Distributed rooftop proximity alarm system based on wireless networking

Abstract

This invention relates to the field of rooftop edge personnel safety monitoring technology, and discloses a distributed rooftop edge personnel proximity sensing and alarm system based on wireless networking. The system includes a node deployment module, a signal synchronization module, a field division module, a proximity discrimination module, and an alarm triggering module. The node deployment module acquires relevant data and generates a node deployment set; the signal synchronization module synchronizes the signals of adjacent nodes and obtains a signal consistency synchronization annotation set; the field division module generates field coverage overlay analysis results; the proximity discrimination module forms a set of abnormal personnel proximity points; and the alarm triggering module generates edge personnel proximity detection and alarm triggering results. This system can optimize rooftop edge personnel proximity monitoring, reduce false alarms, improve monitoring accuracy and reliability, and ensure the safety of personnel in relevant areas.

Description

Technical Field

[0001] This invention relates to the field of rooftop edge safety monitoring technology, specifically a distributed rooftop edge proximity sensing and alarm system based on wireless networking. Background Technology

[0002] With the accelerating pace of urbanization, the construction and use of various high-rise buildings are becoming increasingly common. As a crucial component of buildings, the safety management of rooftop edges is becoming increasingly prominent. Rooftop edges typically refer to areas with a risk of fall, such as the roof's edge or near roof railings. If people approach these areas, accidents are highly likely to occur, posing a serious threat to their lives. Currently, safety monitoring of people near rooftop edges mainly relies on manual inspections and traditional security equipment, but these methods have many limitations.

[0003] Manual inspections require dedicated personnel to periodically check the rooftop edges, which is not only costly in terms of manpower and time, but also limited in frequency and coverage, making it difficult to achieve 24 / 7 seamless monitoring. In special circumstances such as nighttime or inclement weather, the efficiency and accuracy of manual inspections drop significantly, failing to promptly detect dangerous situations where personnel approach the edges. Furthermore, manual inspections are susceptible to human error; fatigue or inattention among inspection personnel may lead to missed inspections, creating potential safety hazards.

[0004] Traditional security equipment, such as surveillance cameras, can provide real-time monitoring of rooftop areas, but they are prone to blind spots due to limitations such as shooting angle and lighting conditions. Especially in complex rooftop environments, obstructions from various facilities and equipment can prevent cameras from clearly capturing human activity in adjacent areas. Furthermore, surveillance videos require real-time human monitoring, and when people approach the edge, it is often difficult to react promptly, resulting in significant alarm delays.

[0005] Furthermore, some existing sensing monitoring systems have shortcomings in wireless networking. The lack of scientific planning in node deployment leads to uneven signal coverage and potential monitoring blind spots. During signal synchronization, signal fluctuations frequently occur due to electromagnetic interference and environmental changes between adjacent nodes, affecting the consistency and accuracy of monitoring data. Simultaneously, these systems fail to fully consider the impact of signal fluctuations on the sensing range when dividing the sensing field, resulting in discrepancies between the field coverage analysis results and the actual situation, leading to inaccurate detection of personnel approaching.

[0006] Furthermore, existing monitoring systems are weak in identifying abnormal points in signal fluctuation zones during the personnel approach detection stage. They often misinterpret normal signal fluctuations as personnel approaching, generating a large number of false alarms. When alarms are triggered, they cannot effectively distinguish locations at risk of false alarms, leading to reduced reliability of alarm results. This not only increases the workload of safety management personnel but may also cause them to become complacent due to frequent false alarms, resulting in a failure to respond promptly when real danger occurs and ultimately causing a safety accident.

[0007] Currently, the field of rooftop edge safety monitoring suffers from problems such as low monitoring efficiency, limited coverage, poor signal stability, insufficient judgment accuracy, and low alarm reliability. There is an urgent need for a technical solution that can achieve accurate, efficient, and all-weather monitoring to meet the actual needs of rooftop edge safety management. Summary of the Invention

[0008] The purpose of this invention is to provide a distributed rooftop proximity sensing alarm system based on wireless networking to solve the problems mentioned in the background art.

[0009] To achieve the above objectives, the present invention provides a distributed rooftop proximity sensing alarm system based on wireless networking, the system comprising:

[0010] The node deployment module obtains the coordinates of the rooftop edge boundary and the node deployment time, collects the signal strength and electromagnetic interference value of the corresponding location on the same day, associates the deployed nodes and calculates the corresponding coverage matching value, and generates a node deployment set.

[0011] The signal synchronization module extracts the coverage matching value and corresponding coordinates from the node deployment set, synchronizes the signals of adjacent nodes in time order, marks the stable and fluctuating segments in adjacent nodes, and obtains the signal consistency synchronization annotation set.

[0012] The field division module obtains the deployment nodes located in the signal stable section of the signal consistency synchronization label set, extracts the node location and sensing range, compares the coverage range with the coverage overlap, evaluates the intensity of the sensing impact under signal fluctuation, and generates the field coverage overlay analysis results.

[0013] The proximity discrimination module identifies abnormal points in the deployment nodes whose sensed response value is greater than the average response benchmark value and are located in the signal fluctuation range in the field coverage overlay analysis results, forming a set of abnormal points where personnel approach.

[0014] The alarm triggering module obtains all points and corresponding point information in the set of abnormal points where personnel approach, marks points with a risk of false alarms, and generates the detection and alarm triggering results of personnel approaching the edge.

[0015] Preferably, the node deployment set includes coverage matching values, spatial coordinates of deployed nodes, and normalized deployment factors; the signal consistency synchronization annotation set specifically includes signal stable segment annotations, signal fluctuation segment annotations, and coverage matching value difference rates between adjacent deployed nodes; the field coverage overlay analysis results include the degree of influence of node position offset on coverage, the degree of influence of sensing range expansion on coverage, and a comparison of coverage response under each signal fluctuation condition; the personnel approaching anomaly point set includes the spatial location of the anomaly point, the signal strength amplitude characteristics of the anomaly point, and the coverage and sensing fluctuation ratio of the anomaly point; and the personnel approaching detection and alarm triggering results include a list of detected anomaly points and a personnel approaching anomaly point set.

[0016] Preferably, the node deployment module includes:

[0017] The boundary information acquisition submodule obtains the coordinates of the rooftop boundary and the node deployment time, collects the signal strength data and electromagnetic interference data corresponding to the coordinates, and records the acquisition results as two deployment factors: signal factor and interference factor, and obtains the environmental factor data set of the deployment node.

