile device.

[0513] For example, when a user's heart rate significantly exceeds their normal level, they can receive an alert saying, "Your heart rate is higher than normal. Please check and take any necessary action." Another example of a prompt message for the generating AI model is, "Generate a sample push notification message to send when an abnormal heart rate is detected."

[0514] In this way, the system can consistently support the health management of the elderly and enable the early detection of abnormalities.

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The sensor device continuously acquires the user's heart rate and body temperature and transmits it to the server via Bluetooth. This data collection provides biometric input. The server saves the received data to storage in real time. At this time, the data's timestamp and device ID are also recorded.

[0518] Step 2:

[0519] The camera device captures the user's movements and facial expressions as video data and transmits it to the server via Wi-Fi. This video data serves as input for analyzing the user's behavior. The server converts the video data into a predefined format and saves it. This conversion process allows for efficient subsequent analysis.

[0520] Step 3:

[0521] The server feeds the collected biometric and video data into a machine learning model built in Python. The machine learning model executes an anomaly detection algorithm and analyzes the input data. If an anomaly pattern is detected in the data, this information is output as alert data.

[0522] Step 4:

[0523] Based on alert data detecting an anomaly, the server generates a push notification. This notification includes information about the anomaly and how to address it. The generated notification is sent to the user's device using a cloud messaging service. The user's device displays the received notification on the screen and notifies the user with sound and vibration.

[0524] Step 5:

[0525] The server analyzes the user's past behavioral data and runs a program to generate an individualized care plan. This care plan generation utilizes machine learning predictive models and rule-based systems. The generated care plan is visually displayed on the user's device, providing specific guidance for improving their lifestyle.

[0526] Step 6:

[0527] The device uses an artificial intelligence conversational agent to interpret and respond to user voice commands in real time. It takes the user's voice as input, analyzes their intent using natural language processing, and generates an appropriate response. The generated response is output as voice or displayed as text, enabling interaction with the user.

[0528] 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.

[0529] This invention is a system for monitoring the health and emotional state of elderly individuals in real time, and comprises a combination of sensor devices, camera devices, an emotion engine, and other analysis and notification means.

[0530] First, sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time, depending on the environment. Meanwhile, camera devices capture video data of the elderly individuals' facial expressions and movements and transmit it to the server. This allows for the simultaneous collection of both physical and behavioral data.

[0531] Next, this system incorporates an emotion engine that analyzes biometric and video data collected by the server to estimate the user's emotional state. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into states such as "happiness," "sadness," and "anger." This makes it possible to monitor the mental health of elderly individuals.

[0532] When abnormal conditions or specific emotions are detected, the server generates an alert. For example, if a sudden change in heart rate or a prolonged state of "sadness" is detected, a notification is immediately sent to the device of the registered caregiver or family member. This notification enables rapid intervention and promotes preventative action.

[0533] Furthermore, when users interact with AI chatbots and voice assistants, the analysis results from the emotion engine enable more personalized conversations. For example, if the system determines that a user is stressed, it may offer relaxing topics or suggest deep breathing reminders.

[0534] Furthermore, the server learns the user's behavioral and emotional patterns over a long period of time and creates an individualized care plan. This provides customized health management tailored to the user's physical and mental needs. Finally, the device notifies the user of this information to help improve their daily life.

[0535] Thus, this invention aims to improve the quality of life for the elderly by monitoring both their health and emotions, and through anomaly detection and appropriate interaction.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The sensor device continuously measures the heart rate and body temperature of elderly individuals and transmits the data to a server.

[0539] Step 2:

[0540] A camera device captures the faces and movements of elderly individuals and transmits the resulting video data to a server. This data is used to capture the elderly individuals' daily activities and changes in their facial expressions.

[0541] Step 3:

[0542] The system receives biometric and video data collected by the server and converts it into a pre-configured format. Simultaneously, it organizes the data with timestamps in preparation for analysis.

[0543] Step 4:

[0544] The server uses machine learning models to perform data analysis. Based on biometric information, it detects abnormal heart rate and body temperature, and uses an emotion engine to analyze changes in the facial expressions of elderly people from video data to determine their emotional state.

[0545] Step 5:

[0546] If an anomaly or a specific emotional state (e.g., "sadness" or "anger") is detected, the server generates an alert and sends a notification to the relevant parties' terminals. This notification includes information about the anomaly and the emotional state.

[0547] Step 6:

[0548] When a user makes a request to an AI chatbot or voice assistant, the device converts the user's voice into text and interprets the request using natural language processing.

[0549] Step 7:

[0550] Based on information obtained from the emotion engine, the device adjusts the conversation content according to the user's emotions and provides personalized follow-up messages and reminders.

[0551] Step 8:

[0552] The server analyzes long-term data and learns the behavioral and emotional patterns of elderly individuals to create personalized care plans, which are then sent to the user's device. This provides specific suggestions to support the user's health promotion activities.

[0553] (Example 2)

[0554] 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."

[0555] In modern society, real-time monitoring of the physical and emotional health of the elderly is a crucial challenge. However, conventional technologies have struggled to comprehensively grasp these conditions and respond quickly. In particular, health management systems for the elderly that take into account changes in emotional state are still insufficient. This invention aims to provide a system that comprehensively monitors not only physical health but also emotional aspects, and that can respond quickly when abnormalities occur.

[0556] 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.

[0557] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring facial expression and motion data from a camera device, and means for data analysis, including an emotion engine that estimates the user's emotional state using this data. This makes it possible to comprehensively monitor the physical and emotional health status of elderly people, detect abnormalities, and respond quickly.

