Community safety supervision system and method based on internet of things

Abstract

The application discloses a community safety supervision system and method based on Internet of Things, relates to the technical field of community safety supervision, and identifies and classifies personnel entering a community, records time points of the personnel entering and exiting the community, obtains the number of the personnel entering the community based on the time points of the personnel entering and exiting the community, calls dispute history records of a monitoring area, analyzes the influence degree of the personnel entering the community on the dispute, marks the monitoring area, analyzes the regional risk of the monitoring area, analyzes the prediction regional risk of a power equipment maintenance date based on the regional risk of the monitoring area, thereby analyzes the best time point of power cut starting, adjusts the key security area of security personnel with time, and based on Internet of Things, the security personnel and the community center transmit information to each other, the application realizes the organic combination of technical means and human prevention and control through a historical data modeling and risk prediction mechanism, and reduces community risks caused by power cut.

Description

Technical Field

[0001] This invention relates to the field of community safety supervision technology, specifically to a community safety supervision system and method based on the Internet of Things. Background Technology

[0002] With the acceleration of urbanization and the increasing complexity of community populations, traditional security management models are gradually revealing their limitations. On the one hand, the lack of dynamic analysis of dwell time and behavioral patterns makes it difficult to accurately identify potential high-risk individuals. Abnormal stay times of temporary visitors and unregistered personnel entering and exiting freely often fail to prompt timely intervention due to a lack of real-time data, leading to the accumulation of security risks. On the other hand, community risk assessments are largely based on experience-based judgments, lacking quantitative analysis of historical data. This makes it difficult to scientifically define the security risk levels of different areas and groups, resulting in an uneven distribution of security resources. High-risk areas are not prioritized, while low-risk areas suffer resource waste, leading to insufficient overall management efficiency and targeting. Furthermore, in unconventional scenarios such as power maintenance and equipment failures, traditional management models lack forward-looking risk prediction and systematic response strategies. Issues such as monitoring failures and delayed manpower deployment often create security management vacuums, failing to effectively guarantee the safety and stability of the community under special circumstances. While the widespread adoption of IoT technology provides a new path for upgrading community security supervision, emergency response relies on manual patrols and hierarchical reporting, resulting in significant information transmission delays. When sudden security incidents occur, it is often difficult to quickly locate the problem area and respond to the situation, impacting incident handling efficiency. Furthermore, traditional methods for utilizing historical data are limited to simple statistics, failing to delve into the intrinsic connections between personnel composition, behavioral patterns, and safety incidents. This makes it difficult to construct dynamic risk prediction models and provide a scientific basis for management decisions. In particular, when dealing with scenarios requiring advance planning, such as power outages, there is a lack of quantitative analysis tools to guide the selection of the optimal solution. Summary of the Invention

[0003] The purpose of this invention is to provide a community safety monitoring system and method based on the Internet of Things to solve the problems mentioned in the background art.

[0004] To address the aforementioned technical problems, this invention provides the following technical solution: a community security supervision method based on the Internet of Things, comprising the following steps: S1. Identify and classify people entering the community, and record the time points when people enter and leave the community; S2. Based on the time points when community personnel enter and exit the community, obtain the number of personnel entering the community, retrieve the historical dispute records of the monitored area, and analyze the degree of influence of personnel entering the community on disputes; S3. Mark the monitoring area and analyze the regional risk of the monitoring area based on the degree of impact of people entering the community on disputes; S4. Based on the regional risk of the monitored area, analyze the predicted regional risk of the maintenance date of power equipment, and thus analyze the optimal time point for the start of the power outage; S5. After determining the optimal time for the power outage to begin, adjust the key security areas for security personnel over time. S6. Based on the Internet of Things, security personnel and community centers transmit information to each other.

[0005] Furthermore, in step S1, after authorization, the cameras installed at the community entrances and exits identify people entering the community, record the time of entry, and identify and mark them as community residents and visitors. The system continues to analyze visitors, setting a stay duration threshold T, and prompting visitors to register their expected stay duration. Visitors whose stay duration is less than the expected stay duration from the time of entry are marked as normal visitors. Visitors whose stay duration is greater than the expected stay duration but less than the sum of the expected stay duration and T are marked as overstaying visitors. Otherwise, they are marked as lingering visitors. With the help of entrance and exit camera recognition technology, community residents and visitors can be accurately distinguished. Visitors are dynamically classified into different risk categories based on their stay status, enabling management to quickly identify high-risk individuals with abnormal stay durations, intervene in advance for verification, reduce potential safety hazards from the source, and change the lag of traditional extensive management.

