Electromagnetic radiation monitoring method and system based on big data analysis

Abstract

The present application relates to the technical field of electromagnetic radiation monitoring, and more particularly to an electromagnetic radiation monitoring method and system based on big data analysis, the steps of the method comprising: acquiring multi-source monitoring big data corresponding to monitoring nodes arranged along roads in a city monitoring area; establishing a traffic flow-frequency selection propagation response relationship corresponding to each target frequency band; determining a traffic flow interpretation residual corresponding to each target frequency band; analyzing a frequency selection electromagnetic radiation recovery response corresponding to each target frequency band after a traffic flow disturbance removal node, to obtain a corrected traffic flow interpretation residual; determining a radiation anomaly degree corresponding to each monitoring node according to the corrected traffic flow interpretation residual, determining a strengthened monitoring area, and performing electromagnetic radiation strengthened monitoring on the strengthened monitoring area. The present application separates electromagnetic radiation influences caused by traffic flow propagation disturbances, thereby improving the accuracy and reliability of electromagnetic radiation anomaly detection in complex urban road environments.

Description

Technical Field

[0001] This invention relates to the field of electromagnetic radiation monitoring technology, and in particular to electromagnetic radiation monitoring methods and systems based on big data analysis. Background Technology

[0002] With the rapid development of wireless communication technology, urban Internet of Things and smart terminal devices, the number of electromagnetic radiation sources in urban spaces is constantly increasing. Electromagnetic radiation monitoring is of great significance for understanding changes in the urban electromagnetic environment, ensuring the stable operation of communication systems, and carrying out electromagnetic environment management.

[0003] In real urban environments, due to building obstruction and road space constraints, electromagnetic radiation monitoring nodes are typically deployed along roads, making the monitoring data susceptible to changes in the road traffic environment. Vehicles, as dynamic propagation media in urban roads, exhibit electromagnetic wave reflection, scattering, and obstruction due to their metal structures and varying vehicle density. This means that the electromagnetic radiation changes acquired by the monitoring nodes simultaneously include variations in radiation sources and the impact of traffic flow disturbances.

[0004] Existing electromagnetic radiation monitoring methods typically rely directly on changes in monitoring data to determine anomalies, failing to adequately consider the impact of traffic flow changes on electromagnetic propagation. This can easily lead to misjudging propagation changes caused by traffic flow as radiation source anomalies, resulting in insufficient accuracy in anomaly detection. Furthermore, existing methods lack mechanisms to verify and correct the impact of traffic flow by utilizing the electromagnetic radiation recovery process after the disturbance is resolved, making it difficult to accurately distinguish between radiation changes caused by changes in the propagation environment and anomalies caused by changes in the state of the radiation source. Summary of the Invention

[0005] To overcome the defects and shortcomings of existing technologies, this invention provides an electromagnetic radiation monitoring method and system based on big data analysis. By separating the electromagnetic radiation effects caused by traffic flow disturbances, it improves the accuracy and reliability of electromagnetic radiation anomaly detection in complex urban road environments.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides an electromagnetic radiation monitoring method based on big data analysis, comprising: Acquire multi-source monitoring big data corresponding to monitoring nodes deployed along roads within the urban monitoring area, including frequency-selective electromagnetic radiation time series data corresponding to each monitoring node, traffic flow status data corresponding to the road sections where each monitoring node is located, and radiation source operation status data within the urban monitoring area. Based on multi-source monitoring big data, historical radiation source steady-state windows are extracted, and the relationship between changes in traffic flow status within the historical radiation source steady-state windows and changes in electromagnetic radiation monitoring corresponding to different target frequency bands is analyzed. Traffic flow-frequency selective propagation response relationship corresponding to each target frequency band is established. Based on the traffic flow status data and traffic flow-frequency selective propagation response relationship within the current monitoring period, determine the traffic flow propagation interpretation quantity corresponding to each target frequency band, and determine the traffic flow interpretation residual corresponding to each target frequency band based on the difference between the traffic flow propagation interpretation quantity and the electromagnetic radiation monitoring changes of the corresponding target frequency band. Based on traffic flow status data, identify traffic flow disturbance removal nodes, analyze the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node, and correct the traffic flow interpretation residuals corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residuals. The degree of radiation anomaly corresponding to each monitoring node is determined based on the corrected traffic flow interpretation residuals, and the enhanced monitoring area is determined based on the spatial distribution of each monitoring node. Electromagnetic radiation enhanced monitoring is then carried out in the enhanced monitoring area.

[0007] Preferably, the step of analyzing the relationship between changes in traffic flow status within the steady-state window of historical radiation sources and changes in electromagnetic radiation monitoring corresponding to different target frequency bands, and establishing the traffic flow-frequency selective propagation response relationship for each target frequency band, includes: The radiation source operation status data, traffic flow status data and frequency-selective electromagnetic radiation time series data are time-aligned according to the same sampling period, and the time-aligned multi-source monitoring big data is divided into sliding windows according to the preset window length. Based on the radiation source operation status data, extract the radiation source's transmission power and service load within each sliding time window, calculate the degree of transmission power fluctuation and service load fluctuation respectively, and select the sliding time window where the degree of transmission power fluctuation and service load fluctuation are both less than the corresponding stable threshold and the radiation source operation mode has not changed, as the historical radiation source steady state window. Within the steady-state window of each historical radiation source, the changes in traffic flow, average vehicle speed, and road occupancy corresponding to adjacent sampling times are normalized to construct the traffic flow state change vector corresponding to the road section where each monitoring node is located, and the changes in frequency-selective electromagnetic radiation monitoring values ​​corresponding to each target frequency band within the same sampling interval are calculated respectively. The traffic flow state change vector is paired with the frequency-selective electromagnetic radiation monitoring value change of each target frequency band at the same sampling time to obtain the traffic flow propagation response sample corresponding to each target frequency band. Using the traffic flow state change vector in the traffic flow propagation response samples corresponding to each target frequency band as input and the change in frequency-selective electromagnetic radiation monitoring value as output, the propagation response coefficients corresponding to different traffic flow state parameters are determined by multiple regression fitting, and the traffic flow-frequency-selective propagation response relationship corresponding to each target frequency band is established.

[0008] Preferably, determining the traffic flow propagation interpretation quantity corresponding to each target frequency band based on traffic flow status data and traffic flow-frequency selection propagation response relationship within the current monitoring period includes: According to the sampling period corresponding to the establishment of the traffic flow-frequency selective propagation response relationship, the traffic flow status data of each monitoring node in the road section within the current monitoring period are sampled over time. Calculate the changes in traffic flow, average vehicle speed, and road occupancy at adjacent sampling times, and construct the current traffic flow state change vector for each sampling interval based on the changes in each traffic flow state parameter. According to the data normalization rules used when establishing the traffic flow-frequency-selective propagation response relationship, the changes in each traffic flow state parameter in the current traffic flow state change vector are normalized. For each target frequency band, the normalized current traffic flow state change vector is input into the traffic flow-frequency selective propagation response relationship of the corresponding target frequency band. The frequency selective propagation response generated by each traffic flow state parameter is determined according to the change amount of each traffic flow state parameter and its corresponding propagation response coefficient. The frequency selective propagation response quantities are summed to obtain the traffic flow propagation interpretation value of the target frequency band within the corresponding sampling interval. The traffic flow propagation interpretation values ​​corresponding to each sampling interval within the current monitoring period are arranged according to the sampling time sequence to obtain the traffic flow propagation interpretation quantity corresponding to each target frequency band.

[0009] Preferably, determining the traffic flow interpretation residuals for each target frequency band based on the difference between the traffic flow propagation interpretation and the electromagnetic radiation monitoring changes in the corresponding target frequency band includes: According to the sampling period corresponding to the traffic flow propagation interpretation, the frequency-selective electromagnetic radiation time series data of each monitoring node in the current monitoring period are time-aligned, and the change in the frequency-selective electromagnetic radiation monitoring value of each target frequency band in adjacent sampling times is calculated respectively. The traffic flow propagation interpretation values ​​corresponding to each target frequency band are extracted and the frequency-selective electromagnetic radiation monitoring value changes are obtained from the traffic flow propagation interpretation values ​​with the same monitoring node, the same target frequency band, and the same sampling interval. The difference between the change in the frequency-selective electromagnetic radiation monitoring value corresponding to each sampling interval and the corresponding traffic flow propagation interpretation value is taken as the traffic flow interpretation residual value for the corresponding sampling interval. The traffic flow interpretation residuals corresponding to each sampling interval within the current monitoring period are arranged according to the sampling time sequence to obtain the traffic flow interpretation residuals corresponding to each target frequency band.

