Scenic area personnel distribution monitoring and early warning system and method

Abstract

The present invention discloses a system and method for monitoring and early warning of personnel distribution in scenic areas, and relates to the technical field of scenic area monitoring. The system includes a memory for storing early warning areas of different safety levels and permitted movement paths divided based on the boundaries of the monitoring area; a real-time monitoring system for comparing the actual position of personnel with the permitted path, and generating an alarm signal when the path is exceeded; a trajectory tracking system for continuously tracking the subsequent path of the personnel until the permitted path is re-entered; and a behavior learning system for updating safety rules based on feedback from the management terminal. The method includes obtaining the real-time position of the personnel and performing trajectory compliance analysis, selecting an alarm level when a deviation is detected, performing dynamic resynchronization through the trajectory tracking system, and updating the safety rules of the geographic information model based on the feedback. The system and method realize dynamic monitoring and early warning of personnel in scenic areas, and improve the efficiency and accuracy of scenic area safety management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of scenic spot monitoring, and in particular to a scenic spot personnel distribution monitoring and early warning system and method. BACKGROUND

[0002] Traditional monitoring systems mostly use fixed cameras or single sensors for local area monitoring, with limited detection range and unable to fully cover every corner of the scenic area. Especially for complex terrain and large scenic areas, it is easy to form a monitoring blind area, which leads to the inability to timely detect abnormal personnel distribution or dangerous behavior. For example, in mountainous scenic areas, traditional cameras may not be able to monitor the activities of tourists in remote areas due to terrain obstructions.

[0003] Secondly, the traditional system lacks effective management of personnel movement paths, often using static safety rules that cannot adapt to dynamic changes in the scenic environment. For example, during the rainy season, the risk level of some stream areas increases, but the traditional system cannot automatically adjust the safety level and allowed path, still following the regular rules, which can easily lead to false positives or false negatives.

[0004] Furthermore, the traditional monitoring system is insufficient in detecting abnormal personnel behavior. When it detects that a person deviates from the normal path, it can only send an alarm signal, but lacks continuous tracking and dynamic management of the person's subsequent trajectory, and cannot form a risk closed-loop management. For example, when a tourist mistakenly enters a restricted area, the traditional system cannot continuously track the tourist's movement trajectory after sending an alarm, making it difficult to ensure that the tourist returns to the safe area in a timely manner.

[0005] In addition, the traditional system does not fully utilize historical data, and cannot optimize and update safety rules based on actual operating conditions and historical accident data, resulting in a gradual decline in the adaptability and accuracy of the system over time. For example, when a certain area frequently experiences tourists deviating from the path, the traditional system cannot automatically include the path in the allowed movement path, still considering it a violation, leading to an increase in false positive rates.

[0006] With the development of technology, although some scenic areas have introduced intelligent monitoring technology, there are still problems such as low coordination efficiency, low detection accuracy, and unreasonable task allocation when dealing with complex scenic environment and multi-target monitoring tasks. For example, there is a lack of effective collaboration mechanism between various monitoring subsystems, resulting in information gaps during personnel tracking; when faced with changes in tourist behavior patterns due to factors such as season and activity, the system cannot adjust the monitoring strategy in a timely manner, making it difficult to meet real-time monitoring needs; and in terms of safety rule optimization, there is a lack of scientific and reasonable methods, which cannot fully utilize the value of historical data, leading to waste of detection resources and low detection efficiency.

[0007] Therefore, there is an urgent need for a scenic area personnel distribution monitoring and early warning system and method that can comprehensively cover, dynamically adjust, continuously track, and have self-learning ability to solve the above problems existing in traditional monitoring systems and improve the efficiency and accuracy of scenic area personnel safety management. SUMMARY

[0008] The purpose of the present application is to provide a scenic area personnel distribution monitoring and early warning system and method to solve the technical problems raised in the technical background.

[0009] The main purpose of the present application is to provide a scenic area personnel distribution monitoring and early warning system, comprising:

[0010] a memory storing a scenic area geographic information model, the scenic area geographic information dividing a plurality of early warning areas with different safety levels based on a plurality of predefined monitoring area boundaries, and storing a safety level value and at least one allowed personnel movement path for each early warning area.

[0011] a real-time monitoring system comparing the actual position of personnel with the at least one allowed movement path of the current early warning area during the operation of the scenic area, and generating an alarm signal and the corresponding safety level when the actual position of personnel exceeds the allowed movement path.

[0012] a trajectory tracking system responding to the alarm signal by continuously tracking the subsequent movement path of personnel and comparing it with the safety rules of the early warning area until the personnel position reenters the allowed path of any early warning area to complete synchronization.

[0013] a behavior learning system receiving feedback instructions from the scenic area management terminal in response to the alarm signal, and updating the safety rules of the geographic information model according to the feedback instructions.

[0014] Further, the behavior learning system dynamically adjusts the safety level value associated with the current early warning area according to the feedback instructions.

