A smart campus security early warning management method and system

Abstract

The present application provides a smart campus security early warning management method and system, which relates to the field of smart campus management technology. It extracts students' security demand information on campus from campus security data; determines the interactive early warning attributes within the target campus security supervision cycle through the security deployment path and trajectory association hierarchy in the historical security event library of different supervision areas of the target campus; determines the security offset node of each supervision area in the target campus according to the security risk index, and then determines the corrected behavior label of the students in the target campus according to the security offset node and the interactive early warning attribute; manages and controls the safety behavior characteristics of students in the target campus based on the corrected behavior label, and generates early warning feedback information of students' activities in the target campus. The present application can integrate and deduce the correlation between student behavior trajectories and dynamic security resource demands to improve the response accuracy of the campus security system.

Description

Technical Field

[0001] The present application relates to the technical field of smart campus management, and more specifically, to a smart campus security warning management method and system. 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, integrate data, intelligently analyze, and coordinate the management of people, objects, environments, and behaviors on campus, thereby achieving an intelligent operational model for education, teaching, campus management, and security. In a smart campus management system, by deploying sensing terminals such as sensors, monitoring equipment, and intelligent access control systems, behavioral data and environmental information from students and faculty are collected in real time. This collected information is centrally analyzed using data platforms to construct behavioral profiles and risk models, and to establish automated response mechanisms. In particular, in campus security management, intelligent approaches can enable a shift from traditional "post-event response" to "pre-event warning and in-event control," improving the efficiency of anticipating and responding to abnormal behavior and emergencies.

[0003] However, existing smart campus security early warning management methods commonly suffer from technical flaws such as a lack of refined identification of individual student behavior, static and rigid early warning rules, and fragmented security response mechanisms across regions. These flaws make it difficult for the system to promptly perceive and dynamically respond to changes in student behavior under different risk scenarios. This results in low accuracy in predicting potential security threats, delayed responses, and inefficient resource scheduling, limiting the intelligent, interconnected, and personalized management capabilities of campus security systems. Therefore, the industry faces the challenge of integrating and deducing the correlation between student behavior trajectories and the dynamic demand for security resources to improve the response accuracy of campus security systems. Summary of the Invention

[0004] This application provides a smart campus security early warning management method and system, which can integrate and deduce the correlation between student behavior trajectories and the dynamic demand for security resources to improve the response accuracy of the campus security system.

[0005] In a first aspect, the present application provides a smart campus security early warning management method, the management method comprising the following steps:

[0006] Collect campus security data in a designated supervision area of ​​a target campus in real time, and extract information on students' security needs on campus from the campus security data;

[0007] The security demand information is correlated and graded to obtain a trajectory correlation level of students' activities on campus. The interactive warning attributes within the security supervision cycle of the target campus are determined based on the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory correlation level.

[0008] Obtaining security risk indicators for different supervision areas in the target campus, determining a security excursion node for each supervision area in the target campus based on the security risk indicators, and then determining a corrective behavior label for the student in the target campus based on the security excursion node and the interactive warning attribute;

[0009] The safety behavior characteristics of students in the target campus are controlled based on the modified behavior labels, and early warning feedback information of students' activities in the target campus is generated.

[0010] In this embodiment, the campus security data refers to multi-source perception information of personnel behavior, environmental status and security events on campus.

[0011] In this embodiment, extracting the security demand information of students on campus from the campus security data specifically includes:

[0012] Determining student behavior trajectories based on security distribution characteristics of the campus security data;

[0013] Determine the amount of security resources to be allocated under different risk scenarios based on the student behavior trajectory;

[0014] The security demand information of students on campus is determined through the security resource allocation amount.

[0015] In this embodiment, the security demand information is correlated and graded to obtain the trajectory correlation level of students' activities on campus, specifically including:

[0016] Constructing a trajectory feature set of student activities through the security demand information;

[0017] Extracting alienation risk information of students' activities on campus from the trajectory feature set;

[0018] Determine risk association rules for students as they move around campus;

[0019] The risk association rules are mapped to the alienated risk information to obtain the trajectory association level of students' activities on campus.

[0020] In this embodiment, the trajectory association level represents a hierarchical structure constructed by combining student behavior trajectories according to their risk level, behavior complexity, and rule matching results.

