Terminal management system for Internet of Things
Through the Internet of Things terminal management system, using sleep monitoring module and facial change analysis, the problem of difficulty in monitoring sleep quality in the existing elderly care model is solved, and the comprehensive real-time monitoring and security guarantee for the elderly is achieved, and the elderly care services are improved. Intelligent level and nursing efficiency.
Patent Information
- Application Number
- CN202411485178.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing elderly care model is difficult to monitor the sleep quality of the elderly in real time, and there are problems such as human resources shortage, inefficient management and inability to grasp the health status in real time, especially at night, it is difficult to detect and deal with emergencies in a timely manner.
Design a terminal management system for the Internet of Things. Through sleep monitoring module and facial change image analysis, the respiratory decibels and air flow rate of the elderly are monitored in real time, and multiple detections and secondary verification are carried out to provide comprehensive sleep management and safety. Assure.
Realize 24-hour real-time monitoring of the elderly, improve the scientificity and intelligence level of elderly care services, enhance the sense of security of sleep and health management of the elderly, reduce the work burden of nursing staff, and improve the efficiency and quality of nursing .
Smart Images

Figure CN119027064A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of terminal management, and more specifically, to a terminal management system oriented to the Internet of Things. Background Art
[0002] The existing elderly care models mainly include home-based elderly care and institutional elderly care, but both have significant deficiencies and challenges in practical applications. In terms of home-based elderly care, it is difficult for family members to monitor the sleep quality of the elderly in real time; in terms of institutional elderly care, there are problems such as irregular service processes, difficulty in real-time warning of potential risks, imperfect elderly health management systems, and excessively high institutional operating costs. In addition, the implementation of medical and nursing care in institutions also faces difficulties in resource coordination and low information system integration. Since the vital signs of the elderly are difficult to monitor in time at night, once an emergency occurs, it is usually difficult to discover and take effective emergency measures in time. The traditional elderly care model mainly relies on caregivers or family members for care, but human monitoring is particularly limited at night. It is difficult to ensure 24-hour real-time attention to the sleep status of the elderly, and it is impossible to evaluate the sleep quality of the elderly. Therefore, the existing elderly care model faces the problems of human resource shortage, low management efficiency, and inability to grasp the health status of the elderly in real time. It is urgent to make innovative breakthroughs in intelligent equipment, information platforms, data sharing and sleep monitoring. In order to solve the above problems, a technical solution is now provided. Summary of the invention
[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides a terminal management system for the Internet of Things, which performs multiple detections on the breathing decibels and airflow rates of the elderly through the first and second sleep monitoring modules, and performs secondary verification of abnormal situations based on the analysis of facial change images, thereby providing all-round real-time monitoring and safety protection for the sleep management of the elderly, so as to solve the problems raised in the above-mentioned background technology.
[0004] To achieve the above object, the present invention provides the following technical solutions: A terminal management system for the Internet of Things, including a smart elderly care service platform and a terminal management device, wherein the smart elderly care service platform includes an SOS management module; the SOS management module is used to monitor the sleep status of a user; the SOS management module includes a sleep monitor, an infrared camera, a breathing detection module and a first sleep monitoring module; the sleep monitor is used to obtain the user's heart rate, breathing rate, number of turning over, number of leaving the bed, first sleep data and second sleep data; the first sleep data includes a first breathing decibel and a first breathing airflow rate; the second sleep data includes a second breathing decibel and a second breathing airflow rate; the breathing detection module is used to obtain a first breathing detection value of the user according to the first sleep data; the first sleep monitoring module is used to obtain a second breathing detection value of the user according to the second sleep data, formulate a first sleep detection strategy based on the first breathing detection value and the second breathing detection value, and perform a preliminary detection on whether the user has sleep abnormalities, wherein the first sleep detection strategy is specifically: Extract the second sleep data into the second breathing detection model and calculate the second breathing detection value: ; Where: is the second breathing detection value, is the number of time points in the second breathing detection period, is the second breath decibel at the i+1th time point, is the second breath decibel at the i-th time point, is the average decibel value of the second breath during the detection period, is the second respiratory airflow rate at the i+1th time point, is the second respiratory airflow rate at the i-th time point, is the average value of the second respiratory airflow rate during the detection period; A first sleep detection strategy is formulated based on the first breathing detection value and the second breathing detection value, and a preliminary detection is performed on whether the user has sleep abnormalities: if the second breathing detection value is greater than the first breathing detection value, the preliminary detection determines that the user has sleep abnormalities; if the second breathing detection value is less than or equal to the first breathing detection value, the preliminary detection determines that the user does not have sleep abnormalities, and a secondary detection instruction is sent to the facial detection module.
