A smart community user behavior intelligent monitoring and early warning method and system
By collecting and analyzing user behavior data in smart communities, identifying identity and behavior patterns, calculating behavior scores and risk indexes, and formulating personalized management strategies, the difficulties of user behavior monitoring and risk assessment are solved, and community safety and management efficiency are improved.
Patent Information
- Application Number
- CN202411133675.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-12-24
- Estimated Expiration
- 2044-08-19
AI Technical Summary
In smart communities, existing technologies are difficult to effectively monitor and evaluate user behavior, resulting in timely discovery of security risks and lack of scientific management strategies.
By collecting user behavior data at the monitoring points of the smart community, identifying user identity and behavior patterns, calculating regional behavior scores and overall behavior scores, calculating regional risk indexes in combination with environmental sensor data, and formulating personalized management plans and early warning strategies.
It realizes accurate identification and risk assessment of user behavior, improves the intelligence level of community safety management, enhances residents' sense of security and life experience, and optimizes resource allocation and community governance.
Smart Images
Figure CN118644094B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of smart communities, and in particular to a method and system for intelligent monitoring and early warning of user behavior in a smart community. Background Art
[0002] With the acceleration of urbanization and the rapid development of science and technology, smart communities have gradually become an important part of modern urban management. Smart communities have improved the efficiency and quality of community services and the living environment of residents through information and intelligent means, becoming an important platform for promoting sustainable social development. Smart communities usually integrate a variety of advanced technologies, such as the Internet of Things, cloud computing, and big data analysis. The combination of these technologies makes community management more intelligent and precise.
[0003] In a smart community, user behavior is an important factor affecting community safety, order, and harmony. Effective user behavior monitoring can not only detect potential safety hazards in a timely manner, but also provide data support for community management, helping managers to formulate more scientific management plans. Through intelligent monitoring of user behavior, it is possible to respond quickly to various events in the community and ensure the safety and stability of the community. It can be seen that how to achieve intelligent monitoring of user behavior in smart communities is an urgent problem to be solved. Summary of the invention
[0004] The purpose of the present invention is to provide a method and system for intelligent monitoring and early warning of user behavior in a smart community to address the deficiencies in the prior art. The method and system can comprehensively collect user behavior data, accurately identify user identities, generate behavior trajectories and scores, thereby reasonably assessing regional risks, formulating personalized management plans and early warning strategies, and providing strong technical support for creating a safe and harmonious smart community.
[0005] An embodiment of the present application provides a method for intelligent monitoring and early warning of user behavior in a smart community, the method comprising:
[0006] Through various monitoring points in the smart community, collect the behavior data of each user in the public area of the smart community;
[0007] According to each user's behavior data, determine the corresponding user's identity type and behavior pattern, and generate the user's behavior trajectory, wherein the user identity type includes: community residents, outsiders;
[0008] According to the user's identity type, behavior pattern, and behavior trajectory, the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community are calculated; wherein the calculation formulas for the regional behavior score and the overall behavior score are as follows:
[0009] Among them, the Score the regional behavior of the i-th user in the k-th common sub-region, Score the overall behavior of the i-th user. is the identity weight value corresponding to the identity type, which is used to reflect the degree of influence of the identity on the behavior. is the behavior score corresponding to the rth behavior pattern in the kth common sub-region and used to assess the behavior risk, is the behavior score corresponding to the jth behavior mode in the smart community, is the trajectory index corresponding to the behavior trajectory in the kth common sub-region, which is used to amplify the overall behavior impact. is the trajectory index corresponding to the behavior trajectory in the smart community, is the number of behavior patterns in the behavior trajectory of the kth common sub-region, is the number of behavior patterns in the behavior trajectory of the smart community; according to the behavior data of each user and the regional behavior score, the regional risk index of each public sub-area of the smart community is calculated; according to the overall behavior score, the personalized management plan of the community users is determined, and according to the regional risk index, the regional early warning strategy of each public sub-area of the community is determined.
[0010] Optionally, the regional risk index is calculated as follows: Among them, the is the regional risk index of the kth common sub-region, is the environmental risk weight of the kth common sub-area, which is obtained based on the comprehensive evaluation of the environmental sensor data in the current common sub-area. is the residence time weight of the i-th user in the k-th common sub-area, is the number of users in the kth public sub-area, is the crowd flow intensity in the kth public sub-area, is the flow impact factor in the kth common sub-area, The historical event impact score of the kth common sub-region is evaluated based on the number and severity of abnormal events that occurred in the region in the past period of time. is the impact factor of historical events, which considers the contribution of abnormal events occurring in the area to the current security risk.