[0015] and the behavior learning system includes a feedback analysis engine, which is configured to:

[0016] when the feedback instruction contains a safety level adjustment, automatically update the level value associated with the current early warning area.

[0017] when the feedback confirms a false alarm, reduce the sensitivity parameter of the same type of alarm in this area.

[0018] when the feedback requires path correction, activate the path generator to create a temporary allowed path.

[0019] Further, the monitoring area boundary is determined by running a safety risk analysis algorithm on the scenic area terrain data by a risk modeling engine, combined with historical accident data to identify the boundary of high-risk areas.

[0020] wherein the risk modeling engine is configured to perform the following operations:

[0021] Input scenic spot terrain point cloud data, hydrogeological report, historical accident database.

[0022] Run Monte Carlo safety risk simulation algorithm.

[0023] Combine with human flow dynamics model to identify high-risk area boundary.

[0024] Output hierarchical boundary coordinate set with weight coefficient.

[0025] Further, the geographic information model generates by simulating personnel flow path, recording the safety state of each warning area and path conversion rule.

[0026] wherein the geographic information model is constructed by a behavior simulator:

[0027] Load scenic spot building BIM model and vegetation cover data.

[0028] Inject typical tourist behavior patterns based on seasonal changes.

[0029] Run multi-agent path planning simulation.

[0030] Record the state transition matrix of each area, which includes the transition relationship between normal path / emergency path / forbidden area.

[0031] Generate path rule library with space-time constraints.

[0032] Further, the scenic spot geographic information includes:

[0033] Area rule table, storing the safety level value and path index corresponding to each warning area.

[0034] Path mapping table, storing the allowed movement path set of each warning area, the path mapping table is accessed through the path index.

[0035] wherein the path mapping table is organized by index cluster, including:

[0036] Main path set, including the GPS coordinate sequence of the allowed movement path.

[0037] Emergency path set, including evacuation path and trigger condition.

[0038] Transition rule set, recording the topological relationship of legal cross-area transition.

[0039] Further, the trajectory tracking system enters a verification mode after completing synchronization, and if the position of the person meets the pre-warning area rule for N consecutive times, it is determined that the synchronization is valid.

[0040] The trajectory tracking system comprises a verification controller:

[0041] After synchronization is completed, a verification mode with adjustable duration is entered.

[0042] The position compliance verification is performed for N consecutive times.

[0043] When the pass rate of N times of verification is ≥95%, it is determined that the synchronization is valid.

[0044] The activation area rule adaptive module adjusts the current path confidence weight.

[0045] Further, the real-time monitoring system suspends the alarm in the verification mode, and if any subsequent position violates the area rule, the trajectory tracking system is triggered to re-execute synchronization.

[0046] The real-time monitoring system performs the following operations in the verification mode:

[0047] A lenient alarm strategy is enabled.

[0048] If the single position deviation standard deviation is greater than the preset tolerance value, the trajectory tracking system is triggered to restart synchronization.

[0049] If the deviation occurs for 2 consecutive times, the verification mode is forcibly exited and an area anomaly report is generated.

[0050] Further, it further comprises:

[0051] The anomaly behavior record library and the deviated trajectory data set with spatiotemporal index stored in the memory.

[0052] The trajectory tracking system stores the trajectory data of the person deviating from the path in the anomaly behavior record library, wherein,

[0053] The trajectory tracking system performs:

[0054] The GPS coordinate sequence deviating from the path is compressed and stored.

[0055] The corresponding timestamp and environmental parameters are associated.

[0056] The high-frequency deviating area is marked to form a risk heat map layer.

[0057] Further, the behavior learning system copies the abnormal trajectory data to the learning database, counts the number of repetitions of the same path deviation, and when the number of repetitions reaches a threshold, updates the geographic information model to include the path as a new allowed moving path.

[0058] The application also provides a scenic spot personnel monitoring and early warning method, comprising the following steps:

[0059] Obtaining the real-time position of the personnel through the multi-source perception layer, comparing the position of the personnel to be tested with the allowed movement path of the current early warning area through the real-time monitoring system, and performing trajectory compliance analysis: projecting the personnel coordinates to the three-dimensional geographic model, comparing the path rule library of the current early warning area, and selecting the alarm level based on the deviation type when detecting path deviation.

[0060] Performing dynamic resynchronization through the trajectory tracking system: starting trajectory prediction based on the motion model, continuously matching adjacent area transfer rules, triggering a synchronization signal when the personnel enter a legal path, and continuously tracking the subsequent position until any early warning area rule is matched again.

[0061] Updating the safety rules of the geographic information model according to the feedback of the management terminal through the behavior learning system, wherein the rule optimization is performed through the behavior learning system: analyzing the structured feedback instructions of the management terminal, reducing the monitoring sensitivity of the area when the feedback confirms false positives, starting the area rule reconstruction engine when the feedback requires rule updating, and outputting the incremental updated geographic information model version.