[0010] Preferably, the step of identifying traffic flow disturbance removal nodes based on traffic flow status data and analyzing the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node includes: The traffic flow, average speed and road occupancy of each monitoring node are extracted from the traffic flow status data and normalized. The normalized traffic flow, the reverse normalized average speed and the road occupancy are then weighted and fused to obtain the traffic flow propagation disturbance intensity at each sampling time. Based on the changing trend of the disturbance intensity propagated by the traffic flow, the magnitude of the decrease in disturbance intensity and the degree of continuous decrease within the preset time window are calculated. The end time of the preset time window when the magnitude of the decrease in disturbance intensity is greater than the preset magnitude threshold and the degree of continuous decrease is greater than the preset continuous decrease threshold is taken as the traffic flow disturbance release node. Using the traffic disturbance removal node as the time boundary, the disturbance holding interval before the traffic disturbance removal node and the post-removal stabilization interval after the traffic disturbance removal node are determined respectively. Calculate the mean value of frequency-selective electromagnetic radiation monitoring for each target frequency band in the disturbance-maintaining interval and the stable interval after disturbance removal. Take the absolute value of the difference between the mean value of frequency-selective electromagnetic radiation monitoring in the stable interval after disturbance removal and the mean value of frequency-selective electromagnetic radiation monitoring in the disturbance-maintaining interval as the recovery amplitude of the corresponding target frequency band. Take the sign of the difference as the recovery direction of the corresponding target frequency band. Take the recovery amplitude and recovery direction as the frequency-selective electromagnetic radiation recovery response for each target frequency band.

[0011] Preferably, the step of correcting the traffic flow interpretation residuals corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residuals includes: For each traffic flow disturbance removal node, the traffic flow propagation interpretation value corresponding to each sampling interval in the disturbance holding interval and the stable interval after removal is extracted by the traffic flow propagation interpretation value corresponding to each target frequency band. The difference between the mean traffic flow propagation interpretation value corresponding to the stable interval after removal and the mean traffic flow propagation interpretation value corresponding to the disturbance holding interval is calculated. The absolute value of the difference is taken as the theoretical recovery amplitude of the corresponding target frequency band, and the sign of the difference is taken as the theoretical recovery direction of the corresponding target frequency band. When the recovery direction in the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band is consistent with the theoretical recovery direction, the corresponding frequency-selective electromagnetic radiation recovery response is taken as the effective recovery response; The ratio of the recovery amplitude corresponding to the effective recovery response to the theoretical recovery amplitude is used as the propagation correction coefficient for the corresponding target frequency band, and the product of the traffic flow propagation interpretation value corresponding to each sampling interval of the target frequency band in the current monitoring period and the propagation correction coefficient is used as the traffic flow propagation interpretation value after correction for the corresponding sampling interval. The difference between the corrected traffic flow propagation interpretation value and the original traffic flow propagation interpretation value for each sampling interval is taken as the propagation interpretation correction value for the corresponding sampling interval, and the difference between the traffic flow interpretation residual value and the propagation interpretation correction value for the corresponding sampling interval is taken as the corrected traffic flow interpretation residual value for the corresponding sampling interval. The traffic flow interpretation residuals corrected for each sampling interval within the current monitoring period are sorted according to the sampling time sequence to obtain the corrected traffic flow interpretation residuals corresponding to each target frequency band.

[0012] Preferably, the step of determining the radiation anomaly level corresponding to each monitoring node based on the corrected traffic flow interpretation residual, and determining the enhanced monitoring area in conjunction with the spatial distribution of each monitoring node, and performing enhanced electromagnetic radiation monitoring in the enhanced monitoring area includes: Based on the traffic flow interpretation residual values ​​of different target frequency bands at each monitoring node within the steady-state window of the historical radiation source at each sampling interval, the historical residual fluctuation range corresponding to each target frequency band is determined. The traffic flow interpretation residual value corresponding to each sampling interval in the corrected traffic flow interpretation residual for each target frequency band in the current monitoring period is compared with the corresponding historical residual fluctuation range. When the corrected traffic flow interpretation residual value exceeds the historical residual fluctuation range, the difference between the traffic flow interpretation residual value and the corresponding historical residual boundary is taken as the residual deviation amplitude, the ratio of the residual deviation amplitude to the width of the historical residual fluctuation range is taken as the residual deviation degree, and the ratio of the number of samples exceeding the historical residual fluctuation range to the total number of samples in the current monitoring period is taken as the residual persistence degree. By weighted summing of the deviation and persistence of the normalized residuals, the frequency band anomaly level corresponding to each target frequency band is obtained, and the average value of the frequency band anomaly level corresponding to all target frequency bands of the same monitoring node is taken as the radiation anomaly level of the corresponding monitoring node. Monitoring nodes with radiation anomalies exceeding a preset radiation anomaly threshold are selected as anomaly monitoring nodes. Enhanced monitoring areas are determined based on the location distribution of the anomaly monitoring nodes and their road relationships, and electromagnetic radiation is enhanced in these areas.

[0013] Secondly, the present invention provides an electromagnetic radiation monitoring system based on big data analysis, comprising: The data acquisition module is used to acquire multi-source monitoring big data corresponding to monitoring nodes deployed along roads within the urban monitoring area, including frequency-selective electromagnetic radiation time series data corresponding to each monitoring node, traffic flow status data corresponding to the road sections where each monitoring node is located, and radiation source operation status data within the urban monitoring area. The propagation response analysis module is used to extract historical radiation source steady-state windows based on multi-source monitoring big data, analyze the relationship between changes in traffic flow status within the historical radiation source steady-state windows and changes in electromagnetic radiation monitoring corresponding to different target frequency bands, and establish traffic flow-frequency selection propagation response relationships for each target frequency band. The traffic flow interpretation residual analysis module is used to determine the traffic flow propagation interpretation quantity corresponding to each target frequency band based on the traffic flow status data and traffic flow-frequency selection propagation response relationship within the current monitoring period, and to determine the traffic flow interpretation residual corresponding to each target frequency band based on the difference between the traffic flow propagation interpretation quantity and the electromagnetic radiation monitoring changes of the corresponding target frequency band. The residual correction module is used to identify traffic flow disturbance removal nodes based on traffic flow status data, analyze the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node, and correct the traffic flow interpretation residual corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residual. The enhanced monitoring module is used to determine the degree of radiation anomaly corresponding to each monitoring node based on the corrected traffic flow interpretation residual, and to determine the enhanced monitoring area in combination with the spatial distribution of each monitoring node, and to carry out enhanced electromagnetic radiation monitoring in the enhanced monitoring area.

[0014] Thirdly, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes an electromagnetic radiation monitoring method based on big data analysis by calling the computer program stored in the memory.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an electromagnetic radiation monitoring method based on big data analysis.

[0016] Compared with the prior art, the present invention has the following advantages and beneficial effects: This invention analyzes the correlation between traffic flow changes and electromagnetic radiation changes in different target frequency bands within a historical window of stable radiation source operation, establishes a traffic flow-frequency-selective propagation response relationship corresponding to the target frequency band, and determines the traffic flow propagation interpretation quantity based on the current traffic flow status, thereby separating the electromagnetic radiation impact caused by traffic flow propagation disturbances. The invention also uses the electromagnetic radiation recovery response after the traffic flow disturbance is resolved to correct the traffic flow interpretation residual, improving the accuracy and reliability of electromagnetic radiation anomaly detection in complex urban road environments. Furthermore, the invention determines the degree of radiation anomaly based on the corrected traffic flow interpretation residual and, combined with the spatial distribution of anomaly monitoring nodes, determines enhanced monitoring areas, enabling dynamic enhanced monitoring of key areas and improving the resource utilization efficiency of urban electromagnetic radiation monitoring. Attached Figure Description

[0017] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating the electromagnetic radiation monitoring method based on big data analysis provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the analysis process for the corrected traffic flow interpretation residuals provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the electromagnetic radiation monitoring system based on big data analysis provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0019] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of the electromagnetic radiation monitoring method based on big data analysis provided in this embodiment of the invention, which specifically includes the following steps: S100. Acquire multi-source monitoring big data corresponding to monitoring nodes deployed along roads within the urban monitoring area, including frequency-selective electromagnetic radiation time series data corresponding to each monitoring node, traffic flow status data corresponding to the road section where each monitoring node is located, and radiation source operation status data within the urban monitoring area. Specifically, fixed or mobile electromagnetic radiation monitoring nodes are deployed along roads within the urban monitoring area. Electromagnetic radiation monitoring equipment with frequency-selective measurement capabilities is configured to continuously collect field strength, power density, or spectral power data for multiple target frequency bands according to a preset sampling period. This data, combined with the monitoring node number, geographical location, and collection timestamp, forms frequency-selective electromagnetic radiation time-series data for each monitoring node. For traffic flow data in the road sections where each monitoring node is located, traffic parameters such as unit-time traffic volume, average vehicle speed, and road occupancy can be obtained through road video surveillance equipment, geomagnetic vehicle detectors, or urban traffic management platforms. These parameters are then associated with the corresponding monitoring nodes based on the road section number and timestamp. For radiation source operational status data within the urban monitoring area, information such as transmission power, service load, operating mode, and on / off status for each radiation source can be obtained through the radiation source equipment management platform and communication base station operation log interface. This data is then uniformly encoded and time-synchronized based on the radiation source number, target frequency band, and collection time, forming a multi-source monitoring big data set that includes frequency-selective electromagnetic radiation data, road traffic flow data, and radiation source operational status data.

