Data processing method and system for low-altitude safety situation analysis based on 5G base station towers

Abstract

The application provides a data processing method and system for low-altitude safety situation analysis based on a 5G base station tower, relates to the technical field of low-altitude safety management and control, and first acquires original signal feature sequences in a continuous monitoring period of distributed 5G base station towers, constructs a dynamic baseline model based on a historical signal feature library, generates an abnormal signal feature set, calls a multi-base-station cooperative identification model to perform cross-base-station correlation analysis, extracts a target signal correlation mode, deduces low-altitude target real-time trajectory parameters by using a triangular positioning algorithm, matches the real-time trajectory parameters with a preset safety management and control area, generates a low-altitude safety situation evaluation report and pushes the low-altitude safety situation evaluation report to a regional safety command platform, so that real-time and accurate evaluation and early warning of low-altitude safety can be realized.

Description

Technical Field

[0001] The present invention relates to the field of low-altitude safety management and control technology, and in particular to a data processing method and system for low-altitude safety situation analysis based on 5G base station towers. Background Art

[0002] In the field of low-altitude safety control, the increasing frequency of low-altitude flight activities, such as illegal drone flights and low-altitude illegal intrusions, poses a serious threat to low-altitude safety. Traditional low-altitude safety monitoring methods rely primarily on radar systems and optical monitoring equipment. While radar systems can detect aerial targets, they are costly, complex to deploy, and susceptible to terrain and weather conditions. Their effectiveness is significantly affected in complex terrain or urban environments. Optical monitoring equipment is significantly affected by lighting conditions and visibility, making it difficult to accurately identify low-altitude targets at night or in inclement weather.

[0003] Furthermore, existing low-altitude safety monitoring methods mostly rely on a single monitoring device, lacking coordination and information fusion between multiple devices. The limited information captured by a single device makes it difficult to fully and accurately grasp the dynamic characteristics and trajectory information of low-altitude targets, making it impossible to conduct a comprehensive and accurate assessment of the low-altitude safety situation. Furthermore, the intrusion risk assessment of low-altitude targets often lacks a scientific and rational basis, which can easily lead to misjudgments or missed detections, and cannot meet the growing demand for low-altitude safety management and control. Summary of the Invention

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a data processing method for low-altitude safety situation analysis based on 5G base station towers, the method comprising:

[0005] Obtaining original signal feature sequences collected from distributed 5G base station towers during a continuous monitoring period, wherein the original signal feature sequences include signal strength fluctuation parameters and signal arrival direction parameters of each base station;

[0006] A dynamic baseline model is constructed based on the historical signal feature library of each 5G base station tower, and baseline comparison processing is performed on the original signal feature sequence to generate an abnormal signal feature set including a signal deviation parameter;

[0007] Calling a pre-trained multi-base station collaborative recognition model to perform cross-base station correlation analysis on the abnormal signal feature set and base station spatial relationship data, and extracting a target signal correlation pattern with spatiotemporal consistency, wherein the target signal correlation pattern includes the signal transmission delay difference and signal strength attenuation gradient between base stations;

[0008] According to the target signal association pattern and the base station geographic location distribution parameters, a triangulation positioning algorithm is used to deduce the real-time trajectory parameters of the low-altitude target, wherein the real-time trajectory parameters include a position coordinate sequence and a moving speed vector;

[0009] The real-time trajectory parameters are spatially matched with the preset security control area data to generate a low-altitude security situation assessment report including the target intrusion risk level, and the low-altitude security situation assessment report is pushed to the regional security command platform.