[0011] Optionally, the residence time weight is: Among them, the is the actual residence time of the i-th user in the k-th public sub-area, is the total monitoring time in the kth common sub-area;
[0012] The crowd flow intensity is: Among them, the is the flow of people in the kth public sub-area, is the total area of the kth public sub-area. Another embodiment of the present application provides a smart community user behavior intelligent monitoring and early warning system, the system comprising: a monitoring module, used to collect the behavior data of each user located in the public area of the smart community through each monitoring point of the smart community; a determination module, used to determine the identity type and behavior pattern of the corresponding user according to the behavior data of each user, and generate the user's behavior trajectory, wherein the user identity type includes: community residents, outsiders; a first calculation module, used to calculate the regional behavior score of each user during the period of being in each public sub-area and the overall behavior score during the period of being in the entire smart community according to the user's identity type, behavior pattern, and behavior trajectory; wherein the calculation formulas for the regional behavior score and the overall behavior score are: Among them, the Score the regional behavior of the i-th user in the k-th common sub-region, Score the overall behavior of the i-th user. is the identity weight value corresponding to the identity type, which is used to reflect the degree of influence of the identity on the behavior. is the behavior score corresponding to the rth behavior pattern in the kth common sub-region and used to assess the behavior risk, is the behavior score corresponding to the jth behavior mode in the smart community, is the trajectory index corresponding to the behavior trajectory in the kth common sub-region, which is used to amplify the overall behavior impact. is the trajectory index corresponding to the behavior trajectory in the smart community, is the number of behavior patterns in the behavior trajectory of the kth common sub-region, is the number of behavior patterns in the behavior trajectory of the smart community; a second calculation module is used to calculate the regional risk index of each public sub-area of the smart community according to the behavior data of each user and the regional behavior score; an early warning module is used to determine the personalized management plan for community users according to the overall behavior score, and determine the regional early warning strategy for each public sub-area of the community according to the regional risk index. Another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the methods described above when running. Another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above. Compared with the prior art, the present invention provides a method for intelligent monitoring and early warning of user behavior in a smart community. The method collects the behavior data of each user located in a public area of the smart community through each monitoring point of the smart community. According to the behavior data of each user, the identity type and behavior pattern of the corresponding user are determined, and the behavior trajectory of the user is generated, wherein the user identity type includes: community residents and outsiders. According to the identity type, behavior pattern and behavior trajectory of the user, the regional behavior score of each user during the period when the user is located in each public sub-area and the overall behavior score during the period when the user is located in the entire smart community are calculated; according to the behavior data of each user and the regional behavior score, the regional risk index of each public sub-area of the smart community is calculated; according to the overall behavior score, the personalized management plan of the community users is determined, and according to the regional risk index, the regional early warning strategy of each public sub-area of the community is determined, so that the user identity can be accurately identified by comprehensively collecting the user behavior data, and the behavior trajectory and score can be generated, so as to reasonably evaluate the regional risk, formulate personalized management plans and early warning strategies, and provide strong technical support for creating a safe and harmonious smart community. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] Figure 1 A hardware structure block diagram of a computer terminal for a smart community user behavior intelligent monitoring and early warning method provided by an embodiment of the present invention;
[0014] Figure 2 A flowchart of a method for intelligent monitoring and early warning of user behavior in a smart community provided by an embodiment of the present invention;
[0015] Figure 3 A schematic diagram of the structure of a smart community user behavior intelligent monitoring and early warning system provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0016] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.
[0017] The embodiment of the present invention first provides a method for intelligent monitoring and early warning of user behavior in a smart community, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc. The following is a detailed description of the method by taking the method running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal of a smart community user behavior intelligent monitoring and early warning method provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown. The memory 104 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the intelligent monitoring and early warning method for user behavior in a smart community in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific network examples may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly. Figure 2 The embodiment of the present invention provides a method for intelligent monitoring and early warning of user behavior in a smart community, which may include the following steps:
[0018] S201, collecting behavior data of each user in a public area of the smart community through each monitoring point of the smart community;
[0019] In smart communities, the process of collecting user behavior data in public areas through various monitoring points plays a vital role. Monitoring points can be a variety of sensors, cameras, RFID devices, smartphone applications, etc. These devices can collect real-time information on the activities of residents and outsiders in public areas of the community. User behavior data usually includes:
[0020] 1. Behavior type: records of activities such as walking, staying, communicating, shopping, etc.
[0021] 2. Timestamp: Record the specific time when each behavior occurs.
[0022] 3. Location data: Determine the user's specific location within the community and help depict the user's activity trajectory.
[0023] 4. User identity information: Identify users as residents or outsiders in the community. The collection of this data is crucial for subsequent analysis of user behavior patterns, identification of potential security risks, and formulation of management strategies.
[0024] 5. Environmental data related to user behavior interaction: such as data collected by environmental sensors such as smoke, temperature and humidity, sound and light, and noise.
[0025] 6. Other relevant data, etc. Function and significance:
[0026] - Security monitoring: By monitoring user behavior in real time, abnormal behavior can be discovered in a timely manner, potential safety hazards can be warned, and the safety of the community can be ensured.
[0027] - Resource optimization: Analyze user behavior data in public areas to help community managers optimize the allocation of public resources and improve service quality.
[0028] - Personalized management: Provide personalized community services to residents based on user behavior patterns to enhance residents’ sense of participation and satisfaction.