[0062] The application has the following beneficial effects:

[0063] 1) The application has dynamic safety level adjustment, and the behavior learning system can dynamically adjust the safety level value of the early warning area according to the feedback instructions of the management terminal. When the feedback instructions contain safety level adjustment, the feedback analysis engine will automatically update the level value of the current early warning area. For example, the administrator can adjust the area risk level according to seasonal changes (such as raising the stream area level from 2 to 4 in the rainy season) or activity. This dynamic adjustment mechanism avoids the response lag caused by fixed levels and can adapt to the dynamic changes of the scenic environment. At the same time, when the feedback confirms false positives, the system will reduce the sensitivity parameters of the same alarm in the area, including positioning error tolerance, path deviation threshold, alarm delay time, etc., thereby reducing the false positive rate and avoiding excessive alarms that interfere with the operation of the scenic area. When the feedback requires path correction, the system will activate the path generator to create a temporary allowed path, such as calculating the feasible path based on the BIM model and injecting time and space constraints, and updating to the path mapping table. This way of dynamically adjusting the safety level and the path makes the system able to accurately warn according to the actual situation, improving the accuracy and effectiveness of the warning.

[0064] 2) Precise division of monitoring area boundary based on risk modeling engine: The monitoring area boundary is determined by running a safety risk analysis algorithm on the scenic spot terrain data through the risk modeling engine, combined with historical accident data. The risk modeling engine inputs the scenic spot terrain point cloud data (such as three-dimensional topography generated by laser radar scanning, identifying steep slopes and rockfall areas), hydrogeological reports (determining flood / landslide risk areas), and historical accident databases (statistical analysis of accident hotspots), runs a Monte Carlo safety risk simulation algorithm, randomly generates a large number of tourist trajectories, simulates the environmental risk of each trajectory, calculates the accident probability, identifies the high-risk area boundary, and outputs a weighted coefficient classified boundary coordinate set. This multi-source data and scientific algorithm-based regional division method can accurately identify high-risk areas within the scenic spot, providing accurate geographic information for subsequent personnel monitoring and early warning, enabling the monitoring system to focus on monitoring high-risk areas, and improving the accuracy of scenic spot safety management.

[0065] 3) Behavior learning system self-optimization: The behavior learning system responds to the feedback instructions of the management terminal in response to the alarm signal, and updates the safety rules of the geographic information model according to the feedback instructions. The system copies the abnormal trajectory data to the learning database, and counts the number of repeated deviations of the same path. When the number of repetitions reaches the threshold, the geographic information model is updated to include the path as a new allowed movement path. For example, when a deviation path deviates beyond the threshold for 3 consecutive months and has no accident record, and meets the safety standards (slope < 25°, no geological disasters), the system will automatically add it as a temporary allowed path and set the time and space constraints. At the same time, the behavior learning system contains a feedback analysis engine that reduces the monitoring sensitivity of the region when the feedback is confirmed as a false alarm, and starts the region rule reconstruction engine when the feedback requires rule update. This self-learning and self-optimization mechanism enables the system to continuously iterate the geographic information model according to the actual operation situation, and adapt to changes in the behavior pattern of the scenic spot tourists.

[0066] 4) Track tracking system verification mechanism to ensure risk closed-loop management: After the track tracking system completes synchronization, it enters verification mode. If the personnel position is detected to comply with the pre-warning area rule for N consecutive times, it is determined that the synchronization is valid. The verification controller enters the adjustable verification mode after synchronization is completed, and continuously performs N times of position compliance verification. When the verification pass rate is ≥95%, it is determined that the synchronization is valid, and the area rule adaptive module is activated to adjust the current path confidence weight. For example, the initial weight is 0.6, and the weight is increased by the learning rate each time the verification is passed. When the weight > 0.8, the monitoring frequency is reduced, and when the weight < 0.4, the unmanned aerial vehicle is started to focus on tracking. In the verification mode, the real-time monitoring system enables the loose alarm strategy. If the single position deviation standard deviation > preset tolerance value triggers the track tracking system to restart synchronization, if the deviation is forced to exit the verification mode for 2 consecutive times, and an area abnormal report is generated. This verification mechanism solves the problem of “lack of tracking after alarm” in traditional monitoring, ensures that personnel can be continuously tracked after entering the forbidden area, until they return to the safe path and pass the verification, forming a risk closed-loop management, and improving the reliability of the scenic safety management.

[0067] 5) Abnormal behavior data analysis: The system stores the abnormal behavior record library and the deviation trajectory data set with time and space index. The track tracking system compresses and stores the trajectory data of the personnel deviating from the path (using the Douglas-Puk algorithm, with an accuracy loss of <0.5 meters), associates the corresponding timestamp and environmental parameters (such as weather, crowd), and marks the high-frequency deviation area to form a risk heat map layer. According to the 1km×1km grid, the deviation frequency is counted, the regional risk score is calculated (risk score = monthly deviation frequency × regional safety level), and the visual layer (red, yellow, green three-color identification high, medium, low risk) is output and updated in real time. BRIEF DESCRIPTION OF DRAWINGS

[0068] Figure 1 The method flowchart of the present application.