[0010] On the other hand, an embodiment of the present invention also provides a data processing system for low-altitude safety situation analysis based on 5G base station towers, including a processor and a machine-readable storage medium, the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0011] Based on the above aspects, the embodiment of the present invention fully utilizes the characteristics of the widespread distribution of 5G base station towers by acquiring the original signal feature sequences collected by distributed 5G base station towers during the continuous monitoring period, thereby realizing large-scale and continuous monitoring of low-altitude areas. A dynamic baseline model is constructed based on the historical signal feature library, and baseline comparison processing is performed on the original signal feature sequence. It can accurately generate an abnormal signal feature set containing signal deviation parameters, and effectively identify low-altitude target signals that may be abnormal. The pre-trained multi-base station collaborative recognition model is called to perform cross-base station correlation analysis on the abnormal signal feature set and base station spatial relationship data, and extract target signal correlation patterns with spatiotemporal consistency, further improving the accuracy and reliability of low-altitude target signal recognition. According to the target signal association pattern and the geographical location distribution parameters of the base station, the triangulation positioning algorithm is used to deduce the real-time trajectory parameters of the low-altitude target, which can accurately obtain the position coordinate sequence and movement speed vector of the low-altitude target. Finally, the real-time trajectory parameters are spatially matched with the preset security control area data to generate a low-altitude security situation assessment report including the target intrusion risk level, and the low-altitude security situation assessment report is pushed to the regional security command platform, realizing real-time and accurate assessment and timely warning of the low-altitude security situation, effectively improving the efficiency and level of low-altitude safety control. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a schematic diagram of the execution flow of the data processing method for low-altitude safety situation analysis based on 5G base station towers provided in an embodiment of the present invention.

[0013] Figure 2 It is a schematic diagram of exemplary hardware and software components of a data processing system for low-altitude safety situation analysis based on 5G base station towers provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1 This is a flow chart of a data processing method for low-altitude safety situation analysis based on 5G base station towers provided by an embodiment of the present invention. The data processing method for low-altitude safety situation analysis based on 5G base station towers is introduced in detail below.

[0015] Step S110: Obtain the original signal feature sequence collected by the distributed 5G base station towers during the continuous monitoring period, where the original signal feature sequence includes the signal strength fluctuation parameters and signal arrival direction parameters of each base station.

[0016] In this embodiment, an area containing multiple distributed 5G base station towers can be selected as the monitoring range. These 5G base station towers continuously collect signals from the low-altitude area according to a preset monitoring frequency. Each 5G base station tower is equipped with a signal receiving device and a direction detection module, which can capture signal changes that may be generated by low-altitude targets in real time. A continuous monitoring cycle refers to a series of continuous time segments from the start of signal collection to the completion of a complete situation analysis. Each monitoring cycle has a fixed duration, and there is no time interval between adjacent cycles.

[0017] During the data collection process, each 5G base station tower records the signal strength fluctuation parameter it receives during each monitoring cycle. This parameter reflects the changes in signal strength during the monitoring period and includes signal strength values ​​at different points in time. The signal arrival direction parameter is also recorded, reflecting the different angles of the signal's arrival direction.

[0018] For example, during the first monitoring cycle of a 5G base station tower, the signal strength fluctuation parameter collected might contain multiple values, corresponding to the signal strength at different milliseconds within that cycle. The signal arrival direction parameter also contains multiple values, corresponding to the direction and angle of the signal at different times. These parameters are transmitted to the data processing center in real time, forming a raw signal feature sequence. Each parameter is associated with the corresponding base station identifier and the monitoring cycle timestamp, allowing subsequent processing to accurately distinguish signal data from different base stations at different times.

[0019] Step S120: construct a dynamic baseline model based on the historical signal feature library of each 5G base station tower, perform baseline comparison processing on the original signal feature sequence, and generate an abnormal signal feature set including a signal deviation parameter.

[0020] After obtaining the original signal feature sequence, a dynamic baseline model was constructed based on the historical signal feature library of each 5G base station tower. This library contains a large amount of signal data collected from each 5G base station tower over a long period of time. All data is collected in a normal communication environment and is not interfered with by low-altitude abnormal targets.

[0021] The purpose of building a dynamic baseline model is to establish a baseline of normal signal characteristics for comparison with the currently collected original signal feature sequence to detect abnormal signals. Data from the historical signal feature library is sorted and analyzed to extract key information that reflects normal signal characteristics, thereby constructing a dynamic baseline model. Subsequently, each parameter in the original signal feature sequence is compared with the baseline parameters in the dynamic baseline model, and the signal deviation parameter is calculated. When the deviation exceeds a set threshold, the corresponding signal feature is classified as an abnormal signal feature set.

