Community-based intelligent security management system

By integrating the quantitative data index, dynamic adjustment of entropy weights, real-time risk monitoring, flow status analysis and flow trend prediction modules in the intelligent security management system, the problems of insufficient data analysis and insufficient emergency response flexibility in the existing technology are solved, and the problem of insufficient data analysis and emergency response flexibility in the existing technology is achieved. More accurate risk assessment and optimized emergency notification process have been implemented, improving the efficiency and foresight of community safety management.

CN119047664AInactive Publication Date: 2024-11-29GUANGDONG JINGAO INFORMATION TECH CO LTD

Patent Information

Application Number
CN202411547185.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-01
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing community-based intelligent security management system has shortcomings in dynamic data analysis and risk prediction, and the emergency response function is difficult to be flexibly adjusted, resulting in the problems of untimely response and insufficient security warning in community security management.

Method used

Using risk indicator quantitative module, entropy weight dynamic adjustment module, real-time risk monitoring module, flow status analysis module and flow trend prediction module, to generate quantitative risk indicators and flow behavior pattern data by collecting and analyzing community security data, and adjusting in real time Risk weights and security levels, optimize emergency notification processes, and generate community management optimization plans.

Benefits of technology

More accurate risk assessment and early warning have been achieved, the foresight and targeted nature of community safety management has been improved, the incidence and impact of security incidents have been reduced, and the overall safety management efficiency has been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047664A_ABST
    Figure CN119047664A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of security and protection management, in particular to an intelligent security and protection management system based on a community, and the system comprises a risk index quantification module which collects a community security and protection data source, extracts intrusion frequency and emergency call times, carries out the classification processing of environment sensing data, and generates a quantification risk index. According to the invention, the risk weight is adjusted in real time according to the change rate and the frequency of each type of data, and more accurate risk assessment is provided for community safety management. By comparing the current data with the historical trend, the security level is updated, and it is ensured that the security measures of the community are closely connected with the actual situation. Through deep analysis and behavior pattern prediction of personnel flow data, a potential concentration area and change time in a community can be identified, and the perspectiveness and pertinence of community safety early warning are further enhanced. And in cooperation with real-time risk assessment, the emergency notification process is optimized, so that the occurrence rate and influence of security incidents are reduced, and the overall security management efficiency of the community is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of security management, and in particular to a community-based intelligent security management system. Background Art

[0002] The field of security management technology improves safety and protection through monitoring, prevention and response. It includes but is not limited to intrusion detection systems, video surveillance, access control systems and environmental monitoring. It also uses information technology and communication technologies such as the Internet of Things, artificial intelligence and big data analysis to integrate these components in an intelligent way. It enhances the ability to predict potential threats and automatically handle security incidents. Security management systems have a wide range of applications, from residential and commercial buildings to industrial facilities and public spaces.

[0003] Among them, the community-based intelligent security management system is a technical system used to improve community safety. It usually integrates elements such as video surveillance, automated access control systems, environmental sensors, and emergency response functions, and integrates and manages these functions through a network platform. This allows real-time monitoring and analysis of activities within the community, so that managers and residents can effectively monitor their living environment.

[0004] Although existing technologies can monitor activities in the community in real time, they are obviously insufficient in dynamic data analysis and risk prediction. In addition, existing technologies rely on standardized processes for emergency response functions, and it is difficult to flexibly adjust response strategies according to actual risk changes, which limits the effectiveness of security systems in the face of complex and changing community safety issues. At the same time, community safety management still faces problems such as untimely response and insufficient safety warnings. For example, when an emergency safety incident occurs, the response process is difficult to adjust in time, resulting in an inaccurate response to specific situations, which increases safety risks. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a community-based intelligent security management system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a community-based intelligent security management system, the system comprising: The risk indicator quantification module collects community security data sources, extracts intrusion frequency and emergency call times, classifies and processes environmental sensing data, and generates quantitative risk indicators; The entropy weight dynamic adjustment module performs weight calculation through the quantitative risk indicators, adjusts the weight of each type of risk indicator according to the change rate and frequency of each type of data, and generates an adjusted risk weight; The real-time risk monitoring module performs real-time monitoring on the adjusted risk weights, compares current data with historical trends, updates the security level, and obtains real-time risk assessment results; The crowd flow analysis module collects the flow data of people in the community, extracts the behavior trends from the frequency of entry and exit and the path selection, performs behavior pattern analysis, and generates a crowd behavior pattern data set; The crowd flow trend prediction module identifies potential concentration areas and change times based on the crowd flow behavior pattern data set, predicts future crowd flow dynamics, and generates crowd flow data prediction results; The security response module combines the real-time risk assessment results and the crowd flow data prediction results to synchronously update the community's security measures, optimize the emergency notification process, and generate a community management optimization plan.