[0029] - Community governance: Based on the results of data analysis, formulate targeted management plans to improve the efficiency of community governance and promote the construction of a harmonious community. One implementation method may include: 1. Deployment of data collection equipment:
[0030] - Set up multiple monitoring points in the public areas of the smart community and use cameras, sensors and other equipment to collect user behavior data in real time.
[0031] - The equipment must have real-time data transmission capabilities so that data can be collected into a central control system.
[0032] 2. Multi-dimensional data fusion:
[0033] - Use multi-sensor data fusion technology to combine video surveillance data, environmental sensor data and user mobile device data to build a multi-dimensional data collection framework.
[0034] - The behavior data of the same user at different monitoring points are associated through time and location tags to ensure that the behavior data of a user can be effectively tracked throughout the community.
[0035] Through the above-mentioned technical algorithm implementation method, the collection of user behavior data in smart communities can be more comprehensive, accurate and efficient, which not only improves the intelligence level of community security management, but also provides users with a better life service experience.
[0036] S202, determining the identity type and behavior pattern of the corresponding user according to the behavior data of each user, and generating the behavior trajectory of the user, wherein the user identity type includes: community resident, outsider;
[0037] In a smart community, determining the identity type and behavior pattern of the corresponding user based on each user's behavior data and generating the user's behavior trajectory is an important part of realizing intelligent monitoring and early warning. Specifically, the core of this step is to make full use of the collected behavior data and analyze the data to identify the user's identity (community resident or outsider) and his behavior pattern. This process involves the following aspects:
[0038] 1. Identification of identity type: Based on the user's behavioral characteristics in public areas (such as activity frequency, activity time period, behavioral preferences, etc.), combined with the background information within the community (such as resident files, visitor registration, etc.), the user is classified as a community resident or outsider. This step can be achieved through big data analysis and machine learning technology.
[0039] 2. Behavior pattern recognition: Analyze user behavior data and identify user behavior patterns, such as common activity types (such as walking, exercise, gatherings, etc.) and behavior characteristics (such as the duration and regularity of behavioral activities). This analysis helps understand users' daily habits and preferences.
[0040] 3. Behavior trajectory generation: Through time series analysis and location tagging, the user's behavior trajectory in the community is constructed. Each user's behavior trajectory provides a comprehensive view of his or her activities in the public area, facilitating further behavior analysis and risk assessment.
[0041] - Risk assessment: By distinguishing between community residents and outsiders and understanding their behavior patterns, potential security risks can be identified in security management. For example, certain unusual behavior patterns may indicate abnormal activities of outsiders.
[0042] - Personalized services: By analyzing behavioral patterns, community managers can provide personalized community services to users based on different identity types and behavioral habits, thereby improving the user experience of the community.
[0043] - Data-driven decision-making: The generated user behavior trajectories provide data support for community management, making decisions more scientific and accurate. For example, the layout and use of public facilities can be optimized based on user trajectory data.
[0044] - Promote community harmony: By monitoring the behavior of community residents and outsiders, it helps to enhance residents' sense of security and promote harmonious community development. One way to achieve this may include:
[0045] 1. Data preprocessing:
[0046] - The collected behavioral data is cleaned using data cleaning technology to remove redundant and noisy data to ensure data quality.
[0047] - Standardize irregular behavior data to facilitate subsequent analysis.
[0048] 2. Identity attribute integration:
[0049] - Combine user profiles (such as registration information and resident ID numbers) in the community management system with real-time monitoring data to identify user identity attributes through quasi-real-time data matching.
[0050] - Introducing graph database technology to form a network relationship diagram between community residents and their identity characteristics (such as address, family members, social circles) to enhance the accuracy of user identity recognition.
[0051] 3. Behavioral pattern extraction:
[0052] - Use clustering analysis methods (such as K-Means or DBSCAN) to group user behavior data and identify user behavior characteristics and patterns.
[0053] - Each type of behavior pattern is associated with a specific label (such as "frequent walking", "occasional gathering", etc.), in this way, user behavior is identified and classified.
[0054] 4. Behavior trajectory generation:
[0055] - Use time series analysis technology and path planning algorithms to track user movement data within the community and generate user behavior trajectories. By analyzing timestamps and location information, a movement path map in different time periods is formed.
[0056] - Combined with GIS (Geographic Information System) technology, user trajectories can be visualized to identify hot spots of user activities. 5. Abnormal behavior detection:
[0057] - Based on the generated user behavior patterns and historical behavior data, a behavior model is built to monitor abnormal user behavior in real time. Machine learning-based anomaly detection algorithms (such as Isolation Forest) are used to identify behaviors that deviate significantly from normal patterns to provide timely warnings.
[0058] - When a significant deviation in user behavior is detected (such as outsiders frequently entering a quiet area), the system will trigger an early warning to improve the effectiveness of security monitoring.
[0059] 6. Data feedback and optimization:
[0060] - Based on user feedback and behavior monitoring results, regularly update and optimize identity recognition and behavior pattern analysis algorithms to improve the intelligence level of the system.
