Home-based comprehensive elderly care service management system based on the Internet of Things

Abstract

The present invention discloses a home-based elderly care comprehensive service management system based on the Internet of Things, and relates to the technical field of the Internet of Things. In order to solve the problems in the prior art that the detection and response speed for emergencies is poor, especially the lack of more intelligent means for emergency handling of elderly people without anyone to accompany them, and the service content fails to fully combine the specific needs of users for intelligent push, and the service model is relatively single; the present invention collects the health status, activity trajectory and environmental data of users in real time through Internet of Things devices, builds a comprehensive perception system, dynamically adjusts and pushes personalized service content according to the user's health records, behavioral habits and actual needs, compares user behavior feature data with historical habits, effectively determines the degree of behavioral deviation, and generates early warning reports in time, which not only improves the real-time and accuracy of behavior monitoring, but also provides customized services according to the personalized needs of users, discovers abnormal behaviors in time, and ensures user safety.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a comprehensive home-based elderly care service management system based on the Internet of Things. Background Art

[0002] Traditional home-based elderly care has many deficiencies in providing non-health management services such as life care and emergency rescue. The Chinese patent with announcement number: CN103942632A discloses an intelligent home-based elderly care service system, which is based on the system platform, the elderly database, call center, community medical center and emergency call terminal, and builds four major service modes: emergency rescue, medical services, life assistance and active care. Relying on the intelligent service system to integrate social service resources, it provides the elderly with all-round home-based medical and nursing care services including emergency rescue, medical services and life assistance, and creates an information-based and intelligent virtual nursing home operation model with "public welfare as the premise, socialization as the basis, and marketization as the supplement", promoting the continuous, healthy and rapid development of the home-based medical and nursing care service industry.

[0003] However, although the above patents solve many deficiencies in some non-health management services, the following problems still exist: In the existing technology, the detection and response speed for emergencies is poor, especially for the emergency handling of unattended elderly people, there is a lack of more intelligent means, and the service content fails to fully combine the specific needs of users for intelligent push, and the service model is relatively single. Summary of the invention

[0004] The purpose of the present invention is to provide a comprehensive home-based elderly care service management system based on the Internet of Things, which collects users' health status, activity trajectory and environmental data in real time through Internet of Things devices, builds a comprehensive perception system, and dynamically adjusts and pushes personalized service content according to users' health records, behavioral habits and actual needs, so as to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The comprehensive home-based elderly care service management system based on the Internet of Things includes: Data collection module, which is used to collect real-time user life data at home based on various sensors and smart devices, including health data, environmental data and behavioral data; The data analysis and processing module is used to process and store the collected life data, analyze the user's behavior patterns, identify regular and abnormal behaviors in daily life, predict potential risks based on the identification results, and issue abnormal warnings; The service request receiving and processing module is used to build an interactive channel between the integrated service management platform and the mobile terminal based on the Internet of Things. The integrated service management platform receives the user's service request based on the interactive channel and calls the corresponding service according to the demand; The service provision module is used to provide corresponding comprehensive services based on the user's service request and the behavior analysis results of the data analysis and processing module.

[0006] Furthermore, the data acquisition module includes: A user data collection unit, used to monitor the user's health data in real time based on the health monitoring device; The behavior monitoring unit is used to monitor the video stream data in the room where the user is located in real time based on the smart device, extract the user's movement path and activity range in the room based on human body characteristics, and identify the user's behavior characteristics; An environmental sensing unit is used to collect the user's living environment data and extract the safety parameters of the living environment based on the living environment data, including temperature, humidity, air quality and safety hazard data; The home appliance control unit is used to collect and control the operating status data of smart home devices and adjust the operating status of smart home devices based on the user's behavioral characteristics; The security monitoring unit is used to deploy various sensors in the user's living environment, monitor potential security threats in the home environment in real time based on various sensors, and issue early warning prompts for identified potential security threats.

[0007] Furthermore, the behavior monitoring unit comprises: A resource occupancy monitoring module, used to monitor in real time the CPU occupancy rate and memory occupancy rate of the communication thread between the behavior monitoring unit and the data analysis and processing module; An occupancy comparison module is used to compare the CPU occupancy and memory occupancy of the communication thread with a preset CPU occupancy threshold and a preset memory occupancy threshold respectively; A historical data retrieval module, used for retrieving the historical data of the communication thread when any one of the CPU occupancy rate and the memory occupancy rate of the communication thread exceeds the corresponding threshold value; A running data extraction module is used to retrieve the CPU occupancy rate, memory occupancy rate and queue length change rate of the communication thread from the historical data of the communication thread operation; A saturation evaluation coefficient acquisition module is used to obtain the saturation evaluation coefficient of the communication thread by using the CPU occupancy rate, memory occupancy rate and queue length change rate of the communication thread; The saturation evaluation coefficient of the communication thread is obtained by the following formula: ; Where S represents the saturation evaluation coefficient of the communication thread; n represents the number of unit time experienced in the historical data; C pi 、N pi and D pi They represent the CPU occupancy rate, memory occupancy rate and queue length change rate corresponding to the i-th unit time respectively; C y and N y Respectively represent the preset CPU occupancy threshold and memory occupancy threshold; α, β, v and δ represent the first adjustment coefficient, the second adjustment coefficient, the third adjustment coefficient and the fourth adjustment coefficient, respectively, and the value ranges of the first adjustment coefficient, the second adjustment coefficient, the third adjustment coefficient and the fourth adjustment coefficient are: 0.47-0.73, 0.16-0.39, 0.58-1.13 and 1.32-2.21; A coefficient comparison module, used for comparing the saturation evaluation coefficient of the communication thread with a preset saturation evaluation coefficient threshold; The frame rate adjustment module is used to adjust the frame rate of the smart device used to monitor the video stream data in the room where the user is located in real time when the saturation evaluation coefficient of the communication thread exceeds a preset saturation evaluation coefficient threshold.

