Smart campus security early warning management method and system

Abstract

The invention provides a smart campus security early warning management method and system, and relates to the technical field of smart campus management, and the method comprises the steps: extracting the security demand information of students in a campus from campus security data; determining interaction early warning attributes in a target campus security supervision period through security deployment paths and track association levels in historical security event libraries of different supervision areas of the target campus; determining a security offset node of each supervision area in the target campus according to the security risk index, and determining a correction behavior tag of the student in the target campus according to the security offset node and the interactive early warning attribute; and managing and controlling the safety behavior characteristics of the students in the target campus according to the corrected behavior labels, and generating early warning feedback information of the activities of the students in the target campus. According to the application, fusion deduction can be carried out on the association relationship between the student behavior track and the security resource dynamic demand, so that the response accuracy of the campus security system is improved.

Description

Technical Field

[0001] This application relates to the technical field of smart campus management. More specifically, this application relates to a method and system for security warning management in a smart campus. Background Art

[0002] Smart campus management refers to the use of information technologies such as the Internet of Things, artificial intelligence, big data, and cloud computing to comprehensively perceive, fuse data, intelligently analyze, and coordinately control people, objects, the environment, and behaviors within the campus, realizing an intelligent operation mode for education and teaching, campus management, and security protection. In the smart campus management system, by deploying sensing terminals such as sensors, monitoring devices, and intelligent access control systems, behavioral data and environmental information of students and faculty are collected in real time; the collected information is centrally analyzed through a data platform to construct behavioral portraits and risk models, and an automatic response mechanism is formed. Especially in campus security management, intelligent means can achieve the transformation from traditional "post-event response" to "pre-event warning and in-event control", improving the prediction and response efficiency for abnormal behaviors and emergencies.

[0003] However, existing methods for security warning management in smart campuses generally have technical defects such as lack of refined identification of individual student behaviors, static and fixed warning rules, and fragmentation of security response mechanisms between regions. As a result, the system is difficult to timely perceive and dynamically respond to the behavioral changes of students in different risk scenarios, leading to low prediction accuracy for potential security threats, lagged responses, and low resource scheduling efficiency, thus restricting the intelligent, interconnected, and personalized management level of the campus security system. Therefore, how to fuse and deduce the correlation between students' behavioral trajectories and the dynamic demand for security resources to improve the response accuracy of the campus security system is an issue faced by the industry. Summary of the Invention

[0004] This application provides a method and system for security warning management in a smart campus, which can fuse and deduce the correlation between students' behavioral trajectories and the dynamic demand for security resources to improve the response accuracy of the campus security system.

[0005] In a first aspect, this application provides a method for security warning management in a smart campus. The management method includes the following steps: Collect campus security data in a designated supervision area of the target campus in real time, and extract security demand information of students within the campus from the campus security data; Perform correlation grading on the security demand information to obtain the trajectory correlation level of students' activities within the campus, and determine the interactive warning attributes within the security supervision period of the target campus through the security deployment paths in the historical security event libraries of different supervision areas of the target campus and the trajectory correlation level; Obtain the security risk indicators of different supervision areas in the target campus, determine the security offset nodes of each supervision area in the target campus according to the security risk indicators, and then determine the corrected behavior labels of students in the target campus from the security offset nodes and the interactive warning attributes; Control the security behavior characteristics of students in the target campus according to the corrected behavior labels, and generate warning feedback information on the activities of students in the target campus.

[0006] In this embodiment, the campus security data refers to multi-source perception information of personnel behavior, environmental status, and security incidents in the campus.

[0007] In this embodiment, extracting the security demand information of students in the campus from the campus security data specifically includes: Determine the student behavior trajectory based on the security distribution characteristics of the campus security data; Determine the security resource allocation amount under different risk scenarios according to the student behavior trajectory; Determine the security demand information of students in the campus through the security resource allocation amount.

[0008] In this embodiment, associating and grading the security demand information to obtain the trajectory association level of students' activities in the campus specifically includes: Construct a trajectory feature set of students' activities through the security demand information; Extract the alienation risk information of students' activities in the campus from the trajectory feature set; Determine the risk association rules when students are active in the campus; Map the risk association rules to the alienation risk information to obtain the trajectory association level of students' activities in the campus.

[0009] In this embodiment, the trajectory association level represents a hierarchical structure constructed by classifying students' behavior trajectories according to their risk levels, behavior complexities, and rule matching results.