[0006] Furthermore, in step 2, X sets of historical community dispute data occurring in the community's public area are retrieved, the dispute locations are marked, and the community's public area is divided into N monitoring areas of equal size. The xth set of historical community dispute data is analyzed, where x = 1, 2, ..., X. When the xth set of historical community disputes occurs, the personnel information within the monitoring area where the xth set of historical community disputes occurs is retrieved, where the number of community personnel is A. x The number of people staying normally is B. x The number of people staying beyond the allotted time is C. x The number of stranded migrant workers is D. x The system retrieves personnel monitoring data from the xth community at the time of the historical disputes, including: the number of community members a in public areas of the community. x The number of people staying normally in the community (b) x The number of people staying in the community beyond their permitted time (c) x The number of stranded migrant workers in the community d x This leads to the influence coefficient k of community members on the xth dispute. x-a =A x / a x The influence coefficient k of normal stay personnel on the xth dispute x-b =B x / bx The influence coefficient k of overstaying personnel on the xth dispute. x-c =C x / c x The influence coefficient k of stranded migrant workers on the xth dispute x-d =D x / d x Substitute each value into x = 1, 2, ..., X to obtain the influence coefficients {k} of community personnel in the public area on X disputes. 1-a ,k 2-a ,…,k x-a ,…,k X-a The influence coefficient of normal stay personnel on X disputes {k} 1-b ,k 2-b ,…,k x-b ,…,k X-b The influence coefficient {k} of overstaying personnel on X disputes. 1-c ,k 2-c ,…,k x-c ,…,k X-c The influence coefficient {k} of stranded migrant workers on X disputes. 1-d ,k 2-d ,…,k x-d ,…,k X-d}, and thus obtain the average influence coefficient K of community personnel in public areas on X disputes. a The average influence coefficient K of normal stay personnel on X disputes b The average impact coefficient K of overstaying personnel on X disputes. c The average impact coefficient K of stranded migrant workers on X disputes d By mining the value of historical dispute data, a scientific quantitative basis for community safety risk assessment is provided. By dividing public areas into several monitoring zones and linking them to historical dispute locations, the system can specifically analyze the distribution of different personnel types within each zone and their correlation with the occurrence of disputes. Specifically, by calculating the ratio of the actual proportion of community residents, normally staying visitors, overstaying visitors, and stranded visitors at the time of a dispute to the overall proportion, the system can quantify the impact of various groups on safety incidents, forming differentiated risk weight indicators. A higher average influence coefficient for a certain group indicates that their actual participation in dispute scenarios is higher than their usual proportion, requiring focused attention. This data-driven analysis mechanism transforms abstract safety risks into comparable quantitative indicators, enabling community management to clearly identify the structure and regional distribution characteristics of high-risk groups. This changes the traditional vague management model that relies on experience-based judgment, achieving early identification of potential risks and precise allocation of resources, thus improving the scientific nature, predictability, and overall effectiveness of community safety management.

[0007] Furthermore, in step S3, N monitoring areas are marked as {H1, H2, ..., H...} n ,…,H N}, at any given time, the monitored area H n Analysis was conducted to determine the number of community residents (a) within the monitored area. n The number of people staying normally is b n The number of people staying beyond the allotted time is c. n The number of stranded migrant workers is d n Then the monitoring area H at the time point n The regional risk value is J n =K a *a n +K b *b n +K c *c n +K d *d n .

[0008] Furthermore, in step S4, T time points with equal intervals are marked as monitoring time points. When a power equipment maintenance notification is received, the power equipment maintenance notification includes the power outage date and outage duration Z caused by the power equipment maintenance. The monitoring area Y days before the power equipment maintenance date is called up, and the regional risk value of the nth monitoring area at the t-th monitoring time point on the y-th day is J. n-t-y Then, the predicted regional risk value J of the nth monitoring area at the t-th monitoring time point of the power equipment maintenance date is calculated. n-t : ; Therefore, the predicted regional risk value of the nth monitoring area at the Tth monitoring time point of the power equipment maintenance date can be obtained as {J}. n-1 J n-2 ,…,J n-t ,…,J n-T The predicted regional risk value of N monitoring areas at the t-th monitoring time point of the power equipment maintenance date is {J}. 1-t J 2-t ,…,J n-t ,…,J N-t}; The predicted community risk value at the t-th monitoring time point of the power equipment maintenance date is calculated as J. t The J t For set {J 1-t J 2-t ,…,J n-t ,…,J N-t The average value of} is used to calculate the estimated risk j during the power outage period starting from the αth monitoring time point.α : ; Where α is the monitoring time point before the power outage begins, β is the monitoring time point after the power outage ends, the total time interval between monitoring time points α and β is greater than or equal to the power outage duration Z, and 1 ≤ α < β ≤ T. Substituting these values ​​into α = 1, 2, ..., T-1, we obtain the risk estimates {j1, j2, ..., j...} for power outages starting from time points α = 1, 2, ..., T-1 respectively. T-1 The system selects the time point with the lowest estimated risk as the start time for the power outage. Through a risk prediction mechanism driven by historical data, it provides intelligent decision support for safety management in special community scenarios. When power outages are necessary for equipment maintenance, the system scientifically predicts the safety risks at different times on the outage date based on regional risk data from multiple historical days, changing the traditional "randomly scheduled" outage model. By calculating the estimated risk for different outage start times, the system can prioritize initiating the outage process during the lowest-risk period, effectively avoiding blind spots in safety management caused by monitoring equipment failure, such as avoiding outages during periods of high concentration of stranded personnel or historical disputes. Simultaneously, combined with the predicted regional risk value, the system can pre-delineate key security areas during the outage, guiding security forces to strengthen patrols and controls in a targeted manner. This allows for precise supplementary measures to manual prevention and control under the limitations of technical equipment, ensuring the smooth progress of power maintenance and other work. Through risk avoidance and resource optimization, it significantly improves the community's safety capabilities under unconventional conditions, ensuring seamless safety management during power outages, minimizing the probability of unexpected events, and enhancing the community's resilience and intelligence in complex scenarios.