[0008] Furthermore, the frame rate adjustment module includes: A frame rate extraction module, used to extract the current frame rate of the smart device; A saturation evaluation coefficient retrieving module, used to retrieve the saturation evaluation coefficient of the communication thread; Retrieving historical data of the operation of the communication thread, and extracting from the historical data the ratio of the number of messages transmitted by the video data stream communication contained in the message queue per unit time; A frame rate adjustment coefficient acquisition module, used to obtain a frame rate adjustment coefficient by using the frame rate of the smart device, the saturation evaluation coefficient of the communication thread and the ratio of the number of messages transmitted by the video stream data communication contained in the queue length per unit time; The frame rate adjustment coefficient is obtained by the following formula: ; Where K represents the frame rate adjustment coefficient; S represents the saturation evaluation coefficient of the communication thread; S y Indicates the preset saturation evaluation coefficient threshold; F min Indicates the minimum frame rate allowed for shooting; F d represents the current frame rate of the smart device; M represents the ratio of the number of messages transmitted by the video stream data communication contained in the current queue length; M bIt represents the standard deviation of the proportion of the number of messages transmitted by the video stream data communication contained in the queue length per unit time; Q represents the ratio of the current queue length to the average queue length; C represents the adjustment coefficient for controlling the influence of the proportion of the number of messages on the frame rate adjustment coefficient, and the value range is 0.21-0.38; B represents the adjustment coefficient for controlling the influence of saturation on the frame rate adjustment coefficient, and the value range is 0.27-0.43: The frame rate adjustment execution module is used to adjust the frame rate of the video in the room where the user is located shot in real time by the current smart device according to the frame rate adjustment coefficient.

[0009] Furthermore, the frame rate adjustment execution module is used to: Extract the frame rate adjustment coefficient; Comparing the frame rate adjustment coefficient with a preset frame rate adjustment coefficient threshold; When the frame rate adjustment coefficient does not exceed the preset frame rate adjustment coefficient threshold, the frame rate of the video captured by the smart device in the room where the user is located in real time is adjusted using the frame rate adjustment coefficient to obtain a first frame rate; The first frame rate is obtained by the following formula: ; Among them, F t01 represents the first frame rate, and when F t01 Less than F min When F t01 =F min ; F d represents the current frame rate of the smart device; K represents the frame rate adjustment coefficient; Controlling shooting of the smart device according to a first frame rate; When the frame rate adjustment coefficient exceeds a preset frame rate adjustment coefficient threshold, the frame rate adjustment times corresponding to the frame rate adjustment coefficient exceeding the preset frame rate adjustment coefficient threshold in the frame rate adjustment history record are retrieved; Extracting the frame rate value before adjustment and the frame rate value after adjustment corresponding to each frame rate adjustment, as well as the CPU occupancy rate release ratio and the memory occupancy rate release ratio of the communication channel after the frame rate adjustment; Obtaining a second frame rate by using the frame rate value before adjustment and the frame rate value after adjustment corresponding to each frame rate adjustment, as well as the CPU occupancy release ratio and the memory occupancy release ratio of the communication channel after the frame rate adjustment in combination with the frame rate adjustment coefficient; The second frame rate is obtained by the following formula: ; Among them, F t02 represents the second frame rate, and when F t02 Less than Fmin When F t02 =F min ; F d represents the current frame rate of the smart device; K represents the frame rate adjustment coefficient; m represents the number of frame rate adjustments corresponding to the frame rate adjustment coefficient in the frame rate adjustment history exceeding the preset frame rate adjustment coefficient threshold; F xi and F hi represents the frame rate value before adjustment and the frame rate value after adjustment corresponding to the i-th frame rate adjustment; C si and N si Indicates the CPU occupancy rate release ratio and memory occupancy rate release ratio of the communication channel after the frame rate adjustment corresponding to the i-th frame rate adjustment; The smart device is controlled to shoot according to the second frame rate.

[0010] Furthermore, the data analysis and processing module includes: A behavior pattern analysis unit is used to analyze the user's daily behavior based on the user's behavior characteristics identified by the behavior monitoring unit, and identify the user's behavior patterns and abnormal situations; An environmental parameter analysis unit is used to evaluate the safety index of the home environment based on the safety parameters extracted by the environmental sensing unit, and to generate risk warnings and optimization suggestions based on the evaluation results; The control instruction output unit is used to generate corresponding control instructions based on the output results of the behavior pattern analysis unit and the environmental parameter analysis unit, and control the corresponding smart home devices to respond and perform operations based on the Internet of Things.

[0011] Furthermore, the data analysis and processing module also includes: The user health warning unit is used to obtain the user's health data and conduct dynamic analysis in combination with historical health records to predict potential health risks and issue warnings; The personalized recommendation unit is used to integrate behavioral patterns, environmental parameters and health data into user portraits, and generate personalized recommendation content to the user's mobile terminal based on the user portrait and service needs.

[0012] Furthermore, the behavior pattern analysis unit identifies the user's behavior patterns and abnormalities, specifically: Acquire the user behavior characteristic data and the sub-data carried by the data acquisition module, and pre-process the behavior characteristic data and the sub-data; Extracting the time series of the sub-data, sorting the pre-processed behavior feature data based on the time series, establishing a continuous behavior feature time axis, and generating dynamic behavior data; Obtain the activity frequency, activity duration distribution and time regularity of the user's behavior from the dynamic behavior data, and identify the user's main activity range based on the user's activity location data; Perform cluster analysis on user activity location data to generate a distribution map of the main activity areas of users, extract the activity time patterns of user behaviors in the distribution map of the main activity areas of users, and identify the periodic characteristics of user behavior patterns; Comparing the dynamic behavior data with preset abnormal behavior data, identifying abnormal behavior features based on the comparison results, and classifying the abnormal behavior data to generate abnormal categories of the abnormal behavior data; Based on the comparison between the behavioral feature data obtained in real time and historical behavioral habits, the user's current behavior deviation degree is determined, and whether there is abnormal behavior is analyzed. The user's behavioral feature report is generated based on the analysis results; When abnormal behavior is detected, an abnormal warning report is generated, including the time, location and description information of the abnormal behavior, and the warning report is pushed to the mobile terminal where the user's family or caregiver is located.

[0013] Furthermore, based on the comparison between the behavioral feature data obtained in real time and the historical behavioral habits, the degree of deviation of the user's current behavior is determined, including: Obtain the user's real-time behavior feature data, and at the same time, obtain the user's historical behavior data from the historical behavior database, and compare the real-time behavior data with the historical data item by item based on the basic data type; Matching the real-time behavior data with the historical behavior habit data, and generating a first target behavior data segment and a second target behavior data segment based on the matching result, wherein the first target behavior data segment is data inconsistent with the historical behavior habit, and the second target behavior data segment is data consistent with the historical behavior habit; Classifying the data in the second target behavior data segment based on the basic data type to generate a plurality of sub-monitoring data groups; Extracting data from a plurality of first target behavior data segments as first data samples, and at the same time, randomly extracting data from each sub-monitoring data group as second data samples; Reading the first data sample, determining the user's behavior feature points, building the user's first behavior network based on the behavior feature points, and deploying the first target behavior data to the first behavior network through the behavior feature points; Based on the deployment characteristics of the first behavior network, the main patterns and habits of the user's behavior are analyzed to determine the user's first behavior habits. Based on the second data sample, a second behavior network is constructed to simulate and analyze the behavior to identify the user's second behavior habits. Assigning weights to the first behavior habit and the second behavior habit respectively, calculating the first habit weight and the second habit weight corresponding to the user, and scoring the first behavior habit and the second behavior habit respectively according to the habit weights to obtain a first score and a second score; Calculate the user's comprehensive behavior score based on the first score and the second score, compare the comprehensive behavior score with a preset scoring threshold, and determine whether the user's current behavior is consistent with historical behavior habits; If the comprehensive behavior score is equal to or greater than the scoring threshold, the behavior is judged to be consistent with the user's historical behavior habits; if the comprehensive behavior score is less than the scoring threshold, the behavior is judged to be deviant; If the behavior is determined to deviate from the user's historical behavior habits, the degree of deviation is evaluated based on the comprehensive behavior score and an early warning report is generated.