[0010] In this embodiment, determining the interactive warning attributes during the security supervision period of the target campus through the security deployment path in the historical security event library of different supervision areas of the target campus and the trajectory association level specifically includes: Obtain the security deployment path in the historical security event library of different supervision areas of the target campus; Determine the collaborative warning rules during the security supervision period of the target campus according to the security deployment path; Determine the interactive warning attributes during the security supervision period of the target campus according to the collaborative warning rules and the trajectory association level.

[0011] In this embodiment, the interactive warning attribute represents an antecedent identifier for cross-regional security responses triggered by the student's behavior trajectory within a given security supervision period.

[0012] In this embodiment, determining the corrected behavior label of the student in the target campus based on the security offset node and the interactive warning attribute specifically includes: Determining the security configuration strategy when the student is active on campus according to the security offset node; Determining the collaborative response logic within the security supervision period of the target campus according to the interactive warning attribute; Determining the corrected behavior label of the student in the target campus through the security configuration strategy and the collaborative response logic.

[0013] In this embodiment, the corrected behavior label represents an identifier for evaluating the security of the student's behavior and adjusting the student's behavior.

[0014] In a second aspect, the present application provides a smart campus security warning management system for implementing a smart campus security warning management method. The management system includes: A data collection module for collecting campus security data in a designated supervision area of the target campus in real time and extracting security requirement information of students within the campus from the campus security data; An association grading module for associating and grading the security requirement information to obtain the trajectory association level of the student's activities within the campus, and determining the interactive warning attribute within the security supervision period of the target campus through the security deployment path in the historical security event library of different supervision areas of the target campus and the trajectory association level; A behavior recognition module for obtaining the security risk indicators of different supervision areas in the target campus, determining the security offset node of each supervision area in the target campus according to the security risk indicators, and then determining the corrected behavior label of the student in the target campus based on the security offset node and the interactive warning attribute; A warning control module for controlling the security behavior characteristics of students in the target campus based on the corrected behavior label and generating warning feedback information on the activities of students in the target campus.

[0015] The technical solution provided by the disclosed embodiments of the present application has the following beneficial effects: Collect campus security data in real time from designated monitoring areas of the target campus, and extract the security demand information of students on campus from the campus security data; perform correlation grading on the security demand information to obtain the trajectory correlation levels of students' activities on campus, and determine the interactive warning attributes during the campus security supervision period of the target campus through the security deployment paths in the historical security event libraries of different monitoring areas of the target campus and the trajectory correlation levels; obtain the security risk indicators of different monitoring areas in the target campus, determine the security offset nodes of each monitoring area in the target campus according to the security risk indicators, and further determine the corrected behavior labels of students in the target campus from the security offset nodes and the interactive warning attributes; control the security behavior characteristics of students in the target campus according to the corrected behavior labels, and generate warning feedback information on the activities of students in the target campus.

[0016] It can be seen that in this application, the behavior changes of students in different risk situations can be sensed in a timely manner and dynamically responded to; among them, the dynamic perception of students' behaviors and the security environment in the campus monitoring area and the accurate demand recognition can timely grasp the security support needs of individual students at specific times and in specific spaces; through the integration of the deployment experience of historical security events and the behavior grading rules, the early judgment of potential risk paths and the dynamic generation of multi-area collaborative warning attributes are realized, thereby enhancing the recognition ability and warning linkage of the security system for complex behavior patterns; through the integrated analysis of resource gaps and risk indicators, the security weak links of each monitoring area are accurately located, and corrected behavior labels are generated in combination with the behavior characteristics of students, realizing the classified management and differential intervention of the behavior risks of individual students, thereby effectively improving the deployment efficiency of security resources and the accuracy of responding to sudden risks; through the matching and linkage of real-time trajectories and the rule library, the intelligent intervention ability and response efficiency of the security system are improved, thereby realizing the active defense and accurate decision-making of campus security management, and promoting the evolution of campus security from passive response to intelligent initiative.

[0017] In summary, the technical solution adopted in this application can perform integrated deduction on the correlation relationship between students' behavior trajectories and the dynamic demand of security resources to improve the response accuracy of the campus security system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 is an exemplary flowchart of a smart campus security warning management method provided by the present application; Figure 2 It is a schematic flowchart of the process for determining the trajectory association level provided by this application; Figure 3 It is a schematic flowchart of the process for determining the security offset node provided by this application; Figure 4 It is a module structure diagram of an intelligent campus security warning management system provided by this application. Specific implementation manners

[0020] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0021] The embodiments of this application provide an intelligent campus security warning management method and system, the core of which is to collect campus security data in a specified supervision area of a target campus in real time, and extract security demand information of students in the campus from the campus security data; perform association grading on the security demand information to obtain the trajectory association level of students' activities in the campus, and determine the interactive warning attribute within the security supervision period of the target campus through the security deployment path in the historical security event library of different supervision areas of the target campus and the trajectory association level; obtain the security risk indicators of different supervision areas in the target campus, determine the security offset node of each supervision area in the target campus according to the security risk indicators, and further determine the corrected behavior label of students in the target campus from the security offset node and the interactive warning attribute; control the safety behavior characteristics of students in the target campus according to the corrected behavior label, and generate warning feedback information on the activities of students in the target campus.