[0007] The present invention has improvements in that the quantitative risk indicators include the number of security intrusions, the frequency of emergency responses, and the number of environmental sensor triggered events; the adjusted risk weight includes the weight value of the risk event, which is adjusted based on the degree of impact on the overall security of the community and the frequency of occurrence; the real-time risk assessment results include updated security level identification, risk change trend analysis, and risk status description based on current data; the crowd behavior pattern data set includes flow route analysis, peak entry and exit time periods, and crowd statistics at key activity nodes; the crowd data prediction results include crowd activity time periods, concentrated activity areas, and crowd increase and decrease trends; the community management optimization plan includes reconfiguration of emergency response processes, adjustment of monitoring strategies, and updating of early warning parameters.

[0008] The present invention is improved in that the risk indicator quantification module includes: The first data extraction submodule collects intrusion frequencies and emergency event call times based on community security data sources, screens key data, and integrates them into extracted security event data; The data classification submodule distinguishes the types and frequencies of environmental sensor alarms based on the extracted security event data, and groups multiple types of event data, including residential intrusion, fire alarm, medical and environmental hazard events, to obtain classified environmental sensor data; The indicator generation submodule analyzes the frequency and severity of each group of data based on the classified environmental sensing data, evaluates the risk indicators, and generates quantitative risk indicators.

[0009] The present invention is improved in that the entropy weight dynamic adjustment module includes: The initial weight setting submodule sets initial impact weights for multiple types of event data based on the quantitative risk indicators, with reference to historical data and the assessment of security experts, and generates weight setting results; The weight adjustment submodule adjusts and updates the weight value based on the weight setting result, according to the current community security event data and environmental monitoring, through the entropy weight method, to match the current security needs of the community and generate the changed weight value; The weight integration submodule uses the changed weight value to update the configuration parameters of the community security monitoring and generate an adjusted risk weight.

[0010] The present invention is improved in that the entropy weight method is according to the formula: ; Calculate the The entropy value of the event type indicates the uncertainty or amount of information about the event type; in, is an adjustment factor used to adjust the calculated influence of entropy according to the needs of the community, It is Event type in The probability of observations, yes The natural logarithm of , which is used in entropy calculations to provide probability weights, It is Event type in The regional risk score in the observation, It is Event type in The severity score of the event in the observations, It is Event type in The frequency of events in observations, It is Event type in The duration of the event in observations, is the number of observations; According to the said The entropy value of the event type is calculated using the formula: ; Calculate new weights ; in, is the total number of event types, is the index of the event type.

[0011] The present invention is improved in that the real-time risk monitoring module comprises: The data comparison submodule collects current community safety data based on the adjusted risk weights, compares historical safety data in historical archives, identifies key change points, and generates data comparison results; The trend analysis submodule identifies the change trend in the data based on the data comparison result, analyzes the periodicity or suddenness of the risk change, and obtains the risk trend identification result; The security level update submodule adjusts the security level label of the community based on the risk trend identification result, matches the security level with the current risk status, and obtains a real-time risk assessment result.

[0012] The present invention is improved in that the crowd flow state analysis module comprises: The second data collection submodule collects the flow data of people in the community, including the frequency of people entering and leaving and the routes they choose, screens key time points and areas, and generates a data set of current flow of people in the community; The behavior trend extraction submodule analyzes key traffic routes and time periods based on the current human flow data set of the community, identifies recurring behavior patterns, and generates behavior trend analysis results; Based on the behavioral trend analysis results, the behavior pattern induction submodule summarizes and organizes the key behavioral characteristics of community traffic, including peak traffic hours and key activity areas, and generates a crowd behavior pattern data set.

