Community safety supervision system and method based on Internet of Things

Abstract

The invention discloses a community safety supervision system and method based on the Internet of Things, and relates to the technical field of community safety supervision, and the method comprises the steps: carrying out the recognition and classification of people entering a community, recording the time points of the people entering the community, and obtaining the number of people entering the community based on the time points of the people entering the community; the method comprises the following steps: calling dispute historical records of a monitoring area, analyzing the degree of influence of people entering a community on disputes, marking the monitoring area, analyzing the area risk of the monitoring area, and analyzing the predicted area risk of the maintenance date of power equipment based on the area risk of the monitoring area, so as to analyze the optimal time point when power failure starts; the key security area of the security personnel is adjusted along with time, information is transmitted between the security personnel and the community center based on the Internet of Things, organic combination of technical means and manual prevention and control is achieved through historical data modeling and a risk prediction mechanism, and community risks caused by power failure are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of community safety supervision, and in particular to a community safety supervision system and method based on the Internet of Things. Background Art

[0002] With the acceleration of urbanization and the increasing complexity of community demographics, traditional security management models are gradually exposing their limitations. First, the lack of dynamic analysis of length of stay and behavioral patterns makes it difficult to accurately identify potentially risky groups. Abnormal stays of temporary visitors and the unauthorized entry and exit of unregistered individuals often hinder timely intervention due to a lack of real-time data, leading to the accumulation of safety hazards. Second, community risk assessments are often based on empirical judgments, lacking quantitative analysis of historical data. This makes it difficult to scientifically define the security risk levels of different areas and populations. This results in an even distribution of security resources, with high-risk areas receiving little priority and resources wasted in low-risk areas, resulting in insufficient overall management efficiency and targetedness. Furthermore, in unusual scenarios such as power maintenance and equipment failures, traditional management models lack forward-looking risk predictions and systematic response strategies. This often leads to security management vacuums due to monitoring failures and delayed manpower scheduling, making it impossible to effectively ensure community safety and stability under unusual circumstances. The adoption of the Internet of Things (IoT) technology offers a new path for upgrading community security supervision. Emergency response relies on manual inspections and tiered reporting, resulting in high information latency. When security incidents occur, it is often difficult to quickly locate the problem area and the appropriate response team, hindering the efficiency of incident handling. In addition, traditional methods are limited to simple statistics in the use of historical data. They do not deeply explore the intrinsic relationship between personnel composition, behavioral patterns and security incidents, making it difficult to build a dynamic risk prediction model and unable to provide a scientific basis for management decisions. Especially when it comes to scenarios that require advance planning, such as power outages, there is a lack of quantitative analysis methods to guide the selection of the optimal solution. Summary of the Invention

[0003] The purpose of the present invention is to provide a community safety supervision system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: 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 they enter and leave the community; S2. Based on the time points when community residents enter and leave the community, the number of people entering the community is obtained, and the dispute history records of the monitored area are retrieved to analyze the impact of the people entering the community on the disputes; S3. Mark the monitoring area and analyze the regional risk of the monitoring area based on the 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 power equipment maintenance date, and thus analyze the optimal time to start the power outage; S5. After determining the optimal time to start the power outage, adjust the security personnel's focus areas 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, people entering the community are identified through cameras installed at the entrances and exits of the community, the time of entry into the community is recorded, and people entering the community are identified and marked as community residents and outsiders. The outsiders are further analyzed, and a stay time threshold T is set to prompt outsiders to register the expected stay time. Outsiders whose stay time is less than the expected stay time from the time of entry into the community are marked as normal stayers, and outsiders whose stay time is greater than the expected stay time but less than the sum of the expected stay time and T from the time of entry into the community are marked as overtime stayers. Otherwise, they are marked as stranded outsiders. With the help of entrance and exit camera recognition technology, community residents and outsiders can be accurately distinguished, and outsiders can be dynamically divided into different risk categories according to their stay status, so that the management party can quickly identify high-risk groups with abnormal stay time, intervene in the inspection in advance, reduce potential safety hazards from the source, and change the lag of traditional extensive management.