[0069] Figure 2 The system framework principle diagram in the present application. DETAILED DESCRIPTION

[0070] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0071] Reference Figure 1 and Figure 2The main purpose of the present application is to provide a scenic spot personnel distribution monitoring and early warning system, comprising: a memory storing a scenic spot geographic information model, the scenic spot geographic information being divided into a plurality of early warning areas with different safety levels based on a plurality of predefined monitoring area boundaries, and a safety level value and at least one allowed personnel movement path being stored for each early warning area; a real-time monitoring system comparing the actual position of personnel with the at least one allowed movement path of the current early warning area during the operation of the scenic spot, and generating an alarm signal and the corresponding safety level when the actual position of personnel exceeds the allowed movement path; a trajectory tracking system responding to the alarm signal by continuously tracking the subsequent movement path of personnel and comparing it with the safety rules of the early warning area until the personnel position reenters the allowed path of any early warning area, thereby completing synchronization; a behavior learning system responding to the alarm signal to receive feedback instructions from the scenic spot management terminal and updating the safety rules of the geographic information model according to the feedback instructions.

[0072] In the above embodiment, the scenic spot geographic information construction logic is as follows: based on the principle of safety level differentiation, the early warning areas are divided, for example, high-risk areas (cliffs, deep water areas) have high safety level values (such as level 5) and few allowed paths; medium-risk areas (steep slopes, construction areas) have medium level values (level 3) and limited paths.

[0073] Low-risk areas (tourist centers, flat land) have low level values (level 1) and relaxed paths.

[0074] Each path in the above needs to meet the space-time constraints, for example: the cableway area only allows movement along the guardrail path; the wildlife protection area prohibits deviation from the viewing platform path. By digitally mapping the physical space rules, a structured data foundation is provided for real-time monitoring, avoiding misjudgment caused by ambiguous rules in traditional monitoring.

[0075] In the above embodiment, the real-time monitoring system adopts dynamic compliance detection, which is a system that continuously matches GPS / Beidou positioning data with the current area path library, and uses a spatial topology algorithm to judge whether the position is within the path buffer area (such as triggering an alarm when deviating from the path by >5 meters). The alarm grading mechanism is as follows: low-level alarm (deviation from the safety path), notify the patrol personnel; high-level alarm (entering the forbidden area), link the broadcasting system to evacuate the crowd. The position deviation is converted into a safety event, and the level value is used to achieve accurate emergency response, avoiding excessive alarm interference in operation.

[0076] In the above embodiment, the trajectory tracking system adopts a resynchronization mechanism, which means that when a person mistakenly enters a restricted area, the system starts a motion trajectory prediction model to predict the moving direction; continuously compares the transfer rules of adjacent areas (for example: returning to the trail from the cliff area requires passing through the designated safety exit); only when the trajectory coincides with the legal path of a certain area, it is determined that "synchronization is completed" and the alarm is removed. It solves the problem of "missing tracking after alarm" in traditional monitoring, ensuring risk closed-loop management.

[0077] In the above embodiment, the behavior learning system adopts dynamic evolution of rules, which means that it receives administrator feedback (such as: "yesterday's cliff false alarm due to tourist photography"), analyzes the instruction type: false alarm confirmation, reduces the sensor sensitivity of the area; path change request generates a temporary viewing path. Through continuous iteration of geographic information models, the rule base adapts to actual operational needs, reducing the cost of manual configuration.

[0078] In the above embodiment, real-time monitoring finds abnormalities, trajectory tracking continuously intervenes, behavior learning optimizes rules, and memory updates geographic information models, forming a "monitoring-tracking-learning" closed loop.

[0079] In some embodiments, the behavior learning system dynamically adjusts the safety level value associated with the current warning area according to the feedback instruction; and the behavior learning system includes a feedback analysis engine, which is configured to: when the feedback instruction includes safety level adjustment, automatically update the level value associated with the current warning area; when the feedback confirms a false alarm, reduce the sensitivity parameters of the same alarm in the area; when the feedback requires path correction, activate the path generator to create a temporary allowed path.

[0080] In the above embodiment, the safety level dynamic adjustment is provided with a trigger condition, which means that the administrator adjusts the area risk level according to the season / activity (such as increasing the stream area level from 2 to 4 in the rainy season). The implementation logic is as follows: the engine calls the API interface of the geographic information model to modify the area level value; synchronously update the alarm threshold of the real-time monitoring system (for example: the tolerance distance of level 4 area is reduced from 10 meters to 2 meters).

[0081] The present application avoids the response lag caused by fixed level through dynamic adjustment, and adapts to dynamic changes in the environment.

[0082] In the above embodiment, the parameter adjustment mechanism is also adjusted through false alarm processing and sensitivity optimization, including: positioning error tolerance, path offset threshold, alarm delay time.

[0083] In the above embodiment, the temporary path generation is generated according to the following method: receiving administrator instructions; calculating feasible paths based on BIM models; injecting space-time constraints; updating to the path mapping table.