[0018] The node parameter configuration submodule performs normalization processing on the signal factor and interference factor data in the deployment node environmental factor data group, establishes a correspondence between the normalized results and the deployment node coordinates, calculates the average of the normalized signal value and the normalized interference value as the coverage matching value, and generates a node deployment set.

[0019] Preferably, the signal synchronization module includes:

[0020] The synchronization benchmark extraction submodule obtains the coverage matching value and corresponding coordinate data in the node deployment set, identifies the synchronization relationship of all deployment nodes in time based on the coordinate information, calls the deployment node time set, and performs signal synchronization calculation and sorting of deployment nodes in time based on the adjacent time threshold, generating an adjacent deployment node time sorting sequence.

[0021] The deviation calibration submodule, based on the time sorting sequence of the adjacent deployment nodes, compares the stable synchronization reference value and the fluctuating synchronization reference value respectively, and integrates them to generate a signal synchronization deviation sequence.

[0022] The consistency labeling submodule extracts the signal change direction and interference change direction between adjacent deployment nodes based on the signal synchronization deviation sequence. It classifies and labels each pair of deployment nodes according to whether their change trends in the two directions are consistent, and records and groups the segments with stable signals and fluctuating signals respectively to obtain a signal consistency synchronization label set.

[0023] Preferably, the field division module includes:

[0024] The field feature extraction submodule filters out segments marked as signal-stable based on the signal consistency synchronization label set, detects the location data and sensing range data of each deployment node within the coverage time period, arranges them in spatial order to form a location spatial sequence and a sensing range sequence, and generates a field coverage spatial sequence set.

[0025] The coverage overlay calculation submodule calculates the position offset rate and sensing range expansion rate between consecutive spatial nodes in the spatial sequence of each deployment node based on the field coverage spatial sequence set. The position offset rate and sensing range expansion rate are compared side by side under the same coverage conditions. The numerical relationship between the two rate indices under the coverage range is identified by joint analysis. The influence value sequence of each deployment node is integrated to establish the field coverage overlay analysis results.

[0026] Preferably, the proximity detection module includes:

[0027] The sequence extraction submodule, based on the field coverage overlay analysis results, filters out deployment nodes whose inductive response values ​​are greater than the average response benchmark value and deployment nodes located in the signal fluctuation range, extracts continuous coverage records of deployment nodes in spatial order, collects coverage range and inductive sensitivity data corresponding to each spatial node, and generates a continuous coverage record set.

[0028] The fluctuation change ratio calculation submodule calls the continuous coverage record set, extracts the coverage value and sensing value of the deployment node at two consecutive spatial nodes, calculates the coverage change ratio and sensing sensitivity change ratio respectively, integrates them into the coverage change ratio sequence and the sensing sensitivity change ratio sequence, and establishes the coverage fluctuation change dataset.

[0029] Based on the coverage fluctuation change dataset, the anomaly identification submodule extracts the signal strength amplitude data and interference fluctuation data of the corresponding spatial segment, determines whether the coverage change ratio and the sensing sensitivity change ratio both exceed the set fluctuation identification threshold, determines whether the signal strength amplitude and interference fluctuation both exceed the anomaly judgment threshold, marks the spatial nodes that meet the conditions as anomaly points, and generates a set of anomaly points where people approach.

[0030] Preferably, the alarm triggering module includes:

[0031] The joint indicator judgment submodule obtains all locations of the personnel approaching the abnormal point set and their corresponding coordinates and identification information, and compares them with the stable response threshold and the fluctuation response threshold respectively to establish a joint response judgment value sequence.

[0032] The abnormal output processing submodule, based on the joint response judgment value sequence, filters out points whose sensing response value is greater than the sensing response risk threshold, whose coverage matching value is lower than the coverage benchmark value, and whose signal consistency label is a fluctuating segment. It extracts the corresponding point number, location identifier, and segment to which it belongs, marks them as detection anomalies with a risk of false alarms, and outputs the points that meet the joint conditions in a structured format as segments, generating the results of personnel approaching the edge detection and alarm triggering.

[0033] Preferably, the system further includes a parameter calibration module, the parameter calibration module comprising:

[0034] The historical data retrieval submodule obtains the node deployment set, signal consistency synchronization annotation set and field coverage overlay analysis results within the historical period, extracts the historical operating parameters and actual detection results of each module, and generates a historical parameter comparison dataset.

[0035] The calibration coefficient calculation submodule calculates the calibration weights of the signal factor and interference factor based on the historical parameter comparison dataset. It then adjusts the calibration weights by weighting them with the normalized signal value and normalized interference value of the currently deployed node, generates a calibrated coverage matching value sequence, and updates the node deployment set.

[0036] Preferably, the system further includes an anomaly tracing module, the anomaly tracing module comprising:

[0037] The trajectory tracking submodule obtains the spatial location and time node information of the personnel approaching the abnormal point set, retrieves the continuous coverage record set and coverage fluctuation change dataset within the corresponding time period, restores the signal strength change trajectory and interference fluctuation trajectory of the abnormal point in chronological order, and generates abnormal point trajectory tracing data.

[0038] Based on the anomaly trajectory tracing data, the responsibility section marking submodule extracts the boundary markers between the stable signal section and the fluctuating signal section, determines the specific location of the section crossed by the anomaly trajectory, marks the main influencing section that caused the anomaly as responsible, and generates the anomaly point responsibility section marking result.

[0039] Preferably, the system further includes a result output module, the result output module comprising:

[0040] The multi-dimensional integration submodule obtains the results of the detection and alarm triggering of personnel approaching the edge, the set of nodes after calibration of the parameter calibration module, and the results of the labeling of the responsibility section of the abnormal point of the anomaly tracing module. It extracts the list of detected abnormal points, the calibration coverage matching value sequence and the responsibility section marking information, and integrates the data according to the three dimensions of detection results, calibration parameters and tracing conclusions to generate a comprehensive output dataset.

[0041] Based on the comprehensive output dataset, the structured output submodule categorizes the list of detected abnormal points by location segment, arranges the calibration coverage matching value sequence by time period, sorts the responsibility segment marking information by degree of impact, and outputs the results in a format combining tables and text, generating the final comprehensive result of personnel proximity detection and alarm.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] This distributed rooftop proximity sensing and alarm system, based on wireless networking, acquires the coordinates of the rooftop edge boundary and the node deployment time through a node deployment module. Simultaneously, it collects the signal strength and daily electromagnetic interference (EMI) values ​​at the corresponding locations, associates the deployed nodes, and calculates coverage matching values ​​to generate a node deployment set. This approach allows node deployment to better suit the actual environment of the rooftop edge. Different rooftop edge areas vary in signal strength and EMI. By accurately collecting this data and calculating coverage matching values, it ensures that the deployed nodes have more reasonable signal coverage, avoiding monitoring blind spots caused by improper node deployment, and enabling each node to function within its optimal coverage area.