[0013] The present invention is improved in that the crowd flow trend prediction module comprises: The area identification submodule analyzes the areas where people flow is concentrated in the community based on the crowd behavior pattern data set, locates the key concentrated areas through the crowd density distribution map, and obtains the concentrated area identification result; The time analysis submodule determines the multi-flow time periods of the area based on the concentrated area identification result by using time series analysis, records the peak flow of people in each time period, and generates key time point analysis results; Based on the analysis results of the key time points, the dynamic prediction submodule evaluates the potential impact of future events or seasonal changes on the flow of people through a hidden Markov model, predicts the trend of future flow of people, and obtains the prediction results of the flow of people data.

[0014] The present invention is improved in that the hidden Markov model is according to the formula: ; Predict future trends in passenger flow; in, is a given observation sequence and parameters , , , Post-state sequence The conditional probability of is a given state sequence Time observation sequence And parameters , , , The joint probability of is a state sequence The prior probability of is the joint probability of the observation sequence and the newly added parameters, is the original observation sequence, including the event data recorded in history, is the community safety level, indicating that at each time point The community safety score is the length of time since the event occurred, is the speed at which the community responds to events, is the predicted frequency of the event, is a sequence of states.

[0015] The present invention is improved in that the security response module comprises: The risk assessment integration submodule analyzes the correlation with the crowd flow data prediction based on the real-time risk assessment results, sorts out the matching degree between the risk and the crowd flow trend, and obtains the risk status data set; The strategy update submodule adjusts the monitoring focus based on the risk status data set and the current risk and crowd flow data, automatically updates the monitoring focus points, and obtains updated monitoring point information; The notification optimization submodule adjusts the priority setting of the community communication network according to the updated monitoring focus results, optimizes the emergency notification process, and generates a community management optimization plan.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the risk weight is adjusted in real time according to the change rate and frequency of various types of data, providing a more accurate risk assessment for community safety management. By comparing the current data with historical trends and updating the security level, it is ensured that the community's safety measures are closely linked to the actual situation. Through in-depth analysis of personnel flow data and prediction of behavioral patterns, potential concentrated areas and change times within the community can be identified, further enhancing the foresight and pertinence of community safety warnings. In conjunction with real-time risk assessment, the emergency notification process is optimized, thereby reducing the incidence and impact of security incidents and improving the overall safety management efficiency of the community. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The module diagram of the community-based intelligent security management system proposed by the present invention; Figure 2 The system framework diagram of the community-based intelligent security management system proposed by the present invention; Figure 3 is a schematic diagram of a risk indicator quantification module of the present invention; Figure 4Schematic diagram of the entropy weight dynamic adjustment module of the present invention; Figure 5 is a schematic diagram of a real-time risk monitoring module of the present invention; Figure 6 is a schematic diagram of a crowd flow state analysis module of the present invention; Figure 7 Schematic diagram of a crowd flow trend prediction module of the present invention; Figure 8 It is a schematic diagram of the security response module of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0020] See also Figure 1 The present invention provides a technical solution: a community-based intelligent security management system, the system includes: The risk indicator quantification module collects community security data sources, extracts intrusion frequency and emergency call times, classifies and processes environmental sensing data, and generates quantitative risk indicators; The entropy weight dynamic adjustment module performs weight calculation by quantifying risk indicators, adjusts the weight of each type of risk indicator according to the change rate and frequency of each type of data, and generates adjusted risk weights; The real-time risk monitoring module performs real-time monitoring on the adjusted risk weights, compares the current data with historical trends, updates the security level, and obtains real-time risk assessment results; The crowd flow analysis module collects the flow data of people in the community, extracts the behavior trends from the frequency of entry and exit and the path selection, performs behavior pattern analysis, and generates a crowd behavior pattern data set; The crowd flow trend prediction module identifies potential concentration areas and change times based on the crowd flow behavior pattern data set, predicts future crowd flow dynamics, and generates crowd flow data prediction results; The security response module combines real-time risk assessment results and crowd flow data prediction results to synchronously update the community's security measures, optimize the emergency notification process, and generate a community management optimization plan.