[0022] Embodiment 1. To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners. Refer to Figure 1 As shown, this figure is an exemplary flowchart of an intelligent campus security warning management method shown in this embodiment of this application. The management method includes the following steps: In step S1, collect campus security data in a specified supervision area of a target campus in real time, and extract security demand information of students in the campus from the campus security data.

[0023] In specific implementation, the real-time collection of campus security data in the designated supervision area of the target campus can be achieved in the following ways: First, in areas with dense population or high risk levels, such as the entrances and exits of teaching buildings, dormitory corridors, the interiors of libraries and experimental buildings, network cameras with high-definition image capture and night vision capabilities are installed. These cameras continuously transmit video streams to the edge computing nodes through the RTSP protocol. Second, RFID access control devices are deployed in all main channels to record student identities and entry and exit time information for constructing behavior paths. At the same time, IoT devices such as infrared human sensors, smoke alarms, and environmental noise sensors are installed to achieve real-time monitoring of illegal stays, fire warnings, or abnormal noises. The data of all sensing devices is first aggregated to the edge computing gateways deployed on the edge side of each area and preliminarily processed through local algorithms, such as image compression, anomaly marking, or data synchronization. Subsequently, this structured or semi-structured data is encrypted and transmitted to the campus security management platform through the MQTT or HTTPS protocol to achieve unified data access. Finally, the real-time recorded campus security data is obtained by reading the data storage unit in the campus security management platform.

[0024] It should be noted that in this application, campus security data refers to multi-source perception information of personnel behavior, environmental status, and security events on campus.

[0025] In this embodiment, the extraction of students' security demand information from the campus security data can be achieved through the following steps: Determine the student behavior trajectory based on the security distribution characteristics of the campus security data; Determine the security resource allocation quantity in different risk scenarios according to the student behavior trajectory; Determine the students' security demand information on campus through the security resource allocation quantity.

[0026] In specific implementation, first, a continuous movement path of students on campus is constructed by integrating video surveillance, access control data, and RFID access records. In the continuous movement path, a trajectory reconstruction algorithm is used to remove abnormal points to obtain an accurate time series trajectory. Behavior feature nodes such as "long stay" and "abnormal crossing of multiple security level areas" are marked in the time series trajectory. The marked behavior feature nodes are used as the student behavior trajectory. Among them, the trajectory reconstruction algorithm can be the splicing of Kalman filtering and a sliding window. Then, a campus security resource distribution map is constructed, recording indicators such as camera density, security patrol frequency, and emergency response time in each area. According to the areas passed by students in the student behavior trajectory, security response ability parameters in different risk scenarios are extracted. Then, the student behavior trajectory, the security distribution map, and the security response ability parameters are superimposed, and the total security response that can be triggered in different risk scenarios is calculated using scenario reasoning based on a Bayesian network. The total security response is used as the security resource allocation amount, where the resource allocation amount includes: the number of cameras that need to be concerned, the number of security personnel interventions, and the alarm possibility level. Finally, when the student behavior trajectory crosses multiple resource - strained areas or there are high - frequency abnormal behaviors, the system marks the corresponding trajectory as the "high - demand" state, and the system attaches a security demand label to this behavior, including risk level, coverage area, priority, and intervention suggestions, forming complete security demand information.

[0027] It should be noted that in this application, the security distribution feature represents an information set such as the density, coverage range, and historical response efficiency of security facilities in different supervision areas, and is used to measure the response ability and prevention and control level of the area to potential risks; the student behavior trajectory refers to the spatio - temporal path information of students moving and staying among different areas on campus; the security resource allocation amount refers to the total amount of security resources that the system needs to mobilize under a specific risk scenario or behavior trajectory; the security demand information refers to the security protection response demand generated by students based on their behavior trajectory, the environment they are in, and the available security resources in a specific time and space background.