[0009] Furthermore, in step S5, by substituting t=α,α+1,…,β one by one, the predicted area risk value of the nth monitored area at the β-α+1th monitoring time point during the power outage is obtained as {J n-α J n-(α+1) ,…,J n-(α+2) ,…,J n-β When the power outage begins, the predicted risk value of the N monitored areas at the α-th monitoring time point is {J}. 1-α J 2-α ,…,J n-α ,…,J N-α The m monitoring areas with the highest predicted risk values ​​are selected as key security areas at time point α. Before time point α+1, security personnel must report the security status of each monitoring area to the community center at least γ times; otherwise, a security anomaly alarm will be triggered at time point α+1. The security status is either normal or abnormal. At time point α+1, the predicted risk value of the N monitoring areas at time point α+1 is {J}.1-(α+1) J 2-(α+1) ,…,J n-(α+1) ,…,J N-(α+1) The system selects the m monitoring areas with the highest predicted risk values ​​as key security areas at time point α+1. Before time point α+2, security personnel must report the security status of each monitoring area to the community center at least γ times; otherwise, a security anomaly alarm will be triggered at time point α+2. This process continues until time point β, when power equipment maintenance is completed. Through dynamic risk assessment and precise prevention and control mechanisms, the community's safety management efficiency in special scenarios such as power outages is significantly improved. Based on the predicted risk values ​​at each time point during a power outage, several areas with the highest risk are selected in real time as key security areas, enabling security forces to focus on high-risk areas and avoiding blind spots caused by resource dispersion. The high-frequency reporting mechanism ensures real-time synchronization of on-site conditions. Security personnel must report the area's dynamics at a prescribed frequency. If a reporting delay or anomaly occurs, the system immediately triggers an alarm, significantly shortening the time difference between risk discovery and response. This closed-loop management model, which combines prediction, positioning, and strong control, effectively compensates for the shortcomings of technical equipment failure during power outages. Through the collaboration of manual intervention and data-driven approaches, dynamic monitoring and immediate handling of high-risk areas are achieved. In practical application, this mechanism can ensure that there are no gaps in community safety management during power outages, reduce the probability of safety accidents caused by lack of monitoring, and increase residents' trust in community security in special scenarios, demonstrating the accuracy and reliability of smart management in emergency prevention and control.

[0010] Furthermore, in step S6, security personnel contact the community center via the Internet of Things (IoT). After receiving information about key security areas, the community center transmits this information to the security personnel via the IoT. When a security anomaly alarm is triggered, the community center locates the security personnel's position via the IoT. By leveraging IoT technology, an efficient security collaborative management system is built, significantly improving the response speed and dispatch accuracy of community security and prevention, ensuring that security forces are always precisely matched with risk areas, enhancing the real-time nature and reliability of community security management, and creating a safer living environment for residents.

[0011] A community security monitoring system based on the Internet of Things (IoT) includes: a personnel access management module, a dispute impact analysis module, a regional risk assessment module, a power maintenance time planning module, a security area dynamic dispatching module, and an IoT information exchange module. The personnel access management module is used to identify and classify personnel entering the community and record the time points when personnel enter and exit the community; The dispute impact analysis module is used to obtain the number of people entering the community based on the time points when people enter and leave the community, call up the historical dispute records of the monitored area, and analyze the degree of impact of people entering the community on disputes. The regional risk assessment module is used to mark monitoring areas and analyze the regional risks of the monitoring areas based on the degree of impact of people entering the community on disputes. The power maintenance time planning module is used to analyze the predicted regional risk of power equipment maintenance dates based on the regional risk of the monitored area, thereby analyzing the optimal time point for the power outage to begin. The security area dynamic scheduling module is used to adjust the key security areas of security personnel over time after determining the optimal time point for the power outage to begin. The IoT information exchange module is used to enable security personnel and community centers to transmit information to each other based on the Internet of Things.