[0006] Furthermore, in step 2, call the data of X groups of historical disputes that occurred in the community public area, mark the dispute locations, divide the community public area into N monitoring areas of equal area, analyze the data of the xth group of historical disputes in the community, x = 1, 2, ..., X, and when the xth group of historical disputes occurs, call the information of the people in the monitoring area where the xth group of historical disputes occurs, where the number of community people is A x , the normal number of outsiders is B x , the number of overtime outsiders is C x , the number of stranded foreign personnel is D x , call the personnel monitoring data of the community when the historical disputes of group x occurred, including: the number of community personnel in the public area in the community a x , the number of people who normally stay in the community b x , the number of people who overstay in the community c x , the number of stranded foreigners in the community c x , and then we can get the influence coefficient k of community members on the x-th 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 the overstaying personnel on the xth dispute x-c =C x / c x , the influence coefficient k of the stranded personnel on the xth dispute x-d =D x / d x , one by one into x = 1, 2, ..., X, and then get the influence coefficient {k 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 of overstaying personnel on X disputes {k 1-c ,k 2-c ,…,k x-c ,…,k X-c}, the influence coefficient of the detained personnel on the X disputes {k 1-d ,k 2-d ,…,k x-d ,…,k X-d}, and then we can get the average influence coefficient K of community members in the public area 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 the stranded personnel on X disputes d By mining the value of historical dispute data, it provides a scientific and quantitative basis for community safety risk assessment. By dividing public areas into several monitoring zones and linking them to historical dispute locations, the system can analyze the correlation between the distribution of different types of personnel within each zone and the occurrence of disputes. Specifically, by calculating the ratio of the actual proportion of community residents, non-residents with normal stays, non-residents with extended stays, and stranded non-residents at the time of a dispute to the overall proportion, the system can quantify the impact of each type of population on security incidents and form differentiated risk weight indicators. A high average impact coefficient for a certain type of personnel indicates that their actual involvement in dispute scenarios is higher than their typical proportion and warrants special attention. This data-driven analysis mechanism transforms abstract security risks into comparable quantitative indicators, enabling community managers to clearly identify the structure and regional distribution characteristics of high-risk populations. This transforms the traditional fuzzy management model that relies on empirical judgment, enabling early identification of potential risks and targeted resource allocation, thereby 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 time point, the monitoring area H n Conduct analysis and monitor the number of community personnel in the area n , the normal number of outsiders is b n , the number of overtime outsiders is c n , the number of stranded foreign personnel 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 of equal interval length are marked as monitoring time points. When a power equipment maintenance notice is received, the power equipment maintenance notice includes the power outage date and power outage duration Z caused by the maintenance of the power equipment. The monitoring area Y days before the power equipment maintenance date is called, and the regional risk value of the nth monitoring area at the tth monitoring time point on the yth day is J n-t-y , and then calculate the predicted regional risk value of the nth monitoring area at the tth monitoring time point on the power equipment maintenance date as J n-t : ; Then, the predicted regional risk value of the nth monitoring area at T monitoring time points on 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 the N monitoring areas at the t-th monitoring time point on the power equipment maintenance date is {J 1-t ,J 2-t ,…,J n-t ,…,J N-t}; Calculate the power outage duration and calculate the predicted community risk value at the tth time point of the power equipment maintenance date as J t , the J t For the set {J 1-t ,J 2-t ,…,J n-t ,…,J N-t}, and then calculate the risk estimate j during the power outage 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 the monitoring time point α and the monitoring time point β is greater than or equal to the power outage duration Z, 1≤α<β≤T, and α=1,2,…,T-1 is substituted one by one to obtain the risk estimation values ​​{j1,j2,…,j t-1}, and then selects the time point that maximizes the risk estimate as the start time of the power outage. This historical data-driven risk prediction mechanism provides intelligent decision-making support for community security management in special scenarios. When faced with power outages due to power equipment maintenance or other situations, the system uses historical regional risk data from multiple days to scientifically predict the safety risks at various times of the outage date, changing the traditional "random" outage scheduling model. By calculating risk estimates for different outage start times, the system can prioritize the lowest-risk time period to initiate the power outage process, effectively avoiding security management blind spots caused by monitoring equipment failures. For example, power outages can be avoided during periods of high concentrations of stranded personnel or historically high levels of disputes. Furthermore, based on the predicted regional risk values, the system can pre-define key security areas during the outage, guiding security forces to strengthen patrols and control in a targeted manner. This allows for precise supplemental manual control measures within the limitations of technical equipment. This not only ensures the smooth execution of tasks such as power maintenance, but also significantly enhances the community's security capabilities under unusual circumstances through risk avoidance and optimized resource allocation. This ensures seamless security management during power outages, minimizes the probability of unexpected incidents, and enhances the community's resilience and intelligence in complex scenarios.