[0061] - Conduct data mining and analyze changes in user behavior trends in order to adjust community management strategies to ensure they adapt to the ever-changing community environment.
[0062] Through the implementation of the above steps, effective identification and analysis of user identities and behavior patterns in smart communities will be achieved, which will not only improve the management efficiency of the community, but also provide residents with a safer and more convenient living environment.
[0063] S203, calculating the regional behavior score of each user during the time they are in each public sub-area and the overall behavior score during the time they are in the entire smart community according to the user's identity type, behavior pattern, and behavior trajectory;
[0064] In this step, the smart community conducts a comprehensive analysis of each user's identity type, behavior pattern, and behavior trajectory, and calculates the corresponding regional behavior score and overall behavior score. This process specifically involves the following aspects:
[0065] 1. Identity type: Evaluate the user's behavior based on their identity in the smart community (such as community residents or outsiders), because users with different identities may show significant differences in behavior patterns. For example, community residents may be more familiar with the community environment and have a higher frequency of activities in certain areas, while outsiders may tend to visit specific public facilities.
[0066] 2. Behavior patterns: Various activities of users in public areas (such as walking, shopping, exercising, etc.) are classified into different behavior patterns. Each behavior pattern corresponds to a different behavior score, which reflects the risk level of the behavior in a specific area.
[0067] 3. Behavior trajectory: The user's behavior trajectory refers to the user's activity path in the community. By analyzing the user's behavior trajectory, it is possible to more accurately assess the degree of activity in a specific area, thereby affecting the regional behavior score. Role and significance: - Risk assessment: By calculating the regional behavior score and the overall behavior score, high-risk and low-risk areas can be effectively identified, thereby helping managers take corresponding measures to improve the safety level of the community.
[0068] - Personalized management: Understand the behavior patterns of users of different identity types and provide them with more targeted services and management solutions. For example, for outsiders who often move around in a certain area, the monitoring of that area can be strengthened.
[0069] - Data-driven decision-making: Data analysis based on scoring can help management formulate scientific and reasonable management strategies, optimize resource allocation, and improve the overall governance level of the community.
[0070] - Community safety: Through dynamic monitoring and scoring mechanisms, abnormal behaviors can be discovered in a timely manner and early warning of abnormal behaviors can be achieved, thereby ensuring the safety of community residents to a greater extent.
[0071] Specifically, a calculation formula for a regional behavior score and the overall behavior score may be: The formula is designed to evaluate the user's behavior in the community through quantitative methods, so as to facilitate precise management and risk control. The formula calculates the regional behavior score of each user in a specific public sub-area. and overall behavior score , by accumulating user behavior data, providing the community with a more effective security management basis.
[0072] Among them, the The regional behavior score of the i-th user in the k-th public sub-area reflects the risk level of the user's behavior in the area. The higher the score, the more potential risk the user's behavior in the area has. is the overall behavior score of the i-th user, indicating the behavior risk of the user in the entire smart community. This score comprehensively considers the behavior patterns of all public sub-areas, thus providing a reference for the overall management of users. The identity weight value corresponding to the identity type is used to reflect the degree of influence of the identity on the behavior, indicating the degree of influence of different identities on the behavior score. Users with different identities have significant differences in behavioral habits and activity frequencies, so different weight values are assigned to them to more scientifically evaluate their respective behavior scores. You can set corresponding weights for different identities in advance based on historical behavior data and the actual situation of the community. is the behavior score corresponding to the rth behavior pattern in the kth common sub-area, which is used to assess the behavior risk, and specifically reflects the risk that the behavior pattern may bring in a specific environment. By scoring different behavior patterns, it is possible to identify which activities are high-risk in the area. A behavior-score mapping table can be pre-built to cover common forms and corresponding scoring criteria. Score the behavior corresponding to the jth behavior pattern in the smart community, similar to , reflecting the risk level of this behavior pattern in the overall community environment. The trajectory index corresponding to the behavior trajectory in the kth common sub-area is used to amplify the overall behavior impact. The higher the trajectory index, the more frequent the user's activities in the area, the longer the trajectory, and the higher the possible risk level. The corresponding standard between the behavior trajectory and the trajectory index can be set by the user based on historical behavior data and the actual situation of the community. It is the trajectory index corresponding to the behavior trajectory in the smart community, which comprehensively reflects the user's activity pattern in the entire community. This parameter provides a basis for evaluating the overall behavior risk. is the number of behavior patterns in the behavior trajectory of the kth common sub-area, indicating the different types of behaviors exhibited by users in this area. The number of behavior patterns in the behavior trajectory of the smart community reflects the total amount of various behaviors displayed by users in the community, providing data support for scoring. By systematically designing these parameters and formulas, the smart community can accurately evaluate user behavior and provide strong support for administrative management, resource allocation and security warning. S204, calculating the regional risk index of each public sub-area of the smart community based on the behavior data of each user and the regional behavior score;
[0073] In this step, the regional risk index of each public sub-area of the smart community is calculated by analyzing the behavior data of each user and the regional behavior score. The specific process is as follows: 1. Data collection: First, the user's behavior data in the public area is collected in real time through the monitoring points in the smart community. This data includes information such as the user's activity time, location, and behavior type.