[0044] The signal synchronization module extracts coverage matching values ​​and corresponding coordinates, synchronizes adjacent node signals in chronological order, and marks stable and fluctuating segments to obtain a signal consistency synchronization label set. This process effectively solves the problem of signal asynchrony between adjacent nodes. In wireless networking, the signals of adjacent nodes are easily affected by various factors, leading to asynchrony. Marking stable and fluctuating segments allows the system to clearly understand the signal change patterns, providing a more reliable signal foundation for subsequent field division and personnel proximity detection, and reducing monitoring errors caused by signal asynchrony.

[0045] The field segmentation module acquires the deployment nodes in signal-stable sections, extracts the node locations and sensing ranges, compares the coverage ranges with coverage overlap, assesses the intensity of the sensing impact under signal fluctuations, and generates field coverage overlay analysis results, fully considering the impact of signal fluctuations on the sensing range. Signal fluctuations are an unavoidable phenomenon in wireless networking, and these fluctuations can change the actual sensing range of nodes. By assessing the intensity of their impact and performing field coverage overlay analysis, field segmentation can be made more accurate, making the system's sensing coverage of rooftop edge areas more consistent with reality, and avoiding missed or false detections of people approaching due to unreasonable field segmentation.

[0046] The proximity detection module identifies anomalous points among deployed nodes whose inductive response values ​​exceed the average response benchmark value and are located within signal fluctuation zones, based on the field coverage overlay analysis results. This forms a set of anomalous personnel proximity points, improving the accuracy of personnel proximity detection. In signal fluctuation zones, misjudgments are prone to occur. By comparing the inductive response value with the average response benchmark value, genuine anomalous personnel proximity points can be effectively filtered out, reducing the misjudgment of normal signal fluctuations as personnel approach and making the anomalous point set more valuable.

[0047] The alarm triggering module acquires all locations and corresponding information of personnel approaching abnormal points, marks locations with a risk of false alarms, and generates personnel approach detection and alarm triggering results, greatly improving alarm reliability. Marking locations with false alarm risks allows safety managers to handle alarm information more effectively, avoiding the interference of numerous false alarms on their judgment. This enables managers to quickly identify genuine hazards and take timely measures to prevent accidents.

[0048] Furthermore, through the collaborative work of its various modules, the entire system achieves an integrated process from node deployment, signal synchronization, field division, proximity detection to alarm triggering, adapting to the complex environmental conditions of rooftop edges. Regardless of structural differences between rooftops or various electromagnetic interferences and signal fluctuations, the system can effectively cope without relying on manual inspections, reducing labor costs. Simultaneously, it enables 24 / 7 real-time monitoring, making rooftop edge safety management more efficient and intelligent. Attached Figure Description

[0049] Figure 1 This is a schematic diagram illustrating the working principle of the distributed rooftop edge proximity sensing alarm system based on wireless networking described in this invention.

[0050] Figure 2 A flowchart generated for a dataset;

[0051] Figure 3 A flowchart illustrating the process of deploying modules to nodes;

[0052] Figure 4 A flowchart illustrating the operation of the signal synchronization module;

[0053] Figure 5 A flowchart illustrating the process of the field partitioning module. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Please see Figures 1-5 This invention provides a distributed rooftop proximity sensing and alarm system based on wireless networking. The system includes a node deployment module, a signal synchronization module, a field division module, a proximity detection module, and an alarm triggering module. The specific implementation is as follows:

[0056] The node deployment module obtains the coordinates of the rooftop edge boundary and the node deployment time, collects the signal strength and electromagnetic interference value of the corresponding location on the same day, associates the deployed nodes and calculates the corresponding coverage matching value, and generates a node deployment set.

[0057] The signal synchronization module extracts the coverage matching value and corresponding coordinates from the node deployment set, synchronizes the signals of adjacent nodes in time order, marks the stable and fluctuating segments in adjacent nodes, and obtains the signal consistency synchronization annotation set.

[0058] The field segmentation module acquires the signal consistency synchronous annotation of the deployment nodes located in the signal stable section, extracts the node location and sensing range, compares the coverage range with the coverage overlap, evaluates the intensity of the sensing impact under signal fluctuation, and generates the field coverage overlay analysis results.

[0059] The proximity discrimination module identifies abnormal points in the deployment nodes whose sensed response value is greater than the average response benchmark value and are located in the signal fluctuation range in the field coverage overlay analysis results, forming a set of abnormal points for personnel proximity;

[0060] The alarm triggering module acquires all points and corresponding point information in the set of abnormal personnel approaching the edge, marks points with a risk of false alarms, and generates the detection and alarm triggering results of personnel approaching the edge.

[0061] Example 1:

[0062] The node deployment set includes coverage matching values, spatial coordinates of deployed nodes, and normalized deployment factors. Coverage matching values ​​reflect the degree of signal coverage and environmental interference adaptation of deployed nodes at their corresponding locations. Deployment node spatial coordinates precisely identify the specific location of each node in the rooftop edge area. Normalized deployment factors are parameters obtained after standardizing signal and interference factors to eliminate the impact of different data volumes. The signal consistency synchronization annotation set specifically consists of signal stable segment annotations, signal fluctuation segment annotations, and the coverage matching value difference rate between adjacent deployed nodes. Signal stable segment annotations mark the time periods and spatial ranges of stable signal transmission between adjacent nodes, while signal fluctuation segment annotations correspond to areas and time periods of unstable signal transmission. The coverage matching value difference rate between adjacent deployed nodes quantifies the degree of difference in coverage matching values ​​between adjacent nodes, thereby determining the consistency of signal coordination between nodes. The field coverage overlay analysis results include the impact of node position offset on coverage, the impact of sensing range expansion on coverage, and a comparison of coverage response under each signal fluctuation condition. The impact of node location offset on coverage is used to assess the effect of the deviation between the actual installation location of the node and the preset coordinates on the signal coverage range. The impact of sensing range expansion on coverage analyzes the changes in coverage effect caused by the expansion or contraction of the sensing range under different conditions. The comparison of coverage response under each signal fluctuation condition records the response changes of the coverage area under different signal fluctuation intensities. The set of abnormal points for personnel approach includes the spatial location of the abnormal point, the signal strength amplitude characteristics of the abnormal point, and the ratio of coverage to sensing fluctuation. The spatial location of the abnormal point clearly indicates the specific location of the abnormal point on the edge of the roof. The signal strength amplitude characteristics of the abnormal point describe the amplitude and trend of signal strength changes at the abnormal point. The ratio of coverage to sensing fluctuation reflects the proportional relationship between coverage range fluctuation and sensing sensitivity fluctuation. The results of personnel approach detection and alarm triggering include a list of detected abnormal points and a set of abnormal points for personnel approach. The list of detected abnormal points summarizes the point numbers and basic information of all points identified as abnormal, while the set of abnormal points for personnel approach is the core basis for triggering alarms.