[0558] A "sensor device" is a device used to collect biometric information such as heart rate and body temperature of elderly people in real time.

[0559] A "camera device" is a device used to acquire video data of elderly people's facial expressions and movements.

[0560] An "emotion engine" is software or hardware that analyzes collected video data and biometric information to estimate the user's emotional state.

[0561] "Means of data analysis" refers to technical means of analyzing collected data and executing a process to detect abnormal conditions and emotional patterns.

[0562] An "alert" is a notification that is generated when an abnormal condition or a specific emotional state is detected.

[0563] An "external terminal" is a device owned by a registered caregiver or family member that can receive notifications such as alerts.

[0564] "Natural language processing" is a technology that enables communication with users through voice or text, and includes processing to understand and respond to users' emotions and requests.

[0565] An "individualized care plan" is a set of suggestions created based on the behavioral and emotional patterns of elderly individuals, aimed at optimizing the user's health and mental state.

[0566] This invention is a system for monitoring the health and emotional state of elderly individuals in real time. The system comprises a combination of a sensor device, a camera device, an emotion engine, and other data analysis and notification means.

[0567] Sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time and stored in a database. Camera devices capture the elderly individuals' facial expressions and movements as video data, which is also transmitted to the server.

[0568] The server uses an emotion engine to analyze collected biometric and video data. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into categories such as "happiness," "sadness," and "anger." The analyzed emotion data is used to monitor the user's mental health.

[0569] If an anomaly is detected, the server generates an alert and sends that information to the terminal. For example, if there is a sudden change in heart rate or a prolonged feeling of "sadness," caregivers and family members will be notified in real time. This allows for prompt action to be taken.

[0570] When users interact with AI chatbots or voice assistants, the conversation becomes more personalized based on analysis results from the emotion engine. This allows for the provision of topics and suggestions tailored to the user. For example, if the system determines that the user is experiencing high stress levels, it may offer relaxing topics or suggest taking deep breaths.

[0571] Furthermore, the server learns the user's long-term behavioral and emotional patterns and creates an individualized care plan. This care plan is designed to provide customized health management tailored to the user's physical and mental needs.

[0572] Specific example:

[0573] If a user continues to experience feelings of sadness, the system will send a notification to the caregiver's device stating, "Continuous sadness has been detected. Confirmation is required."

[0574] Examples of prompts for a generative AI model:

[0575] "Please analyze the emotional state of elderly individuals based on the following data: heart rate, facial expression data, and voice tone."

[0576] "Based on the results of the emotion analysis, please suggest appropriate relaxation methods to the user."

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals. The input is the elderly person's physical data, and the output is the biometric information acquired by the sensor device. This biometric information is transmitted to a server using wireless communication and recorded in a database.

[0580] Step 2:

[0581] The camera device monitors the facial expressions and movements of elderly individuals and acquires video data. The input is video from the elderly individuals, and the output is video data. The video data is transmitted to and stored on a server, similar to sensor devices.

[0582] Step 3:

[0583] The server receives heart rate and body temperature data and performs time-series analysis. The input is biometric data, and data analysis is performed to detect rapid fluctuations and abnormal patterns. The output is the result of the abnormality detection. Specifically, if the heart rate exceeds the normal range, an alert state is triggered.

[0584] Step 4:

[0585] The emotion engine analyzes video data and estimates emotions from facial expressions. The input is video data, and the output is the estimated emotional state. Classifications such as "happiness," "sadness," and "anger" are performed, and analysis results are generated. Specifically, the movements of facial muscles are matched with specific emotional patterns.

[0586] Step 5:

[0587] The server generates an alert upon receiving abnormal biometric data or specific emotional states. Inputs include the detection results of the anomaly and the emotional analysis results, while output is alert information. This alert information is sent to the device and notified to registered caregivers and family members. Specifically, push notifications are sent to the device, enabling a quick response.

[0588] Step 6:

[0589] When users interact with AI chatbots or voice assistants, the conversation is personalized based on the results of sentiment analysis. The input is the user's emotional state, and the output is personalized conversation content. Specifically, if the system determines that the user is stressed, it will suggest ways to relax.

[0590] Step 7:

[0591] The server learns the user's behavioral and emotional patterns based on long-term data and creates an individualized care plan. The input is historical data, and the output is a customized care plan. This provides optimized health management and support for daily life for each user.

[0592] (Application Example 2)

[0593] 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."

[0594] In an aging society, managing the health of the elderly is a crucial issue. In particular, it is necessary to consider not only the physical health but also the emotional well-being of the elderly. While conventional systems focus on monitoring physical health, they have struggled to track emotional states in real time and provide appropriate responses. Furthermore, while rapid responses are required in the event of abnormal conditions or changes in emotional state, automatically providing specific care suggestions has been difficult. This has hindered improvements in the quality of life for the elderly.

[0595] 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.

[0596] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video information from video acquisition devices, means for analyzing this data using machine learning models to detect abnormal states or emotional states, means for generating and notifying alerts when abnormal states or specific emotional states are detected, means for using natural language processing to engage in voice or text-based dialogue with humans, and means for presenting customized care plans based on the user's behavior and emotions. This enables real-time monitoring of the health and emotional state of elderly individuals and allows for the provision of rapid and personalized care plans.

[0597] A "sensor device" is a device used to collect biological information from the body in real time, and is particularly responsible for acquiring data such as heart rate and body temperature.

[0598] A "video acquisition device" is a device used to record a subject's facial expressions and movements, and has the function of transmitting video data to a server in real time.

[0599] A "machine learning model" is an algorithm that uses collected biometric information and video data to analyze and identify abnormal states and emotional states.