[0021] Quantitative risk indicators include the number of security intrusions, emergency response frequency, and the number of environmental sensor triggering events. The adjusted risk weight includes the weight value of the risk event, which is adjusted based on its impact on the overall security of the community and the frequency of occurrence. The real-time risk assessment results include updated security level identification, risk change trend analysis, and risk status description based on current data. The crowd behavior pattern data set includes flow route analysis, peak entry and exit periods, and crowd statistics at key activity nodes. The crowd data prediction results include crowd activity periods, concentrated activity areas, and crowd increase and decrease trends. The community management optimization plan includes reconfiguration of emergency response processes, adjustment of monitoring strategies, and update of early warning parameters.

[0022] See also Figure 2 and Figure 3 , the risk indicator quantification module includes: The first data extraction submodule collects intrusion frequency and emergency event call times based on community security data sources, screens key data, and integrates them into extracted security event data. Based on community security data sources, collect Frequency of invasions per day and emergency call counts ,in represents the number of days. For each day, calculate the sum of intrusions and emergencies: ,get Array of total security events within the day ,in, Indicates Total number of security incidents per day, Represents the total number of days in the dataset.

[0023] The data classification submodule distinguishes the types and frequencies of environmental sensor alarms based on the extracted security event data, and groups multiple types of event data, including residential intrusion, fire alarms, medical and environmental hazard events. The process of obtaining classified environmental sensor data is as follows; right Data in by event type Classify, among which Indicates the type of event, such as residential intrusion, fire alarm, etc. Group by event type and calculate the daily average of each type of event: ,here, Indicates Day is of event type The number of events, Indicates the event type The average number of daily events, summation symbol For all days The accumulation of.

[0024] The indicator generation submodule analyzes the frequency and severity of each set of data based on the classified environmental sensing data, evaluates the risk indicators, and generates quantitative risk indicators in the following process; Average number of daily events based on each type of event , set a severity score for each type of event . Calculate the risk indicator for each event type: , finally, calculate the overall risk index By taking a weighted sum of all types of risk indicators: ,in, Is the event type risk indicators, is the weight of the event type, reflecting the importance of this type of event in the overall risk assessment, and the sum By index Total number of traversal event types , calculate the overall risk index .

[0025] See also Figure 2 and Figure 4 , the entropy weight dynamic adjustment module includes: The initial weight setting submodule sets the initial impact weights for multiple types of event data based on quantitative risk indicators, historical data and the evaluation of security experts. The process of generating the weight setting results is as follows; Based on quantitative risk indicators , refer to historical data and security expert assessment , for each event type Set initial influence weights: ,in, It is Event type. It is Quantitative risk indicators for event types. It is Historical data for the event type. It is Expert assessment of event type. It is a balancing factor that adjusts the relative importance of historical data and expert evaluation in weight setting. is a normalization factor that ensures that all weights add up to 1 and is calculated as: . is the total number of event types.

[0026] The weight adjustment submodule adjusts and updates the weight value based on the weight setting results, according to the current community security event data and environmental monitoring, through the entropy weight method to match the current security needs of the community. The process of generating the changed weight value is as follows; The entropy weight method is based on the formula: ; Calculate the The entropy value of the event type indicates the uncertainty or amount of information about the event type; in, is an adjustment factor used to adjust the calculated influence of entropy according to the needs of the community, It is Event type in The probability of an observation reflects the frequency with which the event type occurs in a particular observation. yes The natural logarithm of , which is used in entropy calculations to provide probability weights, It is Event type in The regional risk score in the observation takes into account the safety level of the area where the incident occurred. It is Event type in The severity score of the event in the observation reflects the possible impact of the event. It is Event type in The frequency of events in observations indicates how often this type of event occurs. It is Event type in The duration of the event in observations indicates the length of the event's lasting effect. is the number of observations, indicating how many event observations there are in total; According to the said The entropy value of the event type is calculated using the formula: ; Calculate new weights ; in, is the total number of event types, which refers to the number of different event types involved. is the index of the event type.