[0063] The boundary information acquisition submodule within the node deployment module is responsible for obtaining the coordinates of the rooftop edge boundary and the node deployment time. When acquiring the coordinates, a high-precision positioning device samples the edge line of the rooftop edge at multiple points, generating a continuous coordinate sequence to ensure the accuracy of the boundary range. The node deployment time is accurate to the minute, recording the exact moment each node is installed. Simultaneously, this submodule collects signal strength data and daily electromagnetic interference data for the corresponding coordinate locations. Signal strength data is acquired in real-time through the node's built-in signal receiver, while daily electromagnetic interference data is continuously collected using dedicated interference detection equipment. The sampling interval is set according to the environmental complexity, typically every 10-30 seconds. The collected signal strength and electromagnetic interference data are recorded as signal factors and interference factors, respectively, forming a deployment node environmental factor data set. This data set is dynamically updated over time to reflect real-time environmental changes.

[0064] The node parameter configuration submodule performs normalization processing on the signal factor and interference factor data in the deployment node environmental factor data group. During normalization, the value ranges of the signal and interference factors are first determined, mapping the actually collected data to the 0-1 interval to eliminate the influence of different physical dimensions. For example, if the actual value range of the signal factor is [-80dBm, -30dBm], then a linear transformation is used to convert each signal factor value into a corresponding value between 0 and 1. A one-to-one correspondence is established between the normalized results and the deployment node coordinates; that is, each coordinate point has a corresponding normalized signal factor and normalized interference factor. Subsequently, the average of the normalized signal value and the normalized interference value is calculated as the coverage matching value. Specifically, the normalized signal value and the normalized interference value of the same node are added together and then divided by 2; the result is the coverage matching value for that node. Finally, the coverage matching value, the spatial coordinates of the deployed nodes, and the normalized deployment factor (i.e., the normalized signal value and the normalized interference value) are integrated together to generate a node deployment set. This set will be stored in the system's database to provide basic data for subsequent module processing.

[0065] The synchronization benchmark extraction submodule in the signal synchronization module retrieves coverage matching values ​​and corresponding coordinate data from the node deployment set. Based on the coordinate information, it determines the spatial distribution of all deployed nodes and then identifies the temporal synchronization relationship of all deployed nodes. It calls the deployment node time set, which contains the deployment time and runtime timestamp of each node. Using an adjacent time threshold as a benchmark (typically 50-100 milliseconds, set according to the node's communication frequency), it performs signal synchronization calculations on the deployed nodes. During the calculation, it compares the signal transmission delay and phase difference of different nodes at the same time point. Then, based on the calculation results, it sorts the nodes, generating an adjacent deployment node time sorting sequence. This sequence reflects the temporal synchronization order of adjacent nodes.

[0066] The deviation calibration submodule compares stable synchronization benchmarks and fluctuating synchronization benchmarks based on the time-series of adjacent deployed nodes. The stable synchronization benchmark is a system-preset standard deviation of signal synchronization between adjacent nodes under ideal conditions, while the fluctuating synchronization benchmark is the average deviation obtained from historical data under fluctuating signal conditions. By comparing the actual measured synchronization deviation with these two benchmarks, the deviation difference is calculated. These deviation differences are then integrated to generate a signal synchronization deviation sequence, which records the signal synchronization deviation between each pair of adjacent nodes.

[0067] The consistency labeling submodule extracts the signal change direction and interference change direction between adjacent deployed nodes based on the signal synchronization deviation sequence. Signal change direction includes signal enhancement, signal weakening, or signal stabilization; interference change direction includes interference enhancement, interference weakening, or interference stabilization. Each pair of deployed nodes is categorized and labeled based on whether their change trends in the two directions are consistent. If the signal change direction and interference change direction are the same (e.g., both enhancing or weakening simultaneously), it is marked as a stable signal segment. If the change directions are opposite, or one direction changes drastically while the other remains stable, it is marked as a fluctuating signal segment. Stable and fluctuating signal segments are recorded and grouped separately. Records include the segment's start and end times and the involved node pairs. Grouping categorizes adjacent segments according to their spatial location, ultimately obtaining a signal consistency synchronization label set. This label set provides a basis for subsequent field division and proximity discrimination based on signal state.

[0068] Example 2:

[0069] The field segmentation module consists of a field feature extraction submodule and a coverage overlay calculation submodule. The field feature extraction submodule receives a signal consistency synchronization annotation set, which includes annotations of stable signal segments, fluctuating signal segments, and the difference rate of coverage matching values ​​between adjacent deployed nodes. The submodule first filters the annotation set, retaining only segments marked as signal-stable. These segments indicate stable node signal transmission and are suitable as the basis for field segmentation. Next, it detects the location and sensing range data of each deployed node within its coverage time period. Location data is obtained through the node's built-in positioning component and includes latitude, longitude, and altitude information. Sensing range data is determined based on the node's sensing parameters and environmental conditions, typically presenting a fan-shaped or circular coverage area centered on the node. These location data are arranged in spatial order to form a location spatial sequence, and the sensing range data are also arranged in the same spatial order to form a sensing range sequence. The two are combined to generate a field coverage spatial sequence set, which completely records the spatial distribution and sensing range of nodes within each stable segment.

[0070] The coverage overlay calculation submodule processes the spatial sequence set of the field coverage, calculating the position offset rate and sensing range expansion rate between consecutive spatial nodes in each deployment node spatial sequence. The position offset rate refers to the change in position between two adjacent spatial nodes per unit time, calculated by dividing the difference in position coordinates of the two nodes by the time interval. The sensing range expansion rate is the result of dividing the difference in sensing range radius between two adjacent spatial nodes by the time interval. Under the same coverage conditions, the position offset rate and sensing range expansion rate are compared side-by-side. These conditions include identical signal strength and electromagnetic interference levels. By jointly analyzing these two rate indicators, the numerical relationship between them and the magnitude of coverage range changes is identified. For example, does an increase in the position offset rate lead to a reduction in coverage range, and does an accelerated sensing range expansion rate accompany a nonlinear expansion of coverage range? The influence values ​​of each deployment node at different time periods and spatial locations are integrated. These influence values ​​combine the effects of position offset and sensing range expansion on the coverage effect, ultimately establishing the field coverage overlay analysis results.