[0074] 2. Regional behavior score: In the previous step, the corresponding regional behavior score (R'_ik) has been generated according to the user identity type and behavior pattern. This score reflects the behavioral risk level of individual users in a specific public sub-area.
[0075] 3. Calculation of regional risk index: Finally, the regional risk index (R_{area_k}) of each public sub-region is calculated using the user's behavior data and regional behavior score. This index reflects the potential security risks in a specific area, allowing community managers to take appropriate security measures in a timely manner. Role and significance: - Risk identification and management: Through the calculation of the regional risk index, community managers can clearly identify high-risk areas, take preventive measures in a timely manner, and improve the overall security of the community.
[0076] - Reasonable allocation of resources: Based on the regional risk index, resources can be effectively allocated to high-risk areas, such as adding surveillance cameras and security personnel, to ensure the effectiveness of security management.
[0077] - Dynamic monitoring and early warning: The regional risk index provides data support for the community to establish a dynamic monitoring mechanism, allowing managers to monitor the safety status of each area in real time and respond quickly according to the degree of risk.
[0078] - Decision support: The regional risk index provides a basis for intelligent decision-making, helping managers to formulate scientific and reasonable community safety management strategies and optimization measures.
[0079] Specifically, a method for calculating a regional risk index may be: Among them, the is the regional risk index of the kth common sub-region, is the environmental risk weight of the kth public sub-area, which is obtained based on a comprehensive assessment of the environmental sensor data in the current public sub-area and is set according to actual conditions, reflecting the impact of the environmental characteristics of each public sub-area on the risk. : This item combines the user's residence time weight with the respective regional behavior score, reflecting the user's behavioral risk in the area. It shows that the longer the user stays in a specific area, the more significant the security risk. is the residence time weight of the i-th user in the k-th public sub-area, which can be set according to the actual situation. is the number of users in the kth public sub-area, is the crowd flow intensity in the kth public sub-area, indicating the flow of people in the kth area. The increase in the flow of people may lead to higher security risks, so this factor needs to be considered when calculating the regional risk. is the flow influencing factor in the kth public sub-area, reflecting the influence of the density of human flow on the regional risk, ensuring the rationality of the assessment of human flow on regional safety risk. Score the impact of historical events in the kth common sub-region based on the number and severity of abnormal events that occurred in the region over the past period of time. Set the scoring criteria based on actual conditions to help managers understand the potential impact of historical events on current risks.
[0080] Said It is the impact factor of historical events. It takes into account the contribution of abnormal events occurring in the area to the current security risks. It is set according to the actual situation, comprehensively considers the impact of past events on the current security risks, and deepens the understanding of risks.
[0081] Specifically, the residence time weight may be: Among them, the is the actual stay time of the i-th user in the k-th public sub-area. The longer it is, the more attention the user pays to the area and the influence of his behavior. is the total monitoring time in the kth common sub-area. The stay weight is calculated by the ratio of these two parameters to ensure the authenticity of the risk score of the user's presence in the area.
[0082] The crowd flow intensity can be: Among them, the is the flow of people in the kth common sub-area, indicating the activity level in the area within a certain period of time. The total area of the kth common sub-area provides a standardized indicator to evaluate the density of the flow. By combining the flow of people with the area, the flow intensity of the area can be accurately reflected.
[0083] By combining the above parameters and formulas, smart communities will be able to monitor user behavior and assess risks more accurately, improving the effectiveness of community management and security.
[0084] S205, determining a personalized management plan for community users based on the overall behavior score, and determining a regional early warning strategy for each public sub-area of the community based on the regional risk index.
[0085] In this step, based on the overall behavior score (R_i) calculated previously, the community management system will develop a personalized management plan for each user, and determine the appropriate regional early warning strategy in combination with the regional risk index (R_{area_k}). These plans and strategies are designed to improve the security and management efficiency of the smart community. The specific process is as follows: 1. Determination of personalized management plan:
[0086] - Based on each user's overall behavior score (R_i), the community management system will evaluate the user's behavior patterns and potential risks in the community to develop personalized management plans. These plans may include specific safety measures, behavior guidance, invitations to social events, community service recommendations, etc.
[0087] - When formulating a plan, the identity type of the user (such as community residents or outsiders) must also be considered to ensure the program is targeted and effective.
[0088] 2. Determination of regional early warning strategy:
[0089] - Based on the regional risk index (R_{area_k}) of each common sub-area, the management system will identify the security level of each area and formulate corresponding early warning strategies.
[0090] - When the risk index of an area exceeds the preset threshold, corresponding early warning measures will be implemented, such as increasing security patrols, strengthening monitoring, issuing community warning information, etc., to deal with potential security threats.