[0012] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: Firstly, by deploying camera recognition technology at community entrances and exits, it is possible to effectively distinguish between community residents and outsiders, and dynamically mark outsiders based on their stay duration, categorizing them into three types: those staying normally, those staying beyond the permitted time, and those lingering. This classification method allows community management to quickly identify individuals who may pose a security risk, and to focus on or investigate outsiders with abnormally long stay times, reducing potential risks at the source. Simultaneously, by combining historical dispute data to calculate the impact coefficient of different groups on disputes, the risk weight of various personnel in security incidents is further quantified. This enables the community to accurately calculate the risk value of each area based on real-time personnel distribution, prioritizing security resources in high-risk areas. This changes the traditional management model, achieving a shift from passive response to proactive prevention, and effectively improving the targeting and effectiveness of community security management.

[0013] On the one hand, historical data modeling and risk prediction mechanisms provide a scientific basis for safety management in special community scenarios. When power outages are necessary for equipment maintenance, the system uses historical monitoring data from multiple days to predict regional risk values ​​at various times on the outage date. By calculating the estimated risk at different outage start times, the system selects the time with the lowest risk to initiate the outage process. This mechanism effectively avoids potential safety hazards caused by power outages during high-risk periods and prevents security management loopholes due to monitoring equipment malfunctions during periods of high concentration of stranded visitors or historical disputes. Simultaneously, during power outages, key security areas are dynamically determined based on predicted regional risk values, and on-site control is strengthened by setting reporting frequencies for security personnel. This ensures that even when technical equipment is temporarily unavailable, community safety can still be accurately guaranteed through manual intervention, achieving an organic combination of technological means and human control, and enhancing the community's safety assurance capabilities under unconventional conditions.

[0014] On the other hand, the collaborative management model based on IoT technology has comprehensively improved the intelligence level of community security supervision and emergency response efficiency. Through the IoT platform, cameras, access control systems, power equipment, and security personnel's terminal devices within the community achieve real-time data sharing and coordinated response. When the system triggers a security anomaly alarm, the community center can use the IoT to locate the security personnel in real time and quickly dispatch nearby forces to handle the situation, shortening the emergency response time. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a structural diagram of a community safety monitoring system based on the Internet of Things according to the present invention; Figure 2 This is a flowchart of a community safety supervision method based on the Internet of Things according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 and Figure 2 This invention provides a technical solution: a community safety supervision method based on the Internet of Things, comprising the following steps: S1. Identify and classify people entering the community, and record the time points when people enter and leave the community; S2. Based on the time points when community personnel enter and exit the community, obtain the number of personnel entering the community, retrieve the historical dispute records of the monitored area, and analyze the degree of influence of personnel entering the community on disputes; S3. Mark the monitoring area and analyze the regional risk of the monitoring area based on the degree of impact of people entering the community on disputes; S4. Based on the regional risk of the monitored area, analyze the predicted regional risk of the maintenance date of power equipment, and thus analyze the optimal time point for the start of the power outage; S5. After determining the optimal time for the power outage to begin, adjust the key security areas for security personnel over time. S6. Based on the Internet of Things, security personnel and community centers transmit information to each other.

[0018] In step S1, after authorization, the cameras installed at the community entrances and exits identify people entering the community, record the time of entry, and identify and mark them as community residents or visitors. The system then analyzes visitors, sets a stay duration threshold T, and prompts visitors to register their expected stay duration. Visitors whose stay duration is less than the expected stay duration from the time of entry are marked as normal visitors. Visitors whose stay duration is greater than the expected stay duration but less than the sum of the expected stay duration and T are marked as overstaying visitors. Otherwise, they are marked as lingering visitors. By using the entrance and exit camera recognition technology, community residents and visitors can be accurately distinguished. Visitors are dynamically categorized into different risk classes based on their stay status, enabling management to quickly identify high-risk individuals with abnormal stay durations, intervene early for verification, reduce potential safety hazards from the source, and change the sluggishness of traditional extensive management.