[0071] The proximity discrimination module comprises a sequence extraction submodule, a fluctuation change ratio calculation submodule, and an anomaly identification submodule. The sequence extraction submodule receives the field coverage overlay analysis results, which include the impact of node position offset on coverage, the impact of sensing range expansion on coverage, and a comparison of coverage response under different signal fluctuation conditions. This submodule filters out two categories of deployed nodes: one category consists of nodes whose sensing response values ​​are greater than the average response benchmark value (calculated based on historical sensing data); the other category consists of nodes located in signal fluctuation zones. Continuous coverage records for these deployed nodes are extracted spatially. These records include the coverage boundary coordinates and sensing signal strength at each time point. Simultaneously, coverage range data and sensing sensitivity data for each spatial node are collected. The sensing sensitivity data reflects the node's sensitivity to personnel approach. These data are then integrated to generate a continuous coverage record set.

[0072] The fluctuation change ratio calculation submodule calls the continuous coverage record set to extract the coverage and sensing values ​​of the deployed nodes at two consecutive spatial nodes. The coverage value quantifies the size of the coverage area, while the sensing value reflects the strength of the sensed signal. The coverage change ratio is calculated by dividing the difference between the coverage value of the subsequent spatial node and the coverage value of the preceding spatial node by the coverage value of the preceding spatial node. Simultaneously, the sensing sensitivity change ratio is calculated by dividing the difference between the sensing value of the subsequent spatial node and the sensing value of the preceding spatial node by the sensing value of the preceding spatial node. The coverage change ratios of all consecutive spatial nodes are arranged sequentially to form a coverage change ratio sequence; similarly, the sensing sensitivity change ratios are arranged sequentially to form a sensing sensitivity change ratio sequence. These two sequences together constitute the coverage fluctuation change dataset.

[0073] The anomaly identification submodule operates based on the coverage fluctuation change dataset, extracting signal strength amplitude data and interference fluctuation data for the corresponding spatial segment. Signal strength amplitude data refers to the maximum change in signal strength within a given spatial segment, while interference fluctuation data represents the amplitude of electromagnetic interference fluctuations within that segment. The submodule first determines whether both the coverage change ratio and the inductive sensitivity change ratio exceed a set fluctuation identification threshold, which is determined based on the system's definition of the normal fluctuation range. Next, it determines whether both the signal strength amplitude and interference fluctuation exceed an anomaly judgment threshold. This anomaly judgment threshold, higher than the fluctuation identification threshold, is used to distinguish between normal and abnormal fluctuations. When all four conditions are met simultaneously—that is, the coverage change ratio and the inductive sensitivity change ratio both exceed the fluctuation identification threshold, and the signal strength amplitude and interference fluctuation both exceed the anomaly judgment threshold—the spatial node is marked as an anomaly. Information from all marked anomaly points is integrated, including the spatial coordinates, corresponding timestamps, and signal change characteristics, to generate a set of anomaly points indicating personnel proximity.

[0074] Example 3:

[0075] The alarm triggering module comprises an indicator joint judgment submodule and an anomaly output processing submodule. The indicator joint judgment submodule receives a set of abnormal personnel approach points and extracts detailed information for all points, including each point's three-dimensional spatial coordinates, unique identifier code, corresponding signal strength record, inductive response value, and the corresponding signal segment label. For each point, this submodule compares its inductive response value with both a stable response threshold and a fluctuation response threshold. The stable response threshold is the baseline value used by the system to determine personnel approach in a stable signal segment, while the fluctuation response threshold is an adjustment baseline value set for a fluctuating signal segment, typically higher than the stable response threshold. The difference between each point and the two thresholds is calculated through comparison, and these two differences are then weighted and summed according to preset weights to establish a joint response judgment value sequence. Each value in the sequence corresponds to a comprehensive judgment result for an abnormal point.

[0076] The anomaly output processing submodule performs subsequent processing based on the joint response judgment value sequence. First, a sensing response risk threshold is set, which is higher than the fluctuation response threshold, to filter out high-risk sensing response signals. Simultaneously, a coverage benchmark value is set as the baseline standard for measuring the coverage effect of deployed nodes. The submodule filters three types of points from the joint response judgment value sequence: points with sensing response values ​​greater than the sensing response risk threshold, points with coverage matching values ​​lower than the coverage benchmark value, and points whose signal consistency labels clearly indicate fluctuation segments. For points that simultaneously meet these three conditions, their point number, specific location identifier (such as the corresponding rooftop edge area number, straight-line distance from the boundary, etc.), and the signal segment information to which they belong are extracted, marking these points as having detection anomalies and a risk of false alarms. Subsequently, these high-risk points are grouped according to their spatial segments, with each group containing details of all eligible points within that segment. Finally, the results are output in a structured format, forming the edge personnel proximity detection and alarm triggering results, which can be directly used to drive subsequent alarm devices.

[0077] The system also includes a parameter calibration module, which consists of a historical data retrieval submodule and a calibration coefficient calculation submodule. The main function of the historical data retrieval submodule is to extract operational data from the system database within historical periods, including node deployment sets, signal consistency synchronization annotation sets, and field coverage overlay analysis results generated over a past period. Simultaneously, it collects the corresponding actual detection results for this historical data, such as the actual proximity of personnel at that time and the accuracy records of alarm triggering. The historical operational parameters are correlated with the actual detection results to generate a historical parameter comparison dataset. This dataset is arranged chronologically, with each data unit containing the system parameters at a specific moment and the corresponding actual situation record.

[0078] The calibration coefficient calculation submodule calculates the calibration coefficients based on a historical parameter comparison dataset. First, it analyzes the deviation between signal factors and actual detection results in historical data to determine the calibration weight of the signal factors. Similarly, it analyzes the deviation between interference factors and actual detection results to determine the calibration weight of the interference factors. The calculation of calibration weights needs to consider the influence of data from different historical periods; recent data has a higher weight than older data. After obtaining the calibration weights for signal factors (denoted as α) and interference factors (denoted as β), the coverage matching value of the currently deployed node is calibrated using the following formula:

[0079] C'=α×S+β×I

[0080] Where C' represents the calibrated coverage matching value, S represents the normalized signal value of the currently deployed node, and I represents the normalized interference value of the currently deployed node. α and β are calibration coefficients, and α+β=1 to ensure that the calibrated values ​​remain within a reasonable range. The calibrated coverage matching value for each deployed node is calculated using this formula, forming a sequence of calibrated coverage matching values. Finally, the newly generated sequence of coverage matching values ​​replaces the original coverage matching values ​​in the node deployment set, completing the update of the node deployment set. The updated set will serve as the foundational data for subsequent system operation.