[0027] The calculation process is as follows: Calculating the probability of an event : For each event type And each observation , collect data to determine the probability of an event. Assume that there are data points, event type Here It happened times, then:

[0028] Integrate other influencing parameters , , , : Regional Risk Score : Risks can be quantified by analyzing the area's past safety record. For example, the number of major incidents that occurred in an area in the past year can be used as a risk indicator.

[0029] Incident severity rating : The incident is scored based on the impact or damage it could cause. For example, a fire may have a higher severity rating than a simple break-in.

[0030] Frequency of events : The frequency of an event during the observation period can be obtained through historical data.

[0031] Event duration : The average duration of an event from start to finish, calculated based on past event records.

[0032] Calculate the entropy value for each event type : Use the entropy formula to combine the probability and the new parameter: ; in, , , , are pre-set coefficients that are adjusted based on the relative importance of each parameter.

[0033] Calculate new weights : Recalculate the weights based on the entropy values ​​of all event types: ; Through the above steps, the entropy value of each event type can be calculated And the updated weights The probability of an event and its specific impact on community safety are taken into account, so that the weights reflect the true level of risk and the needs of the security system. New weights It can help the security system allocate resources and adjust response strategies more accurately, which not only improves the system's response efficiency to high-risk events, but also optimizes the security management of the entire community.

[0034] The weight integration submodule uses the changed weight value to update the configuration parameters of community security monitoring, and the process of generating the adjusted risk weight is as follows; Use the changed weight value , update the configuration parameters of community security monitoring and generate adjusted risk weights: ,in, is the adjusted The weight of the event type. Is the event type risk indicators.

[0035] See also Figure 2 and Figure 5 , the real-time risk monitoring module includes: The data comparison submodule collects current community safety data based on the adjusted risk weights, compares historical safety data from historical archives, identifies key change points, and generates data comparison results in the following process; Based on adjusted risk weights , collect current community safety data and compare historical archived safety data Calculate the data difference ,in, Is the current time point community safety data. The same time point Historical community safety data. It is the difference between current and historical data. These differences are combined with risk weights to generate data comparison results: , It's time point The data comparison results take risk weights into consideration.

[0036] The trend analysis submodule identifies the change trend in the data based on the data comparison results, analyzes the periodicity or suddenness of risk changes, and obtains the risk trend identification results in the following process: Based on data comparison results , using the sliding average method to identify the changing trend in the data. Set the time window size , calculate the trend: , is the window size, used for trend analysis. is the time point within the window, starting from arrive . It's time point The risk trend identification results.

[0037] The security level update submodule adjusts the security level label of the community based on the risk trend identification results, matches the security level with the current risk status, and obtains the real-time risk assessment results in the following process; Based on risk trends Adjust the safety level of your community. Set thresholds And compare ,if Exceeding the threshold , the security level is set to "high risk". Lower than But higher than , the security level is set to "Medium Risk". Lower than , the security level is set to "low risk".

[0038] See also Figure 2 and Figure 6 , the crowd flow status analysis module includes: The second data collection submodule collects the flow data of people in the community, including the frequency of people entering and leaving and the paths they choose, and selects key time points and areas to generate the current flow data set of the community. Collect data on the movement of people in the community , including the frequency of people entering and leaving and the selected path First, calculate each key area and time point Frequency of personnel and path usage: ,in, is the indicator function, represents a single flow event, Indicates a single selected path. This can generate a community current flow dataset.

[0039] The behavior trend extraction submodule analyzes key routes and time periods based on the current community traffic data set, identifies recurring behavior patterns, and generates behavior trend analysis results in the following process: Analyze key traffic routes based on the community’s current traffic data set and time period ,here, It represents the average flow of people on a specific path and in a certain time period. is the total number of days in the observation period, is the number of time periods. Identify recurring behavior patterns and generate behavior trend analysis results.

[0040] The behavior pattern induction submodule summarizes and organizes the key behavior characteristics of community traffic based on the behavior trend analysis results, including peak traffic hours and key activity areas, and generates a crowd behavior pattern dataset in the following process: Based on the results of behavioral trend analysis, summarize and organize the key behavioral characteristics of community traffic, especially the peak traffic hours and key activity areas ,in, It represents the highest flow of people among all observations, which usually occurs during peak hours, and finally records the community flow behavior pattern dataset.