[0600] "Abnormal state alert generation" is a process that notifies users of information when sudden changes in heart rate or body temperature, or specific emotional states, are detected.

[0601] "Natural language processing" is a technology that uses human language to understand and analyze speech and text, thereby facilitating smooth communication.

[0602] A "customized care plan" is a means of proposing an optimized care plan based on the individual health and emotional state of the user.

[0603] The system of the present invention consists mainly of a sensor device, a video acquisition device, and a machine learning model for monitoring the health and emotional state of elderly people in real time. The sensor device acquires biometric information such as the heart rate and body temperature of elderly people in real time and transmits it to a server. The video acquisition device records the facial expressions and movements of elderly people and similarly transmits them to the server.

[0604] The server analyzes this data using machine learning models to identify abnormal conditions and emotional states. Based on the results of this analysis, the server makes recommendations. For example, if the heart rate increases sharply or if the detected emotions differ from normal, it generates an alarm and immediately sends it to the caregiver.

[0605] The server also uses natural language processing to engage in voice or text-based conversations with the user and present personalized care plans tailored to the elderly person's condition. These care plans are designed to support the elderly person's daily life and maintain their mental and physical health.

[0606] Specifically, the server analyzes heart rate and facial expression data, and if it determines that the user is stressed, it offers relaxation suggestions in a conversational format. For example, it can send a reminder to take deep breaths. For this purpose, it sometimes uses prompts constructed by a generative AI model.

[0607] An example of a prompt message is: "Based on the current heart rate and facial expression data of the elderly, identify possible emotional states and recommend an appropriate action plan."

[0608] As a result, this invention can improve the quality of life for the elderly and help maintain a safe and secure life.

[0609] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0610] Step 1:

[0611] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals in real time. This data is transmitted to a server using wireless communication. The input is heart rate and body temperature data, and the output is raw biometric data that is transferred to the server.

[0612] Step 2:

[0613] The video acquisition device records the facial expressions and movements of elderly individuals as video data and transmits it to a server. The input is video data, and the output is unprocessed video data sent to the server.

[0614] Step 3:

[0615] The server inputs the received biometric information and video data into a machine learning model for data analysis. Specifically, the AI ​​model analyzes fluctuations in heart rate and body temperature, as well as changes in facial expression. The input consists of biometric information and video data, and the output is the analysis results regarding health status and emotional state.

[0616] Step 4:

[0617] The server detects abnormal states and emotional states based on the analysis results. If an abnormality is detected, it generates an alert. The input is the analysis results, and the output is the alert information.

[0618] Step 5:

[0619] The server sends the generated alert information to the caregiver's or family member's device and provides instructions if an emergency response is needed. The input is the alert information, and the output is a notification message.

[0620] Step 6:

[0621] The server uses natural language processing to present the user with customized care plans in voice or text. Based on the analyzed emotional state, it suggests relaxation methods and appropriate activities. Input consists of the analysis results and prompts generated by the AI ​​model, while output is the text or voice data presented as the care plan.

[0622] Step 7:

[0623] The user selects actions to improve their daily life based on the presented care plan. The input is the presented care plan, and the output is the actions selected by the user.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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".

[0641] This invention relates to a system for monitoring the health status of elderly individuals in real time and rapidly detecting abnormalities. This system consists of multiple components for acquiring, analyzing, and managing biometric information and video data.

[0642] First, sensor devices continuously acquire biometric information such as the elderly person's heart rate and body temperature. These devices are often worn directly on the body and are designed to transmit data to a central server via Wi-Fi or Bluetooth. Camera devices are also used to monitor the elderly person's movements and facial expressions, and the video data is similarly transmitted to the server.

[0643] Next, the server receives this raw data and analyzes it using a machine learning model. The model identifies patterns in normal health data and detects any deviations as anomalies. If an anomaly is detected, the server automatically generates an alert and sends a notification to the registered caregiver or family member's device. This notification is sent via push notification or email.

[0644] Furthermore, users can interact with AI chatbots and voice assistants on a daily basis. The device uses natural language processing technology to understand voice commands from the user and provide reminders and health status feedback. This feature aims to provide an environment where elderly people can use the system without feeling isolated.

[0645] Furthermore, the server analyzes continuous behavioral patterns and generates individualized care plans. These care plans are customized based on the user's past behavioral data and provide guidance that helps maintain the user's health and prevent dementia. The terminal clearly notifies the user of this information, promoting daily health maintenance activities.

[0646] This combination enables the present invention to realize a system that can consistently monitor the health of elderly people and take necessary actions quickly and efficiently.

[0647] The following describes the processing flow.

[0648] Step 1:

[0649] The sensor device acquires biometric information such as the heart rate and body temperature of elderly individuals and transmits the data to a server. The server then records the timestamp of the received data and the device ID.

[0650] Step 2:

[0651] The camera device captures video data of the elderly person's movements and facial expressions and streams it to a server. The server saves this data frame by frame and prepares it for analysis.

[0652] Step 3:

[0653] The server converts biometric information and video data into JSON format and organizes them as a time series. This prepares the data for the analysis process.

[0654] Step 4:

[0655] The server applies a machine learning model to analyze the data in real time. Here, a range of normal values ​​is defined, and a means is used to detect outliers that fall outside of this range.

[0656] Step 5:

[0657] If an anomaly is detected, the server immediately generates an alert and sends a notification to the devices of caregivers and family members that have been registered in advance.

[0658] Step 6:

[0659] When a user begins interacting with an AI chatbot or voice assistant, the device converts the speech into text and uses natural language processing to understand the user's request.