[0081] Example 4:

[0082] The system includes an anomaly tracing module, which consists of a trajectory tracking submodule and a responsibility segment marking submodule. The trajectory tracking submodule receives data from personnel approaching a set of anomaly points and extracts the spatial location information and corresponding time information for each anomaly. The spatial location information includes the anomaly's three-dimensional coordinates, accurate to the centimeter level, and the time information is accurate to the second, recording the specific moment the anomaly was identified. Based on this information, the submodule retrieves the continuous coverage record set and coverage fluctuation change dataset for the corresponding time period from the system's stored historical data. The continuous coverage record set contains real-time records of coverage range changes and signal strength fluctuations for each deployed node within that time period, while the coverage fluctuation change dataset records the specific values ​​of the coverage change ratio and the sensing sensitivity change ratio. The trajectory tracking submodule processes this data chronologically, reconstructing the signal strength change trajectory and interference fluctuation trajectory from the moment the anomaly is first detected to when it is marked as an anomaly. The signal strength change trajectory is plotted on the horizontal axis with time and the vertical axis with signal strength value, forming a continuous curve that visually displays the rise and fall of signal strength over time; similarly, the interference fluctuation trajectory is plotted on the horizontal axis with time and the vertical axis with interference value, presenting the fluctuation of electromagnetic interference. By integrating these two trajectories, anomaly trajectory tracking data is generated. The data includes the signal strength and interference value at each time point, as well as the slope change of the trajectory, reflecting the rate of signal change.

[0083] The responsibility section marking submodule operates based on anomaly trajectory tracing data. First, it extracts boundary markers between stable and fluctuating signal sections from the data. These boundary markers include spatial coordinates and time nodes. The spatial coordinates mark the physical boundary between stable and fluctuating sections, while the time nodes mark the specific moments when the signal state transitions from stable to fluctuating or vice versa. The submodule analyzes the specific locations where anomaly trajectories cross these boundaries, determining whether the signal change occurred within a stable section, a fluctuating section, or across both sections. If the anomaly trajectory is entirely within a stable signal section, the analysis focuses on whether there are anomalies in the node parameters within that section. If it is entirely within a fluctuating signal section, the analysis examines whether the amplitude and frequency of the fluctuations exceed normal ranges. If the trajectory crosses two sections, the submodule records the signal change characteristics when crossing the boundaries, such as sudden changes in signal strength and peak values ​​of interference fluctuations. Based on these analyses, the main affected sections causing the anomalies are identified. For example, if the signal abrupt change is largest after the anomaly crosses the boundary between a stable and fluctuating section, the fluctuating section is marked as the main affected section; if the signal already shows continuous abnormal changes within a stable section, the stable section is marked as the main affected section. Responsibility is assigned to the main affected sections, including the section number, the numbers of the deployment nodes involved, the start and end times of the section, and its spatial range. This process ultimately generates the anomaly point responsibility section labeling results.

[0084] During operation, the node deployment module continuously updates the coordinates of the rooftop edge boundary via a boundary acquisition submodule. Since the rooftop edge area may undergo subtle changes due to environmental factors (such as temporary obstacle movement caused by wind or minor alterations in the physical morphology of the boundary due to rain erosion), the submodule periodically resamples the positioning equipment to obtain the latest boundary coordinates, ensuring the accuracy of the coordinate data. Simultaneously, it adjusts the node deployment time in real-time; for example, if a deployment node is temporarily moved for maintenance, its deployment time record is updated promptly. Based on this, signal strength and electromagnetic interference data are dynamically acquired. The acquisition frequency is adjusted according to the severity of environmental changes; the frequency is appropriately reduced during periods of stable electromagnetic environment and increased during periods of thunderstorms or when large equipment is operating nearby, which may cause drastic changes in the electromagnetic environment. This dynamic acquisition method ensures that the environmental factor data set of the deployment nodes reflects the current signal and interference status in real time. Each data point in the data set is timestamped for easy tracking of the acquisition time.

[0085] The node parameter configuration submodule uses a sliding window approach for real-time updates when normalizing signal and interference factor data. The size of the sliding window is set according to the data acquisition frequency; for example, if data is acquired every 10 seconds, the window size can be set to include the most recent 10 acquisitions. Within each window, the maximum and minimum values ​​of the signal and interference factors are recalculated as a reference range for normalization, and then the latest data within the window is normalized. This method avoids the problem of outdated normalization standards caused by long-term environmental changes, ensuring the accuracy of coverage matching value calculation. For example, when electromagnetic interference in a certain area remains at a high level for a long period, the sliding window gradually adapts to this change, allowing the normalized interference factor to more reasonably reflect the actual interference situation. By updating the normalization results in real time, parameters such as coverage matching values ​​and normalized deployment factors in the node deployment set can promptly reflect the current actual environmental state, providing reliable data support for subsequent system processing.

[0086] Example 5:

[0087] The system includes a results output module, which consists of a multi-dimensional integration submodule and a structured output submodule. The multi-dimensional integration submodule receives the results of proximity detection and alarm triggering, the calibrated node deployment set generated by the parameter calibration module, and the anomaly point responsibility section labeling results obtained by the anomaly tracing module. It extracts a list of anomaly detection points from the proximity detection and alarm triggering results. This list includes the point numbers, spatial coordinates, and sensor response values ​​of all points marked as having detection anomalies and a risk of false alarms. It also extracts a calibration coverage matching value sequence from the calibrated node deployment set, sorted by deployment node number, recording the calibrated coverage matching value for each node. Finally, it extracts responsibility section labeling information from the anomaly point responsibility section labeling results, including the main affected section number for each anomaly point, the nodes involved within the section, and the spatiotemporal range of the section. The multi-dimensional integration submodule integrates these three types of information according to three dimensions: detection results, calibration parameters, and traceability conclusions. For example, it binds a certain detection anomaly point with its corresponding calibration coverage matching value and the information of the responsible section to form a complete comprehensive record. After all comprehensive records are summarized, a comprehensive output dataset is generated. This dataset is stored in tabular form, and each record contains the basic information of the detection anomaly point, the calibrated parameter value, and the details of the responsible section obtained through traceability.