[0005] As a further solution of the present invention, the SOS management module also includes a face detection module and a second sleep monitoring module; the face detection module is used to obtain a first facial change value according to the first facial change image when receiving a secondary detection instruction: obtain the nose area of the user's face in the first facial change image, and mark the nose tip and nose wings as feature points, continuously and dynamically track the feature points during the face detection process, obtain the horizontal distance between the feature point of the outer edge of the left nose wing and the feature point of the outer edge of the right nose wing at the same time as the first facial feature, calculate the average value of the first facial feature during the face detection process, and determine the average value as the first facial change value of the user's face.
[0006] As a further solution of the present invention, the second sleep monitoring module is used to obtain a second facial change value of the user according to the second facial change image, formulate a second sleep detection strategy based on the second facial change value and the first facial change value, and perform a second detection on whether the user has sleep abnormalities, specifically: obtain the second facial change value of the user according to the second facial change image: obtain the nose area of the user's face in the second facial change image, and mark the nose tip and nose wing as feature points, continuously and dynamically track the feature points during the facial detection process, obtain the horizontal distance between the feature point of the outer edge of the left nose wing and the feature point of the outer edge of the right nose wing at the same time as the second facial feature, obtain the second facial feature range during the facial detection process, calculate the average value of the second facial feature, and determine the average value as the second facial change value of the user's face; formulate a second sleep detection strategy based on the second facial change value and the first facial change value, and perform a second detection on whether the user has sleep abnormalities: if the second facial change value is greater than the first facial change value, the secondary detection determines that the user has sleep abnormalities, and at this time it is determined that the user has sleep abnormalities; if the second breathing detection value is less than or equal to the first breathing detection value, the secondary detection determines that the user does not have sleep abnormalities, and at this time it is determined that the user does not have sleep abnormalities.
[0007] As a further solution of the present invention, the breathing detection module is used to obtain the first breathing detection value of the user according to the first sleep data, obtain the first breathing decibel and the first breathing airflow rate, respectively calculate the mean of the first breathing decibel and the first breathing airflow rate in the detection period, respectively use them as the first distribution coefficient and the second distribution coefficient, import them into the first breathing detection model, calculate the first breathing detection value of the user, and the formula of the first breathing detection model is: ; Where: is the first breath detection value, is the number of time points in the first breathing detection period, is the first breath decibel at the i+1th time point, is the first breath decibel at the i-th time point, is the first distribution coefficient, is the first respiratory airflow rate at the i+1th time point, is the second distribution coefficient, is the first respiratory airflow rate at the i-th time point.
[0008] As a further solution of the present invention, the terminal management device includes an infrared camera, a blood pressure monitor, a wearable detection device terminal, an intelligent detection mattress, a gas leak alarm, a smoke sensor, a water immersion sensor and a door magnetic sensor.
[0009] The technical effects and advantages of a terminal management system for the Internet of Things of the present invention are as follows: the present invention integrates a variety of sensors, monitoring equipment and management modules, and through real-time monitoring of the vital signs, home environment and activity status of the elderly, combined with intelligent analysis and big data display, it makes up for the deficiency of the traditional elderly care model that the sleep status cannot be monitored in real time 24 hours a day, and provides a more refined monitoring method for the health management of the elderly; the breathing decibels and airflow rates of the elderly are detected multiple times by the first and second sleep monitoring modules respectively, and abnormal conditions are verified twice based on the analysis of facial change images, providing all-round real-time monitoring and safety protection for the sleep management of the elderly, improving the scientificity and intelligence level of elderly care services, and also enhancing the sense of security and health protection of the elderly in daily life and sleep; by automatically collecting data, generating reports and providing reminders, the workload of nursing staff can be reduced, while improving the efficiency and quality of nursing. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 A schematic diagram of the structure of a terminal management system for the Internet of Things provided by the present invention; Figure 2 It is the display interface of the safety fence in the smart elderly care service platform; Figure 3 It is the display interface of the central control screen of the smart elderly care service platform; Figure 4 It is the display interface of the early warning center in the smart elderly care service platform; Figure 5 It is the display interface of the work order center of the home service management module; Figure 6 It is the display interface for caregiver management in the home service management module. DETAILED DESCRIPTION
[0011] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solution in the present invention. Obviously, the described technical solution is only a part of the present invention, not all of it. Based on the technical solution in the present invention, all other technical solutions obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0012] Figure 1 FIG. 1 shows a schematic diagram of a terminal management system for the Internet of Things provided by Embodiment 1 of the present invention. Figure 1 As shown, a terminal management system for the Internet of Things in this embodiment includes a smart elderly care service platform and a terminal management device; The smart elderly care service platform is used for nursing management, sleep health management, safety care and big data display; Terminal management equipment is used to collect data.