[0660] Step 7:

[0661] The device provides users with reminder functions and health information feedback, and responds to questions in voice or text.

[0662] Step 8:

[0663] The server analyzes the data it collects over a long period to evaluate behavioral patterns. Based on this, it generates a care plan optimized for the user and sends it to the device. The device then notifies the user of this information, promoting health maintenance.

[0664] (Example 1)

[0665] 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".

[0666] In managing the health of the elderly, real-time, detailed monitoring and prompt responses are required. However, current systems have challenges in data accuracy, the speed of anomaly detection, and smooth communication with users. Furthermore, they lack sufficient functionality to flexibly propose care tailored to individual health conditions, making it difficult to maintain a safe and secure life. Therefore, a new system is needed that consistently monitors the health status of the elderly and provides individualized and effective care.

[0667] 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.

[0668] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video data from camera devices, and means for analyzing this data using a machine learning model and detecting anomalies. This makes it possible to monitor the health status of elderly people in real time and in detail, and to quickly generate and notify alerts when an anomaly is detected. Furthermore, personalized health management can be performed more effectively through the proposal of customized care plans based on behavioral patterns and communication with the user using natural language processing.

[0669] A "sensor device" is a device worn on the body to collect biometric information such as heart rate, body temperature, and blood pressure in elderly individuals in real time.

[0670] A "camera device" is a device used to monitor the movements and facial expressions of elderly people and to acquire video data.

[0671] A "machine learning model" is a computational algorithm used to analyze collected biometric and video data and detect abnormalities that fall outside the normal range.

[0672] "Means for generating and notifying alerts" refers to a system that automatically creates warnings when an anomaly is detected and notifies registered caregivers and family members.

[0673] "Natural language processing" is a technology that enables computers to understand human language and interact with users in either speech or text format.

[0674] A "customized care plan" is a specific plan created based on the user's individual behavioral patterns and health condition, outlining the necessary steps for maintaining their health and providing care.

[0675] An "AI chatbot or voice assistant" is a program that interacts with users using voice or text to provide health information and set reminders.

[0676] This invention is a system for monitoring the health status of elderly people in real time and rapidly detecting abnormalities. Its components include a sensor device, a camera device, a machine learning model, a notification function, a natural language processing function, and a customized care plan function.

[0677] First, the sensor device acquires biometric information such as the user's heart rate and body temperature in real time. This device is designed to be worn on the user's body and transmit data to a server via Wi-Fi or Bluetooth. This makes it possible to continuously monitor the user's health status.

[0678] Next, the camera device records the user's movements and facial expressions. The video data is also transferred to a server and used to understand the user's physical activity and emotional state.

[0679] The data received by the server is analyzed using a machine learning model. This model incorporates algorithms that identify data patterns of normal health conditions and quickly detect anomalies. If an anomaly is detected, the server generates an alert and, on behalf of the user, notifies the devices of registered caregivers and family members.

[0680] Furthermore, the device communicates with the user via text or voice using natural language processing technology. This feature allows users to receive feedback on their health status. It's also possible to use an AI chatbot to give instructions such as, "Set a reminder for today's exercise."

[0681] In addition, the server creates individualized care plans based on past data. This recommends specific actions for maintaining the user's health and preventing dementia. This care plan is naturally integrated into the user's daily life, promoting efficient health management.

[0682] A concrete example of a prompt message is "Tell me how to analyze health data of elderly people and detect abnormalities," which can be input to the generating AI model.

[0683] This system provides users with consistent health monitoring and support to live an independent life with peace of mind.

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The sensor device acquires biometric information such as the heart rate and body temperature of elderly individuals. The input is real-time biometric data. This data is transmitted to a server using communication methods such as Wi-Fi or Bluetooth. Specifically, the device periodically converts the biometric data into digital signals and stores them in a database connected to the server via wireless communication.

[0687] Step 2:

[0688] The camera device records the movements and facial expressions of elderly individuals and collects the resulting video data. The input is physical video information. This data is then converted into digital data and sent to a server. Specifically, the camera captures the user's image, converts the image into a compressed format, and then transfers it to the server for storage in a visual database.

[0689] Step 3:

[0690] The server receives collected biometric and video data and stores it in a database. The input consists of digital data transmitted from sensor and camera devices. The server temporarily stores this data in the database, preparing it for use in the next analysis step. Specifically, the server verifies the data format and adjusts it to a state suitable for analysis.

[0691] Step 4:

[0692] The server uses a machine learning model to analyze biometric and video data. The input is the collected data. As part of the data processing, the machine learning model compares normal and abnormal patterns to detect anomalies. The output is the result of the anomaly detection. For example, if the model detects an abnormal increase in heart rate, an anomaly flag is immediately set.

[0693] Step 5:

[0694] If an anomaly is detected, the server generates an alert and sends a notification to the caregiver's or family member's device. The input is the result of the anomaly detection. Based on this, an alert message is created and sent via push notification or email. Specifically, a notification stating, "Grandma's heart rate is abnormal," is sent to the device.

[0695] Step 6:

[0696] The device uses natural language processing (NLP) capabilities to communicate with the user via voice or text. Input includes voice instructions and questions from the user. The NLP engine analyzes the content and provides appropriate feedback and information. For example, if the user asks, "How am I feeling today?", the device might respond, "Your heart rate and body temperature are within the normal range."

[0697] Step 7:

[0698] The server performs continuous data analysis and generates individualized care plans. Input includes past biometric data and behavioral patterns. Based on the analysis results, it creates a care plan that proposes specific health maintenance and preventative measures. For example, if a user has low exercise levels, it might generate a plan recommending a 15-minute walk daily, which is then notified to the user via their device.