[0041] See also Figure 2 and Figure 7 , the passenger flow trend prediction module includes: The area identification submodule analyzes the areas where people flow is concentrated in the community based on the crowd behavior pattern dataset, locates the key concentrated areas through the crowd density distribution map, and obtains the concentrated area identification result in the following process; Based on crowd behavior pattern dataset , calculate each area Density of traffic : ,in, It is a region density of people flow. It is Observation points in the area Number of people. It is a region The total number of observation points in . It is a region area. Indicates area The total number of observation points in Indicates that the summation starts from the first observation point. The key concentration area is determined through the crowd density distribution map, and the concentration area identification result is obtained : , Select All Area Densities The largest one.

[0042] The time analysis submodule uses time series analysis to determine the multi-flow time periods of the area based on the centralized area identification results, records the peak flow of people in each period, and generates the key time point analysis results in the following process: Based on the results of concentrated area recognition , use time series analysis to determine the multi-flow time periods in the area. Set the time period Peak traffic volume : , It is the time period Peak traffic volume inside. It's time point exist The number of people in the area. It is in the time period The operation of selecting the maximum value within Range Record the peak flow of people in each period and generate analysis results of key time points : : Each time period The peak value of passenger flow constitutes a collection of analysis results at key time points.

[0043] The dynamic prediction submodule uses the hidden Markov model to evaluate the potential impact of future events or seasonal changes on the flow of people based on the analysis results of key time points, and predicts the trend of future flow of people. The process of obtaining the prediction results of flow of people data is as follows: Hidden Markov model, according to the formula: ; Predict future trends in passenger flow; in, is a given observation sequence and parameters , , , Post-state sequence The conditional probability represents the probability of predicting the state of future events given the current and past observation data and additional security-related information. is a given state sequence Time observation sequence And parameters , , , The joint probability of is a state sequence The prior probability of the state sequence that does not consider the specific observed value is estimated based on past data. is the joint probability of the observation sequence and the newly added parameters, that is, the probability of these observations and parameters appearing without any state information, is the original observation sequence, including the event data recorded in history, is the community safety level, indicating that at each time point The community safety score It is the length of time since the most recent event, reflecting the time span from the last major event to the present. It is the community's response speed to recent events and measures the speed of the community's security system's response time. It is the predicted frequency of an event, which is the possible frequency of future events based on historical data analysis. It is a sequence of states, representing a series of possible future events or states; The calculation process is as follows: Parameter definition and data collection: , , and They represent the community's security level, the time since the last major incident, the response speed, and the predicted frequency of incidents. Collecting these parameters requires access to the community security database and incident records. For example, security level It can be based on the crime rate and severity of the incidents over a certain period of time. It can be calculated from the time interval between incident reporting and police response.

[0044] Assuming that the effect of each parameter on the observation is independent, the joint probability can be estimated by multiplying the contribution of each parameter by the state probability: ; Among them, each conditional probability is It needs to be modeled based on historical data, for example, by analyzing the probability distribution of events occurring at different security levels.

[0045] Maximize the conditional probability of the state sequence: Using the updated joint probability and Bayes’ theorem, we can calculate the state sequence Conditional probability given all observations and parameters: ; The final state sequence is chosen by solving The improved hidden Markov model can more accurately predict the impact of future events or seasonal changes on community safety. In particular, the model can comprehensively consider a variety of community-specific safety factors, such as safety level, event history, response speed, and event frequency, making the prediction more in line with actual conditions. Such prediction results can be used to guide the adjustment of community security strategies, optimize resource allocation, and deploy preventive measures in advance, thereby improving the overall safety level of the community and the sense of security of residents.

[0046] See also Figure 2 and Figure 8 , the security response module includes: The risk assessment integration submodule analyzes the correlation with the crowd flow data prediction based on the real-time risk assessment results, sorts out the matching degree between the risk and the crowd flow trend, and obtains the risk status data set in the following process; Based on real-time risk assessment results and traffic data prediction The correlation between risk and flow trend is calculated. , It is the first in the real-time risk assessment results. Item data. It is the first Item data. is the total number of data items.