[0021] In this embodiment, the interactive warning attributes within the target campus security supervision cycle are determined by using the security deployment paths and the trajectory association levels in the historical security event database of different supervision areas of the target campus, specifically including:

[0022] Obtain security deployment paths from the historical security event database of different regulatory areas of the target campus;

[0023] Determine collaborative warning rules within the target campus security supervision cycle based on the security deployment path;

[0024] The interactive warning attributes within the target campus security supervision cycle are determined according to the collaborative warning rules and the trajectory association level.

[0025] In this embodiment, the interactive warning attribute represents an advance indicator of whether a student's behavior trajectory triggers a cross-regional security response within a given security supervision cycle.

[0026] 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 specifically includes:

[0027] Determining a security configuration strategy for students when they are active on campus based on the security offset node;

[0028] Determining the collaborative response logic within the target campus security supervision cycle based on the interactive warning attributes;

[0029] The modified behavior labels of students in the target campus are determined by the security configuration strategy and the collaborative response logic.

[0030] In this embodiment, the modified behavior label represents an identifier for evaluating the safety of student behavior and adjusting the student's behavior.

[0031] In a second aspect, the present application provides a smart campus security early warning management system for executing a smart campus security early warning management method, the management system comprising:

[0032] A data collection module is used to collect campus security data in a designated supervision area of ​​a target campus in real time, and extract information on students' security needs on campus from the campus security data;

[0033] An association and grading module is used to associate and grade the security demand information to obtain a trajectory association level of students' activities on campus, and to determine the interactive warning attributes within the security supervision cycle of the target campus based on the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory association level;

[0034] A behavior recognition module is used to obtain security risk indicators for different supervision areas in the target campus, determine the security deviation node for each supervision area in the target campus based on the security risk indicators, and then determine the corrected behavior label of the student in the target campus based on the security deviation node and the interactive warning attribute;

[0035] The early warning control module is used to control the safety behavior characteristics of students in the target campus based on the modified behavior labels, and generate early warning feedback information on students' activities in the target campus.

[0036] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0037] Campus security data in designated supervision areas of the target campus are collected in real time, and security demand information of students on campus is extracted from the campus security data; the security demand information is correlated and graded to obtain a trajectory correlation level of students' activities on campus, and interactive warning attributes within the security supervision cycle of the target campus are determined through the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory correlation level; security risk indicators of different supervision areas in the target campus are obtained, and security deviation nodes of each supervision area in the target campus are determined based on the security risk indicators, and then corrected behavior labels of students in the target campus are determined based on the security deviation nodes and the interactive warning attributes; the safety behavior characteristics of students in the target campus are managed and controlled based on the corrected behavior labels, and warning feedback information of students' activities in the target campus is generated.

[0038] It can be seen that in this application, it is possible to timely perceive and dynamically respond to changes in students' behavior in different risk situations; among them, the dynamic perception and precise demand identification of student behavior and security environment in the campus supervision area can timely grasp the security support needs of individual students in a specific time and space; through the integration of historical security event deployment experience and behavior classification rules, early analysis of potential risk paths and dynamic generation of multi-region collaborative warning attributes are achieved, thereby enhancing the security system's ability to identify complex behavior patterns and early warning linkage; through the fusion analysis of resource gaps and risk indicators, the weak links in security in each supervision area are accurately located, and corrected behavior labels are generated in combination with students' behavioral characteristics, realizing classified management and differentiated intervention of individual student behavior risks, thereby effectively improving the efficiency of security resource deployment and the accuracy of responding to sudden risks; through the matching and linkage of real-time trajectories and rule bases, the intelligent intervention capability and response efficiency of the security system are improved, thereby realizing active defense and precise decision-making in campus safety management, and promoting the evolution of campus security from passive response to intelligent initiative.

[0039] In summary, the technical solution adopted in this application can integrate and deduce the correlation between student behavior trajectories and the dynamic demand for security resources to improve the response accuracy of the campus security system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 This is an exemplary flow chart of a smart campus security early warning management method provided by this application;

[0042] Figure 2 It is a schematic diagram of the process of determining the trajectory association level provided by this application;

[0043] Figure 3 This is a schematic diagram of the process of determining the security offset node provided by this application;

[0044] Figure 4 This is a module structure diagram of a smart campus security early warning management system provided by this application. DETAILED DESCRIPTION

[0045] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] The embodiment of the present application provides a smart campus security warning management method and system, the core of which is to collect campus security data in a designated supervision area of ​​a target campus in real time, extract students' security demand information on campus from the campus security data; associate and classify the security demand information to obtain a trajectory association level of students' activities on campus, and determine the interactive warning attributes within the security supervision cycle 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 security risk indicators of different supervision areas in the target campus, determine the security offset nodes of each supervision area in the target campus based on the security risk indicators, and then determine the corrected behavior labels of students in the target campus based on the security offset nodes and the interactive warning attributes; manage and control the safety behavior characteristics of students in the target campus based on the corrected behavior labels, and generate warning feedback information on students' activities in the target campus.