[0091] Function and significance:
[0092] - Improve the effectiveness of community safety management: The development of personalized management plans and regional early warning strategies will help focus resources and attention on high-risk users and areas, thereby achieving more efficient safety management.
[0093] - Enhance users' sense of security: Personalized plans based on user behavior allow users to feel that the community values their safety, thereby increasing their trust in the community and their sense of security.
[0094] - Dynamic adaptive management: By monitoring user behavior and regional risks in real time, community management can achieve dynamic adaptive management and adjust strategies in a timely manner to cope with the ever-changing risk environment.
[0095] - Resource optimization configuration: By analyzing the overall behavior score and regional risk index, resources can be allocated more accurately, reducing unnecessary security expenditures and ensuring maximum resource utilization. One implementation method may include:
[0096] Step 1: Data integration and user behavior analysis
[0097] - First, the behavior data and scores of each user collected from the monitoring system are integrated to extract behavior-related features, such as the frequency of participation in activities, length of stay in an area, and behavior patterns. Through cluster analysis methods, the user behavior patterns are classified to identify commonalities and differences.
[0098] Step 2: Generate a personalized management plan
[0099] - Use the decision tree algorithm to generate personalized management plans based on the user's overall behavior score (R_i), combined with behavior category and identity type.
[0100] - Set decision nodes: for example, if R_i is above a certain threshold, select the "safety intervention" option; if it is below the threshold, select the "community activity recommendation" option.
[0101] - Through the tree structure, the management plan can be automatically adjusted for different users to ensure the flexibility and pertinence of the plan. Step 3: Dynamic adjustment of regional risk index
[0102] - Establish a feedback mechanism for the regional risk index (R_{area_k}). Monitor actual events (such as safety accidents, community activities) and the effectiveness of early warning strategies in the region, and update the risk index of each region in real time. - Use machine learning models (such as random forests or support vector machines) to analyze the relationship between historical events and current risk factors, and train a prediction model that dynamically adjusts the regional risk index.
[0103] Step 4: Early warning strategy generation and optimization
[0104] - Based on the updated regional risk index and combined with user behavior data, a genetic algorithm is used to optimize the regional early warning strategy.
[0105] - Define fitness function: The effectiveness of the early warning strategy will be measured by reducing the incident rate and user feedback.
[0106] - Generate initial population: including multiple warning combinations, such as the frequency, content and recipients of information push.
[0107] - Generate a new generation of early warning strategies through crossover and mutation operations, and select the optimal strategy through fitness evaluation.
[0108] Step 5: Establish a multi-level early warning system
[0109] - Establish a multi-level early warning mechanism and divide the early warning strategy into multiple levels:
[0110] - Low risk (green alert): Send regular activity notifications to encourage residents to participate in community activities.
[0111] - Medium risk (yellow alert): Enhance monitoring, increase patrol frequency, and send community safety knowledge push notifications.
[0112] - High risk (red alert): Immediately notify the security team and issue urgent safety reminders to residents.
[0113] Step 6: Feedback and Continuous Improvement
[0114] - Through the feedback data generated by community users, the effectiveness of personalized management solutions and regional early warning strategies can be continuously evaluated and improved. A / B testing can also be introduced to compare the effectiveness of different strategies to ensure that user safety and satisfaction are always the core goals in the management process.
[0115] The above algorithm implementation combines data analysis, machine learning and dynamic adjustment mechanisms to ensure that smart communities can respond to various security challenges efficiently and flexibly. This approach not only emphasizes the importance of personalized services and risk assessment, but also provides an innovative dynamic management framework, providing a new perspective and idea for the security management of smart communities.
[0116] It can be seen that through each monitoring point of the smart community, the behavior data of each user located in the public area of the smart community is collected; based on the behavior data of each user, the identity type and behavior pattern of the corresponding user are determined, and the user's behavior trajectory is generated, wherein the user identity type includes: community residents, outsiders; based on the user's identity type, behavior pattern, and behavior trajectory, the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community are calculated; based on the behavior data of each user and the regional behavior score, the regional risk index of each public sub-area of the smart community is calculated; based on the overall behavior score, the personalized management plan of the community users is determined, and based on the regional risk index, the regional early warning strategy of each public sub-area of the community is determined, so that by comprehensively collecting user behavior data, the user identity can be accurately identified, and the behavior trajectory and score can be generated, so as to reasonably assess the regional risk, formulate personalized management plans and early warning strategies, and provide strong technical support for creating a safe and harmonious smart community.
[0117] Another embodiment of the present invention provides a smart community user behavior intelligent monitoring and early warning system, see Figure 3 , the system may include:
[0118] The monitoring module 301 is used to collect the behavior data of each user in the public area of the smart community through each monitoring point of the smart community;
[0119] The determination module 302 is used to determine the identity type and behavior pattern of the corresponding user according to the behavior data of each user, and generate the behavior trajectory of the user, wherein the user identity type includes: community residents, outsiders;
[0120] The first calculation module 303 is used to calculate the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community according to the identity type, behavior pattern, and behavior trajectory of the user;
[0121] The second calculation module 304 is used to calculate the regional risk index of each public sub-area of the smart community according to each user behavior data and the regional behavior score;
[0122] The early warning module 305 is used to determine the personalized management plan of the community users according to the overall behavior score, and determine the regional early warning strategy of each public sub-area of the community according to the regional risk index.