[0047] The strategy update submodule adjusts the monitoring focus based on the risk status data set and the current risk and flow data, and automatically updates the monitoring focus points. The process of obtaining the updated monitoring point information is as follows; Based on risk status dataset , identify new monitoring focus points , is the risk status dataset a specific element in . Indicates the selection The largest element . express Is a collection The elements in .

[0048] The notification optimization submodule adjusts the priority setting of the community communication network according to the updated monitoring key results, optimizes the emergency notification process, and generates a community management optimization plan. Based on updated monitoring focus results , adjust the priority settings of the community communication network and optimize the emergency notification process. Define the optimized notification efficiency , is an adjustment factor used to increase the sensitivity of the notification process. It is an exponential function, often used to express growth or decay processes. It is the updated monitoring point information obtained from the strategy update submodule. Yes means and The product of takes a negative value and is used in the exponential function.

[0049] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. Community-based intelligent security management system, characterized by: The system comprises: The risk indicator quantification module collects community security data sources, extracts intrusion frequency and emergency call times, classifies and processes environmental sensing data, and generates quantitative risk indicators; The entropy weight dynamic adjustment module performs weight calculation through the quantitative risk indicators, adjusts the weight of each type of risk indicator according to the change rate and frequency of each type of data, and generates an adjusted risk weight; The real-time risk monitoring module performs real-time monitoring on the adjusted risk weights, compares current data with historical trends, updates the security level, and obtains real-time risk assessment results; The crowd flow analysis module collects the flow data of people in the community, extracts the behavior trends from the frequency of entry and exit and the path selection, performs behavior pattern analysis, and generates a crowd behavior pattern data set; The crowd flow trend prediction module identifies potential concentration areas and change times based on the crowd flow behavior pattern data set, predicts future crowd flow dynamics, and generates crowd flow data prediction results; The security response module combines the real-time risk assessment results and the crowd flow data prediction results to synchronously update the community's security measures, optimize the emergency notification process, and generate a community management optimization plan.

2. The community-based intelligent security management system according to claim 1, characterized in that: The quantitative risk indicators include the number of security intrusions, the frequency of emergency responses, and the number of environmental sensor triggered events. The adjusted risk weight includes the weight value of the risk event, which is adjusted based on the degree of impact on the overall security of the community and the frequency of occurrence. The real-time risk assessment results include updated security level identification, risk change trend analysis, and risk status description based on current data. The crowd behavior pattern data set includes flow route analysis, peak entry and exit periods, and crowd statistics at key activity nodes. The crowd data prediction results include crowd activity periods, concentrated activity areas, and crowd increase and decrease trends. The community management optimization plan includes reconfiguration of emergency response processes, adjustment of monitoring strategies, and updating of early warning parameters.

3. The community-based intelligent security management system according to claim 1, characterized in that: The risk indicator quantification module includes: The first data extraction submodule collects intrusion frequencies and emergency event call times based on community security data sources, screens key data, and integrates them into extracted security event data; The data classification submodule distinguishes the types and frequencies of environmental sensor alarms based on the extracted security event data, and groups multiple types of event data, including residential intrusion, fire alarm, medical and environmental hazard events, to obtain classified environmental sensor data; The indicator generation submodule analyzes the frequency and severity of each group of data based on the classified environmental sensing data, evaluates the risk indicators, and generates quantitative risk indicators.

4. The community-based intelligent security management system according to claim 1, characterized in that: The entropy weight dynamic adjustment module includes: The initial weight setting submodule sets initial impact weights for multiple types of event data based on the quantitative risk indicators, with reference to historical data and the assessment of security experts, and generates weight setting results; The weight adjustment submodule adjusts and updates the weight value based on the weight setting result, according to the current community security event data and environmental monitoring, through the entropy weight method, to match the current security needs of the community and generate the changed weight value; The weight integration submodule uses the changed weight value to update the configuration parameters of the community security monitoring and generate an adjusted risk weight.