[0009] Furthermore, in step S5, t=α,α+1,…,β is substituted one by one to obtain the predicted regional risk value of the nth monitoring area at the β-α+1th monitoring time point during the power outage period as {J n-α ,J n-(α+1) ,…,J n-(α+2) ,…,J n-β}, when the power outage begins, the predicted regional risk value of the N monitoring areas at the αth 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 regional risk values ​​as the key security areas at the αth time point. Before the α+1th monitoring time point, the security personnel need to report the security status of each monitoring area to the community center at least γ times. Otherwise, the security abnormality alarm will be triggered at the α+1th time point. The security status is normal or abnormal in the monitoring area. When the α+1th time point is reached, the predicted regional risk value of the N monitoring areas at the α+1th monitoring time point 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 regional risk values ​​are selected as key security areas at time α+1. Security personnel are required to report security conditions in each monitoring area to the community center at least γ times before time α+2. Otherwise, a security anomaly alarm will be triggered at time α+2. This continues until time β, when power equipment maintenance is complete. This dynamic risk assessment and precise prevention and control mechanism significantly improves the effectiveness of community safety management in special scenarios such as power outages. Based on the predicted risk values ​​at each time point during a power outage, the highest-risk areas are selected in real time as key security areas, enabling security forces to focus on high-risk areas and avoiding blind spots caused by dispersed resources. A high-frequency reporting mechanism ensures real-time synchronization of on-site conditions. Security personnel are required to provide regional updates at a prescribed frequency. Any delayed or anomaly reporting triggers an immediate alarm, significantly reducing the time lag between risk detection and response. This closed-loop management model, combining prediction, positioning, and control, effectively mitigates the shortcomings of technical equipment failure during power outages. Through the synergy of manual intervention and data-driven approaches, it enables dynamic monitoring and immediate response to high-risk areas. From the practical application point of view, 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 enhance residents' trust in community security in special scenarios, reflecting the accuracy and reliability of intelligent management in emergency prevention and control.

[0010] Furthermore, in step S6, the security personnel contact the community center through the Internet of Things. After the community center obtains the key security area, it transmits it to the security personnel through the Internet of Things. When the security abnormality alarm is triggered, the community center locates the position of the security personnel through the Internet of Things. With the help of Internet of Things technology, an efficient security collaborative management system is built, which significantly improves the response speed and scheduling accuracy of community safety prevention and control, ensures that the security force is always accurately matched with the risk area, enhances the real-time and reliability of community safety management, and creates a safer living environment for residents.

[0011] A community security supervision system based on the Internet of Things, comprising: 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 scheduling module, and an Internet of Things information exchange module; The personnel entry and exit management module is used to identify and classify people entering the community and record the time points when people 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 community people enter and leave the community, call the dispute history records of the monitored area, and analyze the impact of people entering the community on the disputes; The regional risk assessment module is used to mark the monitoring area and analyze the regional risk of the monitoring area based on the impact of people entering the community on disputes; The power maintenance time planning module is used to analyze the predicted regional risk of the power equipment maintenance date based on the regional risk of the monitored area, thereby analyzing the optimal time point for the start of the power outage; 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 start of the power outage; The Internet of Things information intercommunication module is used to transmit information between security personnel and community centers based on the Internet of Things.