[0013] Terminal management equipment includes infrared cameras, blood pressure monitors, wearable detection equipment terminals, smart detection mattresses, gas leak alarms, smoke sensors, water immersion sensors, and door magnetic sensors; Infrared cameras are used to record user activity trajectories in real time and issue warnings for abnormal situations; abnormal situations include: User falls in a public area: When a user falls in a public area and stays there for a period of time greater than or equal to the preset falling time, an early warning will be generated to remind the nursing staff to handle it in time; User falls in a private area: For private areas such as living rooms and bathrooms, the millimeter-wave radar detects the user's position, speed, and posture to determine whether the user has fallen and generate an early warning; Vital sign monitoring and early warning: Based on the coverage of the bed by millimeter-wave radar, the user's breathing rate, heart rate, time in bed, time out of bed, number of body movements, and number of times they get up are acquired, and breathing rate thresholds and heart rate thresholds are set respectively, and an early warning is issued when the breathing rate threshold or heart rate threshold is exceeded; Abnormal wandering warning: Automatically detect and trigger warnings for moving targets that move back and forth for a long time in the set warning area, including kitchens, bathrooms, stairs, doors and windows; Gesture help: When the user makes a specific gesture in the set scenario, an early warning will be triggered, reminding the caregiver to pay attention and handle it in time.
[0014] Sphygmomanometers are used to measure blood pressure in the elderly on a regular basis; Wearable detection device terminals are used to provide real-time positioning, safety electronic fences, emergency call care, one-click rescue, pedometer, sedentary reminder and two-way voice call functions; in daytime and outdoor care, by providing real-time positioning and emergency call care functions based on wearable detection device terminals, a safety circle is defined for the elderly based on real-time location information, that is, a safety electronic fence. The safety electronic fence creates a safety boundary for specific users based on user safety. The safety boundary includes two position states: normal range and out-of-range. It can be used to ensure that a safety warning can be issued to a designated person after the user exceeds the safety range, thereby reducing the risk of accidents; from the elderly's side, one-click calls can also be made in an emergency. These alarm messages will be presented and reminded differently according to the application scenario through the mini program or PC or large screen, including monitoring the alarm information on the large screen, the push of the mini program and a record of the corresponding information.
[0015] The smart detection mattress is used to obtain the user's heart rate, breathing rate, body movement rate, frequency of getting out of bed, and frequency of turning over through high-sensitivity pressure sensing equipment; at night, through sleep monitoring, a continuous monitoring of the elderly's physiological state and sleep quality is achieved. The indicators obtained through the monitoring of the smart detection mattress will be transmitted and pushed through applications or used for health status analysis of the elderly, guiding the elderly's health management, or timely warning for emergency situations; The gas leak alarm is used to monitor the gas concentration in the air. When the gas concentration exceeds the safety threshold, it will immediately sound and light an alarm. Smoke sensors are used to detect smoke in the environment and immediately trigger a fire alarm when smoke is detected; The water sensor is used to monitor the height of water on the ground. When it is detected that the water level exceeds the safety threshold, an alarm is triggered immediately; Door magnetic sensors are used to monitor door and window switches. When they detect that the doors and windows are not closed or opened without authorization, an alarm will be triggered.
[0016] The smart elderly care service platform includes a remote sleep monitoring center, an SOS management module, a safety fence, a home service management module, a central control screen and an early warning center.