[0020] S200. Based on multi-source monitoring big data, extract the steady-state window of historical radiation sources, analyze the relationship between changes in traffic flow status within the steady-state window of historical radiation sources and changes in electromagnetic radiation monitoring corresponding to different target frequency bands, and establish the traffic flow-frequency selective propagation response relationship corresponding to each target frequency band. By selecting historical time windows of stable radiation source operation from multi-source monitoring big data, and analyzing the correlation between changes in traffic flow status and changes in electromagnetic radiation monitoring at different target frequency bands under the condition that the radiation source's transmission power, service load, and operating mode remain basically unchanged, the interference of changes in the radiation source's own output on the modeling process can be reduced, enabling changes in electromagnetic radiation monitoring to more accurately reflect the impact of changes in the propagation environment caused by road traffic flow. Based on this, traffic flow-frequency selective propagation response relationships are established for different target frequency bands, realizing differentiated characterization of the degree of influence of vehicle blocking, reflection, and scattering on electromagnetic signals of different frequencies. This provides a data foundation for subsequent calculation of traffic flow propagation interpretation based on real-time traffic flow status and separation of traffic flow propagation disturbances from actual radiation anomalies. The relationship between changes in traffic flow status within the historical radiation source steady-state window and changes in electromagnetic radiation monitoring corresponding to different target frequency bands is analyzed, establishing traffic flow-frequency selective propagation response relationships for each target frequency band, including: The radiation source operation status data, traffic flow status data, and frequency-selective electromagnetic radiation time series data are time-aligned according to the same sampling period. Then, the time-aligned multi-source monitoring big data is divided into sliding windows according to a preset window length. Specifically, based on the collection timestamps of various monitoring data, a unified time reference transformation is performed on the radiation source operation status data, road traffic flow status data, and frequency-selective electromagnetic radiation time series data. For example, data from different sources are transformed to a unified time axis, and resampling is performed according to a preset sampling period. The preset sampling period can be set according to the frequency of road traffic state changes and the electromagnetic radiation response speed, for example, setting it to 1 minute, 5 minutes, or 10 minutes, so that adjacent sampling times can reflect changes in the electromagnetic propagation environment caused by changes in vehicle flow. When the sampling time points of different data sources are not completely consistent, the radiation source emission power, service load, traffic flow, average vehicle speed, road occupancy, and electromagnetic radiation monitoring values ​​corresponding to each target frequency band are mapped to the same sampling time according to the interpolation method between adjacent time points, forming a time-synchronized multi-source monitoring data sequence. The duration of flow disturbance and the duration of stable operation of radiation sources are set with a preset window length. The preset window length can be set to multiple consecutive sampling periods of the preset sampling period. For example, when the preset sampling period is 5 minutes, the preset window length can be set to 30 minutes, 60 minutes, or 120 minutes, so that each sliding time window can include the complete traffic flow change process and the corresponding electromagnetic radiation response change process. A fixed step size is set according to the data analysis accuracy and computing resource requirements. The fixed step size can be set to one sampling period, multiple sampling periods, or a certain proportion of the preset window length. For example, the fixed step size can be set to 5 minutes or 10 minutes, so that there is partial data overlap between adjacent sliding time windows, avoiding the loss of state information due to traffic flow change nodes being at the window boundary. The multi-source monitoring data after time synchronization is slid-windowed according to the above preset sampling period, preset window length, and fixed step size, so that each sliding time window includes radiation source state data, traffic flow state data, and electromagnetic radiation change data within the corresponding time range, providing a complete data analysis unit for subsequent screening of radiation source stable states. Based on the radiation source operation status data, the transmission power and service load of the radiation source within each sliding time window are extracted. The fluctuation degree of transmission power and service load are calculated respectively. Sliding time windows in which the fluctuation degree of transmission power and service load are both less than the corresponding stable threshold and the radiation source operation mode has not changed are selected as historical stable state windows of the radiation source. Specifically, for each sliding time window, the transmission power and service load of the radiation source within the sliding time window are extracted. For the fluctuation degree of transmission power, the difference between the maximum output power and the minimum output power within the sliding time window is calculated, and the ratio of the difference to the average transmission power within the sliding time window is taken as the fluctuation degree of transmission power. For the fluctuation degree of service load, the average service load corresponding to each sampling time within the sliding time window is calculated, and the difference between the service load at each sampling point and the average service load is calculated. The average of the absolute values ​​of the differences at each sampling point is taken as the fluctuation degree of service load. The stable thresholds corresponding to the fluctuation degree of transmission power and service load can be obtained by statistically analyzing the fluctuation degree of transmission power and service load of multiple sliding time windows under historical normal conditions, and the sum of the average value of the corresponding fluctuation degree and the standard deviation of the corresponding fluctuation degree is taken as the stable threshold. Within the steady-state window of each historical radiation source, the changes in traffic flow, average vehicle speed, and road occupancy at adjacent sampling times are normalized to construct a traffic flow state change vector for the road segment where each monitoring node is located. Furthermore, the changes in frequency-selective electromagnetic radiation monitoring values ​​for each target frequency band within the same sampling interval are calculated. Specifically, within each steady-state window of a historical radiation source, traffic flow state data, including traffic flow, average vehicle speed, and road occupancy, are acquired in chronological order between two adjacent sampling times. The changes between adjacent sampling times are calculated; for example, the change in traffic flow is obtained by subtracting the traffic flow from the previous sampling time from the current sampling time; the change in average vehicle speed is obtained by subtracting the average vehicle speed from the previous sampling time from the current sampling time; and the change in road occupancy is obtained by subtracting the road occupancy from the previous sampling time. The change in road occupancy is obtained. Since different traffic flow parameters have different dimensions, a normalization method is used for processing: for any change in traffic flow state parameter, the minimum value of the corresponding parameter change within the historical steady-state window is subtracted, and then divided by the difference between the maximum and minimum values ​​of the corresponding parameter change to obtain the normalized parameter change, so that different traffic flow parameters are all converted to a uniform numerical range. The normalized traffic flow change, average speed change, and road occupancy change are combined in a fixed order to form the traffic flow state change vector of the corresponding road segment. Within the same sampling interval, the frequency-selective electromagnetic radiation monitoring values ​​corresponding to each target frequency band are extracted respectively, and the change in radiation monitoring values ​​between adjacent sampling times is calculated, that is, the monitoring value at the current sampling time minus the monitoring value at the previous sampling time, as the change in electromagnetic radiation response of the corresponding target frequency band. The traffic flow state change vector is paired with the frequency-selective electromagnetic radiation monitoring value change of each target frequency band at the same sampling time to obtain the traffic flow propagation response sample corresponding to each target frequency band. Specifically, for each sampling interval within the steady-state window of each historical radiation source, the traffic flow state change vector corresponding to the same time period and the same monitoring node is matched with the electromagnetic radiation monitoring value change of each target frequency band. For example, within a certain sampling interval, the traffic flow state change vector corresponding to the road section is a three-dimensional vector containing changes in traffic volume, average vehicle speed, and road occupancy. It is then combined with the electromagnetic radiation change of each target frequency band to form traffic flow propagation response samples corresponding to different target frequency bands, so that each target frequency band has a data mapping relationship from traffic flow change input to electromagnetic radiation change output. Using the traffic flow state change vector from the traffic flow propagation response samples corresponding to each target frequency band as input and the frequency-selective electromagnetic radiation monitoring value change as output, the propagation response coefficients corresponding to different traffic flow state parameters are determined through multiple regression fitting, establishing the traffic flow-frequency-selective propagation response relationship for each target frequency band. Specifically, an independent multiple regression model is established for each target frequency band, using the traffic flow state change vector from the traffic flow propagation response samples corresponding to that target frequency band as model input and the corresponding frequency-selective electromagnetic radiation monitoring value change as model output. For example, the normalized traffic flow change, average vehicle speed change, and road occupancy change are used as input variables, and the electromagnetic radiation change of the corresponding target frequency band is used as output variable. The mapping relationship between input and output variables is established through multiple linear regression. In the specific fitting process, an input matrix and output vector are constructed based on multiple traffic flow propagation response samples. The least squares method is used to calculate the propagation response coefficients corresponding to each traffic flow state parameter (traffic flow change, average vehicle speed change, and road occupancy change), minimizing the sum of squared errors between the predicted electromagnetic radiation change and the actual monitored change, thereby obtaining different... The influence weights corresponding to traffic flow state parameters are determined. By evaluating the fitting accuracy of the regression model output, when the model prediction error meets the accuracy requirements, the propagation response coefficients of the corresponding target frequency band are saved, forming the traffic flow-frequency selective propagation response relationship for that target frequency band. The fitting accuracy evaluation process involves using the change in frequency selective electromagnetic radiation monitoring values ​​corresponding to each traffic flow propagation response sample within the historical radiation source steady-state window as the actual output value, and using the change in frequency selective electromagnetic radiation monitoring values ​​calculated through the multiple regression model as the predicted output value. The model is then used to determine the appropriate values ​​based on the actual output value and the predicted output value. The coefficient of determination is used to characterize the explanatory power of changes in traffic flow status on changes in electromagnetic radiation in the target frequency band. Specifically, it is calculated as the degree of fit between the predicted output value and the actual output value. When the coefficient of determination of the traffic flow-frequency selective propagation response relationship of the corresponding target frequency band is greater than or equal to the preset accuracy threshold, the propagation response relationship corresponding to the target frequency band is considered to meet the accuracy requirements. The preset accuracy threshold can be set to 0.85, that is, the regression model formed by changes in traffic flow status can explain at least 85% of the statistical variation in the change of the frequency selective electromagnetic radiation monitoring value of the corresponding target frequency band, and the established traffic flow-frequency selective propagation response relationship is considered to be effective.