[0699] (Application Example 1)

[0700] 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".

[0701] In managing the health of the elderly, it is crucial to detect abnormalities in real time and respond quickly. However, conventional systems have shortcomings in data collection and analysis, resulting in challenges in the accuracy of abnormality detection and rapid notification. Furthermore, if the elderly are not tech-savvy, there are communication barriers with the system, making it difficult to alleviate feelings of isolation and manage their health appropriately.

[0702] 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.

[0703] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring video data from a camera device, means for analyzing this data using a machine learning model to detect anomalies, means for generating and notifying alerts when an anomaly is detected, means for responding to voice commands using an artificial intelligence conversational agent, and means for visual display on a mobile information terminal that visualizes real-time health data. This enables highly accurate monitoring of health status, rapid notification of anomalies, and the provision of a sense of security through an easy-to-use interface for the elderly.

[0704] A "sensor device" is a device that continuously acquires biometric information such as a user's heart rate and body temperature, and provides this data to other devices or systems.

[0705] A "camera device" is a device used to capture the user's movements and facial expressions, and is capable of collecting video data.

[0706] A "machine learning model" is a set of algorithms and methods used to analyze collected data and detect anomalies that deviate from normal patterns.

[0707] "Means for detecting anomalies" are technical methods or systems designed to identify data that deviates from normal conditions and to recognize problems.

[0708] A "means for generating and notifying alerts" is a mechanism for promptly informing relevant individuals or organizations when an anomaly is detected.

[0709] An "artificial intelligence conversational agent" is software or a system that uses natural language processing technology to interpret voice commands from a user and provide appropriate responses.

[0710] A "portable information terminal" is an electronic device that an individual can carry with them and use to display and process various types of information.

[0711] The system for implementing this invention aims to monitor the health status of elderly people in real time and to quickly detect abnormalities. This includes sensor devices, camera devices, a cloud server, and a personal digital assistant (PDCA) terminal.

[0712] The server receives biometric information such as heart rate and body temperature collected by sensor devices via Bluetooth or Wi-Fi. It also captures video data of movement and facial expressions from camera devices, and this data is sent to the cloud. The server analyzes this raw data using a machine learning model based on Python, detecting deviations from normal health patterns as anomalies.

[0713] When an anomaly is detected, an alert is sent to the user's mobile device via push notification, for example, through Firebase. The artificial intelligence conversational agent installed on the device uses natural language processing technology to interpret voice commands from the user and set reminders or provide feedback on their health status.

[0714] Furthermore, the system analyzes the user's past behavioral data to generate an individualized care plan. This care plan provides guidance for elderly individuals to maintain their daily health. For example, it recommends changes to daily exercise levels and diet, and displays this information visually on a mobile device.

[0715] For example, when a user's heart rate significantly exceeds their normal level, they can receive an alert saying, "Your heart rate is higher than normal. Please check and take any necessary action." Another example of a prompt message for the generating AI model is, "Generate a sample push notification message to send when an abnormal heart rate is detected."

[0716] In this way, the system can consistently support the health management of the elderly and enable the early detection of abnormalities.

[0717] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0718] Step 1:

[0719] The sensor device continuously acquires the user's heart rate and body temperature and transmits it to the server via Bluetooth. This data collection provides biometric input. The server saves the received data to storage in real time. At this time, the data's timestamp and device ID are also recorded.

[0720] Step 2:

[0721] The camera device captures the user's movements and facial expressions as video data and transmits it to the server via Wi-Fi. This video data serves as input for analyzing the user's behavior. The server converts the video data into a predefined format and saves it. This conversion process allows for efficient subsequent analysis.

[0722] Step 3:

[0723] The server feeds the collected biometric and video data into a machine learning model built in Python. The machine learning model executes an anomaly detection algorithm and analyzes the input data. If an anomaly pattern is detected in the data, this information is output as alert data.

[0724] Step 4:

[0725] Based on alert data detecting an anomaly, the server generates a push notification. This notification includes information about the anomaly and how to address it. The generated notification is sent to the user's device using a cloud messaging service. The user's device displays the received notification on the screen and notifies the user with sound and vibration.

[0726] Step 5:

[0727] The server analyzes the user's past behavioral data and runs a program to generate an individualized care plan. This care plan generation utilizes machine learning predictive models and rule-based systems. The generated care plan is visually displayed on the user's device, providing specific guidance for improving their lifestyle.

[0728] Step 6:

[0729] The device uses an artificial intelligence conversational agent to interpret and respond to user voice commands in real time. It takes the user's voice as input, analyzes their intent using natural language processing, and generates an appropriate response. The generated response is output as voice or displayed as text, enabling interaction with the user.

[0730] 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.

[0731] This invention is a system for monitoring the health and emotional state of elderly individuals in real time, and comprises a combination of sensor devices, camera devices, an emotion engine, and other analysis and notification means.

[0732] First, sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time, depending on the environment. Meanwhile, camera devices capture video data of the elderly individuals' facial expressions and movements and transmit it to the server. This allows for the simultaneous collection of both physical and behavioral data.

[0733] Next, this system incorporates an emotion engine that analyzes biometric and video data collected by the server to estimate the user's emotional state. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into states such as "happiness," "sadness," and "anger." This makes it possible to monitor the mental health of elderly individuals.

[0734] When abnormal conditions or specific emotions are detected, the server generates an alert. For example, if a sudden change in heart rate or a prolonged state of "sadness" is detected, a notification is immediately sent to the device of the registered caregiver or family member. This notification enables rapid intervention and promotes preventative action.