[0019] In step 2, X sets of historical community dispute data that occurred in the community's public area are retrieved, the dispute locations are marked, and the community's public area is divided into N monitoring areas of equal size. The xth set of historical community dispute data is analyzed, where x = 1, 2, ..., X. When the xth set of historical community disputes occurs, the personnel information within the monitoring area where the xth set of historical community disputes occurs is retrieved, where the number of community personnel is A. x The number of people staying normally is B. x The number of people staying beyond the allotted time is C. x The number of stranded migrant workers is D. x The system retrieves personnel monitoring data from the xth community at the time of the historical disputes, including: the number of community members a in public areas of the community. x The number of people staying normally in the community (b) x The number of people staying in the community beyond their permitted time (c) x The number of stranded migrant workers in the community d x This leads to the influence coefficient k of community members on the xth dispute. x-a =A x / a x The influence coefficient k of normal stay personnel on the xth dispute x-b =B x / b x The influence coefficient k of overstaying personnel on the xth dispute. x-c =C x / c x The influence coefficient k of stranded migrant workers on the xth dispute x-d =D x / d x Substitute each value into x = 1, 2, ..., X to obtain the influence coefficients {k} of community personnel in the public area on X disputes.1-a ,k 2-a ,…,k x-a ,…,k X-a The influence coefficient of normal stay personnel on X disputes {k} 1-b ,k 2-b ,…,k x-b ,…,k X-b The influence coefficient {k} of overstaying personnel on X disputes. 1-c ,k 2-c ,…,k x-c ,…,k X-c The influence coefficient {k} of stranded migrant workers on X disputes. 1-d ,k 2-d ,…,k x-d ,…,k X-d}, and thus obtain the average influence coefficient K of community personnel in public areas on X disputes. a The average influence coefficient K of normal stay personnel on X disputes b The average impact coefficient K of overstaying personnel on X disputes. c The average impact coefficient K of stranded migrant workers on X disputes d By mining the value of historical dispute data, a scientific quantitative basis for community safety risk assessment is provided. By dividing public areas into several monitoring zones and linking them to historical dispute locations, the system can specifically analyze the distribution of different personnel types within each zone and their correlation with the occurrence of disputes. Specifically, by calculating the ratio of the actual proportion of community residents, normally staying visitors, overstaying visitors, and stranded visitors at the time of a dispute to the overall proportion, the system can quantify the impact of various groups on safety incidents, forming differentiated risk weight indicators. A higher average influence coefficient for a certain group indicates that their actual participation in dispute scenarios is higher than their usual proportion, requiring focused attention. This data-driven analysis mechanism transforms abstract safety risks into comparable quantitative indicators, enabling community management to clearly identify the structure and regional distribution characteristics of high-risk groups. This changes the traditional vague management model that relies on experience-based judgment, achieving early identification of potential risks and precise allocation of resources, thus improving the scientific nature, predictability, and overall effectiveness of community safety management.

[0020] In step S3, N monitoring areas are marked as {H1, H2, ..., H...} n ,…,H N}, at any given time, the monitored area H n Analysis was conducted to determine the number of community residents (a) within the monitored area. n The number of people staying normally is b n The number of people staying beyond the allotted time is c. n The number of stranded migrant workers is dn Then the monitoring area H at the time point n The regional risk value is J n =K a *a n +K b *b n +K c *c n +K d *d n .

[0021] In step S4, T time points with equal intervals are marked as monitoring time points. When a power equipment maintenance notification is received, the notification includes the power outage date and duration Z caused by the maintenance. The monitoring area Y days before the power equipment maintenance date is retrieved, and the regional risk value of the nth monitoring area at the t-th monitoring time point on the y-th day is J. n-t-y Then, the predicted regional risk value J of the nth monitoring area at the t-th monitoring time point of the power equipment maintenance date is calculated. n-t : ; Therefore, the predicted regional risk value of the nth monitoring area at the Tth monitoring time point of the power equipment maintenance date can be obtained as {J}. n-1 J n-2 ,…,J n-t ,…,J n-T The predicted regional risk value of N monitoring areas at the t-th monitoring time point of the power equipment maintenance date is {J}. 1-t J 2-t ,…,J n-t ,…,J N-t}; The predicted community risk value at the t-th monitoring time point of the power equipment maintenance date is calculated as J. t The J t For set {J 1-t J 2-t ,…,J n-t ,…,J N-t The average value of} is used to calculate the estimated risk j during the power outage period starting from the αth monitoring time point. α : ; Where α is the monitoring time point before the power outage begins, β is the monitoring time point after the power outage ends, the total time interval between monitoring time points α and β is greater than or equal to the power outage duration Z, and 1 ≤ α < β ≤ T. Substituting these values ​​into α = 1, 2, ..., T-1, we obtain the risk estimates {j1, j2, ..., j...} for power outages starting from time points α = 1, 2, ..., T-1 respectively.T-1 The system selects the time point with the lowest estimated risk as the start time for the power outage. Through a risk prediction mechanism driven by historical data, it provides intelligent decision support for safety management in special community scenarios. When power outages are necessary for equipment maintenance, the system scientifically predicts the safety risks at different times on the outage date based on regional risk data from multiple historical days, changing the traditional "randomly scheduled" outage model. By calculating the estimated risk for different outage start times, the system can prioritize initiating the outage process during the lowest-risk period, effectively avoiding blind spots in safety management caused by monitoring equipment failure, such as avoiding outages during periods of high concentration of stranded personnel or historical disputes. Simultaneously, combined with the predicted regional risk value, the system can pre-delineate key security areas during the outage, guiding security forces to strengthen patrols and controls in a targeted manner. This allows for precise supplementary measures to manual prevention and control under the limitations of technical equipment, ensuring the smooth progress of power maintenance and other work. Through risk avoidance and resource optimization, it significantly improves the community's safety capabilities under unconventional conditions, ensuring seamless safety management during power outages, minimizing the probability of unexpected events, and enhancing the community's resilience and intelligence in complex scenarios.