[0028] In step S2, the security demand information is associated and classified to obtain the trajectory association level of students' activities on campus. The interaction warning attribute within the security supervision period of the target campus is determined through the security deployment path in the historical security event library of different supervision areas of the target campus and the trajectory association level.

[0029] Preferably, in this embodiment, the security demand information is associated and classified to obtain the trajectory association level of students' activities on campus. Refer to Figure 2 As shown, this figure is a schematic flowchart of determining the trajectory association level in some embodiments of this application. The trajectory association level in this embodiment can be implemented by the following steps: In step S21, a trajectory feature set of student activities is constructed based on the security requirement information; In step S22, the dissimilation risk information of students' activities on campus is extracted from the trajectory feature set; In step S23, the risk association rules for students' activities on campus are determined; In step S24, the risk association rules are mapped to the dissimilation risk information to obtain the trajectory association level of students' activities on campus.

[0030] Specifically, in implementation, first, when constructing the trajectory feature set of student activities, the student behavior trajectories that have passed the security requirement assessment and their risk level labels are used as inputs. Elements such as single-point residence time, behavior interval, spatial path length and regional span, number of triggered cameras, frequency of security personnel deployment, abnormal entry and exit, crossing the boundary, and frequent round trips are extracted from each student behavior trajectory. The extracted elements are encoded into multi-dimensional vectors to form the trajectory feature set. Then, a normal behavior trajectory template library is introduced, and the dynamic time warping (DTW) is used to identify the behavior segments that deviate significantly from the normal behavior trajectory templates. The clustering algorithm is used to classify the deviated segments to identify the following risk segments: entering key areas during non-peak hours, continuously accessing high-alert areas without authorization, and making multiple short cross-regional round trips, etc. The identified risk segments and their locations, times, and risk labels are used as the dissimilation risk information. Next, frequent pattern mining is performed on a large number of student behavior trajectories. Among them, frequent pattern mining can use the Apriori or FP-Growth algorithm, and the sequential patterns and co-occurrence relationships of risk events occurring in different student behavior trajectories are extracted, such as "long stay at night → enter the closed floor → abnormal alarm". Then, the risk association rules for students' activities on campus are constructed according to the following rules: if behavior A is followed by behavior B and occurs in a specific area, the associated risk is increased; if the three high-frequency behaviors of long stay at night, entering the closed floor, and abnormal alarm appear simultaneously, a comprehensive risk weight is assigned. Finally, the dissimilation risk information in each student behavior trajectory is matched with the risk association rules, the risk linkage structures existing in the student behavior trajectories are marked, and then the trajectory association levels are divided: including: the first-level level, which has the characteristics of full rule matching and high-frequency recurrence and belongs to the key intervention object; the second-level level, with partial rule matching and a potential risk propagation trend; the third-level level, where the behavior trajectory only deviates locally, is concerned but does not require intervention; the trajectory association level of students' activities on campus is output.

[0031] It should be noted that in this application, the trajectory feature set represents a set of structured feature data combining spatial, temporal, behavior pattern, and security requirement attributes in the student behavior trajectory; the alienation risk information represents the local segment attributes of the student behavior trajectory that deviate from the normal behavior pattern, have potential security hazards, and abnormal resource occupancy characteristics; the risk association rule represents the spatio-temporal combination, transfer relationship, and repetition pattern between high-risk behaviors mined from different student behavior trajectories; the trajectory association level represents the hierarchical structure constructed by classifying student behavior trajectories according to their risk levels, behavior complexities, and rule matching results.

[0032] In this embodiment, the interactive warning attribute within the security supervision period of the target campus can be determined by the security deployment path in the historical security event library of different supervision areas of the target campus and the trajectory association level through the following steps: Obtain the security deployment path in the historical security event library of different supervision areas of the target campus; Determine the collaborative warning rule within the security supervision period of the target campus according to the security deployment path; Determine the interactive warning attribute within the security supervision period of the target campus according to the collaborative warning rule and the trajectory association level.