[0735] Furthermore, when users interact with AI chatbots and voice assistants, the analysis results from the emotion engine enable more personalized conversations. For example, if the system determines that a user is stressed, it may offer relaxing topics or suggest deep breathing reminders.

[0736] Furthermore, the server learns the user's behavioral and emotional patterns over a long period of time and creates an individualized care plan. This provides customized health management tailored to the user's physical and mental needs. Finally, the device notifies the user of this information to help improve their daily life.

[0737] Thus, this invention aims to improve the quality of life for the elderly by monitoring both their health and emotions, and through anomaly detection and appropriate interaction.

[0738] The following describes the processing flow.

[0739] Step 1:

[0740] The sensor device continuously measures the heart rate and body temperature of elderly individuals and transmits the data to a server.

[0741] Step 2:

[0742] A camera device captures the faces and movements of elderly individuals and transmits the resulting video data to a server. This data is used to capture the elderly individuals' daily activities and changes in their facial expressions.

[0743] Step 3:

[0744] The system receives biometric and video data collected by the server and converts it into a pre-configured format. Simultaneously, it organizes the data with timestamps in preparation for analysis.

[0745] Step 4:

[0746] The server uses machine learning models to perform data analysis. Based on biometric information, it detects abnormal heart rate and body temperature, and uses an emotion engine to analyze changes in the facial expressions of elderly people from video data to determine their emotional state.

[0747] Step 5:

[0748] If an anomaly or a specific emotional state (e.g., "sadness" or "anger") is detected, the server generates an alert and sends a notification to the relevant parties' terminals. This notification includes information about the anomaly and the emotional state.

[0749] Step 6:

[0750] When a user makes a request to an AI chatbot or voice assistant, the device converts the user's voice into text and interprets the request using natural language processing.

[0751] Step 7:

[0752] Based on information obtained from the emotion engine, the device adjusts the conversation content according to the user's emotions and provides personalized follow-up messages and reminders.

[0753] Step 8:

[0754] The server analyzes long-term data and learns the behavioral and emotional patterns of elderly individuals to create personalized care plans, which are then sent to the user's device. This provides specific suggestions to support the user's health promotion activities.

[0755] (Example 2)

[0756] 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".

[0757] In modern society, real-time monitoring of the physical and emotional health of the elderly is a crucial challenge. However, conventional technologies have struggled to comprehensively grasp these conditions and respond quickly. In particular, health management systems for the elderly that take into account changes in emotional state are still insufficient. This invention aims to provide a system that comprehensively monitors not only physical health but also emotional aspects, and that can respond quickly when abnormalities occur.

[0758] 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.

[0759] In this invention, the server includes means for collecting biometric information from a sensor device, means for acquiring facial expression and motion data from a camera device, and means for data analysis, including an emotion engine that estimates the user's emotional state using this data. This makes it possible to comprehensively monitor the physical and emotional health status of elderly people, detect abnormalities, and respond quickly.

[0760] A "sensor device" is a device used to collect biometric information such as heart rate and body temperature of elderly people in real time.

[0761] A "camera device" is a device used to acquire video data of elderly people's facial expressions and movements.

[0762] An "emotion engine" is software or hardware that analyzes collected video data and biometric information to estimate the user's emotional state.

[0763] "Means of data analysis" refers to technical means of analyzing collected data and executing a process to detect abnormal conditions and emotional patterns.

[0764] An "alert" is a notification that is generated when an abnormal condition or a specific emotional state is detected.

[0765] An "external terminal" is a device owned by a registered caregiver or family member that can receive notifications such as alerts.

[0766] "Natural language processing" is a technology that enables communication with users through voice or text, and includes processing to understand and respond to users' emotions and requests.

[0767] An "individualized care plan" is a set of suggestions created based on the behavioral and emotional patterns of elderly individuals, aimed at optimizing the user's health and mental state.

[0768] This invention is a system for monitoring the health and emotional state of elderly individuals in real time. The system comprises a combination of a sensor device, a camera device, an emotion engine, and other data analysis and notification means.

[0769] Sensor devices collect biometric information such as heart rate and body temperature from elderly individuals. This data is transmitted to a server in real time and stored in a database. Camera devices capture the elderly individuals' facial expressions and movements as video data, which is also transmitted to the server.

[0770] The server uses an emotion engine to analyze collected biometric and video data. Based on facial expression analysis and changes in voice tone, the emotion engine classifies the user's emotions into categories such as "happiness," "sadness," and "anger." The analyzed emotion data is used to monitor the user's mental health.

[0771] If an anomaly is detected, the server generates an alert and sends that information to the terminal. For example, if there is a sudden change in heart rate or a prolonged feeling of "sadness," caregivers and family members will be notified in real time. This allows for prompt action to be taken.

[0772] When users interact with AI chatbots or voice assistants, the conversation becomes more personalized based on analysis results from the emotion engine. This allows for the provision of topics and suggestions tailored to the user. For example, if the system determines that the user is experiencing high stress levels, it may offer relaxing topics or suggest taking deep breaths.

[0773] Furthermore, the server learns the user's long-term behavioral and emotional patterns and creates an individualized care plan. This care plan is designed to provide customized health management tailored to the user's physical and mental needs.

[0774] Specific example:

[0775] If a user continues to experience feelings of sadness, the system will send a notification to the caregiver's device stating, "Continuous sadness has been detected. Confirmation is required."

[0776] Examples of prompts for a generative AI model:

[0777] "Please analyze the emotional state of elderly individuals based on the following data: heart rate, facial expression data, and voice tone."