[0123] It can be seen that through each monitoring point of the smart community, the behavior data of each user located in the public area of the smart community is collected; based on the behavior data of each user, the identity type and behavior pattern of the corresponding user are determined, and the user's behavior trajectory is generated, wherein the user identity type includes: community residents, outsiders; based on the user's identity type, behavior pattern, and behavior trajectory, the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community are calculated; based on the behavior data of each user and the regional behavior score, the regional risk index of each public sub-area of the smart community is calculated; based on the overall behavior score, the personalized management plan of the community users is determined, and based on the regional risk index, the regional early warning strategy of each public sub-area of the community is determined, so that by comprehensively collecting user behavior data, the user identity can be accurately identified, and the behavior trajectory and score can be generated, so as to reasonably assess the regional risk, formulate personalized management plans and early warning strategies, and provide strong technical support for creating a safe and harmonious smart community.
[0124] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.
[0125] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:
[0126] S201, collecting behavior data of each user in a public area of the smart community through each monitoring point of the smart community;
[0127] S202, determining the identity type and behavior pattern of the corresponding user according to the behavior data of each user, and generating the behavior trajectory of the user, wherein the user identity type includes: community resident, outsider;
[0128] S203, calculating the regional behavior score of each user during the time they are in each public sub-area and the overall behavior score during the time they are in the entire smart community according to the user's identity type, behavior pattern, and behavior trajectory;
[0129] S204, calculating the regional risk index of each public sub-area of the smart community according to each user behavior data and the regional behavior score;
[0130] S205, determining a personalized management plan for community users based on the overall behavior score, and determining a regional early warning strategy for each public sub-area of the community based on the regional risk index.
[0131] It can be seen that through each monitoring point of the smart community, the behavior data of each user located in the public area of the smart community is collected; based on the behavior data of each user, the identity type and behavior pattern of the corresponding user are determined, and the user's behavior trajectory is generated, wherein the user identity type includes: community residents, outsiders; based on the user's identity type, behavior pattern, and behavior trajectory, the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community are calculated; based on the behavior data of each user and the regional behavior score, the regional risk index of each public sub-area of the smart community is calculated; based on the overall behavior score, the personalized management plan of the community users is determined, and based on the regional risk index, the regional early warning strategy of each public sub-area of the community is determined, so that by comprehensively collecting user behavior data, the user identity can be accurately identified, and the behavior trajectory and score can be generated, so as to reasonably assess the regional risk, formulate personalized management plans and early warning strategies, and provide strong technical support for creating a safe and harmonious smart community.
[0132] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0133] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0134] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0135] S201, collecting behavior data of each user in a public area of the smart community through each monitoring point of the smart community;
[0136] S202, determining the identity type and behavior pattern of the corresponding user according to the behavior data of each user, and generating the behavior trajectory of the user, wherein the user identity type includes: community resident, outsider;
[0137] S203, calculating the regional behavior score of each user during the time they are in each public sub-area and the overall behavior score during the time they are in the entire smart community according to the user's identity type, behavior pattern, and behavior trajectory;
[0138] S204, calculating the regional risk index of each public sub-area of the smart community according to each user behavior data and the regional behavior score;
[0139] S205, determining a personalized management plan for community users based on the overall behavior score, and determining a regional early warning strategy for each public sub-area of the community based on the regional risk index.
[0140] It can be seen that through each monitoring point of the smart community, the behavior data of each user located in the public area of the smart community is collected; based on the behavior data of each user, the identity type and behavior pattern of the corresponding user are determined, and the user's behavior trajectory is generated, wherein the user identity type includes: community residents, outsiders; based on the user's identity type, behavior pattern, and behavior trajectory, the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community are calculated; based on the behavior data of each user and the regional behavior score, the regional risk index of each public sub-area of the smart community is calculated; based on the overall behavior score, the personalized management plan of the community users is determined, and based on the regional risk index, the regional early warning strategy of each public sub-area of the community is determined, so that by comprehensively collecting user behavior data, the user identity can be accurately identified, and the behavior trajectory and score can be generated, so as to reasonably assess the regional risk, formulate personalized management plans and early warning strategies, and provide strong technical support for creating a safe and harmonious smart community.
[0141] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.