[0033] In specific implementation, first, summarize the security event data in the past several months or semesters to construct a structured historical event library. For each event, extract: trigger source information (starting area, event type, trigger time); response resource allocation record (security personnel mobilization route, video dispatching area, device activation sequence); final disposal feedback (response duration, number of linked areas, event result). Then, use a graph model (such as a directed graph) to abstract the area nodes and response paths into a deployment path graph, record the direction, frequency, and time cost of resource scheduling, and form a dynamic deployment path library. Read the security deployment paths in the historical security event library of different supervision areas of the target campus from the dynamic deployment path library. Then, identify high-frequency linked paths through path analysis algorithms (such as PageRank or path frequency statistics), and analyze the following types of collaboration features: multiple events frequently trigger the same deployment path, events in a certain area often respond simultaneously with the adjacent two areas, and paths with low response efficiency repeatedly appear. Based on the collaboration features, construct collaboration warning rules within the security supervision cycle of the target campus, including: if area A triggers a high-risk behavior and the behavior trajectory involves areas B and C, then trigger a three-level linked warning; if the response time of a certain security deployment path continuously exceeds the set threshold, relevant areas need to be warned in advance. Finally, match the trajectory association level of the current student trajectory with the collaboration warning rules: if the trajectory association level is a first-level trajectory and covers more than two high-frequency deployment paths, directly assign "high-level linked warning"; if the trajectory association level of the student trajectory partially matches the collaboration warning rules and only involves single-path response, assign "medium-level one-way warning"; if the collaboration warning rule is a probabilistic event or a rare response path, mark it as "low-level potential warning". Then extract the affected supervision area numbers; potential deployment resource types (such as whether manual linkage is involved); warning timeliness (effective duration of the warning); linked intensity level (mild, moderate, severe), and use the extracted content as the interactive warning attributes within the security supervision cycle of the target campus.

[0034] It should be noted that in this application, the historical security event library represents a data set recording past security events and response details in each supervision area of the campus; the security deployment path refers to the actual sequence of procedures for the collaborative mobilization of security resources (such as personnel, cameras, alarm devices) across regions after an event is triggered during the response to historical security events; the collaboration warning rule represents a multi-region security event linked response mode summarized based on the historical linked disposal experience of multiple supervision areas; the interactive warning attribute represents the prior identifier for the cross-region security response triggered by the student behavior trajectory within a given security supervision cycle, and the security supervision cycle refers to a dynamic security management period set according to the behavior density, risk prediction, and resource rotation strategy during the dynamic operation of a campus security system.

[0035] In step S3, obtain the security risk indicators of different supervision areas in the target campus, determine the security offset nodes of each supervision area in the target campus according to the security risk indicators, and then determine the corrected behavior labels of students in the target campus from the security offset nodes and the interactive warning attributes.

[0036] Specifically, obtaining the security risk indicators of different supervision areas in the target campus can be implemented in the following way: The system accesses the real-time and historical security data sources of each supervision area, including video surveillance anomalies, access control anomalies, changes in personnel density, alarm records, and security personnel deployment. Then, based on statistical modeling methods (such as sliding time window aggregation and heat matrix analysis), extract core quantitative indicators such as the frequency of security events, the incidence rate of abnormal behaviors, the average response delay, and the proportion of high-risk behaviors per unit time in each area. After normalizing the core quantitative indicators, input them into a weighted evaluation model (such as a weighted scoring model based on AHP) to obtain the security risk scores corresponding to each area, and use the security risk scores as a set of security risk indicators that cover each supervision area and can be dynamically updated, that is, the security risk indicators of different supervision areas in the target campus.

[0037] It should be noted that in this application, the security risk indicator refers to a set of data indicators that measure the probability of security events and the potential harm degree in each supervision area of the campus within a specific time period.

[0038] Preferably, in this embodiment, to determine the security offset nodes of each supervision area in the target campus according to the security risk indicators, refer to Figure 3 As shown in the figure, which is a schematic flowchart of determining the security offset nodes in some embodiments of this application. Determining the security offset nodes in this embodiment can be implemented by the following steps: In step S31, determine the resource gap index in each supervision area of the target campus according to the security risk indicators; In step S32, match and screen the emergency response paths in the historical security event library through the resource gap index to obtain the resource matching status; In step S33, determine the security requirement boundary of each supervision area in the target campus; In step S34, determine the security offset nodes of each supervision area in the target campus according to the resource matching status and the security requirement boundary.

[0039] In specific implementation, first, in combination with the security risk indicators of each supervision area (such as event frequency, response duration, etc.), evaluate the adaptability of the current security resource allocation. Then, use the difference method to calculate the difference between the actually allocated security resources and the demand, and obtain the resource gap index in each supervision area of the target campus. If the resource gap index is large, it indicates that there is a high security risk in this area. Then, according to the resource gap index, screen the resource allocation paths in the historical security event library, match the historical emergency paths that can solve the current regional resource shortage problem, and use the K-nearest neighbor algorithm or the dynamic matching method based on similarity to screen out the event response paths with similar resource allocations in history, form the resource matching status, and record whether the resources can meet the current demand. Next, determine the security demand boundary of each area according to the maximum response capacity of resource allocation and the most complex event processed in the historical security events; and set the minimum boundary of resource allocation through factors such as event processing ability, regional scale, and potential risks, such as the minimum number of security personnel or the minimum camera coverage range of a building, etc., to ensure that all potential risks can be protected within a controllable range. Finally, compare the resource matching status and the security demand boundary. If at a certain moment or in a certain area, the resource matching is insufficient or exceeds the demand boundary, then this area is regarded as having a security deviation node, which will not be elaborated here.