[0021] S300. Based on the traffic flow status data and traffic flow-frequency selective propagation response relationship within the current monitoring period, determine the traffic flow propagation interpretation quantity corresponding to each target frequency band, and determine the traffic flow interpretation residual corresponding to each target frequency band based on the difference between the traffic flow propagation interpretation quantity and the electromagnetic radiation monitoring change of the corresponding target frequency band. By utilizing the traffic flow-frequency-selective propagation response relationship established under historical radiation source steady-state conditions, the impact of changes in road traffic flow status during the current monitoring period on electromagnetic propagation changes is quantified from actual electromagnetic radiation monitoring changes, thereby obtaining the traffic flow propagation interpretation quantities corresponding to different target frequency bands. Since urban electromagnetic radiation monitoring is typically deployed along roads, the monitoring results are easily affected by factors such as vehicle movement, road congestion, and changes in vehicle obstruction. By combining the current traffic flow status changes with the propagation response characteristics corresponding to different frequency bands, the contribution of traffic flow factors to electromagnetic radiation changes can be estimated in advance, providing a basis for subsequent calculation of traffic flow interpretation residuals. Based on the traffic flow status data and traffic flow-frequency-selective propagation response relationship during the current monitoring period, the traffic flow propagation interpretation quantities corresponding to each target frequency band are determined, including: According to the sampling period corresponding to the establishment of the traffic flow-frequency selective propagation response relationship, the traffic flow status data of each monitoring node in the road section within the current monitoring period are sampled over time. Specifically, when establishing the traffic flow-frequency selective propagation response relationship, the sampling period of the traffic flow status data within the steady-state window of the historical radiation source is recorded, and this sampling period is used as the data sampling benchmark for the current monitoring period. For example, if 30 seconds is used as the sampling period during the establishment of the historical model, the traffic flow status data corresponding to each monitoring node in the current monitoring period is also resampled at a time interval of 30 seconds. For traffic flow data from traffic camera equipment, geomagnetic vehicle detection equipment, road sensing equipment, or traffic management platforms, time alignment is performed according to the data timestamp, and linear interpolation is used to map the traffic flow, average vehicle speed, and road occupancy rate collected at different time points to a unified sampling time, so as to obtain the road traffic flow status data sequence corresponding to each sampling time within the current monitoring period, ensuring that the current traffic flow status change has a consistent time scale with the historical propagation response model. The changes in traffic flow, average vehicle speed, and road occupancy at adjacent sampling times are calculated separately. Based on the changes in each traffic flow state parameter, a current traffic flow state change vector is constructed for each sampling interval. Specifically, for any two adjacent sampling times within the current monitoring period, the changes in traffic flow state for the corresponding road segments are calculated. The change in traffic flow is determined by the difference between the number of vehicles at the later sampling time and the number of vehicles at the previous sampling time; the change in average vehicle speed is determined by the difference between the average vehicle speed at the later sampling time and the average vehicle speed at the previous sampling time; and the change in road occupancy is determined by the difference between the road occupancy ratio at the later sampling time and the road occupancy ratio at the previous sampling time. The changes in traffic flow, average vehicle speed, and road occupancy within the same sampling interval are combined in the order of their corresponding parameters to form a traffic flow state change vector for the current sampling interval, which describes the direction and magnitude of changes in road traffic state within that time period. Following the data normalization rules used when establishing the traffic flow-frequency selective propagation response relationship, the changes in each traffic flow state parameter in the current traffic flow state change vector are normalized. Specifically, to eliminate the influence of differences in the dimensions and numerical ranges of different traffic flow state parameters on the propagation response calculation results, the current traffic flow state change vector is processed using a normalization method consistent with that used in the historical traffic flow-frequency selective propagation response relationship establishment phase: for the changes in traffic volume, average vehicle speed, and road occupancy, the maximum and minimum values ​​of the corresponding parameter changes within the steady-state window of the historical radiation source are obtained respectively, and the maximum-minimum normalization method is used for normalization to obtain the normalized parameter changes, maintaining the consistency between the current data and the historical model training data. For each target frequency band, the normalized current traffic flow state change vector is input into the traffic flow-frequency selection propagation response relationship for the corresponding target frequency band. Based on the changes in each traffic flow state parameter and its corresponding propagation response coefficient, the frequency selection propagation response quantity generated by each traffic flow state parameter is determined. These frequency selection propagation responses are then summed to obtain the traffic flow propagation interpretation value for the target frequency band within the corresponding sampling interval. Specifically, for any target frequency band, the corresponding traffic flow-frequency selection propagation response relationship established in the historical period is invoked, which includes the propagation response coefficients corresponding to changes in traffic volume, average vehicle speed, and road occupancy. The normalized traffic flow state change vector corresponding to the current sampling interval is input into the traffic flow-frequency selection... In the propagation response relationship, the contribution of different traffic flow state parameters to the change in electromagnetic radiation of the target frequency band is calculated separately. For example, the normalized change in traffic flow is multiplied by the propagation response coefficient corresponding to the traffic flow to obtain the frequency band propagation response caused by the change in traffic flow; the normalized change in average vehicle speed is multiplied by the propagation response coefficient corresponding to the average vehicle speed to obtain the frequency band propagation response caused by the change in average vehicle speed; the normalized change in road occupancy is multiplied by the propagation response coefficient corresponding to the road occupancy to obtain the frequency band propagation response caused by the change in road occupancy; by accumulating the propagation response quantities corresponding to the above traffic flow factors, the traffic flow propagation interpretation value corresponding to the target frequency band within the sampling interval is obtained. The traffic flow propagation interpretation values ​​corresponding to each sampling interval within the current monitoring period are arranged according to the sampling time sequence to obtain the traffic flow propagation interpretation quantity corresponding to each target frequency band; This study analyzes the difference between the actual monitored electromagnetic radiation changes and the traffic flow propagation interpretations predicted based on traffic flow conditions, thereby separating the portion of electromagnetic radiation changes that cannot be explained by changes in road traffic, i.e., the traffic flow interpretation residuals. Since electromagnetic radiation monitoring data in urban road environments are easily affected by changes in vehicle numbers, road congestion levels, and vehicle movement blocking effects, directly judging radiation anomalies based on changes in electromagnetic radiation monitoring values ​​can easily misjudge normal traffic disturbances as radiation source anomalies. By calculating the difference between the actual electromagnetic radiation changes and the theoretical propagation changes caused by traffic flow, explainable changes caused by traffic flow factors are eliminated. By constructing traffic flow interpretation residuals corresponding to different target frequency bands, the study also preserves the differential response characteristics of electromagnetic signals at different frequencies to traffic flow disturbances, providing a more reliable data foundation for subsequent anomaly detection based on residual persistence, frequency band consistency, and spatial correlation. This improves the accuracy and anti-interference capability of electromagnetic radiation monitoring in complex urban road environments. Based on the difference between the traffic flow propagation interpretation and the electromagnetic radiation monitoring changes of the corresponding target frequency bands, the traffic flow interpretation residuals corresponding to each target frequency band are determined, including: According to the sampling period corresponding to the traffic flow propagation interpretation, the frequency-selective electromagnetic radiation time series data of each monitoring node in the current monitoring period are time-aligned, and the change in the frequency-selective electromagnetic radiation monitoring value of each target frequency band in adjacent sampling times is calculated respectively. The traffic flow propagation interpretation values ​​corresponding to each target frequency band are extracted and the frequency-selective electromagnetic radiation monitoring value changes are obtained from the traffic flow propagation interpretation values ​​with the same monitoring node, the same target frequency band, and the same sampling interval. The difference between the change in the frequency-selective electromagnetic radiation monitoring value corresponding to each sampling interval and the corresponding traffic flow propagation interpretation value is taken as the traffic flow interpretation residual value for the corresponding sampling interval. The traffic flow interpretation residuals corresponding to each sampling interval within the current monitoring period are arranged according to the sampling time sequence to obtain the traffic flow interpretation residuals corresponding to each target frequency band.