[0047] Example 1: In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG, this figure is an exemplary flow chart of a smart campus security early warning management method according to this embodiment of the present application, and the management method includes the following steps:

[0048] In step S1, campus security data in a designated supervision area of ​​a target campus is collected in real time, and security demand information of students on campus is extracted from the campus security data.

[0049] In practice, real-time collection of campus security data within designated regulatory areas of the target campus can be achieved through the following methods: First, network cameras with high-definition image capture and night vision capabilities are installed in areas with high traffic or high risk, such as entrances and exits of teaching buildings, dormitory corridors, libraries, and laboratory buildings. These cameras continuously transmit video streams to edge computing nodes via the RTSP protocol. Second, RFID access control devices are deployed at all major entrances to record student identities and entry and exit times, which are used to construct behavioral pathways. IoT devices, such as infrared motion sensors, smoke alarms, and ambient noise sensors, are also installed to enable real-time monitoring of illegal stays, fire warnings, or unusual noises. Data from all sensor devices is first aggregated to edge computing gateways deployed at the edge of each area for preliminary processing using local algorithms, such as image compression, anomaly flagging, and data synchronization. This structured or semi-structured data is then encrypted and transmitted to the campus security management platform via MQTT or HTTPS, enabling unified data access. Finally, real-time campus security data is retrieved by reading the data storage units in the campus security management platform.

[0050] 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.

[0051] In this embodiment, extracting the security demand information of students on campus from the campus security data can be achieved by using the following steps:

[0052] Determining student behavior trajectories based on security distribution characteristics of the campus security data;

[0053] Determine the amount of security resources to be allocated under different risk scenarios based on the student behavior trajectory;

[0054] The security demand information of students on campus is determined through the security resource allocation amount.

[0055] In its implementation, the system first constructs a continuous student movement path within the campus using fused video surveillance, access control data, and RFID access records. A trajectory reconstruction algorithm is then used to remove outliers from the continuous movement path, resulting in an accurate time series trajectory. Behavioral characteristic nodes, such as "extended stay" and "unusual crossing of multiple security zones," are marked within the time series trajectory and used as the student's behavioral trajectory. The trajectory reconstruction algorithm can be a Kalman filter combined with a sliding window splicing algorithm. Next, a campus security resource distribution map is constructed, recording metrics such as camera density, security patrol frequency, and emergency response time in each zone. Based on the zones passed by students in the student's behavioral trajectory, security response capability parameters are extracted for different risk scenarios. The student's behavioral trajectory, security distribution map, and security response capability parameters are then superimposed. A Bayesian network-based scenario inference algorithm is used to calculate the total security response volume that can be triggered under different risk scenarios. This total security response volume is used as the security resource allocation quantity, which includes the number of cameras to monitor, the number of security personnel interventions, and the alarm probability level. Finally, if the student's behavior trajectory crosses multiple resource-constrained areas or has high-frequency abnormal behaviors, the system will mark the corresponding trajectory as a "high demand" state. The system will label the behavior with a security demand label, including risk level, coverage area, priority and intervention suggestions, to form complete security demand information.

[0056] It should be noted that in this application, the security distribution characteristics represent a collection of information such as the density, coverage and historical response efficiency of security facilities in different regulatory areas, which is used to measure the region's response capability and prevention and control level to potential risks; student behavior trajectory refers to the spatiotemporal path information of students' movement and stay between various areas on campus; the security resource allocation amount refers to the total amount of security resources that the system needs to mobilize under specific risk scenarios or behavior trajectories; security demand information refers to the safety protection response needs generated by students based on their behavior trajectories, the environment they are in and the available security resources in a specific time and space context.

[0057] In step S2, the security demand information is correlated and graded to obtain the trajectory correlation level of students' activities on campus. The interactive warning attributes within the security supervision cycle of the target campus are determined by the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory correlation level.