[0022] Step S121: extracting a historical signal feature sequence within a preset time period in the past from a historical signal feature library of each 5G base station tower, wherein the historical signal feature sequence includes a signal strength fluctuation parameter and a signal arrival direction parameter under a normal communication environment.

[0023] When extracting historical signal feature sequences from the historical signal feature database of each 5G base station tower, it is first necessary to determine a preset time period. This preset time period can be set based on actual monitoring needs and the accumulation of historical data. For example, the past six months can be selected as the preset time period.

[0024] During the extraction process, it is necessary to filter out signal data that belongs to normal communication environments and exclude signal records that have been confirmed to be affected by abnormal interference or failures. The extracted historical signal feature sequence also includes signal strength fluctuation parameters and signal arrival direction parameters, both of which are multi-dimensional numerical sets.

[0025] The historical signal signature sequence for each base station is extracted individually and associated with the base station's identifier. For example, in the historical signal signature sequence for base station A, the signal strength fluctuation parameter includes multiple signal strength values ​​for each monitoring period over the past six months, and the signal arrival direction parameter also includes multiple direction angle values ​​for each monitoring period.

[0026] Step S122: performing time segmentation processing on the historical signal feature sequence, dividing the historical data segments according to the same daily monitoring period, and calculating the statistical distribution range of the signal strength fluctuation parameter and the probability distribution characteristics of the signal arrival direction parameter in each monitoring period.

[0027] After obtaining the historical signal feature sequence, it is time-segmented. The historical data segments are divided according to the same daily monitoring period. For example, each day can be divided into multiple periods, such as morning period, afternoon period, evening period, etc. The length of each period can be set according to the actual situation, such as two hours per period.

[0028] After the division is completed, the statistical distribution range of the signal strength fluctuation parameters in each monitoring period is calculated. The statistical distribution range can be determined by calculating the maximum value, minimum value, average value, standard deviation and other statistics of the signal strength fluctuation parameters in the period. These statistics together constitute the distribution characteristics of the signal strength fluctuation parameters in the period.

[0029] For the signal arrival direction parameter, its probability distribution characteristics are calculated. This means that the probability of different directions appearing within the time period is counted to form a probability distribution table. This probability distribution table can reflect the probability of the signal coming from each direction under normal circumstances. Through this process, the signal characteristic distribution corresponding to each monitoring period can be obtained.

[0030] Step S123: constructing a dynamic baseline model based on the statistical distribution range and probability distribution characteristics, wherein the dynamic baseline model includes a signal strength reference interval and a signal arrival direction reference distribution for each time period.

[0031] After determining the statistical distribution range of the signal strength fluctuation parameters and the probability distribution characteristics of the signal arrival direction parameters within each monitoring period, the dynamic baseline model is constructed. For the signal strength fluctuation parameters, a signal strength baseline interval is determined based on the statistical distribution range of each monitoring period. This signal strength baseline interval is typically centered around the mean value and fluctuates within a set range. This range can be set based on statistical quantities such as standard deviation to cover the majority of signal strength values ​​under normal conditions.

[0032] For the signal arrival direction parameter, a baseline signal arrival direction distribution is determined based on its probability distribution characteristics. This baseline distribution reflects the probability of signals appearing in different directions under normal circumstances. By integrating the signal strength baseline interval and the signal arrival direction distribution for each monitoring period and storing them categorized by time sequence and base station ID, a dynamic baseline model is formed. This dynamic baseline model provides a corresponding baseline for normal signal characteristics as time passes and time periods change.

[0033] Step S124: comparing the signal strength fluctuation parameter in the original signal feature sequence with the signal strength reference interval of the corresponding time period in the dynamic baseline model, calculating the strength deviation value exceeding the reference interval, and generating a signal strength deviation.