[0012] Compared with the existing technology, the beneficial effects achieved by the present invention are: on the one hand, through the camera recognition technology deployed at the entrances and exits of the community, it is possible to effectively distinguish between community members and outsiders, and dynamically mark outsiders according to their length of stay, and divide them into three categories: normal stay, overtime stay, and stranded outsiders. This classification method enables community management to quickly lock in people who may have safety hazards, pay special attention to or check outsiders with abnormal stay time, and reduce potential risks from the source. At the same time, the influence coefficients of different groups of people on disputes are calculated in combination with historical dispute data, and the risk weights of various types of people in security incidents are further quantified, so that the community can accurately calculate the risk value of each area based on the real-time distribution of personnel, and prioritize the deployment of security resources in high-risk areas, changing the traditional management model, realizing the transition from passive response to active prevention, and effectively improving the pertinence and effectiveness of community safety management.

[0013] On the one hand, historical data modeling and risk prediction mechanisms provide a scientific basis for community security management in special scenarios. When faced with power outages, such as those caused by power equipment maintenance, the system uses historical risk data from monitored areas over multiple days to predict regional risk values ​​at various points on the outage date. By calculating risk estimates for different outage start times, the system selects the time with the lowest risk to initiate the outage process. This mechanism effectively mitigates potential safety hazards associated with power outages during high-risk periods and avoids security management loopholes caused by monitoring equipment failure during periods of high concentrations of stranded outsiders or historically high levels of disputes. Furthermore, during outages, key security areas are dynamically identified based on predicted regional risk values, and on-site control is strengthened through methods such as setting reporting frequencies for security personnel. This ensures that even if technical equipment is temporarily unable to fully function, human intervention can still accurately safeguard community safety. This achieves an organic combination of technical means and human control, enhancing the community's security capabilities under unconventional circumstances.

[0014] Furthermore, a collaborative management model based on IoT technology has comprehensively enhanced the intelligence of community security oversight and the efficiency of emergency response. Through the IoT platform, cameras, access control systems, power equipment, and security personnel's terminals within the community achieve real-time data sharing and coordinated response. When a security anomaly alarm is triggered, the community center uses IoT to locate security personnel in real time and quickly dispatch nearby personnel to address the situation, shortening emergency response times. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a structural diagram of a community safety supervision system based on the Internet of Things of the present invention; Figure 2 This is a flow chart of a community safety supervision method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0017] See also Figure 1 and Figure 2 The present 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 they enter and leave the community; S2. Based on the time points when community residents enter and leave the community, the number of people entering the community is obtained, and the dispute history records of the monitored area are retrieved to analyze the impact of the people entering the community on the disputes; S3. Mark the monitoring area and analyze the regional risk of the monitoring area based on the 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 power equipment maintenance date, and thus analyze the optimal time to start the power outage; S5. After determining the optimal time to start the power outage, adjust the security personnel's focus areas 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, people entering the community are identified through cameras installed at the entrances and exits of the community, the time of entry into the community is recorded, and people entering the community are identified and marked as community residents and outsiders. The outsiders are further analyzed, and a stay time threshold T is set to prompt outsiders to register the expected stay time. Outsiders whose stay time is less than the expected stay time from the time of entry into the community are marked as normal stayers. Outsiders whose stay time is greater than the expected stay time but less than the sum of the expected stay time and T from the time of entry into the community are marked as overtime stayers. Otherwise, they are marked as stranded outsiders. With the help of entrance and exit camera recognition technology, community residents and outsiders can be accurately distinguished, and outsiders can be dynamically divided into different risk categories according to their stay status, so that the management can quickly identify high-risk groups with abnormal stay time, intervene in the inspection in advance, reduce potential safety hazards from the source, and change the lag of traditional extensive management.