[0017] The sleep remote monitoring center is used to use smart mattress products to monitor the elderly's vital signs in real time, including checking the elderly's breathing, heart rate, and bed status. For abnormal situations, early warnings will be generated; The SOS management module is used to monitor the user's sleep status; The safety fence is based on user safety and creates a safety boundary for specific users. It has two position states (normal range and out of range), which can ensure that a safety warning can be issued to the designated person when the user exceeds the safety range, reducing the risk of accidents. Figure 2The display interface of the safety fence in the smart elderly care service platform shown; The home service management module is used to formulate the door-to-door service process; The central control screen is used to display remote sleep monitoring; Figure 3 The display interface of the central control screen of the smart elderly care service platform shown; The early warning center is used to record the data of the elderly leaving bed; Figure 4 The display interface of the early warning center in the smart elderly care service platform is shown.
[0018] The home service management module includes work order center, home service provider management, elderly management, caregiver management and service statistics report; The work order center is used to record unassigned work orders, work order management and evaluation management. Specifically, work order management includes: selecting the service object, automatically obtaining customer information, and customizing the service address; selecting the service item and time, and making appointments / making service plans in advance; before and during the door-to-door service, the door-to-door service personnel can be reassigned according to the work status of the service personnel; Figure 5 The display interface of the work order center of the home service management module shown; Home service provider management is used for branches to independently maintain service provider information. Each service provider has an independent administrator to manage their own work orders. Elderly management is used to add, delete, modify and check related settings for the elderly who have signed home door-to-door services. In this interface, the elderly's residential address is set, and subsequent caregivers are linked to provide door-to-door services based on the set address; Nursing management includes remote monitoring of nursing staff; e.g. Figure 6 The display interface of the home service management module care worker management is shown; The service statistics report includes statistics on services for the elderly and statistics on services for nursing staff.
[0019] Specifically, the SOS management module includes a sleep monitor, an infrared camera, a breathing detection module, a first sleep monitoring module, a face detection module and a second sleep monitoring module; the sleep monitor is connected to the breathing detection module and the first sleep monitoring module respectively, the breathing detection module is connected to the first sleep monitoring module, the infrared camera is connected to the face detection module and the second sleep monitoring module respectively, and the face detection module is connected to the second sleep monitoring module; The sleep monitor is used to obtain the user's heart rate, breathing rate, number of turning over, number of leaving the bed, first sleep data and second sleep data; the first sleep data includes first breathing decibels and first breathing airflow rate; the second sleep data includes second breathing decibels and second breathing airflow rate; The infrared camera is used to obtain a first facial change image and a second facial change image of the user; The breathing detection module is used to obtain a first breathing detection value of the user according to the first sleep data; The first sleep monitoring module is used to obtain a second breathing detection value of the user according to the second sleep data, formulate a first sleep detection strategy based on the first breathing detection value and the second breathing detection value, and perform a preliminary detection on whether the user has sleep abnormalities; The facial detection module is used to obtain a first facial change value according to the first facial change image when receiving a secondary detection instruction; The second sleep monitoring module is used to obtain a second facial change value of the user according to the second facial change image, formulate a second sleep detection strategy based on the second facial change value and the first facial change value, and perform a second detection on whether the user has sleep abnormalities.
[0020] Specifically, the first sleep data is monitored by a sleep monitor to obtain the user's first breathing decibel and first breathing airflow rate within one month; the second sleep data is monitored in real time by the sleep monitor to obtain the second breathing decibel and second breathing airflow rate after one month.
[0021] The first facial change image is an image of the facial change of the user within one month obtained through a camera; the second facial change image is an image of the facial change after one month obtained through real-time monitoring by a camera.
[0022] The breathing detection module is used to obtain the first breathing detection value of the user according to the first sleep data, obtain the first breathing decibel and the first breathing airflow rate, respectively calculate the mean of the first breathing decibel and the first breathing airflow rate in the detection period, respectively use them as the first distribution coefficient and the second distribution coefficient, import them into the first breathing detection model, and calculate the first breathing detection value of the user. The formula of the first breathing detection model is: ; Where: is the first breath detection value, is the number of time points in the first breathing detection period, is the first breath decibel at the i+1th time point, is the first breath decibel at the i-th time point, is the first distribution coefficient, is the first respiratory airflow rate at the i+1th time point, is the second distribution coefficient, is the first respiratory airflow rate at the i-th time point.