[0022] In step S5, substituting t=α,α+1,…,β one by one, the predicted area risk value of the nth monitoring area at the β-α+1th monitoring time point during the power outage is obtained as {J n-α J n-(α+1) ,…,J n-(α+2) ,…,J n-β When the power outage begins, the predicted risk value of the N monitored areas at the α-th monitoring time point is {J}. 1-α J 2-α ,…,J n-α ,…,J N-α The m monitoring areas with the highest predicted risk values ​​are selected as key security areas at time point α. Before time point α+1, security personnel must report the security status of each monitoring area to the community center at least γ times; otherwise, a security anomaly alarm will be triggered at time point α+1. The security status is either normal or abnormal. At time point α+1, the predicted risk value of the N monitoring areas at time point α+1 is {J}. 1-(α+1) J 2-(α+1) ,…,J n-(α+1) ,…,J N-(α+1)The system selects the m monitoring areas with the highest predicted risk values ​​as key security areas at time point α+1. Before time point α+2, security personnel must report the security status of each monitoring area to the community center at least γ times; otherwise, a security anomaly alarm will be triggered at time point α+2. This process continues until time point β, when power equipment maintenance is completed. Through dynamic risk assessment and precise prevention and control mechanisms, the community's safety management efficiency in special scenarios such as power outages is significantly improved. Based on the predicted risk values ​​at each time point during a power outage, several areas with the highest risk are selected in real time as key security areas, enabling security forces to focus on high-risk areas and avoiding blind spots caused by resource dispersion. The high-frequency reporting mechanism ensures real-time synchronization of on-site conditions. Security personnel must report the area's dynamics at a prescribed frequency. If a reporting delay or anomaly occurs, the system immediately triggers an alarm, significantly shortening the time difference between risk discovery and response. This closed-loop management model, which combines prediction, positioning, and strong control, effectively compensates for the shortcomings of technical equipment failure during power outages. Through the collaboration of manual intervention and data-driven approaches, dynamic monitoring and immediate handling of high-risk areas are achieved. In practical application, this mechanism can ensure that there are no gaps in community safety management during power outages, reduce the probability of safety accidents caused by lack of monitoring, and increase residents' trust in community security in special scenarios, demonstrating the accuracy and reliability of smart management in emergency prevention and control.

[0023] In step S6, security personnel contact the community center via the Internet of Things (IoT). After receiving information about key security areas, the community center transmits this information to the security personnel via the IoT. When a security anomaly alarm is triggered, the community center locates the security personnel's position via the IoT. By leveraging IoT technology, an efficient security collaborative management system is built, significantly improving the response speed and dispatch accuracy of community security and prevention, ensuring that security forces are always precisely matched with risk areas, enhancing the real-time nature and reliability of community security management, and creating a safer living environment for residents.

[0024] A community safety supervision system based on the Internet of Things (IoT) includes: a personnel access management module, a dispute impact analysis module, a regional risk assessment module, a power maintenance time planning module, a security area dynamic dispatching module, and an IoT information exchange module. The personnel access management module is used to identify and classify people entering the community and record the time when they enter and exit the community. The dispute impact analysis module is used to obtain the number of people entering and leaving the community based on the time points when they enter and leave the community, and to retrieve the historical dispute records of the monitored area to analyze the degree of impact of the people entering the community on the disputes. The regional risk assessment module is used to mark monitoring areas and analyze the regional risks of the monitoring areas based on the degree of impact of people entering the community on disputes. The power maintenance time planning module is used to analyze the predicted regional risk of power equipment maintenance dates based on the regional risk of the monitored area, thereby analyzing the optimal time point for the power outage to begin. The security zone dynamic scheduling module is used to adjust the key security areas of security personnel over time after determining the optimal time point for the power outage to begin. The IoT information exchange module is used to enable security personnel and community centers to exchange information based on the Internet of Things (IoT).

[0025] Example 1: Firstly, in terms of personnel access management, smart access control equipment is installed at the main entrances and exits of the community, which can automatically identify the identity of residents and record the time of entry and exit. For visitors, a combination of manual registration and camera recognition is used to accurately distinguish different types such as residents, visitors, and outsiders, and to record the specific time of each entry into the community in detail.

[0026] When the dispute impact analysis module is running, the system uses long-term accumulated personnel entry and exit data to count the number of people entering the community at different times, and simultaneously retrieves historical dispute records within the monitored area. By comparing the composition of personnel and the frequency of disputes at different times, staff can analyze which types of personnel enter during specific periods and have a significant impact on regional disputes.