[0084] In some embodiments, the monitoring area boundary is determined by running a safety risk analysis algorithm on the scenic spot terrain data by a risk modeling engine, in combination with historical accident data; wherein the risk modeling engine is configured to perform the following operations: input scenic spot terrain point cloud data, hydrogeological report, historical accident database; run Monte Carlo safety risk simulation algorithm to identify high-risk area boundary; output weighted coefficient grading boundary coordinate set.

[0085] In the above embodiments, the multi-source data includes terrain point cloud data, hydrogeological report and historical accident database, wherein the terrain point cloud data includes laser radar scanning to generate three-dimensional topography, and identifies steep slopes and rockfall areas; the hydrogeological report includes determining flood / landslide risk areas (such as river channel expansion range in rainy season).

[0086] The historical accident database includes statistical analysis of accident hotspots, etc.

[0087] In the above embodiments, the Monte Carlo safety risk simulation algorithm includes: randomly generating 100,000 groups of tourist trajectories to construct diversified tourist action path samples; for each step of each trajectory, in combination with terrain, facilities, weather and other factors, simulating corresponding environmental risks, such as high risk in complex terrain and risk increase in bad weather; according to environmental risks and trajectory characteristics, using a probability model (such as an algorithm based on historical accident data), calculating the probability of accidents at each point on the trajectory; aggregating all trajectory points by location, and statistically analyzing high-accident-probability areas, and visualizing them with a heat map, with darker colors representing higher risks. Identify the area with the deepest color and highest probability in the heat map, extract its boundary, and use it as a high-risk area for safety warning, control planning.

[0088] In some embodiments, the geographic information model is generated by simulating personnel flow paths, recording the safety status of each warning area and path conversion rules; wherein the geographic information model is constructed by a behavior simulator: loading scenic spot building BIM model and vegetation coverage data; injecting typical tourist behavior patterns based on seasonal changes; running multi-agent path planning simulation; recording the state transition matrix of each area, which includes the conversion relationship between normal path, emergency path and forbidden zone; generating a path rule library with space-time constraints.

[0089] In the above, the geographical information model is dynamically generated by the behavior simulator, solving the static defect of the traditional scenic spot rule base. It is realized in five steps: 1) Multi-source data loading: Import the scenic building BIM model (including load-bearing structure, safety exit position) and vegetation cover data (distinguish between passable lawn and ecological protection area); 2) Tourist behavior mode injection: Based on season / event, preset typical behavior rule base: Peak season mode: high tourist density, path selection tends to shortcut; Snow season mode: automatically activate anti-skid path, close ice viewing platform; Large event mode: bind temporary evacuation channel coordinates. 3) Multi-agent path simulation: Simulate tens of thousands of tourist moving tracks (including different speed agents such as old people and children), and find bottleneck areas through stress testing. 4) Output key indicators: Peak period stack road retention risk coefficient; Emergency evacuation path traffic efficiency (such as the number of people passing per minute). 5) State transition matrix generation: Record the state transition relationship of each area under abnormal conditions:

[0090] Normal path -> emergency path: When the main path of the viewing platform is closed due to fire, the west standby exit is automatically switched; Emergency path -> forbidden area: When the standby exit is full, the adjacent dangerous area is blocked.

[0091] In some embodiments, the scenic geographical information includes: a region rule table storing a safety level value and a path index corresponding to each warning region; a path mapping table storing a set of allowed moving paths for each warning region, the path mapping table being accessed through the path index; wherein the path mapping table is organized by index cluster, including: a main path set containing a sequence of GPS coordinates of allowed moving paths; an emergency path set containing evacuation paths and trigger conditions; a transfer rule set recording the topological relationship of legal cross-region transfer.

[0092] In the above, the geographical information model is defined to have a three-layer structured storage scheme, realizing millisecond-level path compliance judgment, wherein the region rule table (core index) contains region ID, safety level, path index pointer in each record, the safety level is valued (1-5 levels), and is directly associated with alarm response level. Path mapping table (organized by index cluster): main path set: store GPS coordinate sequence of all compliant moving paths, each path with a travel time window: emergency path set: evacuation path bound with trigger conditions; transfer rule set: describe the topological relationship of cross-region movement.

[0093] The above data association mechanism: Real-time monitoring system calls region rule table to obtain safety level, locates coordinate sequence through path index, and verifies cross-region legality through topological relationship.

[0094] In some embodiments, the trajectory tracking system enters a verification mode after completing synchronization, and if the personnel position meets the pre-warning area rule for N consecutive times, it is determined that the synchronization is valid; wherein the trajectory tracking system comprises a verification controller: after synchronization is completed, a verification mode with adjustable duration is entered; N times of position compliance verification are continuously performed; when the pass rate of N times of verification is ≥95%, it is determined that the synchronization is valid; and the area rule adaptive module is activated to adjust the current path confidence weight.