[0058] Preferably, in this embodiment, the security demand information is associated and graded to obtain the track association level of students' activities on campus, with reference to Figure 2 As shown in FIG, this figure is a schematic diagram of the process of determining the track association level in some embodiments of the present application. In this embodiment, the track association level can be determined by the following steps:

[0059] In step S21, a trajectory feature set of student activities is constructed using the security demand information;

[0060] In step S22, the alienation risk information of the student's activities on campus is extracted from the trajectory feature set;

[0061] In step S23, the risk association rules for students' activities on campus are determined;

[0062] In step S24, the risk association rules are mapped to the alienated risk information to obtain the trajectory association level of the students' activities on campus.

[0063] In its implementation, the trajectory feature set of student activities is constructed by first taking student behavior trajectories and their risk level labels, which have been assessed for security needs, as input. From each student's trajectory, elements such as single-point dwell time, behavior interval, spatial path length and area span, number of cameras triggered, frequency of security personnel dispatch, abnormal entry and exit, boundary crossing, and frequent round-trips are extracted. These extracted elements are encoded into multidimensional vectors to form the trajectory feature set. Then, a normal behavior trajectory template library is introduced, and dynamic time warping (DTW) is used to identify behavior segments that significantly deviate from the normal behavior trajectory template. A clustering algorithm is used to classify these deviating segments, identifying risk segments such as entering key areas during off-peak hours, repeatedly visiting high-alert areas without authorization, and making multiple short trips across areas. These identified risk segments, along with their location, time, and risk labels, are used as alienated risk information. Next, frequent pattern mining is performed on a large number of student behavior trajectories. Frequent pattern mining can use the Apriori or FP-Growth algorithm. Sequential patterns and co-occurrence relationships of risk events are extracted from different student behavior trajectories, such as "extended nighttime stay → entering a closed floor → abnormal alarm." Risk association rules for student activities on campus are then constructed according to the following rules: If behavior A is followed by behavior B and occurs in a specific area, the associated risk increases. If the three high-frequency behaviors of extended nighttime stay, entering a closed floor, and abnormal alarm occur simultaneously, a comprehensive risk weight is assigned. Finally, the alienated risk information in each student's behavior trajectory is matched with the risk association rules, marking the risk linkage structure within the student's behavior trajectory. The trajectory association hierarchy is then divided into: the first level, which has full rule matching and high-frequency recurrence characteristics and is a key intervention target; the second level, which has partial rule matching and potential risk transmission trends; and the third level, which has only local deviations in the behavior trajectory and is of concern but does not require intervention. The resulting trajectory association hierarchy for student activities on campus is output.

[0064] It should be noted that in this application, the trajectory feature set represents a set of structured feature data that combines the spatial, temporal, behavioral patterns and security demand attributes in the student behavior trajectory; the alienation risk information represents the local segment attributes in the student behavior trajectory that deviate from the normal behavior pattern, have potential safety hazards and abnormal resource occupancy characteristics; the risk association rules represent the spatiotemporal combination, transfer relationship and repetition pattern between high-risk behaviors mined in different student behavior trajectories; the trajectory association hierarchy represents a hierarchical structure constructed by constructing student behavior trajectories according to their risk level, behavioral complexity and rule matching results.

[0065] In this embodiment, the following steps can be used to determine the interactive warning attributes within the security supervision cycle of the target campus based on the security deployment paths and the trajectory association level in the historical security event library of different supervision areas of the target campus:

[0066] Obtain security deployment paths from the historical security event database of different regulatory areas of the target campus;

[0067] Determine collaborative warning rules within the target campus security supervision cycle based on the security deployment path;

[0068] The interactive warning attributes within the target campus security supervision cycle are determined according to the collaborative warning rules and the trajectory association level.