[0040] It should be noted that in this application, the resource gap index represents the unmet security demand in each supervision area under the current security resource allocation; the emergency response path represents that when a security event occurs, the security resources are based on the event type and regional demand; the resource matching status represents whether the resource allocation paths that have occurred in the historical security event library can effectively meet the security demand of the current area; the security demand boundary represents the boundary of the minimum resource allocation required for different security events within a specific time and regional range; the security deviation node represents the node where the allocation of security resources in the area is abnormal or insufficient under a specific scenario.

[0041] In this embodiment, determining the corrected behavior label of the student in the target campus based on the security deviation node and the interactive warning attribute can be implemented by the following steps: Determine the security configuration strategy when the student is active on campus according to the security deviation node; Determine the collaborative response logic within the security supervision cycle of the target campus according to the interactive warning attribute; Determine the corrected behavior label of the student in the target campus through the security configuration strategy and the collaborative response logic.

[0042] In specific implementation, first, for each security offset node, according to its security requirement boundary and resource gap index, a specific security configuration strategy is formulated. For example, if the camera coverage in a certain area is insufficient, the system will provide solutions such as enhancing camera monitoring or dispatching more security personnel according to the resource gap. Then, according to the interactive warning attributes (such as multiple areas triggering warnings simultaneously, cross-behavior patterns, or events with a high risk level), it is evaluated whether multi-area collaborative response is required, and then according to the distribution and level of the warning events, the collaborative response logic within the target campus security supervision period is set. For example, if a security event in one area affects the safety of the adjacent area, the monitoring resources or personnel in the adjacent area will be automatically dispatched, and the response priority will be increased. Finally, by analyzing the behavior trajectories of students (such as abnormal stays, area access frequencies, etc.), combined with the security configuration strategy and collaborative response logic, it is judged whether the students' behaviors deviate from the normal mode. If the behaviors of students trigger high-risk or resource-allocation-insufficient situations in certain areas, correction behavior labels for the students in the target campus are generated according to the predetermined rules. The predetermined rules include: if a student frequently enters and exits high-risk areas without triggering the due security response, mark the student's behavior as "unsafe" or "correction necessary".

[0043] It should be noted that in this application, the security configuration strategy represents a combination of reasonable resource allocation and security measures determined according to the security requirements, resource allocation, and risk assessment of different areas within the campus; the collaborative response logic represents the strategy of how to coordinate and mobilize resources and respond to security threats among multiple areas in the security system when warnings occur in multiple monitoring areas; the correction behavior label represents an identifier for evaluating the security of students' behaviors and adjusting students' behaviors.

[0044] In step S4, the security behavior characteristics of students in the target campus are controlled according to the correction behavior label, and warning feedback information on the activities of students in the target campus is generated.

[0045] In this embodiment, the security behavior characteristics of students in the target campus are controlled according to the correction behavior label, and the warning feedback information on the activities of students in the target campus can be implemented by the following steps: Based on the security classification attributes and associated disposal strategies in the correction behavior label, a dynamic hierarchical control rule library is constructed; Collect the real-time trajectory data of students within the campus; Match the real-time trajectory data with the dynamic hierarchical control rule library, and trigger the regionalized control instruction set in the target campus; The security behavior characteristics of students in the target campus are jointly controlled by the regionalized control instruction set to obtain the security warning trend; Determine the warning feedback information on the activities of students in the target campus according to the security warning trend.