[0088] The structured output submodule processes the comprehensive output dataset. First, it categorizes the list of detected anomaly points by location segment. Location segments are divided according to the physical structure of the rooftop edge, such as the east edge segment, south edge segment, and corner segment. Anomaly points belonging to the same location segment are grouped together, and within each group, they are sorted by their distance from the boundary, with points closer to the boundary appearing first. For the calibration coverage matching value sequence, it is arranged by time period, which can be set to hour, day, or week. Within each time period, the calibration coverage matching values ​​are arranged in the order of deployment node numbers, forming the basic data for the time-series variation curve, facilitating the observation of how the coverage matching values ​​of different nodes change over time. The responsibility segment marking information is sorted by the degree of influence, which is determined comprehensively based on factors such as the number of anomaly points within the segment and the intensity amplitude of the anomaly signal. Responsible segments with higher influence are listed first. Each responsibility segment lists the anomaly points it contains and their corresponding detection information.

[0089] The output format combines tables and text. The tables consist of three main tables: a classification table of detected anomaly points, with headers including location segment, point number, spatial coordinates, sensor response value, and false alarm risk level; a time series table of calibration coverage matching values, with headers including time period, node number, and calibration coverage matching value; and a responsibility segment ranking table, with headers including responsibility segment number, impact level, number of anomalies, and involved nodes. The text section provides supplementary explanations of the table content, such as explaining the reasons for the concentration of detected anomalies in a certain location segment, the overall trend of calibration coverage matching value changes, and the criteria for determining the impact level of the responsibility segment. The text explanations are concise and clear, avoiding redundant descriptions. In this way, the information in the comprehensive output dataset is presented in a clear and organized form, generating the final comprehensive result of personnel approach detection and alarm at the edge. This result can be directly provided to rooftop safety management personnel for developing corresponding safety management measures.

[0090] When synchronizing signals from adjacent nodes, the signal synchronization module dynamically adjusts the adjacent time threshold based on the electromagnetic environment characteristics at different times. Electromagnetic environment characteristics include electromagnetic interference intensity and signal transmission stability. For example, during weekdays, due to the presence of numerous surrounding electrical devices and stronger electromagnetic interference, signal transmission is easily affected. In this case, the adjacent time threshold is reduced, such as to 50 milliseconds, to improve signal synchronization accuracy. Conversely, at night or on holidays, when the electromagnetic environment is relatively stable, the adjacent time threshold can be increased, such as to 100 milliseconds, to reduce the system's computational load. The consistency labeling submodule optimizes the classification and labeling algorithm by incorporating segment characteristics from historical data when marking stable and fluctuating signal segments. Segment characteristics in historical data include the duration and amplitude of stable and fluctuating signal segments under different seasons and weather conditions. The algorithm learns these characteristics and adjusts the threshold for determining whether the direction of signal change is consistent with the direction of interference change. For example, in environments prone to signal fluctuations, such as rainy days, the threshold for determining stable signal segments is appropriately increased to reduce false positives. This optimization improves the reliability of the signal consistency synchronization label set, making the labeling results more consistent with actual electromagnetic environment changes.

[0091] The coverage overlay calculation submodule within the field segmentation module introduces a spatial weighting factor when calculating the location offset rate and sensing range expansion rate. This spatial weighting factor is set according to the importance of different areas. Areas of high importance, such as corners at the edge of a rooftop or hazardous areas easily accessible to personnel, have larger spatial weighting factors. These factors assign greater weight to the location offset and sensing range expansion of these areas during rate calculations, making the calculation results more reflective of coverage changes in critical areas. Conversely, areas of lower importance, such as flat areas far from the edge, have smaller spatial weighting factors, reducing their impact on the overall coverage analysis. By introducing the spatial weighting factor, the field coverage overlay analysis results better align with the actual safety management needs of rooftop edges, highlighting coverage changes in critical areas and providing more targeted data support for subsequent proximity detection and alarm triggering.

[0092] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0093] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A distributed rooftop edge proximity sensing and alarm system based on wireless networking, characterized in that, The system includes: The node deployment module obtains the coordinates of the rooftop edge boundary and the node deployment time, collects the signal strength and electromagnetic interference value of the corresponding location on the same day, associates the deployed nodes and calculates the corresponding coverage matching value, and generates a node deployment set. The signal synchronization module extracts the coverage matching value and corresponding coordinates from the node deployment set, synchronizes the signals of adjacent nodes in time order, marks the stable and fluctuating segments in adjacent nodes, and obtains the signal consistency synchronization annotation set. The field division module obtains the deployment nodes located in the signal stable section of the signal consistency synchronization label set, extracts the node location and sensing range, compares the coverage range with the coverage overlap, evaluates the intensity of the sensing impact under signal fluctuation, and generates the field coverage overlay analysis results. The field partitioning module includes: The field feature extraction submodule filters out segments marked as signal-stable based on the signal consistency synchronization label set, detects the location data and sensing range data of each deployment node within the coverage time period, arranges them in spatial order to form a location spatial sequence and a sensing range sequence, and generates a field coverage spatial sequence set. Based on the field coverage spatial sequence set, the coverage overlay calculation submodule calculates the position offset rate and sensing range expansion rate between consecutive spatial nodes in the spatial sequence of each deployment node. The position offset rate and sensing range expansion rate are compared side by side under the same coverage conditions. By jointly analyzing the two types of rate indicators, the numerical relationship of the change in the coverage range is identified. The influence value sequence of each deployment node is integrated to establish the field coverage overlay analysis results. The proximity discrimination module identifies abnormal points in the deployment nodes whose sensed response value is greater than the average response benchmark value and are located in the signal fluctuation range in the field coverage overlay analysis results, forming a set of abnormal points where personnel approach. The alarm triggering module obtains all points and corresponding point information in the set of abnormal points where personnel approach, marks points with a risk of false alarms, and generates the detection and alarm triggering results of personnel approaching the edge.

2. The distributed rooftop proximity sensing and alarm system based on wireless networking as described in claim 1, characterized in that, The node deployment set includes coverage matching values, spatial coordinates of deployed nodes, and normalized deployment factors. The signal consistency synchronization annotation set specifically includes annotations of stable signal sections, annotations of fluctuating signal sections, and the difference rate of coverage matching values ​​between adjacent deployed nodes. The field coverage overlay analysis results include the degree of influence of node position offset on coverage, the degree of influence of sensing range expansion on coverage, and a comparison of coverage response under each signal fluctuation condition. The personnel approaching anomaly point set includes the spatial location of the anomaly point, the signal strength amplitude characteristics of the anomaly point, and the coverage and sensing fluctuation ratio of the anomaly point. The personnel approaching detection and alarm triggering results include a list of detected anomaly points and a personnel approaching anomaly point set.