[0095] In the above, the verification controller workflow includes entering the verification mode when the trajectory tracking system confirms that the personnel returns to the allowed path (such as the visitor returning from the restricted area to the viewing platform); and the adjustable parameter N (default 5 times): continuously performing position compliance verification.

[0096] In the above, the dynamic determination logic includes determining that the synchronization is valid if the position is within the path buffer zone (such as ±5 meters) for 5 consecutive times; and if the pass rate is ≥95%, the adaptive module is activated to increase the path confidence weight.

[0097] In the above, the confidence weight optimization includes an initial weight of 0.6 (for new paths or high-risk areas), and the weight is increased by a learning rate (default +0.1) each time verification is passed; when the weight is >0.8, the system reduces the monitoring frequency (such as reducing the positioning sampling from 1 time / second to 1 time / 10 seconds); and when the weight is <0.4, it is automatically marked as a high-risk individual and the unmanned aerial vehicle is started for focused tracking.

[0098] In the above, the abnormal handling mechanism includes finding a single deviation during verification, specifically including: in flat terrain, the tolerance radius is expanded to 15 meters; and in cliff areas, if the deviation exceeds 5 meters, the tracking is immediately restarted.

[0099] In some embodiments, the real-time monitoring system suspends the alarm in the verification mode, and if any subsequent position violates the area rule, the trajectory tracking system is triggered to re-execute synchronization; wherein the real-time monitoring system performs the following operations in the verification mode: enabling a lenient alarm strategy; if the single position deviation standard deviation is > the preset tolerance value, triggering the trajectory tracking system to restart synchronization; and if the deviation occurs for 2 consecutive times, forcibly exiting the verification mode and generating an area abnormality report.

[0100] During trajectory tracking verification, a hierarchical lenient strategy is used to balance safety and false positives, and the specific strategy switching rule is: when the trajectory tracking system enters the verification mode, the real-time monitoring system automatically switches to the lenient strategy, and the path buffer zone radius is expanded from the regular 5 meters to 15 meters; and the maximum tolerance time is extended from 10 seconds to 30 seconds.

[0101] Key trigger conditions: single deviation tolerance value position standard deviation >20 meters triggers an alarm in ordinary areas; and single deviation tolerance value is standard deviation >5 meters in dangerous areas (cliffs / deep water), which triggers the trajectory synchronization to restart.

[0102] Forced exit mechanism: 2 consecutive position deviations; or 3 cumulative deviations, forced exit verification mode and generate a report.

[0103] Report generation logic: contains deviation coordinate sequence, environmental parameters (weather / human flow), historical statistics of similar events.

[0104] In the above, the abnormal behavior record library stored in the memory and the deviation trajectory data set of the space-time index; the trajectory tracking system stores the trajectory data of the personnel deviating from the path to the abnormal behavior record library, wherein the trajectory tracking system performs: compressed storage of the GPS coordinate sequence deviating from the path; associate corresponding time stamp and environmental parameters; mark high-frequency deviation area to form risk heat map layer.

[0105] In the above, a deviation database with space-time index is constructed to drive the precision of safety management. Specifically, a trajectory compression storage technology is used, such as using the Douglas-Pok algorithm to compress GPS points and retaining key inflection points (accuracy loss <0.5 meters); forming multi-dimensional data association, analyzing peak period risk by binding time stamp; marking specific stack deviation rate under rain and fog weather by associating environmental parameters.

[0106] Risk heat map layer generation: count the number of deviations according to 1km×1km grid, calculate regional risk score: risk score = monthly deviation frequency × regional safety level Output visual layer: red (high risk), yellow (medium risk), green (low risk).

[0107] Set a dynamic updating mechanism to refresh the heat map in real time with new deviation data.

[0108] In some embodiments, the behavior learning system copies abnormal trajectory data to a learning database, and counts the number of repetitions of deviation of the same path; when the number of repetitions reaches a threshold, the geographic information model is updated to include the path as a new allowed moving path.

[0109] In the above, the behavior learning system has an automatic correction path rule based on group behavior data, specifically, high-frequency deviation statistical analysis: extract the same path deviation data from the abnormal record library; set a dynamic threshold (default 100 times / month), trigger the path optimization process.

[0110] The path legality upgrade rule includes: condition 1: the deviated path meets the safety standard (slope <25°, no geological disaster); condition 2: deviation exceeds threshold for 3 consecutive months and no accident record; if the conditions are met, it is automatically added as a temporary allowed path and injected into the path mapping table.

[0111] Space-time constraints binding includes: temporary path setting validity period: lawn shortcut: only activated in peak season (5-10 months) streamside water point: open from 9:00 to 17:00 every day in rainy season (6-8 months).

[0112] The application further provides a scenic spot personnel monitoring and early warning method, comprising the following steps:

[0113] The real-time position of the personnel is acquired through the multi-source perception layer, the real-time monitoring system compares the position of the personnel to be measured with the allowed moving path of the current early warning area, and trajectory compliance analysis is performed: the personnel coordinates are projected to a three-dimensional geographic model; the path rule library of the current early warning area is compared; when path deviation is detected, the alarm level is selected based on the deviation type.