[0014] Furthermore, the service request receiving and processing module includes: User management unit, used to manage the personal information and service records of all users on the platform; The request processing unit is used to receive and process service requests from users through the platform, classify and prioritize the service requests according to their content, assign them to the service provision module, and track and update the request progress in real time.

[0015] Furthermore, the service provision module includes: Intelligent reminder unit, used to send intelligent reminders to users regularly according to their personalized needs and health conditions, including health management, life care and environmental control; The service scheduling unit is used to connect with various service resources in the platform and schedule corresponding service resources according to the user's request and actual needs, combined with the priority sorting of the request content; The call warning unit is used to immediately trigger the emergency call and warning mechanism when receiving abnormal behavior or warning information, and provides a one-key calling function for users to make emergency calls.

[0016] Compared with the prior art, the present invention has the following beneficial effects: By real-time monitoring and comparing user behavior feature data with historical habits, the degree of behavioral deviation can be effectively determined and early warning reports can be generated in a timely manner. This not only improves the real-time and accuracy of behavior monitoring, but also provides customized services based on user's personalized needs, detects abnormal behavior in a timely manner, and ensures user safety. At the same time, it provides data support for decision-making, enhances user experience, and realizes intelligent and refined behavior analysis and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a module diagram of the Internet of Things-based home-based comprehensive elderly care service management system of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In order to solve the technical problems in the existing technology, such as the poor detection and response speed for emergencies, especially the lack of more intelligent means for emergency treatment of unattended elderly people, the failure of intelligent push of service content in line with the specific needs of users, and the relatively single service model, please refer to Figure 1 , this embodiment provides the following technical solutions: The comprehensive home-based elderly care service management system based on the Internet of Things includes: Data collection module, which is used to collect users' life data at home in real time based on various sensors and smart devices, including health data, environmental data and behavior data. Various sensors such as temperature and humidity sensors, smoke sensors, and gas sensors are used to monitor the safety of the home environment. Smart devices such as infrared sensors, cameras (with privacy protection functions), and pressure sensing pads are used to monitor users' activity trajectories and abnormal behaviors (such as falls); The data analysis and processing module is used to process and store the collected life data, analyze the user's behavior patterns, identify regular and abnormal behaviors in daily life, predict potential risks such as cardiovascular disease and fall risks based on the identification results, and issue abnormal warnings; The service request receiving and processing module is used to build an interactive channel between the integrated service management platform and the mobile terminal based on the Internet of Things. The integrated service management platform receives service requests from users, such as the elderly, their families, and caregivers, based on the interactive channel, and calls corresponding services based on demand; The service provision module is used to provide comprehensive services including life care, health management, and emergency rescue based on the user's service request and the behavior analysis results of the data analysis and processing module.

[0020] In this embodiment, by real-time monitoring and comparing user behavior feature data with historical habits, the degree of behavior deviation can be effectively determined and early warning reports can be generated in a timely manner. This not only improves the real-time and accuracy of behavior monitoring, but also provides customized services based on user personalized needs, detects abnormal behavior in a timely manner, and ensures user safety. At the same time, it provides data support for decision-making, enhances user experience, and realizes intelligent and refined behavior analysis and management.

[0021] In this embodiment, the data acquisition module includes: A user data collection unit, used to monitor the user's health data in real time based on the health monitoring device; The behavior monitoring unit is used to monitor the video stream data in the room where the user is located in real time based on the smart device, extract the user's movement path and activity range in the room based on human body characteristics, identify the user's behavior characteristics, and identify abnormal conditions such as falling and sitting for a long time; Environmental sensing unit, used to collect the user's living environment data, and extract the safety parameters of the living environment based on the living environment data, including temperature, humidity, air quality and safety hazard data. For example, deploy temperature and humidity sensors to monitor changes in indoor temperature and humidity to ensure that the environment is suitable, use smoke sensors and gas sensors to detect fire hazards and gas leaks, and abnormal data trigger an alarm mechanism; Home appliance control unit, used to collect and control the operating status data of smart home devices (such as air conditioners, lights, curtains, etc.), monitor the power consumption and usage of devices in real time, and adjust the operating status of smart home devices based on user behavior characteristics (such as automatically turning lights on and off according to activity trajectories) to achieve automatic adjustment of the home environment; The security monitoring unit is used to deploy various sensors in the user's living environment, monitor potential security threats in the home environment in real time based on various sensors, and issue early warning prompts for identified potential security threats.

[0022] In this embodiment, by integrating user health data, behavioral characteristics, environmental parameters and home appliance control, a comprehensive monitoring system is provided for users to ensure the comprehensiveness and real-time nature of the data. The security monitoring unit protects the safety of users' lives and property. For example, door and window sensors are deployed to detect the switch status of doors and windows in real time to prevent users from accidentally going out or invading the environment. Alarm buttons or emergency call devices are configured. Users can trigger an alarm signal with one click when encountering an emergency. Security monitoring data is encrypted and transmitted to the platform through a security gateway. Abnormal signals automatically notify family members or caregivers, and can be linked to start rescue services.