[0027] During the regional risk assessment phase, management personnel mark various monitored areas within the community based on the results of the dispute impact analysis. Parking lots and senior activity squares, where disputes frequently occur, are designated as high-risk areas; green belts and areas around fire lanes, with less pedestrian traffic and very few historical disputes, are designated as low-risk areas; and areas in between are designated as medium-risk. This grading clearly presents the potential risk levels of different areas.

[0028] Once the power maintenance time planning module is activated, the system will prioritize equipment maintenance needs in high-risk areas. When formulating power outage maintenance plans, peak activity periods will be avoided, and periods with fewer people in high-risk areas will be selected, such as the early morning to dawn, to maintain the power equipment in the parking lot. This reduces the impact of power outages on residents and lowers the safety risks caused by monitoring failures.

[0029] The dynamic dispatching of security zones is automatically triggered after the power outage time is determined. Security departments adjust patrol priorities in real time based on the risk level and outage period of each area. During power outages in high-risk areas, the frequency of patrols is increased, and dedicated personnel are assigned to fixed locations to ensure that security and prevention measures in those areas are not weakened. Simultaneously, the IoT information interoperability module ensures real-time communication. Security personnel receive instructions from the community center in real time via handheld devices, enabling immediate feedback in case of emergencies. The community center can also use real-time information to allocate surrounding resources, forming an efficient security network. The entire system is interconnected, achieving comprehensive intelligent management of community personnel, security, and equipment, effectively improving community governance efficiency and residents' sense of security.

[0030] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A community safety supervision method based on the Internet of Things, characterized in that: The method includes the following steps: S1. Identify and classify people entering the community, and record the time points when people enter and leave the community; S2. Based on the time points when people enter and leave the community, obtain the number of people entering the community, retrieve the historical dispute records of the monitored area, and analyze the degree of influence of people entering the community on disputes; S3. Mark the monitoring area and analyze the regional risk of the monitoring area based on the degree of impact of people entering the community on disputes; S4. Based on the regional risk of the monitored area, analyze the predicted regional risk of the maintenance date of power equipment, and thus analyze the optimal time point for the start of the power outage; S5. After determining the optimal time for the power outage to begin, adjust the key security areas for security personnel over time. S6. Based on the Internet of Things, security personnel and community centers transmit information to each other; In step 2, X sets of historical community dispute data that occurred in the community's public area are retrieved, the dispute locations are marked, and the community's public area is divided into N monitoring areas of equal size. The xth set of historical community dispute data is analyzed, where x = 1, 2, ..., X. When the xth set of historical community disputes occurs, the personnel information within the monitoring area where the xth set of historical community disputes occurs is retrieved, where the number of community personnel is A. x The number of people staying normally is B. x The number of people staying beyond the allotted time is C. x The number of stranded migrant workers is D. x The system retrieves personnel monitoring data from the xth community at the time of the historical disputes, including: the number of community members a in public areas of the community. x The number of people staying normally in the community (b) x The number of people staying in the community beyond their permitted time (c) x The number of stranded migrant workers in the community d x This leads to the influence coefficient k of community members on the xth dispute. x-a =A x / a x The influence coefficient k of normal stay personnel on the xth dispute x-b =B x / b x The influence coefficient k of overstaying personnel on the xth dispute. x-c =C x / c x The influence coefficient k of stranded migrant workers on the xth dispute x-d =D x / d x Substitute each value into x = 1, 2, ..., X to obtain the influence coefficients {k} of community personnel in the public area on X disputes. 1-a ,k 2-a ,…,k x-a ,…,k X-a The influence coefficient of normal stay personnel on X disputes {k} 1-b ,k 2-b ,…,k x-b ,…,k X-b The influence coefficient {k} of overstaying personnel on X disputes. 1-c ,k 2-c ,…,k x-c ,…,k X-c The influence coefficient {k} of stranded migrant workers on X disputes. 1-d ,k 2-d ,…,k x-d ,…,k X-d }, and thus obtain the average influence coefficient K of community personnel in public areas on X disputes. a The average influence coefficient K of normal stay personnel on X disputes b The average impact coefficient K of overstaying personnel on X disputes. c The average impact coefficient K of stranded migrant workers on X disputes d ; In step S3, N monitoring areas are marked as {H1, H2, ..., H...} n ,…,H N }, at any given time, the monitored area H n Analysis was conducted to determine the number of community residents (a) within the monitored area. n The number of people staying normally is b n The number of people staying beyond the allotted time is c. n The number of stranded migrant workers is d n Then the monitoring area H at the time point n The regional risk value is J n =K a *a n +K b *b n +K c *c n +K d *d n ; In step S4, T time points with equal intervals are marked as monitoring time points. When a power equipment maintenance notification is received, the notification includes the power outage date and duration Z caused by the maintenance. The monitoring area Y days before the power equipment maintenance date is retrieved, and the regional risk value of the nth monitoring area at the t-th monitoring time point on the y-th day is J. n-t-y Then, the predicted regional risk value J of the nth monitoring area at the t-th monitoring time point of the power equipment maintenance date is calculated. n-t : ； Therefore, the predicted regional risk value of the nth monitoring area at the Tth monitoring time point of the power equipment maintenance date can be obtained as {J}. n-1 J n-2 ,…,J n-t ,…,J n-T The predicted regional risk value of N monitoring areas at the t-th monitoring time point of the power equipment maintenance date is {J}. 1-t J 2-t ,…,J n-t ,…,J N-t }; The predicted community risk value at the t-th monitoring time point of the power equipment maintenance date is calculated as J. t The J t For set {J 1-t J 2-t ,…,J n-t ,…,J N-t The average value of} is used to calculate the estimated risk j during the power outage period starting from the αth monitoring time point. α : ； Where α is the monitoring time point before the power outage begins, β is the monitoring time point after the power outage ends, the total time interval between monitoring time points α and β is greater than or equal to the power outage duration Z, and 1 ≤ α < β ≤ T. Substituting these values ​​into α = 1, 2, ..., T-1, we obtain the risk estimates {j1, j2, ..., j...} for power outages starting from time points α = 1, 2, ..., T-1 respectively. T-1 Therefore, the time point that minimizes the risk estimate is selected as the start time of the power outage.