Claims
1. A smart community user behavior intelligent monitoring and early warning method, characterized in that: The method comprises: Through various monitoring points in the smart community, collect the behavior data of each user in the public area of the smart community; According to each user's behavior data, determine the corresponding user's identity type and behavior pattern, and generate the user's behavior trajectory, wherein the user identity type includes: community residents, outsiders; According to the user's identity type, behavior pattern, and behavior trajectory, the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community are calculated; wherein the calculation formulas for the regional behavior score and the overall behavior score are as follows: Wherein, R′_ik is the regional behavior score of the ith user in the kth common sub-area, R_i is the overall behavior score of the ith user, w_i is the identity weight value corresponding to the identity type used to reflect the degree of influence of the identity on the behavior, S_ir is the behavior score corresponding to the rth behavior mode in the kth common sub-area used to assess the behavior risk, S_ij is the behavior score corresponding to the jth behavior mode in the smart community, P′_ik is the trajectory index corresponding to the behavior trajectory in the kth common sub-area used to amplify the overall behavior impact, P_i is the trajectory index corresponding to the behavior trajectory in the smart community, v is the number of behavior patterns in the behavior trajectory of the kth common sub-area, and m is the number of behavior patterns in the behavior trajectory of the smart community; According to each user behavior data and the regional behavior score, the regional risk index of each public sub-area of the smart community is calculated; the regional risk index is calculated as follows: Wherein, R_{area_k} is the regional risk index of the kth public sub-area, Env_k is the environmental risk weight of the kth public sub-area, which is obtained based on a comprehensive evaluation of the environmental sensor data in the current public sub-area, alpha_ik is the residence time weight of the ith user in the kth public sub-area, u is the number of users in the kth public sub-area, D_trafffc_k is the crowd flow intensity in the kth public sub-area, lambda_k is the flow impact factor in the kth public sub-area, S_incident_k is the historical event impact score of the kth public sub-area, which is evaluated based on the number and severity of abnormal events that occurred in the public sub-area in the past period of time, and gamma_k is the historical event impact factor, which considers the contribution of abnormal events that occurred in the public sub-area to the current security risk; Based on the overall behavior score, a personalized management plan for community users is determined, and based on the regional risk index, a regional early warning strategy for each public sub-area of the community is determined.
2. The method according to claim 1, characterized in that in, The residence time weight is: Wherein, T_stay_ik is the actual stay time of the i-th user in the k-th public sub-area, and T_total_k is the total monitoring time in the k-th public sub-area; The crowd flow intensity is: Wherein, the V_traffic_k is the flow of people in the kth public sub-area, and the A_area_k is the total area of the kth public sub-area.
3. A smart community user behavior intelligent monitoring and early warning system, characterized in that: The system comprises: The monitoring module is used to collect the behavior data of each user in the public area of the smart community through various monitoring points of the smart community; A determination module is used to determine the identity type and behavior pattern of the corresponding user according to the behavior data of each user, and generate the user's behavior trajectory, wherein the user identity type includes: community residents, outsiders; The first calculation module is used to calculate the regional behavior score of each user during the period when they are in each public sub-area and the overall behavior score during the period when they are in the entire smart community according to the user's identity type, behavior pattern, and behavior trajectory; wherein the calculation formulas for the regional behavior score and the overall behavior score are: Wherein, R′_ik is the regional behavior score of the ith user in the kth common sub-area, R_i is the overall behavior score of the ith user, w_i is the identity weight value corresponding to the identity type used to reflect the degree of influence of the identity on the behavior, S_ir is the behavior score corresponding to the rth behavior mode in the kth common sub-area used to assess the behavior risk, S_ij is the behavior score corresponding to the jth behavior mode in the smart community, P′_ik is the trajectory index corresponding to the behavior trajectory in the kth common sub-area used to amplify the overall behavior impact, P_i is the trajectory index corresponding to the behavior trajectory in the smart community, v is the number of behavior patterns in the behavior trajectory of the kth common sub-area, and m is the number of behavior patterns in the behavior trajectory of the smart community; The second calculation module is used to calculate the regional risk index of each public sub-area of the smart community according to each user behavior data and the regional behavior score; the regional risk index is calculated as follows: Wherein, R_{area_k} is the regional risk index of the kth public sub-area, Env_k is the environmental risk weight of the kth public sub-area, which is obtained based on a comprehensive evaluation of the environmental sensor data in the current public sub-area, alpha_ik is the residence time weight of the ith user in the kth public sub-area, u is the number of users in the kth public sub-area, D_trafffc_k is the crowd flow intensity in the kth public sub-area, lambda_k is the flow impact factor in the kth public sub-area, S_incident_k is the historical event impact score of the kth public sub-area, which is evaluated based on the number and severity of abnormal events that occurred in the public sub-area in the past period of time, and gamma_k is the historical event impact factor, which considers the contribution of abnormal events that occurred in the public sub-area to the current security risk; The early warning module is used to determine the personalized management plan for community users based on the overall behavior score, and to determine the regional early warning strategy for each public sub-area of the community based on the regional risk index.
4. The system according to claim 3, characterized in that in, The residence time weight is: Wherein, T_stay_ik is the actual stay time of the i-th user in the k-th public sub-area, and T_total_k is the total monitoring time in the k-th public sub-area; The crowd flow intensity is: Wherein, the V_traffc_k is the flow of people in the kth public sub-area, and the A_area_k is the total area of the kth public sub-area.
5. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 2 when executed.
6. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 2.