[0023] Specifically, the behavior monitoring unit includes: A resource occupancy monitoring module, used to monitor in real time the CPU occupancy rate and memory occupancy rate of the communication thread between the behavior monitoring unit and the data analysis and processing module; An occupancy comparison module is used to compare the CPU occupancy and memory occupancy of the communication thread with a preset CPU occupancy threshold and a preset memory occupancy threshold respectively; A historical data retrieval module, used for retrieving the historical data of the communication thread when any one of the CPU occupancy rate and the memory occupancy rate of the communication thread exceeds the corresponding threshold value; A running data extraction module is used to retrieve the CPU occupancy rate, memory occupancy rate and queue length change rate of the communication thread from the historical data of the communication thread operation; A saturation evaluation coefficient acquisition module is used to obtain the saturation evaluation coefficient of the communication thread by using the CPU occupancy rate, memory occupancy rate and queue length change rate of the communication thread; The saturation evaluation coefficient of the communication thread is obtained by the following formula: ; Where S represents the saturation evaluation coefficient of the communication thread; n represents the number of unit time experienced in the historical data; C pi 、N pi and D pi They represent the CPU occupancy rate, memory occupancy rate and queue length change rate corresponding to the i-th unit time respectively; C y and N y Respectively represent the preset CPU occupancy threshold and memory occupancy threshold; α, β, v and δ represent the first adjustment coefficient, the second adjustment coefficient, the third adjustment coefficient and the fourth adjustment coefficient, respectively, and the value ranges of the first adjustment coefficient, the second adjustment coefficient, the third adjustment coefficient and the fourth adjustment coefficient are: 0.47-0.73, 0.16-0.39, 0.58-1.13 and 1.32-2.21; A coefficient comparison module, used for comparing the saturation evaluation coefficient of the communication thread with a preset saturation evaluation coefficient threshold; The frame rate adjustment module is used to adjust the frame rate of the smart device used to monitor the video stream data in the room where the user is located in real time when the saturation evaluation coefficient of the communication thread exceeds a preset saturation evaluation coefficient threshold.

[0024] The technical effect of the above technical solution is: through the resource occupancy monitoring module, the CPU occupancy and memory occupancy of the communication thread between the behavior monitoring unit and the data analysis and processing module can be monitored in real time. This real-time monitoring ensures that the system can detect resource usage anomalies in a timely manner and provides basic data for subsequent early warning and adjustment. The occupancy comparison module compares the CPU and memory occupancy monitored in real time with the preset threshold. Once the threshold is exceeded, the historical data retrieval module is triggered to retrieve the historical operation data of the communication thread. This step helps to quickly locate the time period of abnormal resource occupancy and provide a basis for subsequent analysis and adjustment. The operation data extraction module extracts the CPU occupancy, memory occupancy and queue length change rate from the historical data. These three indicators jointly reflect the operation status of the communication thread. Through the analysis of multi-dimensional data, the performance bottleneck of the communication thread can be more comprehensively understood. The saturation evaluation coefficient acquisition module uses the above three indicators to calculate the saturation evaluation coefficient of the communication thread, which is an indicator that comprehensively reflects the operation status of the communication thread. Through the preset formula and adjustment coefficient, the sensitivity of the evaluation coefficient to different indicators can be flexibly adjusted to make it more in line with the needs of actual application scenarios. The coefficient comparison module compares the calculated saturation evaluation coefficient with the preset threshold. Once the threshold is exceeded, the frame rate adjustment module adjusts the frame rate of the smart device. This dynamic adjustment strategy helps to optimize resource usage while ensuring monitoring quality, avoiding system performance degradation caused by excessive resource usage. This technical solution achieves comprehensive management and optimization of communication thread performance through real-time monitoring, early warning, problem location, multi-dimensional data analysis, saturation evaluation and dynamic adjustment. This not only improves the stability and efficiency of the system, but also helps to extend the service life of smart devices and reduce maintenance costs.

[0025] In summary, this technical solution realizes effective monitoring and dynamic adjustment of communication thread performance through a series of modules and strategies, thereby improving the overall performance of the system and user experience.

[0026] Specifically, the frame rate adjustment module includes: A frame rate extraction module, used to extract the current frame rate of the smart device; A saturation evaluation coefficient retrieving module, used to retrieve the saturation evaluation coefficient of the communication thread; Retrieving historical data of the operation of the communication thread, and extracting from the historical data the ratio of the number of messages transmitted by the video data stream communication contained in the message queue per unit time; A frame rate adjustment coefficient acquisition module, used to obtain a frame rate adjustment coefficient by using the frame rate of the smart device, the saturation evaluation coefficient of the communication thread and the ratio of the number of messages transmitted by the video stream data communication contained in the queue length per unit time; The frame rate adjustment coefficient is obtained by the following formula: ; Where K represents the frame rate adjustment coefficient; S represents the saturation evaluation coefficient of the communication thread; S y Indicates the preset saturation evaluation coefficient threshold; F min Indicates the minimum frame rate allowed for shooting; F d represents the current frame rate of the smart device; M represents the ratio of the number of messages transmitted by the video stream data communication contained in the current queue length; M b It represents the standard deviation of the proportion of the number of messages transmitted by the video stream data communication contained in the queue length per unit time; Q represents the ratio of the current queue length to the average queue length; C represents the adjustment coefficient for controlling the influence of the proportion of the number of messages on the frame rate adjustment coefficient, and the value range is 0.21-0.38; B represents the adjustment coefficient for controlling the influence of saturation on the frame rate adjustment coefficient, and the value range is 0.27-0.43: The frame rate adjustment execution module is used to adjust the frame rate of the video in the room where the user is located shot in real time by the current smart device according to the frame rate adjustment coefficient.

[0027] The technical effect of the above technical solution is that the frame rate extraction module can obtain the frame rate of the current smart device in real time, which is the basis for subsequent frame rate adjustment. By accurately controlling the frame rate, the smoothness and clarity of the video picture can be ensured and the user experience can be improved. The saturation evaluation coefficient retrieval module can obtain the saturation evaluation coefficient of the communication thread, which comprehensively reflects the running state of the communication thread. Combined with the proportion of the number of messages transmitted by the video stream data communication contained in the queue length per unit time, the load of the communication thread can be more comprehensively evaluated, providing a reliable basis for frame rate adjustment. The frame rate adjustment coefficient acquisition module uses information such as the current frame rate, the saturation evaluation coefficient of the communication thread and the proportion of the number of messages to calculate the frame rate adjustment coefficient through a preset formula. This coefficient takes into account a variety of factors and can intelligently adjust the frame rate to adapt to different communication loads and video shooting requirements. By introducing the adjustment coefficient C that controls the influence of the proportion of the number of messages on the frame rate adjustment coefficient and the adjustment coefficient B that controls the influence of the saturation on the frame rate adjustment coefficient, the technical solution can flexibly adjust the frame rate adjustment coefficient to adapt to different application scenarios and user needs. This dynamic adaptability helps to improve the stability and efficiency of the system. The frame rate adjustment execution module adjusts the frame rate of the video currently shot by the smart device in real time according to the frame rate adjustment coefficient. By optimizing the frame rate, system resources can be reasonably allocated to avoid resource waste and performance bottlenecks, and the overall performance of the system can be improved. This technical solution can ensure the smoothness and clarity of the video by intelligently adjusting the frame rate, while reducing system resource consumption and improving user experience. This is especially important for application scenarios that require long-term video shooting and transmission.