[0019] In step 2, call the data of X groups of historical disputes that occurred in the community public area, mark the dispute locations, divide the community public area into N monitoring areas of equal area, analyze the data of the xth group of historical disputes, x = 1, 2, ..., X, and when the xth group of historical disputes occurs, call the information of the people in the monitoring area where the xth group of historical disputes occurs, where the number of community people is A. x , the normal number of outsiders is B x , the number of overtime outsiders is C x , the number of stranded foreign personnel is D x , call the personnel monitoring data of the community when the historical disputes of group x occurred, including: the number of community personnel in the public area in the community a x , the number of people who normally stay in the community b x, the number of people who overstay in the community c x , the number of stranded foreigners in the community c x , and then we can get the influence coefficient k of community members on the x-th 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 the overstaying personnel on the xth dispute x-c =C x / c x , the influence coefficient k of the stranded personnel on the xth dispute x-d =D x / d x , one by one into x = 1, 2, ..., X, and then get the influence coefficient {k 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 of overstaying personnel on X disputes {k 1-c ,k 2-c ,…,k x-c ,…,k X-c}, the influence coefficient of the detained personnel on the X disputes {k 1-d ,k 2-d ,…,k x-d ,…,k X-d}, and then we can get the average influence coefficient K of community members in the public area 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 the stranded personnel on X disputes dBy mining the value of historical dispute data, it provides a scientific and quantitative basis for community safety risk assessment. By dividing public areas into several monitoring zones and linking them to historical dispute locations, the system can analyze the correlation between the distribution of different types of personnel within each zone and the occurrence of disputes. Specifically, by calculating the ratio of the actual proportion of community residents, non-residents with normal stays, non-residents with extended stays, and stranded non-residents at the time of a dispute to the overall proportion, the system can quantify the impact of each type of population on security incidents and form differentiated risk weight indicators. A high average impact coefficient for a certain type of personnel indicates that their actual involvement in dispute scenarios is higher than their typical proportion and warrants special attention. This data-driven analysis mechanism transforms abstract security risks into comparable quantitative indicators, enabling community managers to clearly identify the structure and regional distribution characteristics of high-risk populations. This transforms the traditional fuzzy management model that relies on empirical judgment, enabling early identification of potential risks and targeted resource allocation, thereby improving the scientific nature, predictability, and overall effectiveness of community safety management.

[0020] In step S3, mark N monitoring areas as {H1, H2, ..., H n ,…,H N}, at any time point, the monitoring area H n Conduct analysis and monitor the number of community personnel in the area n , the normal number of outsiders is b n , the number of overtime outsiders is c n , the number of stranded foreign personnel 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 .

[0021] In step S4, mark T time points of equal interval length as monitoring time points. When receiving the power equipment maintenance notice, the power equipment maintenance notice includes the power outage date and power outage duration Z caused by the maintenance of the power equipment. The monitoring area Y days before the power equipment maintenance date is called. The regional risk value of the nth monitoring area at the tth monitoring time point on the yth day is J n-t-y , and then calculate the predicted regional risk value of the nth monitoring area at the tth monitoring time point on the power equipment maintenance date as J n-t : ; Then, the predicted regional risk value of the nth monitoring area at T monitoring time points on 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 the N monitoring areas at the t-th monitoring time point on the power equipment maintenance date is {J 1-t ,J 2-t ,…,J n-t ,…,J N-t}; Calculate the power outage duration and calculate the predicted community risk value at the tth time point of the power equipment maintenance date as J t , the J t For the set {J 1-t ,J 2-t ,…,J n-t ,…,J N-t}, and then calculate the risk estimate j during the power outage 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 the monitoring time point α and the monitoring time point β is greater than or equal to the power outage duration Z, 1≤α<β≤T, and α=1,2,…,T-1 is substituted one by one to obtain the risk estimation values ​​{j1,j2,…,j t-1}, and then selects the time point that maximizes the risk estimate as the start time of the power outage. This historical data-driven risk prediction mechanism provides intelligent decision-making support for community security management in special scenarios. When faced with power outages due to power equipment maintenance or other situations, the system uses historical regional risk data from multiple days to scientifically predict the safety risks at various times of the outage date, changing the traditional "random" outage scheduling model. By calculating risk estimates for different outage start times, the system can prioritize the lowest-risk time period to initiate the power outage process, effectively avoiding security management blind spots caused by monitoring equipment failures. For example, power outages can be avoided during periods of high concentrations of stranded personnel or historically high levels of disputes. Furthermore, based on the predicted regional risk values, the system can pre-define key security areas during the outage, guiding security forces to strengthen patrols and control in a targeted manner. This allows for precise supplemental manual control measures within the limitations of technical equipment. This not only ensures the smooth execution of tasks such as power maintenance, but also significantly enhances the community's security capabilities under unusual circumstances through risk avoidance and optimized resource allocation. This ensures seamless security management during power outages, minimizes the probability of unexpected incidents, and enhances the community's resilience and intelligence in complex scenarios.