[0778] "Based on the results of the emotion analysis, please suggest appropriate relaxation methods to the user."

[0779] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0780] Step 1:

[0781] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals. The input is the elderly person's physical data, and the output is the biometric information acquired by the sensor device. This biometric information is transmitted to a server using wireless communication and recorded in a database.

[0782] Step 2:

[0783] The camera device monitors the facial expressions and movements of elderly individuals and acquires video data. The input is video from the elderly individuals, and the output is video data. The video data is transmitted to and stored on a server, similar to sensor devices.

[0784] Step 3:

[0785] The server receives heart rate and body temperature data and performs time-series analysis. The input is biometric data, and data analysis is performed to detect rapid fluctuations and abnormal patterns. The output is the result of the abnormality detection. Specifically, if the heart rate exceeds the normal range, an alert state is triggered.

[0786] Step 4:

[0787] The emotion engine analyzes video data and estimates emotions from facial expressions. The input is video data, and the output is the estimated emotional state. Classifications such as "happiness," "sadness," and "anger" are performed, and analysis results are generated. Specifically, the movements of facial muscles are matched with specific emotional patterns.

[0788] Step 5:

[0789] The server generates an alert upon receiving abnormal biometric data or specific emotional states. Inputs include the detection results of the anomaly and the emotional analysis results, while output is alert information. This alert information is sent to the device and notified to registered caregivers and family members. Specifically, push notifications are sent to the device, enabling a quick response.

[0790] Step 6:

[0791] When users interact with AI chatbots or voice assistants, the conversation is personalized based on the results of sentiment analysis. The input is the user's emotional state, and the output is personalized conversation content. Specifically, if the system determines that the user is stressed, it will suggest ways to relax.

[0792] Step 7:

[0793] The server learns the user's behavioral and emotional patterns based on long-term data and creates an individualized care plan. The input is historical data, and the output is a customized care plan. This provides optimized health management and support for daily life for each user.

[0794] (Application Example 2)

[0795] 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".

[0796] In an aging society, managing the health of the elderly is a crucial issue. In particular, it is necessary to consider not only the physical health but also the emotional well-being of the elderly. While conventional systems focus on monitoring physical health, they have struggled to track emotional states in real time and provide appropriate responses. Furthermore, while rapid responses are required in the event of abnormal conditions or changes in emotional state, automatically providing specific care suggestions has been difficult. This has hindered improvements in the quality of life for the elderly.

[0797] 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.

[0798] In this invention, the server includes means for collecting biometric information from sensor devices, means for acquiring video information from video acquisition devices, means for analyzing this data using machine learning models to detect abnormal states or emotional states, means for generating and notifying alerts when abnormal states or specific emotional states are detected, means for using natural language processing to engage in voice or text-based dialogue with humans, and means for presenting customized care plans based on the user's behavior and emotions. This enables real-time monitoring of the health and emotional state of elderly individuals and allows for the provision of rapid and personalized care plans.

[0799] A "sensor device" is a device used to collect biological information from the body in real time, and is particularly responsible for acquiring data such as heart rate and body temperature.

[0800] A "video acquisition device" is a device used to record a subject's facial expressions and movements, and has the function of transmitting video data to a server in real time.

[0801] A "machine learning model" is an algorithm that uses collected biometric information and video data to analyze and identify abnormal states and emotional states.

[0802] "Abnormal state alert generation" is a process that notifies users of information when sudden changes in heart rate or body temperature, or specific emotional states, are detected.

[0803] "Natural language processing" is a technology that uses human language to understand and analyze speech and text, thereby facilitating smooth communication.

[0804] A "customized care plan" is a means of proposing an optimized care plan based on the individual health and emotional state of the user.

[0805] The system of the present invention consists mainly of a sensor device, a video acquisition device, and a machine learning model for monitoring the health and emotional state of elderly people in real time. The sensor device acquires biometric information such as the heart rate and body temperature of elderly people in real time and transmits it to a server. The video acquisition device records the facial expressions and movements of elderly people and similarly transmits them to the server.

[0806] The server analyzes this data using machine learning models to identify abnormal conditions and emotional states. Based on the results of this analysis, the server makes recommendations. For example, if the heart rate increases sharply or if the detected emotions differ from normal, it generates an alarm and immediately sends it to the caregiver.

[0807] The server also uses natural language processing to engage in voice or text-based conversations with the user and present personalized care plans tailored to the elderly person's condition. These care plans are designed to support the elderly person's daily life and maintain their mental and physical health.

[0808] Specifically, the server analyzes heart rate and facial expression data, and if it determines that the user is stressed, it offers relaxation suggestions in a conversational format. For example, it can send a reminder to take deep breaths. For this purpose, it sometimes uses prompts constructed by a generative AI model.

[0809] An example of a prompt message is: "Based on the current heart rate and facial expression data of the elderly, identify possible emotional states and recommend an appropriate action plan."

[0810] As a result, this invention can improve the quality of life for the elderly and help maintain a safe and secure life.

[0811] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0812] Step 1:

[0813] The sensor device collects biometric information such as heart rate and body temperature from elderly individuals in real time. This data is transmitted to a server using wireless communication. The input is heart rate and body temperature data, and the output is raw biometric data that is transferred to the server.

[0814] Step 2:

[0815] The video acquisition device records the facial expressions and movements of elderly individuals as video data and transmits it to a server. The input is video data, and the output is unprocessed video data sent to the server.

[0816] Step 3:

[0817] The server inputs the received biometric information and video data into a machine learning model for data analysis. Specifically, the AI ​​model analyzes fluctuations in heart rate and body temperature, as well as changes in facial expression. The input consists of biometric information and video data, and the output is the analysis results regarding health status and emotional state.