[0028] In summary, this technical solution achieves dynamic adjustment of the frame rate of videos shot by smart devices through strategies such as precise frame rate control, comprehensive evaluation of communication thread performance, intelligent frame rate adjustment, strong dynamic adaptability and optimized resource utilization, thereby improving the stability and efficiency of the system and optimizing the user experience.

[0029] Specifically, the frame rate adjustment execution module is used to: Extract the frame rate adjustment coefficient; Comparing the frame rate adjustment coefficient with a preset frame rate adjustment coefficient threshold; When the frame rate adjustment coefficient does not exceed the preset frame rate adjustment coefficient threshold, the frame rate of the video captured by the smart device in the room where the user is located in real time is adjusted using the frame rate adjustment coefficient to obtain a first frame rate; The first frame rate is obtained by the following formula: ; Among them, F t01 represents the first frame rate, and when F t01 Less than F min When Ft01 =F min ; F d represents the current frame rate of the smart device; K represents the frame rate adjustment coefficient; Controlling shooting of the smart device according to a first frame rate; When the frame rate adjustment coefficient exceeds a preset frame rate adjustment coefficient threshold, the frame rate adjustment times corresponding to the frame rate adjustment coefficient exceeding the preset frame rate adjustment coefficient threshold in the frame rate adjustment history record are retrieved; Extracting the frame rate value before adjustment and the frame rate value after adjustment corresponding to each frame rate adjustment, as well as the CPU occupancy rate release ratio and the memory occupancy rate release ratio of the communication channel after the frame rate adjustment; Obtaining a second frame rate by using the frame rate value before adjustment and the frame rate value after adjustment corresponding to each frame rate adjustment, as well as the CPU occupancy release ratio and the memory occupancy release ratio of the communication channel after the frame rate adjustment in combination with the frame rate adjustment coefficient; The second frame rate is obtained by the following formula: ; Among them, F t02 represents the second frame rate, and when F t02 Less than F min When F t02 =F min ; F d represents the current frame rate of the smart device; K represents the frame rate adjustment coefficient; m represents the number of frame rate adjustments corresponding to the frame rate adjustment coefficient in the frame rate adjustment history exceeding the preset frame rate adjustment coefficient threshold; F xi and F hi represents the frame rate value before adjustment and the frame rate value after adjustment corresponding to the i-th frame rate adjustment; C si and N si Indicates the CPU occupancy rate release ratio and memory occupancy rate release ratio of the communication channel after the frame rate adjustment corresponding to the i-th frame rate adjustment; The smart device is controlled to shoot according to the second frame rate.

[0030] The technical effect of the above technical solution is that the module can intelligently adjust the frame rate of the video shot by the smart device according to the frame rate adjustment coefficient. When the frame rate adjustment coefficient does not exceed the preset threshold, the first frame rate is directly calculated using the coefficient, and the shooting of the smart device is regulated accordingly. This intelligent adjustment mechanism helps to ensure the smoothness and clarity of the video picture while optimizing the utilization of system resources. When calculating the first frame rate and the second frame rate, a minimum value is set as a protection mechanism. When the calculated frame rate is lower than, it is directly taken as the adjusted frame rate. This helps to ensure that a certain video quality can be maintained even when resources are tight or the load is high. When the frame rate adjustment coefficient exceeds the preset threshold, the module will retrieve the frame rate adjustment history record and use these historical data to calculate the second frame rate. This use of historical data helps to more accurately evaluate the current system status and possible adjustment effects, so as to make more reasonable frame rate adjustment decisions. When calculating the second frame rate, not only the current frame rate adjustment coefficient and the current frame rate are considered, but also the number of historical frame rate adjustments, the frame rate values ​​before and after each adjustment, and the proportion of communication channel resources released after the frame rate adjustment are considered. This multi-dimensional consideration helps to more comprehensively evaluate the impact of frame rate adjustment and ensure that the adjusted system performance is optimized. The module can dynamically adjust the frame rate according to different frame rate adjustment coefficients and system status. This dynamic adaptability helps ensure that the system can maintain stable performance under various load and resource conditions. By intelligently adjusting the frame rate, the module can ensure the smoothness and clarity of the video picture while reducing system resource consumption. This helps to improve the user experience, especially in application scenarios that require long-term video shooting and transmission.

[0031] In summary, this technical solution achieves precise control of the frame rate of videos shot by smart devices through strategies such as intelligent frame rate adjustment, protection of minimum frame rate, utilization of historical data, multi-dimensional considerations, dynamic adaptability and optimization of user experience, thereby improving the stability and efficiency of the system and optimizing the user experience.

[0032] In this embodiment, the data analysis and processing module includes: A behavior pattern analysis unit is used to analyze the user's daily behavior based on the user's behavior characteristics identified by the behavior monitoring unit, and identify the user's behavior patterns and abnormal situations; An environmental parameter analysis unit is used to evaluate the safety index of the home environment based on the safety parameters extracted by the environmental sensing unit, and to generate risk warnings and optimization suggestions based on the evaluation results; The control instruction output unit is used to generate corresponding control instructions based on the output results of the behavior pattern analysis unit and the environmental parameter analysis unit. For example, if an elderly person is detected to have fallen, an instruction is sent to activate the emergency call device or dial a designated number. If the temperature and humidity are not suitable, an instruction is sent to adjust the status of the air conditioner or humidifier. The corresponding smart home devices are controlled based on the Internet of Things to respond and execute operations.

[0033] In this embodiment, the data analysis and processing module further includes: The user health warning unit is used to obtain the user's health data and conduct dynamic analysis in combination with historical health records to predict potential health risks and issue warnings and push them to relevant parties (such as family members, caregivers or medical institutions), such as potential risks such as cardiovascular disease and high blood sugar; The personalized recommendation unit is used to integrate behavioral patterns, environmental parameters and health data into user portraits, including living habits, health trends and environmental needs. According to the user portraits and service needs, personalized recommendation content is generated to the user's mobile terminal, and personalized service suggestions for the living habits and health status of the elderly are pushed, such as: health management: recommending suitable diet plans or exercise plans; life services: reminding users to participate in community activities and make appointments for housekeeping services; environmental optimization: recommending adjustments to the home environment to improve comfort, and dynamically adjusting recommendation strategies based on user feedback.

[0034] In this embodiment, the behavior pattern analysis unit and the environmental parameter analysis unit realize all-round user behavior and environmental monitoring through refined data processing and analysis, can effectively identify the user's behavioral patterns and abnormal situations, effectively improve residential safety and quality of life, can timely identify abnormal behavior and environmental risks, and quickly issue control instructions to ensure that users receive timely assistance in emergency situations, dynamically analyze the user's health data, predict health risks in advance, provide users with personalized health warnings and care suggestions, and provide customized service suggestions based on the user's behavioral habits, health status and environmental needs, thereby enhancing the personalization of services and user satisfaction.