[0022] S400. Identify traffic flow disturbance removal nodes based on traffic flow status data, analyze the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node, and correct the traffic flow interpretation residuals corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residuals. By utilizing the disturbance dissipation characteristics during road traffic flow changes, key time points are identified where vehicle obstruction and dense vehicle propagation disturbances gradually dissipate. Further analysis is conducted on the response changes of electromagnetic radiation monitoring values ​​after the traffic flow disturbance dissipates as the propagation environment recovers. During urban road electromagnetic radiation monitoring, vehicles act as dynamic propagation obstructors, causing varying degrees of attenuation or enhancement of electromagnetic signals in different frequency bands. As vehicle density decreases and road traffic resumes, the electromagnetic propagation path gradually recovers, and the monitoring values ​​show a certain recovery trend. By identifying the traffic flow disturbance dissipation points and extracting the electromagnetic radiation change characteristics before and after dissipation, the recovery amplitude and direction corresponding to different target frequency bands can be obtained. This allows for the assessment of the impact of traffic flow obstruction changes on electromagnetic radiation changes, providing a dynamic correction basis for subsequent correction of traffic flow interpretation residuals. Based on traffic flow status data, the traffic flow disturbance dissipation points are identified, and the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the dissipation points is analyzed, including: Traffic flow, average speed, and road occupancy are extracted from traffic flow data for each monitoring node's road segment and normalized. The normalized traffic flow, inversely normalized average speed, and road occupancy are then weighted and fused to obtain the traffic flow propagation disturbance intensity at each sampling time. Specifically, traffic flow, average speed, and road occupancy are obtained from traffic sensing equipment, road video analysis systems, or traffic management platforms for each monitoring node's road segment within the current monitoring period. Traffic flow represents the number of vehicles passing through the monitored road segment per unit time, average speed represents vehicle movement, and road occupancy represents the degree to which vehicles occupy road space. Since these parameters have different dimensions, normalization is required. For traffic flow and road occupancy, a maximum-minimum normalization method is used to convert the corresponding parameters to a range of 0 to 1: the parameter value at the current sampling time is subtracted from the minimum value of the parameter within the historical statistical period, and then divided by the difference between the maximum and minimum values ​​of the parameter to obtain the normalized value. The traffic flow characteristic value and road occupancy characteristic value are obtained. For average vehicle speed, since lower vehicle speed usually indicates higher road congestion and stronger vehicle blocking effect, reverse normalization processing is required: the maximum and minimum average vehicle speed values ​​are determined based on historical road operation data, and the difference between the maximum average vehicle speed value and the average vehicle speed at the current sampling time is used as the reverse average vehicle speed difference value. The difference between the maximum and minimum average vehicle speed values ​​is calculated as the average vehicle speed reference value, and the ratio of the reverse average vehicle speed difference value to the average speed reference value is used as the reverse normalized average vehicle speed. When the vehicle speed decreases, the reverse normalized average vehicle speed increases, which can maintain the same disturbance direction as the increase in traffic flow and road occupancy. The normalized traffic flow characteristic value, the reverse normalized average vehicle speed characteristic value, and the road occupancy characteristic value are weighted and fused according to preset weights to obtain the traffic flow propagation disturbance intensity at the corresponding sampling time. Among them, each weight can be determined by correlation analysis based on the degree of influence of different traffic flow parameters on electromagnetic radiation changes within the steady-state window of historical radiation sources. Based on the changing trend of traffic flow disturbance intensity, the decrease amplitude and the degree of continuous decrease within a preset time window are calculated. The end time of the preset time window where the decrease amplitude exceeds a preset decrease amplitude threshold and the degree of continuous decrease exceeds a preset continuous decrease threshold is taken as the traffic flow disturbance release node. Specifically, to avoid misjudgment caused by abrupt changes in a single sampling point, a sliding analysis is performed on the traffic flow disturbance intensity sequence according to the preset time window. The preset time window can be set according to the speed of traffic state change and electromagnetic radiation response time, for example, set to the time range corresponding to 5 to 20 consecutive sampling periods; when the sampling period is 30 seconds, the preset time window can be set to 2.5 minutes to 10 minutes. For each sliding time window, the average disturbance intensity corresponding to the beginning position of the window and the average disturbance intensity corresponding to the end position of the window are calculated, and the difference between the two is calculated. The difference between the sampling points is taken as the magnitude of the decrease in disturbance intensity. Simultaneously, to determine whether the traffic disturbance is continuously subsiding, the number of samples where the disturbance intensity gradually decreases at adjacent sampling times within the window is counted, and the proportion of the decreasing sampling number to the total number of samples in the window is calculated. This proportion is taken as the degree of continuous decrease. When the magnitude of the decrease in disturbance intensity is greater than a preset decrease magnitude threshold, and the degree of continuous decrease is greater than a preset continuous decrease threshold, the road traffic disturbance is considered to be being resolved, and the end time of this sliding window is taken as the traffic disturbance resolution node. The decrease magnitude threshold can be determined based on the historical range of normal traffic changes. For example, the average decrease magnitude during historical road traffic recovery processes can be calculated and set to 1 to 1.5 times the average decrease magnitude. The continuous decrease threshold can be set to 0.6 to 0.8, meaning that when more than 60% to 80% of the sampling points within the window show a continuous decreasing trend, a stable subsidence process is considered to exist. Using the traffic disturbance removal node as the time boundary, the disturbance holding interval before the traffic disturbance removal node and the post-removal stabilization interval after the traffic disturbance removal node are determined respectively. Specifically, using the identified traffic disturbance removal node as the time boundary, the range of changes in traffic flow propagation disturbance intensity is searched forward and backward respectively. The disturbance holding interval is used to represent the time stage when vehicles are densely packed and the road propagation environment is continuously affected. Specifically, it can be determined by traversing historical sampling points backward from the traffic disturbance removal node. When the traffic flow propagation disturbance intensity corresponding to consecutive sampling points is greater than or equal to a preset disturbance holding threshold, the corresponding consecutive time period is determined as the disturbance holding interval. The disturbance holding threshold can be determined based on historical road conditions. The distribution of disturbance intensity under normal traffic flow conditions is determined, for example, by taking the sum of the mean disturbance intensity and the standard deviation of the disturbance intensity under historical low traffic flow conditions. The stable interval after the disturbance is resolved is used to represent the time period during which the road propagation environment returns to stability after the traffic flow disturbance is resolved. Specifically, it can be determined by traversing the sampling points backward from the traffic flow disturbance resolution node. When the traffic flow propagation disturbance intensity corresponding to consecutive sampling points is lower than the preset resolution threshold and the disturbance intensity fluctuation amplitude is less than the preset stability threshold, the corresponding time period is determined as the stable interval after the disturbance is resolved. The resolution threshold is used to determine whether the vehicle disturbance has been basically eliminated, and the stability threshold is used to avoid selecting time periods that are still in a process of drastic change. The number of consecutive sampling points can be set to 5 to 10 sampling points. Calculate the mean value of frequency-selective electromagnetic radiation monitoring for each target frequency band in the disturbance-maintaining interval and the stable interval after disturbance removal. Take the absolute value of the difference between the mean value of frequency-selective electromagnetic radiation monitoring in the stable interval after disturbance removal and the mean value of frequency-selective electromagnetic radiation monitoring in the disturbance-maintaining interval as the recovery amplitude of the corresponding target frequency band. Take the sign of the difference as the recovery direction of the corresponding target frequency band. Take the recovery amplitude and recovery direction as the frequency-selective electromagnetic radiation recovery response for each target frequency band. Because the impact of traffic flow changes on the electromagnetic radiation propagation environment has a certain lag and recovery process, the traffic flow propagation interpretation relationship established solely based on the current traffic flow status cannot fully reflect the response deviation that exists during the propagation path recovery process after the traffic flow disturbance subsides. This can lead to some electromagnetic radiation changes caused by changes in the propagation environment being misjudged as radiation source anomalies. By analyzing the frequency-selective electromagnetic radiation recovery response after the traffic flow disturbance is resolved, the actual electromagnetic propagation environment recovery process is compared with the theoretical traffic flow propagation impact process to determine the dynamic correction degree of the traffic flow propagation interpretation. The corrected propagation interpretation is then used to recalculate the traffic flow interpretation residual, thereby reducing the interference of road vehicle obstruction, scattering, and propagation path changes on anomaly detection results. Please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a schematic diagram of the analysis process for the corrected traffic flow interpretation residuals provided in an embodiment of the present invention, including: For each traffic flow disturbance removal node, the traffic flow propagation interpretation value corresponding to each sampling interval in the disturbance holding interval and the stable interval after removal is extracted by the traffic flow propagation interpretation value corresponding to each target frequency band. The difference between the mean traffic flow propagation interpretation value corresponding to the stable interval after removal and the mean traffic flow propagation interpretation value corresponding to the disturbance holding interval is calculated. The absolute value of the difference is taken as the theoretical recovery amplitude of the corresponding target frequency band, and the sign of the difference is taken as the theoretical recovery direction of the corresponding target frequency band. When the recovery direction in the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band is consistent with the theoretical recovery direction, the corresponding frequency-selective electromagnetic radiation recovery response is taken as an effective recovery response. Specifically, when the recovery direction in the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band is consistent with the theoretical recovery direction, it indicates that the trend of electromagnetic radiation change matches the recovery trend of traffic flow propagation influence, that is, the radiation change in this frequency band is mainly affected by changes in the traffic flow propagation environment, and the frequency-selective electromagnetic radiation recovery response is determined as an effective recovery response. When the directions are inconsistent, it indicates that the electromagnetic radiation change in this frequency band may be affected by changes in radiation source power, changes in traffic load, or other environmental factors, and is not used as a basis for traffic flow propagation correction. The ratio of the recovery amplitude corresponding to the effective recovery response to the theoretical recovery amplitude is used as the propagation correction coefficient for the corresponding target frequency band, and the product of the traffic flow propagation interpretation value corresponding to each sampling interval of the target frequency band in the current monitoring period and the propagation correction coefficient is used as the traffic flow propagation interpretation value after correction for the corresponding sampling interval. The difference between the corrected traffic flow propagation interpretation value and the original traffic flow propagation interpretation value for each sampling interval is taken as the propagation interpretation correction value for the corresponding sampling interval, and the difference between the traffic flow interpretation residual value and the propagation interpretation correction value for the corresponding sampling interval is taken as the corrected traffic flow interpretation residual value for the corresponding sampling interval. The traffic flow interpretation residuals corrected for each sampling interval within the current monitoring period are sorted according to the sampling time sequence to obtain the corrected traffic flow interpretation residuals corresponding to each target frequency band.