3. The distributed rooftop proximity sensing alarm system based on wireless networking as described in claim 1, characterized in that, The node deployment module includes: The boundary information acquisition submodule obtains the coordinates of the rooftop boundary and the node deployment time, collects the signal strength data and electromagnetic interference data corresponding to the coordinates, and records the acquisition results as two deployment factors: signal factor and interference factor, and obtains the environmental factor data set of the deployment node. The node parameter configuration submodule performs normalization processing on the signal factor and interference factor data in the deployment node environmental factor data group, establishes a correspondence between the normalized results and the deployment node coordinates, calculates the average of the normalized signal value and the normalized interference value as the coverage matching value, and generates a node deployment set.

4. The distributed rooftop proximity sensing alarm system based on wireless networking according to claim 3, characterized in that, The signal synchronization module includes: The synchronization benchmark extraction submodule obtains the coverage matching value and corresponding coordinate data in the node deployment set, identifies the synchronization relationship of all deployment nodes in time based on the coordinate information, calls the deployment node time set, and performs signal synchronization calculation and sorting of deployment nodes in time based on the adjacent time threshold, generating an adjacent deployment node time sorting sequence. The deviation calibration submodule, based on the time sorting sequence of the adjacent deployment nodes, compares the stable synchronization reference value and the fluctuating synchronization reference value respectively, and integrates them to generate a signal synchronization deviation sequence. The consistency labeling submodule extracts the signal change direction and interference change direction between adjacent deployment nodes based on the signal synchronization deviation sequence. It classifies and labels each pair of deployment nodes according to whether their change trends in the two directions are consistent, and records and groups the segments with stable signals and fluctuating signals respectively to obtain a signal consistency synchronization label set.

5. The distributed rooftop proximity sensing alarm system based on wireless networking according to claim 4, characterized in that, The proximity detection module includes: The sequence extraction submodule, based on the field coverage overlay analysis results, filters out deployment nodes whose inductive response values ​​are greater than the average response benchmark value and deployment nodes located in the signal fluctuation range, extracts continuous coverage records of deployment nodes in spatial order, collects coverage range and inductive sensitivity data corresponding to each spatial node, and generates a continuous coverage record set. The fluctuation change ratio calculation submodule calls the continuous coverage record set, extracts the coverage value and sensing value of the deployment node at two consecutive spatial nodes, calculates the coverage change ratio and sensing sensitivity change ratio respectively, integrates them into the coverage change ratio sequence and the sensing sensitivity change ratio sequence, and establishes the coverage fluctuation change dataset. Based on the coverage fluctuation change dataset, the anomaly identification submodule extracts the signal strength amplitude data and interference fluctuation data of the corresponding spatial segment, determines whether the coverage change ratio and the sensing sensitivity change ratio both exceed the set fluctuation identification threshold, determines whether the signal strength amplitude and interference fluctuation both exceed the anomaly judgment threshold, marks the spatial nodes that meet the conditions as anomaly points, and generates a set of anomaly points where people approach.

6. The distributed rooftop proximity sensing alarm system based on wireless networking according to claim 5, characterized in that, The alarm triggering module includes: The joint indicator judgment submodule obtains all locations of the personnel approaching the abnormal point set and their corresponding coordinates and identification information, and compares them with the stable response threshold and the fluctuation response threshold respectively to establish a joint response judgment value sequence. The abnormal output processing submodule, based on the joint response judgment value sequence, filters out points whose sensing response value is greater than the sensing response risk threshold, whose coverage matching value is lower than the coverage benchmark value, and whose signal consistency label is a fluctuating segment. It extracts the corresponding point number, location identifier, and segment to which it belongs, marks them as detection anomalies with a risk of false alarms, and outputs the points that meet the joint conditions in a structured format as segments, generating the results of personnel approaching the edge detection and alarm triggering.

7. The distributed rooftop proximity sensing alarm system based on wireless networking according to claim 6, characterized in that, The system also includes a parameter calibration module, which comprises: The historical data retrieval submodule obtains the node deployment set, signal consistency synchronization annotation set and field coverage overlay analysis results within the historical period, extracts the historical operating parameters and actual detection results of each module, and generates a historical parameter comparison dataset. The calibration coefficient calculation submodule calculates the calibration weights of the signal factor and interference factor based on the historical parameter comparison dataset. It then adjusts the calibration weights by weighting them with the normalized signal value and normalized interference value of the currently deployed node, generates a calibrated coverage matching value sequence, and updates the node deployment set.

8. The distributed rooftop proximity sensing alarm system based on wireless networking according to claim 7, characterized in that, The system also includes an anomaly tracing module, which includes: The trajectory tracking submodule obtains the spatial location and time node information of the personnel approaching the abnormal point set, retrieves the continuous coverage record set and coverage fluctuation change dataset within the corresponding time period, restores the signal strength change trajectory and interference fluctuation trajectory of the abnormal point in chronological order, and generates abnormal point trajectory tracing data. Based on the anomaly trajectory tracing data, the responsibility section marking submodule extracts the boundary markers between the stable signal section and the fluctuating signal section, determines the specific location of the section crossed by the anomaly trajectory, marks the main influencing section that caused the anomaly as responsible, and generates the anomaly point responsibility section marking result.

9. The distributed rooftop proximity sensing alarm system based on wireless networking according to claim 8, characterized in that, The system further includes a result output module, which includes: The multi-dimensional integration submodule obtains the results of the detection and alarm triggering of personnel approaching the edge, the set of nodes after calibration of the parameter calibration module, and the results of the labeling of the responsibility section of the abnormal point of the anomaly tracing module. It extracts the list of detected abnormal points, the calibration coverage matching value sequence and the responsibility section marking information, and integrates the data according to the three dimensions of detection results, calibration parameters and tracing conclusions to generate a comprehensive output dataset. Based on the comprehensive output dataset, the structured output submodule categorizes the list of detected abnormal points by location segment, arranges the calibration coverage matching value sequence by time period, sorts the responsibility segment marking information by degree of impact, and outputs the results in a format combining tables and text, generating the final comprehensive result of personnel proximity detection and alarm.

Images