[0023] The first sleep monitoring module is used to obtain the second breathing detection value of the user according to the second sleep data, formulate a first sleep detection strategy based on the first breathing detection value and the second breathing detection value, and perform a preliminary detection on whether the user has sleep abnormalities. The first sleep detection strategy is specifically: Extract the second sleep data into the second breathing detection model and calculate the second breathing detection value: ; Where: is the second breathing detection value, is the number of time points in the second breathing detection period, is the second breath decibel at the i+1th time point, is the second breath decibel at the i-th time point, is the average decibel value of the second breath during the detection period, is the second respiratory airflow rate at the i+1th time point, is the second respiratory airflow rate at the i-th time point, is the average value of the second respiratory airflow rate during the detection period; A first sleep detection strategy is formulated based on the first breathing detection value and the second breathing detection value, and a preliminary detection is performed on whether the user has sleep abnormalities: if the second breathing detection value is greater than the first breathing detection value, the preliminary detection determines that the user has sleep abnormalities; if the second breathing detection value is less than or equal to the first breathing detection value, the preliminary detection determines that the user does not have sleep abnormalities, and a secondary detection instruction is sent to the facial detection module.
[0024] Through a variety of sensors (such as sleep monitors, breathing detection modules, and facial detection modules), the system collects data such as the elderly's heart rate, breathing decibels, airflow rate, and the number of times they turn over in real time, enabling the system to analyze the elderly's sleep status in an all-round and multi-level manner and conduct scientific sleep monitoring; by collecting and comparing the first sleep data within a month with the second sleep data one month later, it can identify long-term health change trends and thus promptly discover potential health problems; through comprehensive calculations of breathing decibels and airflow rates, based on complex mathematical models, it can efficiently detect breathing abnormalities. When breathing abnormalities exceed the set threshold, it can issue an early warning to help caregivers intervene in a timely manner; when the preliminary test results show that there is no sleep abnormality, facial change detection will also be triggered to ensure that no potential sleep problems are missed; by acquiring facial change images through an infrared camera and tracking nasal feature points, it can further confirm sleep abnormalities by analyzing subtle facial changes, especially when the user's heartbeat or breathing is abnormal, providing a more accurate detection method.
[0025] The facial detection module is used to obtain a first facial change value according to the first facial change image when receiving a secondary detection instruction: obtain the nose area of the user's face in the first facial change image, and mark the nose tip and nose wings as feature points, continuously and dynamically track the feature points during the facial detection process, obtain the horizontal distance between the feature points of the outer edge of the left nose wing and the outer edge of the right nose wing at the same moment as the first facial feature, calculate the average value of the first facial feature during the facial detection process, and determine the average value as the first facial change value of the user's face.
[0026] The second sleep monitoring module is used to obtain a second facial change value of the user according to the second facial change image, formulate a second sleep detection strategy based on the second facial change value and the first facial change value, and perform a second detection on whether the user has sleep abnormalities, specifically: Obtain the second facial change value of the user according to the second facial change image: obtain the nose area of the user's face in the second facial change image, and mark the nose tip and nose wings as feature points, continuously and dynamically track the feature points during the facial detection process, obtain the horizontal distance between the feature points of the left nose wing outer edge and the right nose wing outer edge at the same time as the second facial feature, obtain the second facial feature range during the facial detection process, calculate the average value of the second facial feature, and determine the average value as the second facial change value of the user's face; formulate a second sleep detection strategy based on the second facial change value and the first facial change value, and perform a second detection on whether the user has sleep abnormalities: if the second facial change value is greater than the first facial change value, then the secondary detection determines that the user has sleep abnormalities, and at this time it is determined that the user has sleep abnormalities; if the second breathing detection value is less than or equal to the first breathing detection value, then the secondary detection determines that the user does not have sleep abnormalities, and at this time it is determined that the user does not have sleep abnormalities.