[0023] S500. Determine the radiation anomaly level corresponding to each monitoring node based on the corrected traffic flow interpretation residual, and determine the enhanced monitoring area based on the spatial distribution of each monitoring node, and conduct enhanced electromagnetic radiation monitoring in the enhanced monitoring area. Because electromagnetic radiation monitoring values ​​in urban road environments are affected by multiple factors, including the operating status of radiation sources, changes in propagation due to vehicle obstruction, and changes in the road environment, it is difficult to accurately determine abnormal radiation events based solely on the original monitoring values. By utilizing the corrected traffic flow interpretation residuals, the influence of known traffic flow propagation factors on electromagnetic radiation changes is eliminated, allowing the remaining residuals to more accurately reflect abnormal changes caused by non-traffic flow factors such as radiation source anomalies and sudden changes in the propagation environment. Furthermore, a dynamic anomaly evaluation benchmark is established based on the residual fluctuation range under historical stable conditions. The anomaly characteristics of each frequency band are quantified from two dimensions: the degree of residual deviation and the degree of anomaly persistence. Information from different frequency bands is then integrated to form the radiation anomaly degree at the monitoring node level. Based on this, combined with the spatial distribution of anomaly nodes and road relationships, key enhanced monitoring areas are determined, realizing the transformation from general monitoring of the entire area to precise enhanced monitoring of anomaly areas. This improves the efficiency of electromagnetic radiation anomaly detection, the utilization rate of monitoring resources, and the accuracy of anomaly location in complex urban environments. The radiation anomaly degree corresponding to each monitoring node is determined based on the corrected traffic flow interpretation residuals, and enhanced monitoring areas are determined based on the spatial distribution of each monitoring node. Enhanced electromagnetic radiation monitoring is then conducted in these enhanced monitoring areas, including: Based on the traffic flow interpretation residual values ​​of different target frequency bands at each sampling interval within the historical radiation source steady-state window, the historical residual fluctuation range corresponding to each target frequency band is determined. Specifically, the traffic flow interpretation residual value sequence corresponding to each monitoring node and each target frequency band is extracted through the historical radiation source steady-state window. Since the historical radiation source steady-state window represents a stable state of radiation source transmission power and service load, the residual changes in the historical radiation source steady-state window mainly reflect normal road propagation disturbances, monitoring noise, and random environmental fluctuations. For each monitoring node and target frequency band, the traffic flow interpretation residual values ​​corresponding to the same sampling interval within all historical steady-state windows are statistically analyzed to calculate the residual mean and residual standard deviation. The historical residual fluctuation range is determined based on the upper and lower fluctuation range of the residual mean. For example, the historical residual mean is used as the center value, and the center value plus or minus the historical residual standard deviation is used as the upper and lower boundaries to form the normal residual change range of the corresponding target frequency band, which is used to characterize the allowable residual fluctuation range of the monitoring node under normal operating conditions. The traffic flow interpretation residual values ​​for each sampling interval in the corrected traffic flow interpretation residuals for each target frequency band within the current monitoring period are compared with the corresponding historical residual fluctuation ranges. When the corrected traffic flow interpretation residual value exceeds the historical residual fluctuation range, the difference between the traffic flow interpretation residual value and the corresponding historical residual boundary is taken as the residual deviation amplitude. The ratio of the residual deviation amplitude to the width of the historical residual fluctuation range is taken as the residual deviation degree. The ratio of the number of samples exceeding the historical residual fluctuation range to the total number of samples in the current monitoring period is taken as the residual persistence degree. Specifically, For residual values ​​that exceed the range, calculate the absolute difference between the current residual value and the corresponding anomaly boundary as the residual deviation amplitude, which is used to represent the current anomaly level. Divide the residual deviation amplitude by the width of the historical residual fluctuation range, i.e., the difference between the upper and lower boundaries of the historical residual, to obtain the residual deviation level, thus achieving a normalized comparison of anomaly amplitudes between different monitoring nodes and different frequency bands. Count the number of sampling points that exceed the historical residual fluctuation range in the current monitoring period, and divide it by the total number of sampling points in the current monitoring period to obtain the residual persistence level, which is used to represent the proportion of the duration of the abnormal state. By weighted summing of the deviation and persistence of the normalized residuals, the frequency band anomaly level corresponding to each target frequency band is obtained, and the average value of the frequency band anomaly level corresponding to all target frequency bands of the same monitoring node is taken as the radiation anomaly level of the corresponding monitoring node. Monitoring nodes with radiation anomalies exceeding a preset threshold are selected as anomalous monitoring nodes. Enhanced monitoring areas are determined based on the location distribution and road relationships of these anomalous monitoring nodes, and electromagnetic radiation is enhanced in these areas. Specifically, the radiation anomaly level of each monitoring node is compared with the preset threshold. When the radiation anomaly level of a monitoring node exceeds the preset threshold, that node is identified as an anomalous monitoring node. The spatial coordinates, road locations, and road topology of the anomalous monitoring nodes are obtained. Cluster analysis is performed based on the spatial distance and road connectivity between the anomalous monitoring nodes: the spatial distance and road connectivity between any two anomalous monitoring nodes can be calculated. When the spatial distance between two nodes is less than the average node distance of all monitoring nodes and a road connection exists, the two anomalous monitoring nodes are assigned to the same anomalous region, resulting in different candidate enhanced monitoring regions. These candidate regions are then ranked according to the average radiation anomaly level within their respective regions, and the top 10% of regions with the highest anomaly risk are selected as enhanced monitoring regions. Enhanced electromagnetic radiation monitoring in these enhanced monitoring regions may include increasing the electromagnetic radiation sampling frequency of the monitoring nodes corresponding to the enhanced monitoring region or increasing the number of scans in the target frequency band to obtain more granular frequency-selective electromagnetic radiation change information.