[0114] Dynamic resynchronization is performed through the trajectory tracking system: trajectory prediction based on a motion model is started, adjacent area transfer rules are continuously matched, a synchronization signal is triggered when the personnel enter a legal path, and subsequent positions are continuously tracked until any early warning area rule is matched again.

[0115] The safety rules of the geographic information model are updated according to the feedback of the management terminal through the behavior learning system, wherein rule optimization is performed through the behavior learning system: the structured feedback instructions of the management terminal are analyzed; when the feedback confirms a false alarm, the monitoring sensitivity of the area is reduced; when the feedback requires rule updating, an area rule reconstruction engine is started; and an incrementally updated geographic information model version is output.

[0116] In the above, the real-time position of the personnel is acquired through the multi-source perception layer, the real-time monitoring system compares the path and analyzes the trajectory compliance, the multi-source perception layer in the application integrates positioning technologies such as GPS, Beidou and other sensor devices, and can acquire the position information of the personnel in the scenic spot in real time. After the real-time monitoring system acquires the real-time position of the personnel, the personnel coordinates are projected to a three-dimensional geographic model stored in the storage, the geographic model divides the early warning areas of different safety levels based on the pre-defined monitoring area boundary, and stores a set of allowed moving paths for each area. The real-time monitoring system compares the actual position of the personnel with the path rule library of the current early warning area through a spatial topology algorithm, judges whether the personnel position is in the buffer zone of the allowed moving path (such as triggering an alarm when the path deviation > 5 meters), and selects the corresponding alarm level based on the deviation type (such as deviation from a safe path or entering a forbidden area) when path deviation is detected. The high-level alarm links the broadcasting system to evacuate the crowd. This way of comparing the personnel position with the three-dimensional geographic model and the path rule library in real time realizes dynamic compliance detection of the personnel moving path, ensures that the abnormal behavior of the personnel can be found in time and the corresponding alarm signal is sent.

[0117] The application realizes dynamic resynchronization through a trajectory tracking system. When the real-time monitoring system detects that the personnel path deviates and generates an alarm signal, the trajectory tracking system starts the dynamic resynchronization mechanism in response to the alarm signal. The trajectory tracking system first starts trajectory prediction based on a motion model to predict the moving direction of the personnel, and then continuously matches the transfer rules of adjacent areas (for example, returning to the trail from the cliff area requires passing through the designated safety exit). The system continuously tracks the subsequent moving path of the personnel and compares it with the safety rules of the warning area, until the personnel position reenters the allowed path of any warning area to trigger a synchronization signal and complete synchronization. After synchronization is completed, the trajectory tracking system enters the verification mode and continuously performs N times of position compliance verification. If the verification pass rate is ≥ 95%, it is determined that the synchronization is valid. This dynamic resynchronization mechanism solves the problem of missing tracking after alarm in traditional monitoring, ensures continuous tracking of abnormal personnel until they return to the safe path, and forms a risk closed-loop management.

[0118] The application updates the safety rules of the geographic information model according to the feedback of the management terminal through the behavior learning system. The behavior learning system receives the feedback instructions of the scenic area management terminal in response to the alarm signal, and updates the safety rules of the geographic information model according to the feedback instructions. When the management terminal feedback is confirmed as a false alarm, the behavior learning system reduces the monitoring sensitivity of the area and adjusts the sensitivity parameters (such as positioning error tolerance, path deviation threshold, etc.). When the feedback requires rule update, the area rule reconstruction engine is started to analyze the structured feedback instructions of the management terminal, such as safety level adjustment, path correction, etc. For example, when the feedback instruction contains safety level adjustment, the current warning area level value is automatically updated, and the alarm threshold of the real-time monitoring system is also updated synchronously. When the feedback requires path correction, the path generator is activated to create a temporary allowed path, and the path mapping table is updated. In addition, the behavior learning system also copies the abnormal trajectory data to the learning database, counts the number of repeated path deviations of the same type, and updates the geographic information model when the number of repetitions reaches the threshold to include the path as a new allowed moving path. This mechanism of updating the geographic information model according to the feedback of the management terminal and historical abnormal data enables the system to continuously adapt to changes in the actual operation of the scenic area.

[0119] In the foregoing specification, examples have been described with reference to specific example implementations. It will be evident, however, that various modifications and changes can be made thereto without departing from the scope as set forth in the following claims. The claims are not limited to the specific examples described above.