[0035] In this embodiment, the behavior pattern analysis unit identifies the user's behavior patterns and abnormalities, specifically: Obtain the user behavior feature data transmitted by the data acquisition module and the sub-data it carries, including timestamps, location data, and activity types, and pre-process the behavior feature data and sub-data, including cleaning, removing outliers and noise data, and unifying the format to ensure data integrity and consistency; Extracting the time series of the sub-data, sorting the pre-processed behavior feature data based on the time series, establishing a continuous behavior feature time axis, and generating dynamic behavior data; Obtain the activity frequency, activity duration distribution and time pattern of the user's behavior from the dynamic behavior data, such as the morning peak hours and night rest time, etc., and identify the user's main activity range based on the user's activity location data, including the high-frequency stay area in the room; Perform cluster analysis on user activity location data to generate a distribution map of the main activity areas of users, extract the activity time patterns of user behaviors in the distribution map of the main activity areas of users, and identify the periodic characteristics of user behavior patterns; Comparing the dynamic behavior data with preset abnormal behavior data, identifying abnormal behavior characteristics based on the comparison results, such as long-term inactivity or falling, the lower limit of daily activity times and the upper limit of inactivity time, and classifying the abnormal behavior data to generate abnormal categories of the abnormal behavior data; Based on the comparison between the behavioral characteristic data obtained in real time and the historical behavioral habits, the user's current behavior deviation is determined, and whether there is abnormal behavior is analyzed. Based on the analysis results, a user's behavioral characteristic report is generated, updated to the user's behavior file, and updated on a daily, weekly or monthly basis; When abnormal behavior is detected, an abnormal warning report is generated, including the time, location and description information of the abnormal behavior, and the warning report is pushed to the mobile terminal where the user's family or caregiver is located.

[0036] In this embodiment, through time series analysis and the establishment of dynamic behavior data, the frequency, duration distribution and time regularity of user behavior are revealed, the accuracy of behavior pattern recognition is enhanced, the user's main activity area is clarified, and the understanding of user behavior patterns is enhanced. It not only provides timely warning information for the user's family or caregivers, but also promotes personalized care and safety management, thereby significantly improving the user's quality of life and safety.

[0037] In this embodiment, based on the comparison between the behavior feature data acquired in real time and the historical behavior habits, the deviation degree of the user's current behavior is determined, specifically including: Obtain the user's real-time behavior feature data, including activity type, activity time period, activity frequency, activity duration, etc. At the same time, obtain the user's historical behavior data from the historical behavior database, including their daily activity pattern, frequency distribution, preferred behavior, etc. Based on basic data types such as behavior pattern, time period, frequency, etc., compare the real-time behavior data with the historical data item by item; Match the real-time behavior data with the historical behavior habit data, and generate a first target behavior data segment and a second target behavior data segment based on the matching result, wherein the first target behavior data segment is data inconsistent with the historical behavior habit, indicating that the user's current behavior deviates from his historical behavior, and the second target behavior data segment is data consistent with the historical behavior habit, indicating that the user's current behavior is consistent with the historical behavior; Classifying the data in the second target behavior data segment based on the basic data type to generate a number of sub-monitoring data groups, each of which represents a refined behavior pattern and can reflect more specific behavior habits; Extracting data from a plurality of first target behavior data segments as first data samples, and at the same time, randomly extracting data from each sub-monitoring data group as second data samples; The first data sample is read to determine the user's behavioral feature points, such as time distribution, activity frequency, etc., and a first behavioral network of the user is constructed based on the behavioral feature points, which reflects the user's behavioral structure under a specific behavioral mode, and the first target behavior data is deployed to the first behavioral network through the behavioral feature points; Based on the deployment characteristics of the first behavior network, the main patterns and habits of the user's behavior are analyzed to determine the user's first behavior habits. Based on the second data sample, a second behavior network is constructed to simulate and analyze the behavior to identify the user's second behavior habits. Assigning weights to the first behavior habit and the second behavior habit respectively, calculating the first habit weight and the second habit weight corresponding to the user, and scoring the first behavior habit and the second behavior habit respectively according to the habit weights to obtain a first score and a second score; Calculate the user's comprehensive behavior score based on the first score and the second score, compare the comprehensive behavior score with a preset scoring threshold, and determine whether the user's current behavior is consistent with historical behavior habits; If the comprehensive behavior score is equal to or greater than the scoring threshold, the behavior is judged to be consistent with the user's historical behavior habits; if the comprehensive behavior score is less than the scoring threshold, the behavior is judged to be deviant; If the behavior is determined to deviate from the user's historical behavior habits, the degree of deviation is evaluated based on the comprehensive behavior score, and an early warning report is generated, including the specific circumstances of the behavior deviation, the time period of the deviation, and cause analysis.

[0038] In this embodiment, by acquiring the user's behavioral feature data in real time and comparing it with historical behavioral habits, the degree of deviation of the user's behavior can be discovered in a timely manner and accurately evaluated. By comparing historical behavioral habits, a more personalized user behavior analysis can be provided, which helps to better understand the user's characteristics and needs. It not only helps to improve the efficiency of behavior monitoring and early warning, but also provides users with personalized analysis and services, thereby improving user experience. By building a behavioral network, the changing trajectory of user behavior can be traced, providing a basis for analyzing the causes of deviation and providing data support for decision makers.

[0039] In this embodiment, the service request receiving and processing module includes: User management unit, which is used to manage the personal information and service records of all users on the platform, including the user's identity information (such as name, age, contact information), health status, family member information, historical service records, etc.; The request processing unit is used to receive and process service requests from users through the platform, classify and prioritize service requests according to the content of the service requests (such as emergency rescue, life care, health management, etc.), assign them to the service provision module, and track and update the progress of the requests in real time.

[0040] In this embodiment, through the user registration and authentication mechanism, it is ensured that only authorized users can access the platform, and their information files can be automatically updated according to user needs, and real-time updated user data can be maintained. Users submit service requirements through the platform's interactive channels (such as mobile applications, websites or smart terminals) and are tracked in real time to ensure the timeliness and accuracy of service provision, thereby improving user experience.

[0041] In this embodiment, the service providing module includes: Intelligent reminder unit, which is used to send intelligent reminders to users regularly according to their personalized needs and health conditions, including health management (such as medication, regular check-up reminders), life care (such as living, diet suggestions) and environmental control (such as temperature and humidity adjustment, light switches, etc.); The service scheduling unit is used to connect with various service resources in the platform and schedule corresponding service resources according to the user's request and actual needs, combined with the priority sorting of the request content. When a user requests health management services, it automatically schedules suitable health management plans or professional doctors based on their health data and historical records; The call warning unit is used to immediately trigger the emergency call and warning mechanism when receiving abnormal behavior or warning information, and provides a one-key calling function for users to make emergency calls.