[0024] In this embodiment of the invention, the determination of parameters such as weighting weights and preset thresholds can also be achieved by: constructing a dataset by acquiring multi-source monitoring big data, substituting it into the dataset to calculate the degree of transmission power fluctuation, the degree of service load fluctuation, the intensity of traffic flow propagation disturbance, the degree of frequency band anomaly, the magnitude of the decrease in disturbance intensity, and the degree of radiation anomaly; simultaneously acquiring the expert judgment results on the degree of transmission power fluctuation, the degree of service load fluctuation, the degree of traffic flow propagation disturbance, the degree of frequency band anomaly, the magnitude of the decrease in disturbance intensity, and the degree of radiation anomaly; importing the calculated degree of transmission power fluctuation, the degree of service load fluctuation, the intensity of traffic flow propagation disturbance, the degree of frequency band anomaly, the magnitude of the decrease in disturbance intensity, the degree of radiation anomaly, and the judgment results into fitting software, and outputting the weighting weights and preset thresholds that meet the maximum judgment accuracy.

[0025] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an electromagnetic radiation monitoring system based on big data analysis provided in an embodiment of the present invention, including: The data acquisition module 210 is used to acquire multi-source monitoring big data corresponding to the monitoring nodes deployed along the roads within the urban monitoring area, including frequency-selective electromagnetic radiation time series data corresponding to each monitoring node, traffic flow status data corresponding to the road sections where each monitoring node is located, and radiation source operation status data within the urban monitoring area. The propagation response analysis module 220 is used to extract the steady-state window of historical radiation sources based on multi-source monitoring big data, analyze the relationship between changes in traffic flow status within the steady-state window of historical radiation sources and changes in electromagnetic radiation monitoring corresponding to different target frequency bands, and establish the traffic flow-frequency selection propagation response relationship corresponding to each target frequency band. The traffic flow interpretation residual analysis module 230 is used to determine the traffic flow propagation interpretation quantity corresponding to each target frequency band based on the traffic flow status data and traffic flow-frequency selection propagation response relationship within the current monitoring period, and to determine the traffic flow interpretation residual corresponding to each target frequency band based on the difference between the traffic flow propagation interpretation quantity and the electromagnetic radiation monitoring changes of the corresponding target frequency band. The residual correction module 240 is used to identify the traffic flow disturbance removal node based on the traffic flow status data, analyze the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node, and correct the traffic flow interpretation residual corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residual. The enhanced monitoring module 250 is used to determine the degree of radiation anomaly corresponding to each monitoring node based on the corrected traffic flow interpretation residual, and to determine the enhanced monitoring area in combination with the spatial distribution of each monitoring node, and to carry out enhanced electromagnetic radiation monitoring in the enhanced monitoring area.

[0026] The steps for implementing the corresponding functions of each parameter and each unit module in the electromagnetic radiation monitoring system based on big data analysis of the present invention can be referred to the parameters and steps in the embodiments of the electromagnetic radiation monitoring method based on big data analysis described above, and will not be repeated here.

[0027] Please refer to Figure 4 The present invention also provides an electronic device 300, including a memory 310, a processor 320, and a communication bus 330; the memory 310 and the processor 320 are connected via the communication bus 330. The memory 310 stores an electromagnetic radiation monitoring method based on big data analysis, which can be loaded by the processor 320 and executed as provided in the above embodiments.

[0028] The memory 310 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 310 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the electromagnetic radiation monitoring method based on big data analysis provided in the above embodiments, etc. The data storage area may store data involved in the electromagnetic radiation monitoring method based on big data analysis provided in the above embodiments, etc.

[0029] Processor 320 may include one or more processing cores. Processor 320 executes instructions, programs, code sets, or instruction sets stored in memory 310, and calls data stored in memory 310 to perform various functions and process data according to the present invention. Processor 320 may be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of processor 320 may also be other types, and the embodiments of the present invention do not specifically limit this.

[0030] The communication bus 330 may include a path for transmitting information between the aforementioned components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 330 may be divided into an address bus, a data bus, a control bus, etc.

[0031] This invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments, which is an electromagnetic radiation monitoring method based on big data analysis.

[0032] In this embodiment of the invention, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, a computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0033] 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.

[0034] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to the technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this invention.

Claims

1. A method for monitoring electromagnetic radiation based on big data analysis, characterized in that, include: Acquire multi-source monitoring big data corresponding to monitoring nodes deployed along roads within the urban monitoring area, including frequency-selective electromagnetic radiation time series data corresponding to each monitoring node, traffic flow status data corresponding to the road sections where each monitoring node is located, and radiation source operation status data within the urban monitoring area. Based on multi-source monitoring big data, historical radiation source steady-state windows are extracted, and the relationship between changes in traffic flow status within the historical radiation source steady-state windows and changes in electromagnetic radiation monitoring corresponding to different target frequency bands is analyzed. Traffic flow-frequency selective propagation response relationship corresponding to each target frequency band is established. Based on the traffic flow status data and traffic flow-frequency selective propagation response relationship within the current monitoring period, determine the traffic flow propagation interpretation quantity corresponding to each target frequency band, and determine the traffic flow interpretation residual corresponding to each target frequency band based on the difference between the traffic flow propagation interpretation quantity and the electromagnetic radiation monitoring changes of the corresponding target frequency band. Based on traffic flow status data, identify traffic flow disturbance removal nodes, analyze the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node, and correct the traffic flow interpretation residuals corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residuals. The step of correcting the traffic flow interpretation residuals corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residuals includes: For each traffic flow disturbance removal node, the traffic flow propagation interpretation value corresponding to each sampling interval in the disturbance holding interval and the stable interval after removal is extracted by the traffic flow propagation interpretation value corresponding to each target frequency band. The difference between the mean traffic flow propagation interpretation value corresponding to the stable interval after removal and the mean traffic flow propagation interpretation value corresponding to the disturbance holding interval is calculated. The absolute value of the difference is taken as the theoretical recovery amplitude of the corresponding target frequency band, and the sign of the difference is taken as the theoretical recovery direction of the corresponding target frequency band. When the recovery direction in the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band is consistent with the theoretical recovery direction, the corresponding frequency-selective electromagnetic radiation recovery response is taken as the effective recovery response; The ratio of the recovery amplitude corresponding to the effective recovery response to the theoretical recovery amplitude is used as the propagation correction coefficient for the corresponding target frequency band, and the product of the traffic flow propagation interpretation value corresponding to each sampling interval of the target frequency band in the current monitoring period and the propagation correction coefficient is used as the traffic flow propagation interpretation value after correction for the corresponding sampling interval. The difference between the corrected traffic flow propagation interpretation value and the original traffic flow propagation interpretation value for each sampling interval is taken as the propagation interpretation correction value for the corresponding sampling interval, and the difference between the traffic flow interpretation residual value and the propagation interpretation correction value for the corresponding sampling interval is taken as the corrected traffic flow interpretation residual value for the corresponding sampling interval. The traffic flow interpretation residuals corrected for each sampling interval within the current monitoring period are sorted according to the sampling time sequence to obtain the corrected traffic flow interpretation residuals corresponding to each target frequency band. The degree of radiation anomaly corresponding to each monitoring node is determined based on the corrected traffic flow interpretation residuals, and the enhanced monitoring area is determined based on the spatial distribution of each monitoring node. Electromagnetic radiation enhanced monitoring is then carried out in the enhanced monitoring area.

2. The electromagnetic radiation monitoring method based on big data analysis according to claim 1, characterized in that, The analysis establishes the relationship between changes in traffic flow status within the steady-state window of historical radiation sources and changes in electromagnetic radiation monitoring corresponding to different target frequency bands, and establishes the traffic flow-frequency selective propagation response relationship for each target frequency band, including: The radiation source operation status data, traffic flow status data and frequency-selective electromagnetic radiation time series data are time-aligned according to the same sampling period, and the time-aligned multi-source monitoring big data is divided into sliding windows according to the preset window length. Based on the radiation source operation status data, extract the radiation source's transmission power and service load within each sliding time window, calculate the degree of transmission power fluctuation and service load fluctuation respectively, and select the sliding time window where the degree of transmission power fluctuation and service load fluctuation are both less than the corresponding stable threshold and the radiation source operation mode has not changed, as the historical radiation source steady state window. Within the steady-state window of each historical radiation source, the changes in traffic flow, average vehicle speed, and road occupancy corresponding to adjacent sampling times are normalized to construct the traffic flow state change vector corresponding to the road section where each monitoring node is located, and the changes in frequency-selective electromagnetic radiation monitoring values ​​corresponding to each target frequency band within the same sampling interval are calculated respectively. The traffic flow state change vector is paired with the frequency-selective electromagnetic radiation monitoring value change of each target frequency band at the same sampling time to obtain the traffic flow propagation response sample corresponding to each target frequency band. Using the traffic flow state change vector in the traffic flow propagation response samples corresponding to each target frequency band as input and the change in frequency-selective electromagnetic radiation monitoring value as output, the propagation response coefficients corresponding to different traffic flow state parameters are determined by multiple regression fitting, and the traffic flow-frequency-selective propagation response relationship corresponding to each target frequency band is established.