[0069] In the specific implementation, first, the security event data in the past few months or semesters are summarized to build a structured historical event library. For each event, the following information is extracted: trigger source information (starting area, event type, trigger time); response resource allocation record (security personnel mobilization route, video scheduling area, equipment activation order); final disposal feedback (response duration, number of linkage areas, event results). Then, a graph model (such as a directed graph) is used to abstract the regional nodes and response paths into an allocation path graph, recording the direction, frequency and time overhead of resource scheduling to form a dynamic allocation path library. The security allocation paths in the historical security event library of different regulatory areas of the target campus are read from the dynamic allocation path library. Then, high-frequency linkage paths are identified through path analysis algorithms (such as PageRank or path frequency statistics). The following collaborative features are analyzed: multiple events frequently triggering the same dispatch path, events in a certain area often responding simultaneously to two adjacent areas, and recurring paths with low response efficiency. Based on these collaborative features, collaborative warning rules are constructed for the target campus security monitoring cycle. These include: if high-risk behavior is triggered in area A and the behavioral trajectory involves areas B and C, a three-level linkage warning is triggered; if the response time of a security dispatch path continuously exceeds a set threshold, an early warning is issued for the relevant areas. Finally, the trajectory association level of the current student trajectory is matched with the collaborative warning rules: if the trajectory association level is a first-level trajectory and covers two or more high-frequency dispatch paths, a "high-level linkage warning" is directly assigned; if the trajectory association level of the student trajectory partially matches the collaborative warning rule and only involves a single path response, a "medium-level one-way warning" is assigned; if the collaborative warning rule represents a probabilistic event or a rare response path, a "low-level potential warning" is marked. Then extract the affected supervision area number; potential types of resource deployment (such as whether manual linkage is involved); warning timeliness (warning effective duration); linkage intensity level (mild, moderate, severe), and use the extracted content as the interactive warning attributes within the target campus security supervision cycle.

[0070] It should be noted that, in this application, the historical security event database refers to a data set that records past security events and response details in various regulatory areas on campus; the security deployment path refers to the actual process sequence of cross-regional coordinated mobilization of security resources (such as personnel, cameras, and alarm devices) after the event is triggered in the response to historical security events; the collaborative early warning rule refers to a multi-region security event linkage response mode summarized based on the historical linkage handling experience of multiple regulatory areas; the interactive early warning attribute refers to the advance identification of student behavior trajectories triggering cross-regional security responses within a given security supervision cycle. The security supervision cycle refers to a dynamic security management period set by a campus security system in dynamic operation based on behavior density, risk prediction, and resource rotation strategy.

[0071] In step S3, security risk indicators of different supervision areas in the target campus are obtained, and security deviation nodes of each supervision area in the target campus are determined based on the security risk indicators. Then, the corrective behavior labels of students in the target campus are determined based on the security deviation nodes and the interactive warning attributes.

[0072] In practice, obtaining security risk indicators for different regulatory areas within the target campus can be achieved through the following methods: The system accesses real-time and historical security data sources for each regulatory area, including video surveillance anomalies, access control anomalies, changes in occupancy density, alarm records, and security personnel movements. Next, based on statistical modeling methods (such as sliding time window aggregation and heat matrix analysis), core quantitative indicators are extracted for each area, including the frequency of security events per unit time, the incidence of abnormal behavior, the mean response latency, and the proportion of high-risk behaviors. These core quantitative indicators are then normalized and input into a weighted evaluation model (e.g., a weighted scoring model based on AHP) to derive a security risk score for each area. This security risk score serves as a dynamically updateable set of security risk indicators covering all regulatory areas, i.e., the security risk indicators for different regulatory areas within the target campus.

[0073] It should be noted that, in this application, the security risk index refers to a set of data indicators that measure the probability and potential degree of harm of security incidents occurring in various regulatory areas on campus within a specific time period.

[0074] Preferably, in this embodiment, the security offset node of each supervision area in the target campus is determined according to the security risk index, referring to Figure 3 As shown in FIG, this figure is a schematic diagram of the process of determining a security offset node in some embodiments of the present application. In this embodiment, determining a security offset node can be implemented using the following steps:

[0075] In step S31, a resource gap index in each supervision area of ​​the target campus is determined based on the security risk index;

[0076] In step S32, the emergency response paths in the historical security event database are matched and screened using the resource gap index to obtain a resource matching status;

[0077] In step S33, the security requirement boundary of each supervision area in the target campus is determined;

[0078] In step S34, the security offset node of each supervision area in the target campus is determined according to the resource matching status and the security requirement boundary.