[0034] When the dynamic baseline model is built, the signal intensity fluctuation parameters in the original signal feature sequence are compared with the signal intensity reference interval in the dynamic baseline model. First, the monitoring time period corresponding to each signal intensity fluctuation parameter in the original signal feature sequence is determined, and then the signal intensity reference interval in the dynamic baseline model for the time period is found.

[0035] Each value in the signal intensity fluctuation parameter is compared with the upper and lower limits of the reference interval. If the value is within the reference interval, it means that the value is within the normal range. If the value exceeds the reference interval, the difference between the value and the nearest boundary of the reference interval is calculated, which is the intensity deviation value.

[0036] All intensity deviation values that exceed the reference interval are sorted to generate a signal intensity deviation degree, which can comprehensively reflect the deviation degree of the original signal intensity fluctuation parameter from the reference interval. For example, for the signal intensity fluctuation parameter of a certain monitoring time period, multiple values exceed the reference interval. After calculating the intensity deviation value of each exceeding value, the signal intensity deviation degree of the time period is generated by averaging or weighting.

[0037] Step S125: The signal arrival direction parameter in the original signal feature sequence is compared with the signal arrival direction reference distribution in the dynamic baseline model for the corresponding time period, the direction probability density deviation value is calculated, and the signal direction deviation degree is generated.

[0038] Similarly, for the signal arrival direction parameter in the original signal feature sequence, it also needs to be compared with the signal arrival direction reference distribution in the dynamic baseline model for the corresponding time period. First, the monitoring time period corresponding to the signal arrival direction parameter is determined, and then the signal arrival direction reference distribution for the time period is found.

[0039] The probability density of each direction angle in the signal arrival direction parameter in the reference distribution is calculated, and then the actual frequency is compared with the probability density to obtain the direction probability density deviation value. These deviation values are summarized and processed to generate a signal direction deviation degree, which is also a multi-dimensional value set for reflecting the deviation of the original signal arrival direction parameter from the reference distribution.

[0040] For example, in a certain monitoring time period, there are multiple direction angles in the signal arrival direction parameter. The probability density of each angle in the reference distribution is calculated, and then compared with the frequency of the angle in the original data to obtain the direction probability density deviation value of each angle. Then the signal direction deviation degree of the time period is generated by calculation.

[0041] Step S126: The signal intensity deviation degree and the signal direction deviation degree are weighted and fused to generate a comprehensive signal deviation degree parameter, and the weight of the weighted and fused is determined according to the signal stability analysis result in the historical data.

[0042] After obtaining the signal intensity deviation degree and the signal direction deviation degree, the two deviation degrees need to be weighted and fused to generate a comprehensive signal deviation degree parameter. The process of weighted and fused is that the two deviation degrees are multiplied by the corresponding weight respectively, and then the results are spliced to form the comprehensive signal deviation degree parameter.

[0043] The weight here is determined according to the signal stability analysis result in the historical data. By analyzing the historical data, it is known that under normal circumstances, the stability of signal intensity and signal direction is known, if the signal intensity is more stable in the historical data and is less affected by interference, then the corresponding weight may be relatively low, and if the signal direction is more easily affected by abnormal targets and is poor in stability, then the corresponding weight may be relatively high.

[0044] For example, after analyzing the historical data, it is determined that the weight of the signal intensity deviation degree is 0.4, and the weight of the signal direction deviation degree is 0.6, then in the weighted and fused, each value of the signal intensity deviation degree is multiplied by 0.4, and each value of the signal direction deviation degree is multiplied by 0.6, and then the two results are spliced to form the comprehensive signal deviation degree parameter.

[0045] Step S127: The original signal feature sequence segments whose comprehensive signal deviation degree parameters exceed the preset threshold are screened out to generate an abnormal signal feature set containing signal deviation degree parameters.

[0046] After generating the comprehensive signal deviation degree parameter, a preset threshold needs to be set, which is determined according to a large amount of historical data and practical application experience, and is used to judge whether the original signal feature sequence is abnormal. Each value in the comprehensive signal deviation degree parameter is compared with the preset threshold, if a value exceeds the preset threshold, it means that the corresponding original signal feature sequence segment is abnormal.