[0022] In step S5, t=α,α+1,…,β is substituted one by one to obtain the predicted regional risk value of the nth monitoring area at the β-α+1th monitoring time point during the power outage period as {J n-α ,J n-(α+1) ,…,J n-(α+2) ,…,J n-β}, when the power outage begins, the predicted regional risk value of the N monitoring areas at the αth 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 regional risk values ​​as the key security areas at the αth time point. Before the α+1th monitoring time point, the security personnel need to report the security status of each monitoring area to the community center at least γ times. Otherwise, the security abnormality alarm will be triggered at the α+1th time point. The security status is normal or abnormal in the monitoring area. When the α+1th time point is reached, the predicted regional risk value of the N monitoring areas at the α+1th monitoring time point 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 regional risk values ​​are selected as key security areas at time α+1. Security personnel are required to report security conditions in each monitoring area to the community center at least γ times before time α+2. Otherwise, a security anomaly alarm will be triggered at time α+2. This continues until time β, when power equipment maintenance is complete. This dynamic risk assessment and precise prevention and control mechanism significantly improves the effectiveness of community safety management in special scenarios such as power outages. Based on the predicted risk values ​​at each time point during a power outage, the highest-risk areas are selected in real time as key security areas, enabling security forces to focus on high-risk areas and avoiding blind spots caused by dispersed resources. A high-frequency reporting mechanism ensures real-time synchronization of on-site conditions. Security personnel are required to provide regional updates at a prescribed frequency. Any delayed or anomaly reporting triggers an immediate alarm, significantly reducing the time lag between risk detection and response. This closed-loop management model, combining prediction, positioning, and control, effectively mitigates the shortcomings of technical equipment failure during power outages. Through the synergy of manual intervention and data-driven approaches, it enables dynamic monitoring and immediate response to high-risk areas. From the practical application point of view, 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 enhance residents' trust in community security in special scenarios, reflecting the accuracy and reliability of intelligent management in emergency prevention and control.

[0023] In step S6, the security personnel contact the community center through the Internet of Things. After the community center obtains the key security area, it transmits it to the security personnel through the Internet of Things. When the security abnormality alarm is triggered, the community center locates the position of the security personnel through the Internet of Things. With the help of Internet of Things technology, an efficient security collaborative management system is built, which significantly improves the response speed and scheduling accuracy of community safety prevention and control, ensures that the security force is always accurately matched with the risk area, enhances the real-time and reliability of community safety management, and creates a safer living environment for residents.

[0024] A community security supervision system based on the Internet of Things, comprising: 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 scheduling module, and an Internet of Things information exchange module; The personnel entry and exit management module is used to identify and classify people entering the community and record the time points when people 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 community members enter and leave the community, call the dispute history records of the monitored area, and analyze the impact of people entering the community on the disputes; The regional risk assessment module is used to mark the monitoring area and analyze the regional risk of the monitoring area based on the 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 start of power outages; The security area dynamic scheduling module is used to adjust the security personnel's key security areas over time after determining the optimal time point for the start of the power outage; The IoT information intercommunication module is used to transmit information between security personnel and community centers based on the IoT.

[0025] Example 1: First, in terms of personnel entry and exit management, smart access control devices are installed at the main entrances and exits of the community, which can automatically identify the identity of residents and record entry and exit times. For visitors, manual registration and camera recognition are combined to accurately distinguish between different types of residents, visitors, outsiders, etc., and the specific time period of each entry into the community is recorded in detail.

[0026] When the Dispute Impact Analysis module is running, the system counts the number of people entering the community during each time period based on accumulated data on personnel entry and exit. It also simultaneously retrieves historical records of disputes within the monitored area. By comparing the demographics of people entering the community during different time periods with the frequency of disputes, staff can analyze which types of people, during specific periods, have a significant impact on regional disputes.