[0027] By tracking and analyzing facial features, the system not only relies on physiological data such as breathing decibels and airflow rate, but also combines the user's facial changes (such as the expansion and contraction of the nose wings) to further verify whether there is sleep abnormality, which can significantly improve the accuracy of detection and reduce the possibility of false alarms and missed alarms. When the first round of breathing detection shows that the user has abnormalities, a second confirmation is performed through facial detection. If both tests show abnormalities, it can be finally determined that the user does have sleep abnormalities, avoiding false warnings caused by single data fluctuations. By dynamically tracking facial feature points such as the tip of the nose and the wings of the nose, it can capture the subtle facial changes caused by the user's breathing in real time, especially when the user is sleeping late. When the user breathes, the expansion and contraction of the nostrils can reflect the depth of the breathing, thereby more accurately judging abnormal breathing. Real-time analysis and detection are performed based on the user's current facial changes, so that the detection results are timely and dynamic, and can promptly identify changes in the user's sleep status. By combining facial changes and respiratory changes, the system can effectively filter out false alarms caused by other reasons (such as short-term respiratory fluctuations). Only when both the facial change value and the respiratory change value exceed the set threshold, the system will finally issue a sleep abnormality warning, thereby improving the effectiveness of the early warning, ensuring that the user's true sleep state can be accurately reflected, and reducing invalid early warning prompts.
[0028] By integrating infrared cameras, smart mattresses, blood pressure monitors, and breathing detection modules, it can comprehensively collect users' sleep-related data (such as heart rate, breathing rate, body movement times, etc.), and conduct comprehensive analysis through multiple algorithms; it monitors the activities of the elderly in different areas (public areas and private areas), and based on the detection data, it can promptly identify and issue fall warnings, reminding nursing staff to deal with them to avoid delayed rescue; for specific warning areas (such as kitchens, bathrooms, stairs, etc.), it can detect whether the elderly have abnormal wandering or dangerous behaviors, and intervene in time to avoid accidents; through wearable devices, the elderly's activity range is monitored during the day and outdoors, and a safe electronic fence is demarcated. When the elderly exceed the preset safety area, they can be When the elderly are in full range, the system will issue an early warning and notify relevant personnel to reduce the risk of the elderly getting lost. The wearable device can not only locate in real time, but also provide a one-click call function. When the elderly are in an emergency, they can quickly send out a distress signal to ensure that they can get help in time in an emergency. The first and second sleep monitoring modules are used to perform multiple tests on the elderly's breathing decibels and airflow rates, and based on the analysis of facial change images, abnormal situations are verified for the second time to ensure that abnormal situations can be identified in a timely and accurate manner to avoid underreporting. The facial detection module obtains the elderly's facial changes in real time by tracking facial features such as the nose, and combined with the breathing data, it can further analyze the elderly's sleep condition and whether their breathing is normal.
[0029] The embodiment of the present invention integrates a variety of sensors, monitoring equipment and management modules. Through real-time monitoring of the vital signs, home environment and activity status of the elderly, combined with intelligent analysis and big data display, it makes up for the deficiency of the traditional elderly care model that cannot monitor the sleep status in real time 24 hours a day, and provides a more refined monitoring method for the health management of the elderly; the first and second sleep monitoring modules respectively detect the breathing decibels and airflow rates of the elderly for multiple times, and perform secondary verification of abnormal conditions based on the analysis of facial change images, which provides all-round real-time monitoring and safety protection for the sleep management of the elderly, improves the scientificity and intelligence level of elderly care services, and also enhances the sense of security and health protection of the elderly in daily life and sleep; by automatically collecting data, generating reports and providing reminders, it can reduce the workload of nursing staff and improve the efficiency and quality of nursing.