3. The electromagnetic radiation monitoring method based on big data analysis according to claim 1, characterized in that, The step of determining the traffic flow propagation interpretation for each target frequency band based on traffic flow status data and traffic flow-frequency selection propagation response relationship within the current monitoring period includes: According to the sampling period corresponding to the establishment of the traffic flow-frequency selective propagation response relationship, the traffic flow status data of each monitoring node in the road section within the current monitoring period are sampled over time. Calculate the changes in traffic flow, average vehicle speed, and road occupancy at adjacent sampling times, and construct the current traffic flow state change vector for each sampling interval based on the changes in each traffic flow state parameter. According to the data normalization rules used when establishing the traffic flow-frequency-selective propagation response relationship, the changes in each traffic flow state parameter in the current traffic flow state change vector are normalized. For each target frequency band, the normalized current traffic flow state change vector is input into the traffic flow-frequency selective propagation response relationship of the corresponding target frequency band. The frequency selective propagation response generated by each traffic flow state parameter is determined according to the change amount of each traffic flow state parameter and its corresponding propagation response coefficient. The frequency selective propagation response quantities are summed to obtain the traffic flow propagation interpretation value of the target frequency band within the corresponding sampling interval. The traffic flow propagation interpretation values ​​corresponding to each sampling interval within the current monitoring period are arranged according to the sampling time sequence to obtain the traffic flow propagation interpretation quantity corresponding to each target frequency band.

4. The electromagnetic radiation monitoring method based on big data analysis according to claim 1, characterized in that, The determination of the traffic flow interpretation residuals for each target frequency band based on the difference between the traffic flow propagation interpretation and the electromagnetic radiation monitoring changes for the corresponding target frequency band includes: According to the sampling period corresponding to the traffic flow propagation interpretation, the frequency-selective electromagnetic radiation time series data of each monitoring node in the current monitoring period are time-aligned, and the change in the frequency-selective electromagnetic radiation monitoring value of each target frequency band in adjacent sampling times is calculated respectively. The traffic flow propagation interpretation values ​​corresponding to each target frequency band are extracted and the frequency-selective electromagnetic radiation monitoring value changes are obtained from the traffic flow propagation interpretation values ​​with the same monitoring node, the same target frequency band, and the same sampling interval. The difference between the change in the frequency-selective electromagnetic radiation monitoring value corresponding to each sampling interval and the corresponding traffic flow propagation interpretation value is taken as the traffic flow interpretation residual value for the corresponding sampling interval. The traffic flow interpretation residuals corresponding to each sampling interval within the current monitoring period are arranged according to the sampling time sequence to obtain the traffic flow interpretation residuals corresponding to each target frequency band.

5. The electromagnetic radiation monitoring method based on big data analysis according to claim 1, characterized in that, The step of identifying traffic flow disturbance removal nodes based on traffic flow status data and analyzing the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node includes: The traffic flow, average speed and road occupancy of each monitoring node are extracted from the traffic flow status data and normalized. The normalized traffic flow, the reverse normalized average speed and the road occupancy are then weighted and fused to obtain the traffic flow propagation disturbance intensity at each sampling time. Based on the changing trend of the disturbance intensity propagated by the traffic flow, the magnitude of the decrease in disturbance intensity and the degree of continuous decrease within the preset time window are calculated. The end time of the preset time window when the magnitude of the decrease in disturbance intensity is greater than the preset magnitude threshold and the degree of continuous decrease is greater than the preset continuous decrease threshold is taken as the traffic flow disturbance release node. Using the traffic disturbance removal node as the time boundary, the disturbance holding interval before the traffic disturbance removal node and the post-removal stabilization interval after the traffic disturbance removal node are determined respectively. Calculate the mean value of frequency-selective electromagnetic radiation monitoring for each target frequency band in the disturbance-maintaining interval and the stable interval after disturbance removal. Take the absolute value of the difference between the mean value of frequency-selective electromagnetic radiation monitoring in the stable interval after disturbance removal and the mean value of frequency-selective electromagnetic radiation monitoring in the disturbance-maintaining interval as the recovery amplitude of the corresponding target frequency band. Take the sign of the difference as the recovery direction of the corresponding target frequency band. Take the recovery amplitude and recovery direction as the frequency-selective electromagnetic radiation recovery response for each target frequency band.

6. The electromagnetic radiation monitoring method based on big data analysis according to claim 5, characterized in that, The process of determining the radiation anomaly level corresponding to each monitoring node based on the corrected traffic flow interpretation residual, and determining the enhanced monitoring area based on the spatial distribution of each monitoring node, and then conducting enhanced electromagnetic radiation monitoring in the enhanced monitoring area includes: Based on the traffic flow interpretation residual values ​​of different target frequency bands at each monitoring node within the steady-state window of the historical radiation source at each sampling interval, the historical residual fluctuation range corresponding to each target frequency band is determined. The traffic flow interpretation residual value corresponding to each sampling interval in the corrected traffic flow interpretation residual for each target frequency band in the current monitoring period is compared with the corresponding historical residual fluctuation range. When the corrected traffic flow interpretation residual value exceeds the historical residual fluctuation range, the difference between the traffic flow interpretation residual value and the corresponding historical residual boundary is taken as the residual deviation amplitude, the ratio of the residual deviation amplitude to the width of the historical residual fluctuation range is taken as the residual deviation degree, and the ratio of the number of samples exceeding the historical residual fluctuation range to the total number of samples in the current monitoring period is taken as the residual persistence degree. By weighted summing of the deviation and persistence of the normalized residuals, the frequency band anomaly level corresponding to each target frequency band is obtained, and the average value of the frequency band anomaly level corresponding to all target frequency bands of the same monitoring node is taken as the radiation anomaly level of the corresponding monitoring node. Monitoring nodes with radiation anomalies exceeding a preset radiation anomaly threshold are selected as anomaly monitoring nodes. Enhanced monitoring areas are determined based on the location distribution of the anomaly monitoring nodes and their road relationships, and electromagnetic radiation is enhanced in these areas.

7. An electromagnetic radiation monitoring system based on big data analysis, used to implement the electromagnetic radiation monitoring method based on big data analysis as described in any one of claims 1-6, characterized in that, The system includes: The data acquisition module is used to acquire multi-source monitoring big data corresponding to monitoring nodes deployed along roads within the urban monitoring area, including frequency-selective electromagnetic radiation time series data corresponding to each monitoring node, traffic flow status data corresponding to the road sections where each monitoring node is located, and radiation source operation status data within the urban monitoring area. The propagation response analysis module is used to extract historical radiation source steady-state windows based on multi-source monitoring big data, analyze the relationship between changes in traffic flow status within the historical radiation source steady-state windows and changes in electromagnetic radiation monitoring corresponding to different target frequency bands, and establish traffic flow-frequency selection propagation response relationships for each target frequency band. The traffic flow interpretation residual analysis module is used to determine the traffic flow propagation interpretation quantity corresponding to each target frequency band based on the traffic flow status data and traffic flow-frequency selection propagation response relationship within the current monitoring period, and to determine the traffic flow interpretation residual corresponding to each target frequency band based on the difference between the traffic flow propagation interpretation quantity and the electromagnetic radiation monitoring changes of the corresponding target frequency band. The residual correction module is used to identify traffic flow disturbance removal nodes based on traffic flow status data, analyze the frequency-selective electromagnetic radiation recovery response corresponding to each target frequency band after the traffic flow disturbance removal node, and correct the traffic flow interpretation residual corresponding to each target frequency band based on the electromagnetic radiation recovery response to obtain the corrected traffic flow interpretation residual. The enhanced monitoring module is used to determine the degree of radiation anomaly corresponding to each monitoring node based on the corrected traffic flow interpretation residual, and to determine the enhanced monitoring area in combination with the spatial distribution of each monitoring node, and to carry out enhanced electromagnetic radiation monitoring in the enhanced monitoring area.

8. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the electromagnetic radiation monitoring method based on big data analysis as described in any one of claims 1-6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that, The device stores instructions that, when executed on a computer, cause the computer to perform the electromagnetic radiation monitoring method based on big data analysis as described in any one of claims 1-6.

Images