[0047] All original signal feature sequence segments that exceed the preset threshold are screened out, these segments contain signal intensity fluctuation parameters, signal arrival direction parameters and corresponding signal deviation degree parameters. These segments are sorted and stored according to the base station identifier and the monitoring period timestamp, and an abnormal signal feature set is generated.

[0048] Step S130: Call the pre-trained multi-base station cooperative identification model to perform cross-base station correlation analysis on the abnormal signal feature set and base station spatial relationship data, extract the target signal correlation mode with spatio-temporal consistency, and the target signal correlation mode includes the signal transmission delay difference and signal strength attenuation gradient between base stations.

[0049] After obtaining the abnormal signal feature set, the pre-trained multi-base station cooperative identification model is called for processing. At the same time, base station spatial relationship data needs to be introduced, which includes the geographical position relationship between each 5G base station tower, such as distance, direction, etc.

[0050] The multi-base station cooperative identification model performs cross-base station correlation analysis on the data in the abnormal signal feature set and the base station spatial relationship data, that is, whether there is a correlation between the abnormal signals collected by different base stations. The above correlation includes both temporal consistency and spatial rationality. Through analysis, the model can extract the target signal correlation mode with spatio-temporal consistency, which contains key information such as signal transmission delay difference and signal strength attenuation gradient between base stations, and can reflect the transmission characteristics and variation law of abnormal signals between different base stations.

[0051] Step S131: Time alignment processing is performed on the abnormal signal feature set, and the abnormal signal feature segments of different base stations are calibrated in time dimension according to the monitoring period timestamp to generate a time-aligned abnormal signal set.

[0052] Before performing cross-base station correlation analysis, the abnormal signal feature set needs to be time-aligned. Since there may be slight time differences in signal collection by different base stations, in order to ensure the accuracy of the analysis, these abnormal signal feature segments must be calibrated in time dimension.

[0053] The specific method is to match and adjust the abnormal signal feature segments of different base stations according to the monitoring period timestamp, so that the abnormal signal feature segments of all base stations in the same monitoring period can be accurately corresponded. For example, the abnormal signal feature segments of all base stations in the first monitoring period are grouped into one group, and in the second monitoring period, they are grouped into another group, and so on.

[0054] After the above processing, a time-aligned abnormal signal set is generated, and the data in the abnormal signal set is arranged in order according to the monitoring period timestamp and the base station identifier. Each monitoring period contains abnormal signal feature segments of multiple base stations, and these abnormal signal feature segments are consistent in time.

[0055] Step S132: Call the base station spatial relationship database to obtain the geographic location parameters of each 5G base station tower, calculate the spatial relative azimuth angle between any two base stations, generate a base station spatial azimuth matrix, and the geographic location parameters include longitude parameters, latitude parameters and altitude parameters.

[0056] Call the base station spatial relationship database to obtain the geographic location parameters of each 5G base station tower, which includes longitude parameters, latitude parameters and altitude parameters, each parameter is a specific numerical value for accurately positioning the spatial position of the base station.

[0057] Then, the spatial relative azimuth angle between any two base stations is calculated. For each pair of base stations, take one of the base stations as a reference point, and calculate the azimuth angle of the other base station relative to the reference point through its longitude parameter and latitude parameter. Organize all the spatial relative azimuth angles between two base stations, and store them in the form of a matrix to generate a base station spatial azimuth matrix.

[0058] For example, assuming there are three base stations, base station A, base station B and base station C, the azimuth angle of base station B relative to base station A, the azimuth angle of base station C relative to base station A, the azimuth angle of base station A relative to base station B, the azimuth angle of base station C relative to base station B, the azimuth angle of base station A relative to base station C, and the azimuth angle of base station B relative to base station C are calculated. Arrange these azimuth angles in the matrix according to the set order to form the spatial azimuth matrix of the three base stations.