[0818] Step 4:

[0819] The server detects abnormal states and emotional states based on the analysis results. If an abnormality is detected, it generates an alert. The input is the analysis results, and the output is the alert information.

[0820] Step 5:

[0821] The server sends the generated alert information to the caregiver's or family member's device and provides instructions if an emergency response is needed. The input is the alert information, and the output is a notification message.

[0822] Step 6:

[0823] The server uses natural language processing to present the user with customized care plans in voice or text. Based on the analyzed emotional state, it suggests relaxation methods and appropriate activities. Input consists of the analysis results and prompts generated by the AI ​​model, while output is the text or voice data presented as the care plan.

[0824] Step 7:

[0825] The user selects actions to improve their daily life based on the presented care plan. The input is the presented care plan, and the output is the actions selected by the user.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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."

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] The following is further disclosed regarding the embodiments described above.

[0848] (Claim 1)

[0849] To monitor the health status of the elderly in real time,

[0850] A means of collecting biometric information from a sensor device,

[0851] A means of acquiring video data from a camera device,

[0852] A means of analyzing this data using machine learning models and detecting anomalies,

[0853] A means of generating and notifying alerts when an anomaly is detected,

[0854] A means of communicating with users via voice or text using natural language processing,

[0855] A means of proposing a customized care plan based on behavioral patterns,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, which acquires information including heart rate and body temperature as biological information.

[0859] (Claim 3)

[0860] The system according to claim 1, which continuously improves the accuracy of data analysis by applying a machine learning model.

[0861] "Example 1"

[0862] (Claim 1)

[0863] To monitor the health status of the elderly in real time,

[0864] A means of collecting biometric information from a sensor device,

[0865] A means of acquiring video data from a camera device,

[0866] A means of analyzing this data using machine learning models and detecting anomalies,

[0867] A means of generating and notifying alerts when an anomaly is detected,

[0868] A means of communicating with users via voice or text using natural language processing,

[0869] A means of proposing a customized care plan based on behavioral patterns,

[0870] A means of continuously analyzing data and generating individualized care plans,

[0871] A means of providing users with health information and reminders through an AI chatbot or voice assistant,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, which acquires information including heart rate and body temperature as biological information.

[0875] (Claim 3)

[0876] The system according to claim 1, which continuously improves the accuracy of data analysis by applying a machine learning model.

[0877] "Application Example 1"

[0878] (Claim 1)

[0879] To monitor the health status of the elderly in real time,

[0880] A means of collecting biometric information from a sensor device,

[0881] A means of acquiring video data from a camera device,

[0882] A means of analyzing this data using machine learning models and detecting anomalies,

[0883] A means of generating and notifying alerts when an anomaly is detected,

[0884] A means of communicating with users via voice or text using natural language processing,

[0885] A means of proposing a customized care plan based on behavioral patterns,

[0886] A means including an artificial intelligence conversational agent that responds to voice commands,

[0887] A visual display means on a mobile information terminal that visualizes real-time health data,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, which acquires information including heart rate and body temperature as biological information.

[0891] (Claim 3)

[0892] The system according to claim 1, which continuously improves the accuracy of data analysis by applying a machine learning model.

[0893] "Example 2 of combining an emotion engine"

[0894] (Claim 1)

[0895] To monitor the health and emotional state of elderly people in real time,

[0896] A means of collecting biometric information from a sensor device,

[0897] A means for acquiring facial expression and motion data from a camera device,

[0898] This includes a data analysis method that includes an emotion engine for estimating the user's emotional state using this data,

[0899] A means of generating an alert when an anomaly is detected and notifying an external terminal,

[0900] A means of personalizing conversations with users using natural language processing,

[0901] A means of learning the user's behavioral and emotional patterns and proposing an individualized care plan,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, which acquires heart rate and body temperature as biometric information and classifies emotional states including "happiness," "sadness," and "anger."

[0905] (Claim 3)

[0906] The system according to claim 1, wherein a machine learning model is applied and the accuracy of the analysis is continuously improved by an emotion engine.

[0907] "Application example 2 when combining with an emotional engine"

[0908] (Claim 1)

[0909] To monitor the health and emotional state of elderly people in real time,

[0910] A means of collecting biometric information from a sensor device,

[0911] A means for acquiring video information from a video acquisition device,

[0912] A means of analyzing this data using machine learning models to detect abnormal states or emotional states,

[0913] A means of generating and notifying alerts when an abnormal state or a specific emotional state is detected,

[0914] A means of using natural language processing to engage in voice or text-based dialogue with humans,

[0915] A means of presenting customized care plans based on the user's behavior and emotions,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, which acquires information including heart rate information and body temperature as biological information.

[0919] (Claim 3)

[0920] The system according to claim 1, which continuously improves the accuracy of data analysis by applying a learning algorithm. [Explanation of symbols]

[0921] 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. To monitor the health status of the elderly in real time, A means of collecting biometric information from a sensor device, A means of acquiring video data from a camera device, A means of analyzing this data using machine learning models and detecting anomalies, A means of generating and notifying alerts when an anomaly is detected, A means of communicating with users via voice or text using natural language processing, A means of proposing a customized care plan based on behavioral patterns, A means including an artificial intelligence conversational agent that responds to voice commands, A visual display means on a mobile information terminal that visualizes real-time health data, A system that includes this.

2. The system according to claim 1, which acquires information including heart rate and body temperature as biological information.

3. The system according to claim 1, which continuously improves the accuracy of data analysis by applying a machine learning model.

Images