Claims

1. A scenic area personnel distribution monitoring and early warning system, characterized in that: include: A memory storing a scenic area geographic information model, wherein the scenic area geographic information is divided into a plurality of warning areas with different security levels based on a plurality of predefined monitoring area boundaries, and storing a security level value and at least one allowed personnel movement path for each warning area; A real-time monitoring system that compares the actual position of a person with at least one permitted movement path in the current warning area during the operation of the scenic area, and generates an alarm signal and a corresponding safety level when the actual position of a person exceeds the permitted movement path; A trajectory tracking system, in response to the alarm signal, synchronizes the person's subsequent movement path by continuously tracking the person's subsequent movement path and comparing it with the safety rules of the warning area until the person's position re-enters the allowed path of any warning area; a behavior learning system, receiving a feedback instruction from the scenic area management terminal in response to the alarm signal, and updating the safety rules of the geographic information model according to the feedback instruction; The behavior learning system dynamically adjusts the safety level value associated with the current warning area according to the feedback instruction; The behavior learning system includes a feedback parsing engine, which is configured to: When the feedback instruction includes a safety level adjustment, the level value associated with the current warning area is automatically updated; When the feedback is confirmed to be a false alarm, the sensitivity parameters of similar alarms in the area will be reduced; When feedback requires path correction, the path generator is activated to create a temporary permissible path; The boundaries of the monitoring area are determined by running a safety risk analysis algorithm on the terrain data of the scenic area through a risk modeling engine, and identifying the boundaries of high-risk areas in combination with historical accident data; The risk modeling engine is configured to perform the following operations: Input scenic area terrain point cloud data, hydrogeological reports, and historical accident database; Run the Monte Carlo security risk simulation algorithm; Combined with crowd flow dynamics model to identify high-risk area boundaries; Output the hierarchical boundary coordinate set with weight coefficients; The geographic information model is generated by simulating the flow paths of personnel, recording the safety status of each warning area and the path conversion rules; The geographic information model is constructed by a behavior simulator: Load the scenic area building BIM model and vegetation coverage data; Inject typical tourist behavior patterns based on seasonal changes; Run multi-agent path planning simulations; Recording a state transition matrix of each area, wherein the transition matrix includes a transition relationship between a normal path / an emergency path / a restricted area; Generate a path rule base with time and space constraints; The scenic area geographic information includes: Area rule table, which stores the security level value and path index corresponding to each warning area; A path mapping table storing a set of allowed movement paths for each warning area, wherein the path mapping table is accessed through the path index; The path mapping table is organized by index cluster and contains: The main path set contains the GPS coordinate sequence of the allowed movement paths; Emergency path set, including evacuation paths and triggering conditions; Transfer rule set, which records the topological relationship of legal cross-region transfers; The trajectory tracking system enters the verification mode after completing the synchronization. If the person's position is detected to meet the warning area rules for N consecutive times, the synchronization is determined to be valid; The trajectory tracking system includes a verification controller: After synchronization is complete, it enters verification mode with adjustable duration; Perform N consecutive position compliance checks; When the pass rate of N verifications is ≥95%, the synchronization is considered valid; Activate the regional rule adaptive module to adjust the current path confidence weight; The real-time monitoring system suspends alarming in verification mode, and if any subsequent position violates the zone rules, the trajectory tracking system is triggered to re-execute synchronization; Wherein, the real-time monitoring system performs the following operations in verification mode: Enable relaxed alert policy; If the single position deviation standard deviation is greater than the preset tolerance value, the trajectory tracking system is triggered to restart synchronization; If there are two consecutive deviations, the verification mode will be forced to exit and a regional abnormality report will be generated.

2. The scenic area personnel distribution monitoring and early warning system according to claim 1 is characterized in that: Also includes: a library of abnormal behavior records and a spatiotemporally indexed deviation trajectory dataset stored in the memory; The trajectory tracking system stores the trajectory data of the person deviating from the path into the abnormal behavior record library, wherein: The trajectory tracking system performs: Compress and store the GPS coordinate sequence that deviates from the path; Associate the corresponding timestamps and environment parameters; High-frequency deviation areas are marked to form a risk thermal layer.

3. The scenic area personnel distribution monitoring and early warning system according to claim 2 is characterized by: The behavior learning system copies the abnormal trajectory data to the learning database and counts the number of repetitions of the same path deviation; when the number of repetitions reaches a threshold, the geographic information model is updated to include the path as a new allowed movement path.

4. A method for monitoring and early warning of personnel in a scenic area, characterized in that: The steps include: The system uses a multi-source perception layer to obtain the real-time location of the person, and uses a real-time monitoring system to compare the location of the person to be measured with the allowed movement path in the current warning area. It also performs trajectory compliance analysis: projecting the person's coordinates onto a three-dimensional geographic model. Compare the current warning area path rule library; when a path deviation is detected, select the alarm level based on the deviation type Dynamic resynchronization is performed through the trajectory tracking system: trajectory prediction based on the motion model is initiated, the adjacent area transfer rules are continuously matched, a synchronization signal is triggered when the person enters a legal path, and subsequent positions are continuously tracked until any warning area rules are matched again; The behavioral learning system updates the security rules of the geographic information model based on feedback from the management terminal. The behavioral learning system performs rule optimization: parsing the structured feedback instructions from the management terminal; reducing the monitoring sensitivity of the area when the feedback confirms a false alarm; starting the regional rule reconstruction engine when the feedback requires a rule update; and outputting an incrementally updated version of the geographic information model.

Images