[0030] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0031] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A terminal management system for the Internet of Things, including a smart elderly care service platform and a terminal management device, characterized in that: The smart elderly care service platform includes an SOS management module; the SOS management module is used to monitor the sleep status of the user; the SOS management module includes a sleep monitor, an infrared camera, a breathing detection module and a first sleep monitoring module; the sleep monitor is used to obtain the user's heart rate, breathing rate, number of turning over, number of leaving the bed, first sleep data and second sleep data; the first sleep data includes a first breathing decibel and a first breathing airflow rate; the second sleep data includes a second breathing decibel and a second breathing airflow rate; The breathing detection module is used to obtain a first breathing detection value of the user according to the first sleep data; The first sleep monitoring module is used to obtain the second breathing detection value of the user according to the second sleep data, formulate a first sleep detection strategy based on the first breathing detection value and the second breathing detection value, and perform a preliminary detection on whether the user has sleep abnormalities. The first sleep detection strategy is specifically: Extract the second sleep data into the second breathing detection model and calculate the second breathing detection value: ; Where: is the second breathing detection value, is the number of time points in the second breathing detection period, is the second breath decibel at the i+1th time point, is the second breath decibel at the i-th time point, is the average decibel value of the second breath during the detection period, is the second respiratory airflow rate at the i+1th time point, is the second respiratory airflow rate at the i-th time point, is the average value of the second respiratory airflow rate during the detection period; Formulate a first sleep detection strategy according to the first breathing detection value and the second breathing detection value, and perform a preliminary detection on whether the user has sleep abnormality: if the second breathing detection value is greater than the first breathing detection value, the preliminary detection determines that the user has sleep abnormality; If the second breathing detection value is less than or equal to the first breathing detection value, the preliminary detection determines that the user does not have sleep abnormalities, and sends a secondary detection instruction to the face detection module.
2. A terminal management system for the Internet of Things according to claim 1, characterized in that: The SOS management module also includes a face detection module and a second sleep monitoring module; the face detection module is used to obtain a first face change value according to the first face change image when receiving a secondary detection instruction: obtain the nose area of the user's face in the first face change image, and mark the nose tip and nose wings as feature points, continuously and dynamically track the feature points during the face detection process, obtain the horizontal distance between the feature point of the outer edge of the left nose wing and the feature point of the outer edge of the right nose wing at the same time as the first facial feature, calculate the average value of the first facial feature during the face detection process, and determine the average value as the first facial change value of the user's face.
3. A terminal management system for the Internet of Things according to claim 2, characterized in that: The second sleep monitoring module is used to obtain the second facial change value of the user according to the second facial change image, formulate a second sleep detection strategy based on the second facial change value and the first facial change value, and perform a second detection on whether the user has sleep abnormalities, specifically: obtain the second facial change value of the user according to the second facial change image: obtain the nose area of the user's face in the second facial change image, and mark the nose tip and nose wing as feature points, continuously and dynamically track the feature points during the facial detection process, obtain the horizontal distance between the feature point of the outer edge of the left nose wing and the feature point of the outer edge of the right nose wing at the same time as the second facial feature, obtain the second facial feature range during the facial detection process, calculate the average value of the second facial feature, and determine the average value as the second facial change value of the user's face; formulate a second sleep detection strategy based on the second facial change value and the first facial change value, and perform a second detection on whether the user has sleep abnormalities: if the second facial change value is greater than the first facial change value, the secondary detection determines that the user has sleep abnormalities, and at this time it is determined that the user has sleep abnormalities; if the second breathing detection value is less than or equal to the first breathing detection value, the secondary detection determines that the user does not have sleep abnormalities, and at this time it is determined that the user does not have sleep abnormalities.
4. A terminal management system for the Internet of Things according to claim 1, characterized in that: The breathing detection module is used to obtain the first breathing detection value of the user according to the first sleep data, obtain the first breathing decibel and the first breathing airflow rate, respectively calculate the mean of the first breathing decibel and the first breathing airflow rate in the detection period, respectively use them as the first distribution coefficient and the second distribution coefficient, import them into the first breathing detection model, and calculate the first breathing detection value of the user. The formula of the first breathing detection model is: ; Where: is the first breathing detection value, is the number of time points in the first breathing detection period, is the first breath decibel at the i+1th time point, is the first breath decibel at the i-th time point, is the first distribution coefficient, is the first respiratory airflow rate at the i+1th time point, is the second distribution coefficient, is the first respiratory airflow rate at the i-th time point.
5. The terminal management system for the Internet of Things according to claim 1, characterized in that: Terminal management devices include infrared cameras, blood pressure monitors, wearable detection device terminals, smart detection mattresses, gas leak alarms, smoke sensors, water immersion sensors and door magnetic sensors.
Citation Information
Patent Citations
Intelligent nursing system serving old people
CN116013031A
Intelligent control electric mattress
CN117204699A
Pressure control device based on snoring sound intensity and apnea mode
CN117562506A
Sleep disorder auxiliary diagnosis and doctor's advice effect tracking system
CN117690577A
System and method for determining sleep stage
US20150230750A1