2. The community safety supervision method based on the Internet of Things according to claim 1, characterized in that: In step S1, after authorization, the cameras installed at the community entrances and exits are used to identify people entering the community, record the time of entry, identify and mark people entering the community as community members and outsiders, continue to analyze outsiders, set a stay duration threshold T, prompt outsiders to register the expected stay duration, and mark outsiders whose stay duration is less than the expected stay duration from the time of entry into the community as normal stayers, and mark outsiders whose stay duration is greater than the expected stay duration but less than the sum of the expected stay duration and T as overstayers, otherwise, they are marked as overstaying outsiders.

3. The community safety supervision method based on the Internet of Things according to claim 2, characterized in that: In step S5, by substituting t=α,α+1,…,β one by one, the predicted area risk value of the nth monitoring area at the β-α+1 monitoring time points during the power outage is obtained as {J n-α J n-(α+1) ,…,J n-(α+2) ,…,J n-β When the power outage begins, the predicted risk value of the N monitored areas at the α-th monitoring time point is {J}. 1-α J 2-α ,…,J n-α ,…,J N-α } Select the m monitoring areas with the highest predicted risk values ​​as the key security areas at time point α. Before time point α+1, security personnel need to report the security status of each monitoring area to the community center at least γ times. Otherwise, a security anomaly alarm will be triggered at time point α+1. The security status is either normal or abnormal in the monitoring area. At time point α+1, the predicted regional risk value of the N monitored areas at time point α+1 is {J}. 1-(α+1) J 2-(α+1) ,…,J n-(α+1) ,…,J N-(α+1) The m monitoring areas with the highest predicted risk values ​​are selected as the key security areas at time point α+1. Before time point α+2, security personnel need to report the security status of each monitoring area to the community center at least γ times. Otherwise, a security anomaly alarm will be triggered at time point α+2. The maintenance of power equipment will be completed at time point β.

4. A community safety supervision method based on the Internet of Things according to claim 3, characterized in that: In step S6, security personnel contact the community center via the Internet of Things (IoT). After the community center obtains the key security areas, it transmits the information to the security personnel via the IoT. When a security anomaly alarm is triggered, the community center locates the security personnel's position via the IoT.

5. A community safety monitoring system based on the Internet of Things (IoT), wherein the system is applied to the community safety monitoring method based on the IoT as described in any one of claims 1-4, characterized in that: The system includes: a personnel access management module, a dispute impact analysis module, a regional risk assessment module, a power maintenance time planning module, a security area dynamic dispatch module, and an Internet of Things information exchange module; The personnel access management module is used to identify and classify personnel entering the community and record the time points when personnel enter and exit the community; The dispute impact analysis module is used to obtain the number of people entering the community based on the time points when people enter and leave the community, call up the historical dispute records of the monitored area, and analyze the degree of impact of people entering the community on disputes. The regional risk assessment module is used to mark monitoring areas and analyze the regional risks of the monitoring areas based on the degree of impact of people entering the community on disputes. The power maintenance time planning module is used to analyze the predicted regional risk of power equipment maintenance dates based on the regional risk of the monitored area, thereby analyzing the optimal time point for the power outage to begin. The security area dynamic scheduling module is used to adjust the key security areas of security personnel over time after determining the optimal time point for the power outage to begin. The IoT information exchange module is used to enable security personnel and community centers to transmit information to each other based on the Internet of Things.

Images