[0027] During the regional risk assessment phase, managers will label each monitored area within the community based on the results of the dispute impact analysis. Parking lots and senior citizen activity plazas, where disputes frequently occur, are designated high-risk areas. Green belts and areas surrounding fire escape routes, where there is less traffic and a minimal history of disputes, are designated low-risk areas. Areas in between are designated medium-risk. This grading clearly demonstrates the potential risk levels of different areas.

[0028] Once the power maintenance schedule module is activated, the system prioritizes equipment maintenance needs in high-risk areas. When developing power outage maintenance plans, the system avoids peak activity times and selects less crowded times in high-risk areas, such as early morning to early morning hours, to maintain parking lot electrical equipment. This minimizes the impact of power outages on residents and reduces safety risks associated with ineffective monitoring.

[0029] The dynamic scheduling of security areas is automatically triggered after the power outage time is determined. The security department adjusts the patrol focus in real time according to the risk level and power outage period of each area. During power outages in high-risk areas, the frequency of patrols by security personnel is increased, and dedicated personnel are assigned to fixed-point guard duty to ensure that the security control efforts in the area are not reduced. At the same time, the Internet of Things information exchange module ensures real-time communication. Security personnel receive instructions from the community center in real time through handheld devices, and can provide immediate feedback in the event of an emergency. The community center can also deploy surrounding resources through real-time information to form an efficient security protection network. The entire system is interconnected, realizing all-round intelligent management of community personnel, security, and equipment, effectively improving the governance efficiency of the community and the sense of security of residents.

[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 embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A community safety supervision method based on the Internet of Things, characterized by: The method comprises the following steps: S1. Identify and classify people entering the community and record the time they enter and leave the community; S2. Based on the time points when community residents enter and leave the community, the number of people entering the community is obtained, and the dispute history records of the monitored area are retrieved to analyze the impact of the people entering the community on the disputes; S3. Mark the monitoring area and analyze the regional risk of the monitoring area based on the 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 power equipment maintenance date, and thus analyze the optimal time to start the power outage; S5. After determining the optimal time to start the power outage, adjust the security personnel's focus areas over time; S6. Based on the Internet of Things, security personnel and community centers transmit information to each other.

2. The method for community safety supervision based on the Internet of Things according to claim 1, characterized in that: In step S1, after authorization, people entering the community are identified through cameras installed at the entrances and exits of the community, and the time of entry into the community is recorded. People entering the community are identified and marked as community residents and outsiders, and the outsiders are further analyzed. A stay time threshold T is set, and outsiders are prompted to register the expected stay time. Outsiders whose stay time is less than the expected stay time from the time of entry into the community are marked as normal stayers. Outsiders whose stay time is greater than the expected stay time but less than the sum of the expected stay time and T from the time of entry into the community are marked as overstayers. Otherwise, they are marked as stranded outsiders.

3. The method for community safety supervision based on the Internet of Things according to claim 2, characterized in that: In step 2, call the data of X groups of historical disputes that occurred in the community public area, mark the dispute locations, divide the community public area into N monitoring areas of equal area, analyze the data of the xth group of historical disputes, x = 1, 2, ..., X, and when the xth group of historical disputes occurs, call the information of the people in the monitoring area where the xth group of historical disputes occurs, where the number of community people is A. x , the normal number of outsiders is B x , the number of overtime outsiders is C x , the number of stranded foreign personnel is D x , call the personnel monitoring data of the community when the historical disputes of group x occurred, including: the number of community personnel in the public area in the community a x , the number of people who normally stay in the community b x , the number of people who overstay in the community c x , the number of stranded foreigners in the community c x , and then we can get the influence coefficient k of community members on the x-th 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 the overstaying personnel on the xth dispute x-c =C x / c x , the influence coefficient k of the stranded personnel on the xth dispute x-d =D x / d x , one by one into x = 1, 2, ..., X, and then get the influence coefficient {k 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 of overstaying personnel on X disputes {k 1-c ,k 2-c ,…,k x-c ,…,k X-c }, the influence coefficient of the detained personnel on the X disputes {k 1-d ,k 2-d ,…,k x-d ,…,k X-d }, and then we can get the average influence coefficient K of community members in the public area 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 the stranded personnel on X disputes d .