[0079] In specific implementation, the adaptability of the current security resource allocation is first assessed based on the security risk indicators of each regulatory area (such as incident frequency and response time). A difference method is then used to calculate the difference between the actual allocated security resources and the required resources, resulting in a resource gap index for each regulatory area within the target campus. A large resource gap index indicates a high security risk in that area. Next, based on the resource gap index, resource allocation paths in the historical security event database are screened for historical emergency response paths that can address the resource shortage in the current area. A K-nearest neighbor algorithm or a dynamic matching method based on similarity is used to identify historical event response paths with similar resource allocations. This creates a resource matching status and records whether the resources meet the current demand. Next, the security demand boundary for each area is determined based on the maximum response capacity of resource allocation in historical security events and the most complex events handled. Minimum resource allocation boundaries, such as the minimum number of security personnel per building or the minimum camera coverage, are set based on factors such as incident handling capacity, regional size, and potential risks. This ensures that all potential risks are protected within a manageable range. Finally, compare the resource matching status and the security demand boundary. If the resource matching is insufficient or exceeds the demand boundary at a certain moment or in an area, the area is considered to have a security offset node, which will not be discussed here.

[0080] It should be noted that, in this application, the resource gap index indicates the amount of security demand that cannot be covered by the current security resource configuration in each regulatory area; the emergency response path indicates that when a security incident occurs, security resources are based on the type of incident and regional needs; the resource matching status indicates whether the resource allocation path that has occurred in the historical security event library can effectively meet the security needs of the current area; the security demand boundary indicates the boundary of the minimum resource configuration required for different security incidents within a specific time and area; the security offset node indicates a node where the configuration of security resources in the area is abnormal or insufficient under specific circumstances.

[0081] 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 achieved by the following steps:

[0082] Determining a security configuration strategy for students when they are active on campus based on the security offset node;

[0083] Determining the collaborative response logic within the target campus security supervision cycle based on the interactive warning attributes;

[0084] The modified behavior labels of students in the target campus are determined by the security configuration strategy and the collaborative response logic.

[0085] In its implementation, a specific security configuration strategy is first developed for each security deviation node based on its security demand boundary and resource gap index. For example, if camera coverage in a particular area is insufficient, the system will provide solutions to enhance camera surveillance or deploy additional security personnel based on the resource gap. Next, based on interactive alert attributes (such as simultaneous alerts in multiple areas, overlapping behavioral patterns, or high-risk events), the system assesses whether a multi-region coordinated response is necessary. The coordinated response logic within the target campus security monitoring cycle is then configured based on the distribution and severity of the alert events. For example, if a security incident in one area impacts the safety of adjacent areas, monitoring resources or personnel in adjacent areas will be automatically dispatched, and the response priority will be increased. Finally, by analyzing student behavior trajectories (such as unusual stops and frequency of area visits), combined with security configuration strategies and coordinated response logic, it is determined whether student behavior deviates from normal patterns. If a student's behavior triggers high-risk or resource-inadequate situations in certain areas, a corrective behavior label for the student within the target campus is generated according to predefined rules. Predefined rules include labeling students' behavior as "unsafe" or "needs correction" if they frequently enter and exit high-risk areas without triggering the appropriate security response.

[0086] It should be noted that in this application, the security configuration strategy refers to a combination of reasonable resource allocation and security measures determined based on the security needs, resource allocation, and risk assessment of different areas on campus; the collaborative response logic refers to a strategy for coordinating and mobilizing resources and responding to security threats among multiple areas in the security system when an early warning occurs in multiple monitoring areas; the corrected behavior label refers to an identifier for evaluating the safety of student behavior and adjusting student behavior.

[0087] In step S4, the safety behavior characteristics of students in the target campus are controlled based on the modified behavior labels, and early warning feedback information of students' activities in the target campus is generated.

[0088] In this embodiment, the following steps may be used to manage and control the safety behavior characteristics of students in the target campus based on the modified behavior labels and generate early warning feedback information about the students' activities in the target campus:

[0089] Building a dynamic hierarchical control rule library based on the security classification attributes and associated disposal strategies in the modified behavior tags;

[0090] Collect real-time trajectory data of students on campus;

[0091] Matching the real-time trajectory data with the dynamic hierarchical control rule library and triggering a regionalized control instruction set in the target campus;

[0092] The regionalized control instruction set is used to control the safety behavior characteristics of students in the target campus in a coordinated manner to obtain security warning trends;

[0093] Determine early warning feedback information on student activities in the target campus based on the security early warning trend.