[0046] In the specific implementation, first, different behavior categories are constructed according to the security classification attributes (such as abnormal behavior, frequent entry and exit of high-risk areas, etc.) in the modified behavior tags and the associated disposal strategies. Each category corresponds to a set of specific control rules. For example, "frequent entry and exit of prohibited areas" may require stricter behavior inspections or personnel tracking; then, based on the risk level of student behavior, dynamic hierarchical control rules are created for each behavior category. For high-risk behaviors, automatic alarms, security patrols and other measures can be set; while low-risk behaviors may only need to be recorded and analyzed, and all dynamic hierarchical control rules are composed of dynamic hierarchical control rule libraries. Next, a real-time positioning system is deployed on campus, such as real-time tracking of student locations through technologies such as WIFI, GPS, and RFID; students' real-time location, activity area, stay time and other data are continuously collected, and student behavior characteristics are recorded through monitoring and sensors, such as the time point of entering or leaving a specific area, the movement path, etc., and the recorded student behavior characteristics are used as real-time trajectory data of students on campus. Thirdly, through pattern recognition and behavior analysis, the real-time trajectory data of students is matched with the behavior characteristics in the dynamic hierarchical control rule library to determine whether the students have high-risk behaviors. If potential risk behaviors are matched, the corresponding regional control instruction set is triggered according to the dynamic hierarchical control rule library. For example, if a student enters a restricted area, the system may issue a security personnel arrival instruction or trigger the access control system. Then, according to the triggered regional control instruction set, the security system and security personnel in the area are linked to control, for example, increasing the monitoring density of a certain area, or directly intervening in the behavior of students to ensure that the security needs of the area are met, that is, to obtain the security warning trend; the regional control instruction set will automatically adjust according to the changes in real-time data to ensure that security management can adapt to changes in student behavior and campus environment. Finally, based on the real-time changes in student behavior and the response of the security system, the potential security event trend is analyzed. For example, if a certain area frequently triggers security events, the system will predict that there may be a large security risk in the area; according to the security warning trend, detailed warning feedback information is generated, including the specific behavior risk level, the corresponding security measures, and related intervention suggestions, and the security personnel or managers are notified in time.

[0047] It should be noted that in this application, the security classification attribute represents the standard for classifying student behavior types according to the security risks of student behavior; the associated disposal strategy represents the corresponding countermeasures formulated according to the risk level of student behavior based on the security classification attribute; the dynamic grading control rule library refers to a set of rule libraries dynamically generated according to the severity of different security incidents and the corrected behavior labels, which is used to formulate different security response measures and control strategies, and this dynamic grading control rule library will be adjusted according to the real-time security threats on campus and the changes in student behavior; the real-time trajectory data represents the information such as the real-time location, movement path, and stay time of students on campus collected by various security devices; the regionalized control instruction set represents a set of specific behavior intervention instructions issued according to the security requirements of different regions based on the dynamic grading control rules; the security behavior characteristics refer to the behavior patterns of students on campus, including normal activities, abnormal behaviors, potential risks, etc.; the security warning trend represents the warning information about the occurrence trend of potential security incidents generated based on the real-time monitoring of student behavior, trajectory analysis, and security response; the warning feedback information represents the alarm or notification information generated by the system according to the security warning trend and fed back to relevant management personnel or students.

[0048] It can be seen that in this application, the behavior changes of students in different risk situations can be timely perceived and dynamically responded to; among them, the dynamic perception and accurate demand identification of student behavior and the security environment in the campus supervision area can timely master the security support needs of individual students at specific times and locations; through the integration of the deployment experience of historical security incidents and the behavior grading rules, the early judgment of potential risk paths and the dynamic generation of multi-region collaborative warning attributes are realized, so as to enhance the recognition ability and warning linkage of the security system for complex behavior patterns; through the integrated analysis of resource gaps and risk indicators, the security weak links in each supervision area are accurately located, and corrected behavior labels are generated in combination with the behavior characteristics of students, so as to realize the classified management and differential intervention of the behavior risks of individual students, thus effectively improving the deployment efficiency of security resources and the accuracy of dealing with sudden risks; through the matching and linkage of real-time trajectories and the rule library, the intelligent intervention ability and response efficiency of the security system are improved, so as to realize the active defense and accurate decision-making of campus security management, and promote the evolution of campus security from passive response to intelligent initiative.

[0049] In summary, the technical solution adopted in this application can fuse and deduce the correlation between the student behavior trajectory and the dynamic demand of security resources to improve the response accuracy of the campus security system.

[0050] Embodiment 2, this application provides a smart campus security warning management system. Refer to Figure 4 As shown in the figure, which is a module structure diagram of a smart campus security warning management system according to this embodiment of this application. The management system includes: The data acquisition module 100 is used to collect the campus security data in the specified supervision area of the target campus in real time, and extract the security demand information of students on campus from the campus security data; The association and grading module 200 is used to perform association and grading on the security demand information to obtain the trajectory association levels of students' activities on campus, and determine the interaction warning attributes during the security supervision period of the target campus through the security deployment paths in the historical security event libraries of different supervision areas of the target campus and the trajectory association levels; The behavior recognition module 300 is used to obtain the security risk indicators of different supervision areas in the target campus, determine the security offset nodes of each supervision area in the target campus according to the security risk indicators, and further determine the corrected behavior labels of students in the target campus from the security offset nodes and the interaction warning attributes; The warning control module 400 is used to control the safety behavior characteristics of students in the target campus according to the corrected behavior labels, and generate warning feedback information on the activities of students in the target campus.