5. The community-based intelligent security management system according to claim 4 is characterized in that: The entropy weight method is based on the formula: ; Calculate the The entropy value of the event type indicates the uncertainty or amount of information about the event type; in, is an adjustment factor used to adjust the calculated influence of entropy according to the needs of the community, It is Event type in The probability of observations, yes The natural logarithm of , which is used in entropy calculations to provide probability weights, It is Event type in The regional risk score in the observation, It is Event type in The severity score of the event in the observations, It is Event type in The frequency of events in observations, It is Event type in The duration of the event in observations, is the number of observations; According to the said The entropy value of the event type is calculated using the formula: ; Calculate new weights ; in, is the total number of event types, is the index of the event type.

6. The community-based intelligent security management system according to claim 1, characterized in that: The real-time risk monitoring module includes: The data comparison submodule collects current community safety data based on the adjusted risk weights, compares historical safety data in historical archives, identifies key change points, and generates data comparison results; The trend analysis submodule identifies the change trend in the data based on the data comparison result, analyzes the periodicity or suddenness of the risk change, and obtains the risk trend identification result; The security level update submodule adjusts the security level label of the community based on the risk trend identification result, matches the security level with the current risk status, and obtains a real-time risk assessment result.

7. The community-based intelligent security management system according to claim 1, characterized in that: The crowd flow status analysis module includes: The second data collection submodule collects the flow data of people in the community, including the frequency of people entering and leaving and the routes they choose, screens key time points and areas, and generates a data set of current flow of people in the community; The behavior trend extraction submodule analyzes key traffic routes and time periods based on the current human flow data set of the community, identifies recurring behavior patterns, and generates behavior trend analysis results; Based on the behavioral trend analysis results, the behavior pattern induction submodule summarizes and organizes the key behavioral characteristics of community traffic, including peak traffic hours and key activity areas, and generates a crowd behavior pattern data set.

8. The community-based intelligent security management system according to claim 1, characterized in that: The crowd flow trend prediction module includes: The area identification submodule analyzes the areas where people flow is concentrated in the community based on the crowd behavior pattern data set, locates the key concentrated areas through the crowd density distribution map, and obtains the concentrated area identification result; The time analysis submodule determines the multi-flow time periods of the area based on the concentrated area identification result by using time series analysis, records the peak flow of people in each time period, and generates key time point analysis results; Based on the analysis results of the key time points, the dynamic prediction submodule evaluates the potential impact of future events or seasonal changes on the flow of people through a hidden Markov model, predicts the trend of future flow of people, and obtains the prediction results of the flow of people data.

9. The community-based intelligent security management system according to claim 8, characterized in that: The hidden Markov model is based on the formula: ; Predict future trends in passenger flow; in, is a given observation sequence and parameters , , , Post-state sequence The conditional probability of is a given state sequence Time observation sequence And parameters , , , The joint probability of is a state sequence The prior probability of is the joint probability of the observation sequence and the newly added parameters, is the original observation sequence, including the event data recorded in history, is the community safety level, indicating that at each time point The community safety score is the length of time since the event occurred, is the speed at which the community responds to events, is the predicted frequency of the event, is a sequence of states.

10. The community-based intelligent security management system according to claim 1, characterized in that: The security response module includes: The risk assessment integration submodule analyzes the correlation with the crowd flow data prediction based on the real-time risk assessment results, sorts out the matching degree between the risk and the crowd flow trend, and obtains the risk status data set; The strategy update submodule adjusts the monitoring focus based on the risk status data set and the current risk and crowd flow data, automatically updates the monitoring focus points, and obtains updated monitoring point information; The notification optimization submodule adjusts the priority setting of the community communication network according to the updated monitoring focus results, optimizes the emergency notification process, and generates a community management optimization plan.

Citation Information

Patent Citations

  • Community intelligent management service method and system based on big data

    CN117875718A

  • Method and system for dynamically monitoring and evaluating regional sustainable development

    CN117952308A

  • Community safety intelligent management and control system based on grid management

    CN118447664A

  • Chemoport training device

    KR1020250084528A

Cited By

  • Security monitoring method and system based on Internet of Things

    CN119338655A

  • Ecological environment health intelligent assessment and management system based on PSR and entropy weight dynamic self-adaption

    CN120088113A

  • Intelligent security and protection dynamic risk assessment and prevention and control system based on multi-source data fusion

    CN120410216A

  • Community classification-based intelligent rat-patient intervention method and system

    CN121189884A