[0094] In specific implementation, different behavior categories are first constructed based on 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 handling strategies. Each category corresponds to a specific set of control rules. For example, "frequent entry and exit of prohibited areas" may require stricter behavior checks or personnel tracking. Dynamic hierarchical control rules are then created for each behavior category based on the risk level of the student's behavior. For high-risk behavior, measures such as automatic alarms and security patrols can be set up. Low-risk behavior may only require recording and analysis. All dynamic hierarchical control rules are then organized into a dynamic hierarchical control rule library. Next, a real-time positioning system is deployed on campus, such as using Wi-Fi, GPS, RFID, and other technologies to track students' locations in real time. Data such as students' real-time location, activity areas, and dwell time are continuously collected. Monitoring and sensors are used to record student behavioral characteristics, such as the time of entry and exit of specific areas and movement paths. The recorded student behavior characteristics are used as real-time trajectory data on the campus. Next, through pattern recognition and behavioral analysis, students' real-time trajectory data is matched with behavioral characteristics in a dynamic hierarchical control rule library to determine whether the student exhibits high-risk behavior. If a potential risk behavior is found, the corresponding regionalized control command 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 attendance command or trigger the access control system. Based on the triggered regionalized control command set, the security system and security personnel in the area will then implement coordinated control measures. For example, monitoring density in a specific area may be increased or student behavior may be directly intervened to ensure that the security needs of that area are met, thereby generating security early warning trends. The regionalized control command set automatically adjusts based on real-time data changes, ensuring that security management can adapt to changes in student behavior and the campus environment. Finally, based on real-time changes in student behavior and the responses of the security system, potential security incident trends are analyzed. For example, if security incidents are frequently triggered in a certain area, the system may predict that a significant security risk may exist in that area. Based on the security early warning trends, detailed early warning feedback information is generated, including the specific behavioral risk level, corresponding security measures, and relevant intervention recommendations, which are promptly notified to security personnel or management.

[0095] It should be noted that in this application, the security classification attribute represents the standard for dividing student behavior types according to the security risks of student behavior; the associated disposal strategy represents the corresponding response measures formulated based on the risk level of student behavior according to the security classification attribute; the dynamic hierarchical control rule base refers to a set of rule bases dynamically generated according to the severity of different security incidents and the corrected behavior labels, which are used to formulate different security response measures and control strategies. The dynamic hierarchical control rule base will be adjusted according to the real-time security threats and changes in student behavior on campus; real-time trajectory data represents information such as the real-time location, movement path and residence time of students on campus collected by various security equipment; the regionalized control instruction set represents a set of specific behavior intervention instructions issued according to the dynamic hierarchical control rules for the security needs of different areas; safety behavior characteristics refer to the behavior patterns of students on campus, including normal activities, abnormal behaviors, potential risks, etc.; security warning trends represent warning information about the trend of potential security incidents generated based on real-time monitoring, trajectory analysis and security response of student behavior; warning feedback information represents alarm or notification information generated by the system based on security warning trends and fed back to relevant managers or students.

[0096] It can be seen that in this application, it is possible to timely perceive and dynamically respond to changes in students' behavior in different risk situations; among them, the dynamic perception and precise demand identification of student behavior and security environment in the campus supervision area can timely grasp the security support needs of individual students in a specific time and space; through the integration of historical security event deployment experience and behavior classification rules, early analysis of potential risk paths and dynamic generation of multi-region collaborative warning attributes are achieved, thereby enhancing the security system's ability to identify complex behavior patterns and early warning linkage; through the fusion analysis of resource gaps and risk indicators, the weak links in security in each supervision area are accurately located, and corrected behavior labels are generated in combination with students' behavioral characteristics, realizing classified management and differentiated intervention of individual student behavior risks, thereby effectively improving the efficiency of security resource deployment and the accuracy of responding to sudden risks; through the matching and linkage of real-time trajectories and rule bases, the intelligent intervention capability and response efficiency of the security system are improved, thereby realizing active defense and precise decision-making in campus safety management, and promoting the evolution of campus security from passive response to intelligent initiative.

[0097] In summary, the technical solution adopted in this application can integrate and deduce the correlation between student behavior trajectories and the dynamic demand for security resources to improve the response accuracy of the campus security system.