4. The method for community safety supervision based on the Internet of Things according to claim 3, characterized in that: In step S3, mark N monitoring areas as {H1, H2, ..., H n ,…,H N }, at any time point, the monitoring area H n Conduct analysis and monitor the number of community personnel in the area n , the normal number of outsiders is b n , the number of overtime outsiders is c n , the number of stranded foreign personnel 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 .

5. The method for community safety supervision based on the Internet of Things according to claim 4, characterized in that: In step S4, mark T time points of equal interval length as monitoring time points. When receiving the power equipment maintenance notice, the power equipment maintenance notice includes the power outage date and power outage duration Z caused by the maintenance of the power equipment. The monitoring area Y days before the power equipment maintenance date is called. The regional risk value of the nth monitoring area at the tth monitoring time point on the yth day is J n-t-y , and then calculate the predicted regional risk value of the nth monitoring area at the tth monitoring time point on the power equipment maintenance date as J n-t : ； Then, the predicted regional risk value of the nth monitoring area at T monitoring time points on 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 the N monitoring areas at the t-th monitoring time point on the power equipment maintenance date is {J 1-t ,J 2-t ,…,J n-t ,…,J N-t }.

6. The method for community safety supervision based on the Internet of Things according to claim 5, characterized in that: Calculate the power outage duration and calculate the predicted community risk value at the tth time point of the power equipment maintenance date as J t , the J t For the set {J 1-t ,J 2-t ,…,J n-t ,…,J N-t }, and then calculate the risk estimate j during the power outage 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 the monitoring time point α and the monitoring time point β is greater than or equal to the power outage duration Z, 1≤α<β≤T, and α=1,2,…,T-1 is substituted one by one to obtain the risk estimation values ​​{j1,j2,…,j t-1 }, and then select the time point that makes the risk estimate value as the power outage start time point.

7. The method for community safety supervision based on the Internet of Things according to claim 6, characterized in that: In step S5, t=α,α+1,…,β is substituted one by one to obtain the predicted regional risk value of the nth monitoring area at the β-α+1th monitoring time point during the power outage period as {J n-α ,J n-(α+1) ,…,J n-(α+2) ,…,J n-β }, when the power outage begins, the predicted regional risk value of the N monitoring areas at the αth 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 regional risk values ​​as the key security areas at the αth time point. Before the α+1th monitoring time point, security personnel need to report the security status of each monitoring area to the community center at least γ times. Otherwise, a security abnormality alarm will be triggered at the α+1th time point. The security status is either normal or abnormal in the monitoring area. When the α+1th time point is reached, the predicted regional risk value of the N monitoring areas at the α+1th monitoring time point is {J 1-(α+1) ,J 2-(α+1) ,…,J n-(α+1) ,…,J N-(α+1) }, select the m monitoring areas with the highest predicted regional risk values ​​as the key security areas at the α+1th time point. Before the α+2th monitoring time point, security personnel need to report the security status to the community center at least γ times in each monitoring area, otherwise a security abnormality alarm will be triggered at the α+2th time point; until the βth time point is reached, the power equipment maintenance is completed.

8. The method for community safety supervision based on the Internet of Things according to claim 6, characterized in that: In step S6, the security personnel contact the community center through the Internet of Things. After the community center obtains the key security area, it transmits it to the security personnel through the Internet of Things. When the security abnormality alarm is triggered, the community center locates the position of the security personnel through the Internet of Things.

9. A community safety supervision system based on the Internet of Things, wherein the system is applied to the community safety supervision method based on the Internet of Things according to any one of claims 1 to 7, 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 scheduling module and an Internet of Things information exchange module; The personnel entry and exit management module is used to identify and classify people entering the community and record the time points when people 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 community people enter and leave the community, call the dispute history records of the monitored area, and analyze the impact of people entering the community on the disputes; The regional risk assessment module is used to mark the monitoring area and analyze the regional risk of the monitoring area based on the impact of people entering the community on disputes; The power maintenance time planning module is used to analyze the predicted regional risk of the power equipment maintenance date based on the regional risk of the monitored area, thereby analyzing the optimal time point for the start of the power outage; 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 start of the power outage; The Internet of Things information intercommunication module is used to transmit information between security personnel and community centers based on the Internet of Things.

Images