[0051] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0052] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disc memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0053] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitations, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, commodity or device including the element.

Claims

1. A security warning management method for a smart campus, characterized in that, The management method includes the following steps: Collect campus security data in a designated supervision area of the target campus in real time, and extract the security demand information of students on campus from the campus security data; Associate and classify the security demand information to obtain the trajectory association level of students' activities on campus, and determine the interactive warning attributes within the security supervision period of the target campus through the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory association level; Obtain the security risk indicators of different supervision areas in the target campus, determine the security offset nodes of each supervision area in the target campus according to the security risk indicators, and then determine the corrected behavior labels of students in the target campus from the security offset nodes and the interactive warning attributes; Control the security behavior characteristics of students in the target campus according to the corrected behavior labels, and generate warning feedback information on the activities of students in the target campus.

2. The intelligent campus security warning management method according to claim 1, characterized in that, The campus security data refers to multi-source perception information of personnel behavior, environmental status, and security events on campus.

3. A smart campus security warning management method according to claim 1, characterized in that, Extracting the security demand information of students on campus from the campus security data specifically includes: Determine the student behavior trajectory based on the security distribution characteristics of the campus security data; Determine the security resource allocation amount under different risk scenarios according to the student behavior trajectory; Determine the security demand information of students on campus through the security resource allocation amount.

4. The intelligent campus security warning management method according to claim 1, wherein, Associating and classifying the security demand information to obtain the trajectory association level of students' activities on campus specifically includes: Construct a trajectory feature set of students' activities through the security demand information; Extract the dissimilation risk information of students' activities on campus from the trajectory feature set; Determine the risk association rules when students are active on campus; Map the risk association rules to the dissimilation risk information to obtain the trajectory association level of students' activities on campus.

5. A smart campus security warning management method according to claim 1, characterized in that, The trajectory association level represents a hierarchical structure constructed by classifying students' behavior trajectories according to their risk levels, behavior complexities, and rule matching results.

6. The intelligent campus security warning management method according to claim 1, wherein, Determining the interactive warning attributes within the security supervision period of the target campus through the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory association level specifically includes: Obtain the security deployment paths in the historical security event library of different supervision areas of the target campus; Determine the collaborative warning rules within the security supervision period of the target campus according to the security deployment paths; Determine the interactive warning attributes within the security supervision period of the target campus according to the collaborative warning rules and the trajectory association level.

7. The intelligent campus security warning management method according to claim 1, characterized in that, The interactive warning attribute represents an antecedent identifier for cross-regional security responses triggered by students' behavior trajectories within a given security supervision period.

8. The intelligent campus security warning management method according to claim 1, characterized in that Determining the corrected behavior labels of students in the target campus from the security offset nodes and the interactive warning attributes specifically includes: Determine the security configuration strategy when students are active on campus according to the security offset nodes; Determine the collaborative response logic within the security supervision period of the target campus according to the interactive warning attributes; Determine the corrected behavior labels of students in the target campus through the security configuration strategy and the collaborative response logic.

9. A smart campus security warning management method as claimed in claim 1, characterized in that, The described corrective behavior label represents an identifier for evaluating the safety of students' behaviors and making behavior adjustments to students.

10. A smart campus security warning management system for implementing a smart campus security warning management method according to any one of claims 1 to 9, characterized in that, The management system includes: A data collection module, configured to collect in real time the campus security data in a designated supervision area of a target campus, and extract the security requirement information of students within the campus from the campus security data; An association grading module, configured to perform association grading on the security requirement information to obtain the trajectory association level of students' activities within the campus, and determine the interaction warning attribute within the security supervision period of the target campus through the security deployment path in the historical security event library of different supervision areas of the target campus and the trajectory association level; A behavior recognition module, configured to obtain the security risk indicators of different supervision areas in the target campus, determine the security deviation nodes of each supervision area in the target campus according to the security risk indicators, and further determine the corrective behavior label of students in the target campus from the security deviation nodes and the interaction warning attribute; A warning control module, configured to control the safety behavior characteristics of students in the target campus according to the corrective behavior label, and generate warning feedback information on the activities of students in the target campus.

Images