[0098] Example 2: This application provides a smart campus security early warning management system, referring to Figure 4 As shown in FIG, this figure is a module structure diagram of a smart campus security early warning management system according to this embodiment of the present application, and the management system includes:

[0099] The data collection module 100 is used to collect campus security data in a designated supervision area of ​​a target campus in real time, and extract information on students' security needs on campus from the campus security data;

[0100] The association and grading module 200 is configured to perform association and grading on the security demand information to obtain a trajectory association level of the student's activities on campus, and determine the interactive warning attributes within the security supervision cycle of the target campus based on the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory association level;

[0101] The behavior recognition module 300 is configured to obtain security risk indicators for different regulatory areas on the target campus, determine a security excursion node for each regulatory area on the target campus based on the security risk indicators, and further determine a corrected behavior label for the student on the target campus based on the security excursion node and the interactive warning attribute;

[0102] The early warning control module 400 is used to control the safety behavior characteristics of students in the target campus based on the modified behavior labels, and generate early warning feedback information on students' activities in the target campus.

[0103] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, or magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0105] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. A smart campus security early warning management method, characterized in that: The management method comprises the following steps: Collect campus security data in a designated supervision area of ​​a target campus in real time, and extract information on students' security needs on campus from the campus security data; The security demand information is correlated and graded to obtain a trajectory correlation level of students' activities on campus. The interactive warning attributes within the security supervision cycle of the target campus are determined based on the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory correlation level. Obtaining security risk indicators for different supervision areas in the target campus, determining a security excursion node for each supervision area in the target campus based on the security risk indicators, and then determining a corrective behavior label for the student in the target campus based on the security excursion node and the interactive warning attribute; Controlling the safety behavior characteristics of students in the target campus based on the modified behavior labels, and generating early warning feedback information on students' activities in the target campus; The security demand information is correlated and graded to obtain the correlation level of the student's activity trajectory on campus, specifically including: Constructing a trajectory feature set of student activities through the security demand information; Extracting alienation risk information of students' activities on campus from the trajectory feature set, wherein the alienation risk information represents local segment attributes of the student's behavior trajectory that deviate from normal behavior patterns, have potential safety hazards, and have abnormal resource occupancy characteristics; Determine risk association rules for students as they move around campus; Mapping the risk association rules to the alienated risk information to obtain a trajectory association hierarchy of students' activities on campus, wherein the trajectory association hierarchy represents a hierarchical structure constructed by combining student behavior trajectories according to their risk level, behavior complexity, and rule matching results; The interactive warning attributes within the target campus security supervision cycle are determined by using the security deployment paths in the historical security event database of different supervision areas of the target campus and the trajectory association level, specifically including: Obtain security deployment paths from the historical security event database of different regulatory areas of the target campus; Determine collaborative warning rules within the target campus security supervision cycle based on the security deployment path; Determining, based on the collaborative warning rules and the trajectory association level, interactive warning attributes within the target campus security supervision cycle, wherein the interactive warning attributes represent advance indicators of student behavior trajectories triggering cross-regional security responses within a given security supervision cycle; The method of determining the corrected behavior label of the student in the target campus based on the security deviation node and the interactive warning attribute specifically includes: Determining a security configuration strategy for students when they are active on campus based on the security offset node; Determining the collaborative response logic within the target campus security supervision cycle based on the interactive warning attributes; The modified behavior tag of the student in the target campus is determined by the security configuration strategy and the collaborative response logic, wherein the modified behavior tag represents an identifier for evaluating the safety of the student's behavior and adjusting the student's behavior.

2. A smart campus security early 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 early warning management method as claimed in claim 1, characterized in that: Extracting the security demand information of students on campus from the campus security data specifically includes: Determining student behavior trajectories based on security distribution characteristics of the campus security data; Determine the amount of security resources to be allocated under different risk scenarios based on the student behavior trajectory; The security demand information of students on campus is determined through the security resource allocation amount.

4. A smart campus security early warning management system, used to implement a smart campus security early warning management method according to any one of claims 1 to 3, characterized in that: The management system includes: A data collection module is used to collect campus security data in a designated supervision area of ​​a target campus in real time, and extract information on students' security needs on campus from the campus security data; An association and grading module is used to associate and grade the security demand information to obtain a trajectory association level of students' activities on campus, and to determine the interactive warning attributes within the security supervision cycle of the target campus based on the security deployment paths in the historical security event library of different supervision areas of the target campus and the trajectory association level; A behavior recognition module is used to obtain security risk indicators for different supervision areas in the target campus, determine the security deviation node for each supervision area in the target campus based on the security risk indicators, and then determine the corrected behavior label of the student in the target campus based on the security deviation node and the interactive warning attribute; The early warning control module is used to control the safety behavior characteristics of students in the target campus based on the modified behavior labels, and generate early warning feedback information on students' activities in the target campus.

Images