[0059] Step S133: Extract the signal arrival direction parameters of each base station in the time-aligned abnormal signal set, calculate the direction deviation angle between the signal detection direction and the relative direction of the base station combined with the base station spatial azimuth matrix, and generate a direction consistency parameter, which represents the degree of consistency of the detection direction of different base stations to the same target.

[0060] Extract the signal arrival direction parameters of each base station from the time-aligned abnormal signal set, which are a set of multi-dimensional numerical values reflecting the signal direction detected by each base station at different times. Then, combined with the previously generated base station spatial azimuth matrix, calculate the direction deviation angle between the signal detection direction and the relative direction of the base station.

[0061] For any two base stations, the spatial relative azimuth angle between them can be obtained from the base station spatial azimuth matrix. Compare the signal arrival direction parameters of each base station with the relative azimuth angle to calculate the angle difference between them, which is the direction deviation angle.

[0062] By further processing and calculating the direction deviation angle, a directional consistency parameter is generated. The value of this directional consistency parameter indicates the degree of consistency in the detection directions of the same target by different base stations. The smaller the direction deviation angle, the more consistent the directions detected by different base stations, and the larger the value of the directional consistency parameter. Conversely, the larger the direction deviation angle, the smaller the value of the directional consistency parameter.

[0063] Step S1331: extracting signal arrival direction parameters of any two base stations in the same monitoring period from the time-aligned abnormal signal set, and recording them as the first base station signal direction parameter and the second base station signal direction parameter respectively.

[0064] To calculate the directional deviation angle, we first select any two base stations from the time-aligned anomaly signal set and extract the direction-of-arrival parameters of their signals during the same monitoring period. To facilitate differentiation and calculation, we denote the direction-of-arrival parameter of one base station as the first base station signal direction parameter, and the other as the second base station signal direction parameter.

[0065] For example, base station A and base station B are selected and their signal direction of arrival parameters for the third monitoring period are extracted. The signal direction of arrival parameter for base station A is the first base station signal direction parameter, and the signal direction of arrival parameter for base station B is the second base station signal direction parameter. These parameters are multi-dimensional numerical sets that contain signal direction angle information at different times within the monitoring period.

[0066] Step S1332: extracting the spatial relative azimuth angle corresponding to the two base stations from the base station spatial azimuth matrix, and recording it as the theoretical azimuth angle between the base stations.

[0067] After extracting the signal arrival direction parameters of the two base stations, the spatial relative azimuth angle corresponding to the two base stations is found from the base station spatial orientation matrix. This spatial relative azimuth angle is calculated based on the geographic location parameters of the two base stations and reflects the theoretical orientation relationship between them. It is recorded as the theoretical inter-base station azimuth angle.

[0068] For example, for base station A and base station B, find their corresponding spatial relative azimuth angles from the base station spatial orientation matrix. Assuming it is a certain angle value, this angle value is the theoretical azimuth angle between base stations, which represents the spatial orientation of base station B relative to base station A, or vice versa, which is determined according to the definition of the matrix.

[0069] Step S1333: Compare the first base station signal direction parameter with the theoretical azimuth angle between base stations to calculate a first direction deviation angle, where the first direction deviation angle is the absolute value of the difference between the first base station signal direction parameter and the theoretical azimuth angle between base stations.

[0070] Next, the first base station signal direction parameter is compared with the base station inter-theoretical azimuth. For each value in the first base station signal direction parameter, the base station inter-theoretical azimuth is subtracted, and the absolute value of the difference is obtained to obtain the first direction deviation angle corresponding to each value.

[0071] For example, the first base station signal direction parameter contains multiple angle values. Each value is subtracted from the base station inter-theoretical azimuth, and the absolute value is obtained to obtain multiple first direction deviation angle values. These values collectively constitute the first direction deviation angle, which reflects the deviation of the signal direction detected by the first base station from the base station inter-theoretical azimuth.

[0072] Step S1334: The second base station signal direction parameter is compared with the reverse angle of the base station inter-theoretical azimuth, and the second direction deviation angle is calculated. The reverse angle is an angle value obtained by adding one hundred and eighty degrees to the base station inter-theoretical azimuth.