[0042] In this embodiment, the intelligent reminder unit automatically adjusts the timeliness and frequency of the reminder content based on the user's behavior patterns and real-time data to ensure that it matches the user's daily habits, and makes dynamic adjustments according to emergencies or deviations in user behavior to promptly remind family members or caregivers. The service scheduling unit can not only handle routine service requests, but also automatically schedule resources according to priority and service availability in an emergency to ensure efficient, accurate and responsive services. It can promptly notify the user's family members, caregivers and emergency rescue teams through a calling mechanism to ensure that users can receive rapid assistance in an emergency.

[0043] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. The integrated home-based elderly care service management system based on the Internet of Things is characterized by: include: Data collection module, which is used to collect real-time user life data at home based on various sensors and smart devices, including health data, environmental data and behavioral data; The data analysis and processing module is used to process and store the collected life data, analyze the user's behavior patterns, identify regular and abnormal behaviors in daily life, predict potential risks based on the identification results, and issue abnormal warnings; The service request receiving and processing module is used to build an interactive channel between the integrated service management platform and the mobile terminal based on the Internet of Things. The integrated service management platform receives the user's service request based on the interactive channel and calls the corresponding service according to the demand; The service provision module is used to provide corresponding comprehensive services based on the user's service request and the behavior analysis results of the data analysis and processing module.

2. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 1, characterized in that: Data acquisition module, including: A user data collection unit, used to monitor the user's health data in real time based on the health monitoring device; The behavior monitoring unit is used to monitor the video stream data in the room where the user is located in real time based on the smart device, extract the user's movement path and activity range in the room based on human body characteristics, and identify the user's behavior characteristics; An environmental sensing unit is used to collect the user's living environment data and extract the safety parameters of the living environment based on the living environment data, including temperature, humidity, air quality and safety hazard data; The home appliance control unit is used to collect and control the operating status data of smart home devices and adjust the operating status of smart home devices based on the user's behavioral characteristics; The security monitoring unit is used to deploy various sensors in the user's living environment, monitor potential security threats in the home environment in real time based on various sensors, and issue early warning prompts for identified potential security threats.

3. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 2, characterized in that: Behavioral monitoring unit, including: A resource occupancy monitoring module, used to monitor in real time the CPU occupancy rate and memory occupancy rate of the communication thread between the behavior monitoring unit and the data analysis and processing module; An occupancy comparison module is used to compare the CPU occupancy and memory occupancy of the communication thread with a preset CPU occupancy threshold and a preset memory occupancy threshold respectively; A historical data retrieval module, used for retrieving the historical data of the communication thread when any one of the CPU occupancy rate and the memory occupancy rate of the communication thread exceeds the corresponding threshold value; A running data extraction module is used to retrieve the CPU occupancy rate, memory occupancy rate and queue length change rate of the communication thread from the historical data of the communication thread operation; A saturation evaluation coefficient acquisition module is used to obtain the saturation evaluation coefficient of the communication thread by using the CPU occupancy rate, memory occupancy rate and queue length change rate of the communication thread; The saturation evaluation coefficient of the communication thread is obtained by the following formula: ； Where S represents the saturation evaluation coefficient of the communication thread; n represents the number of unit time experienced in the historical data; C pi 、N pi and D pi They represent the CPU occupancy rate, memory occupancy rate and queue length change rate corresponding to the i-th unit time respectively; C y and N y Respectively represent the preset CPU occupancy threshold and memory occupancy threshold; α, β, v and δ represent the first adjustment coefficient, the second adjustment coefficient, the third adjustment coefficient and the fourth adjustment coefficient, respectively, and the value ranges of the first adjustment coefficient, the second adjustment coefficient, the third adjustment coefficient and the fourth adjustment coefficient are: 0.47-0.73, 0.16-0.39, 0.58-1.13 and 1.32-2.21; A coefficient comparison module, used for comparing the saturation evaluation coefficient of the communication thread with a preset saturation evaluation coefficient threshold; The frame rate adjustment module is used to adjust the frame rate of the smart device used to monitor the video stream data in the room where the user is located in real time when the saturation evaluation coefficient of the communication thread exceeds a preset saturation evaluation coefficient threshold.

4. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 3, characterized in that: Frame rate adjustment module, including: A frame rate extraction module, used to extract the current frame rate of the smart device; A saturation evaluation coefficient retrieving module, used to retrieve the saturation evaluation coefficient of the communication thread; Retrieving historical data of the operation of the communication thread, and extracting from the historical data the ratio of the number of messages transmitted by the video data stream communication contained in the message queue per unit time; A frame rate adjustment coefficient acquisition module, used to obtain a frame rate adjustment coefficient by using the frame rate of the smart device, the saturation evaluation coefficient of the communication thread and the ratio of the number of messages transmitted by the video stream data communication contained in the queue length per unit time; The frame rate adjustment coefficient is obtained by the following formula: ； Where K represents the frame rate adjustment coefficient; S represents the saturation evaluation coefficient of the communication thread; S y Indicates the preset saturation evaluation coefficient threshold; F min Indicates the minimum frame rate allowed for shooting; F d represents the current frame rate of the smart device; M represents the ratio of the number of messages transmitted by the video stream data communication contained in the current queue length; M b It represents the standard deviation of the proportion of the number of messages transmitted by the video stream data communication contained in the queue length per unit time; Q represents the ratio of the current queue length to the average queue length; C represents the adjustment coefficient for controlling the influence of the proportion of the number of messages on the frame rate adjustment coefficient, and the value range is 0.21-0.38; B represents the adjustment coefficient for controlling the influence of saturation on the frame rate adjustment coefficient, and the value range is 0.27-0.43: The frame rate adjustment execution module is used to adjust the frame rate of the video in the room where the user is located shot in real time by the current smart device according to the frame rate adjustment coefficient.

5. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 4, characterized in that: The frame rate adjustment execution module is used to: Extract the frame rate adjustment coefficient; Comparing the frame rate adjustment coefficient with a preset frame rate adjustment coefficient threshold; When the frame rate adjustment coefficient does not exceed the preset frame rate adjustment coefficient threshold, the frame rate of the video captured by the smart device in the room where the user is located in real time is adjusted using the frame rate adjustment coefficient to obtain a first frame rate; The first frame rate is obtained by the following formula: ； Among them, F t01 represents the first frame rate, and when F t01 Less than F min When F t01 =F min ; F d represents the current frame rate of the smart device; K represents the frame rate adjustment coefficient; Controlling shooting of the smart device according to a first frame rate; When the frame rate adjustment coefficient exceeds a preset frame rate adjustment coefficient threshold, the frame rate adjustment times corresponding to the frame rate adjustment coefficient exceeding the preset frame rate adjustment coefficient threshold in the frame rate adjustment history record are retrieved; Extracting the frame rate value before adjustment and the frame rate value after adjustment corresponding to each frame rate adjustment, as well as the CPU occupancy rate release ratio and the memory occupancy rate release ratio of the communication channel after the frame rate adjustment; Obtaining a second frame rate by using the frame rate value before adjustment and the frame rate value after adjustment corresponding to each frame rate adjustment, as well as the CPU occupancy release ratio and the memory occupancy release ratio of the communication channel after the frame rate adjustment in combination with the frame rate adjustment coefficient; The second frame rate is obtained by the following formula: ； Among them, F t02 represents the second frame rate, and when F t02 Less than F min When F t02 =F min ; F d represents the current frame rate of the smart device; K represents the frame rate adjustment coefficient; m represents the number of frame rate adjustments corresponding to the frame rate adjustment coefficient in the frame rate adjustment history exceeding the preset frame rate adjustment coefficient threshold; F xi and F hi represents the frame rate value before adjustment and the frame rate value after adjustment corresponding to the i-th frame rate adjustment; C si and N si Indicates the CPU occupancy rate release ratio and memory occupancy rate release ratio of the communication channel after the frame rate adjustment corresponding to the i-th frame rate adjustment; The smart device is controlled to shoot according to the second frame rate.

6. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 2, characterized in that: Data analysis and processing module, including: A behavior pattern analysis unit is used to analyze the user's daily behavior based on the user's behavior characteristics identified by the behavior monitoring unit, and identify the user's behavior patterns and abnormal situations; An environmental parameter analysis unit is used to evaluate the safety index of the home environment based on the safety parameters extracted by the environmental sensing unit, and to generate risk warnings and optimization suggestions based on the evaluation results; The control instruction output unit is used to generate corresponding control instructions based on the output results of the behavior pattern analysis unit and the environmental parameter analysis unit, and control the corresponding smart home devices to respond and perform operations based on the Internet of Things.

7. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 6, characterized in that: The data analysis and processing module also includes: The user health warning unit is used to obtain the user's health data and conduct dynamic analysis in combination with historical health records to predict potential health risks and issue warnings; The personalized recommendation unit is used to integrate behavioral patterns, environmental parameters and health data into user portraits, and generate personalized recommendation content to the user's mobile terminal based on the user portrait and service needs.

8. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 7, characterized in that: The behavior pattern analysis unit identifies the user's behavior patterns and anomalies, specifically: Acquire the user behavior characteristic data and the sub-data carried by the data acquisition module, and pre-process the behavior characteristic data and the sub-data; Extracting the time series of the sub-data, sorting the pre-processed behavior feature data based on the time series, establishing a continuous behavior feature time axis, and generating dynamic behavior data; Obtain the activity frequency, activity duration distribution and time regularity of the user's behavior from the dynamic behavior data, and identify the user's main activity range based on the user's activity location data; Perform cluster analysis on user activity location data to generate a distribution map of the main user activity areas, extract the activity time patterns of user behavior in the distribution map of the main user activity areas, and identify the periodic characteristics of user behavior patterns; Comparing the dynamic behavior data with preset abnormal behavior data, identifying abnormal behavior features based on the comparison results, and classifying the abnormal behavior data to generate abnormal categories of the abnormal behavior data; Based on the comparison between the behavioral feature data obtained in real time and historical behavioral habits, the user's current behavior deviation degree is determined, and whether there is abnormal behavior is analyzed. The user's behavioral feature report is generated based on the analysis results; When abnormal behavior is detected, an abnormal warning report is generated, including the time, location and description information of the abnormal behavior, and the warning report is pushed to the mobile terminal where the user's family or caregiver is located.

9. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 8, characterized in that: Based on the comparison between the behavioral feature data obtained in real time and the historical behavioral habits, the deviation degree of the user's current behavior is determined, including: Obtain the user's real-time behavior feature data, and at the same time, obtain the user's historical behavior data from the historical behavior database, and compare the real-time behavior data with the historical data item by item based on the basic data type; Matching the real-time behavior data with the historical behavior habit data, and generating a first target behavior data segment and a second target behavior data segment based on the matching result, wherein the first target behavior data segment is data inconsistent with the historical behavior habit, and the second target behavior data segment is data consistent with the historical behavior habit; Classifying the data in the second target behavior data segment based on the basic data type to generate a plurality of sub-monitoring data groups; Extracting data from a plurality of first target behavior data segments as first data samples, and at the same time, randomly extracting data from each sub-monitoring data group as second data samples; Reading the first data sample, determining the user's behavior feature points, building the user's first behavior network based on the behavior feature points, and deploying the first target behavior data to the first behavior network through the behavior feature points; Based on the deployment characteristics of the first behavior network, the main patterns and habits of the user's behavior are analyzed to determine the user's first behavior habits. Based on the second data sample, a second behavior network is constructed to simulate and analyze the behavior to identify the user's second behavior habits. Assigning weights to the first behavior habit and the second behavior habit respectively, calculating the first habit weight and the second habit weight corresponding to the user, and scoring the first behavior habit and the second behavior habit respectively according to the habit weights to obtain a first score and a second score; Calculate the user's comprehensive behavior score based on the first score and the second score, compare the comprehensive behavior score with a preset scoring threshold, and determine whether the user's current behavior is consistent with historical behavior habits; If the comprehensive behavior score is equal to or greater than the scoring threshold, the behavior is judged to be consistent with the user's historical behavior habits; if the comprehensive behavior score is less than the scoring threshold, the behavior is judged to be deviant; If the behavior is determined to deviate from the user's historical behavior habits, the degree of deviation is evaluated based on the comprehensive behavior score and an early warning report is generated.

10. The integrated home-based elderly care service management system based on the Internet of Things as claimed in claim 9, characterized in that: The service request receiving and processing module includes: User management unit, used to manage the personal information and service records of all users on the platform; The request processing unit is used to receive and process service requests from users through the platform, classify and prioritize the service requests according to their content, assign them to the service provision module, and track and update the progress of the requests in real time; Service provision modules include: Intelligent reminder unit, used to send intelligent reminders to users regularly according to their personalized needs and health conditions, including health management, life care and environmental control; The service scheduling unit is used to connect with various service resources in the platform and schedule corresponding service resources according to the user's request and actual needs, combined with the priority sorting of the request content; The call warning unit is used to immediately trigger the emergency call and warning mechanism when receiving abnormal behavior or warning information, and provides a one-key calling function for users to make emergency calls.

Images