[0073] For the second base station signal direction parameter, since it is opposite to the position of the first base station, it needs to be compared with the reverse angle of the base station inter-theoretical azimuth. The reverse angle is calculated by adding one hundred and eighty degrees to the base station inter-theoretical azimuth.

[0074] Then, each value in the second base station signal direction parameter is subtracted from the reverse angle, and the absolute value of the difference is obtained to obtain the second direction deviation angle corresponding to each value. For example, each angle value in the second base station signal direction parameter is subtracted from the reverse angle, and the absolute value is obtained to obtain multiple second direction deviation angle values. These values constitute the second direction deviation angle, which reflects the deviation of the signal direction detected by the second base station from the reverse angle of the base station inter-theoretical azimuth.

[0075] Step S1335: The first direction deviation angle and the second direction deviation angle are arithmetically averaged to generate an average direction deviation angle.

[0076] After obtaining the first direction deviation angle and the second direction deviation angle, the two angle values are added and then divided by two to obtain the average direction deviation angle through the above calculation method. For example, if the first direction deviation angle is a certain angle value and the second direction deviation angle is another angle value, the result of adding the two is divided by two to obtain the average direction deviation angle. The average direction deviation angle comprehensively reflects the deviation of the signal detection direction from the relative position of the base stations, and can more comprehensively reflect the overall deviation between the signal detection direction and the relative position of the base stations.

[0077] Step S1336: Calculate the direction consistency parameter according to the average direction deviation angle. The direction consistency parameter is negatively correlated with the average direction deviation angle. The smaller the average direction deviation angle, the larger the direction consistency parameter.

[0078] The direction consistency parameter is calculated according to the average direction deviation angle. Since the direction consistency parameter is negatively correlated with the average direction deviation angle, when the average direction deviation angle is small, the direction consistency parameter is large, and vice versa. In the specific calculation, a certain conversion of the average direction deviation angle can be adopted, so that the converted result can reflect the negative correlation. For example, a reference angle can be set, and the reference angle is subtracted from the average direction deviation angle, and then divided by the reference angle, and the result is the direction consistency parameter. The direction consistency parameter calculated by the above method can intuitively reflect the degree of consistency of the detection directions of different base stations to the same target.

[0079] Step S1337: Compare the direction consistency parameter with a preset direction consistency threshold. If the direction consistency parameter is greater than the direction consistency threshold, mark the base station pair as a potential cooperative base station pair.

[0080] A direction consistency threshold is preset, which is determined according to a large amount of historical data and actual application scenarios, and is used to determine whether two base stations are likely to detect the same target. The calculated direction consistency parameter is compared with the threshold. If the direction consistency parameter is greater than the direction consistency threshold, it means that the detection directions of the two base stations to the same target are highly consistent, so the base station pair is marked as a potential cooperative base station pair.

[0081] Step S1338: Normalize the direction consistency parameters of all potential cooperative base station pairs to generate direction consistency parameter values.

[0082] Since the direction consistency parameters of different potential cooperative base station pairs may be in different numerical ranges, in order to facilitate subsequent analysis and comparison, the direction consistency parameters need to be normalized. The normalization method can be to subtract the minimum value of all direction consistency parameters from each direction consistency parameter, and then divide by the difference between the maximum and minimum values of all direction consistency parameters, and the result is the normalized direction consistency parameter value. After normalization, the direction consistency parameter values of all potential cooperative base station pairs are in the same numerical interval, which is more conducive to cross-base station correlation analysis.

[0083] Step S134: According to the direction consistency parameter, filter out base station combinations with a direction consistency degree exceeding a preset threshold to generate a cooperative base station pair set. Each base station pair in the cooperative base station pair set includes two base station identifiers with spatial correlation and a corresponding direction consistency parameter.

[0084] After obtaining the normalized directional consistency parameter values ​​for all potential collaborative base station pairs, they are again screened based on a preset directional consistency threshold. Potential collaborative base station pairs whose normalized directional consistency parameter values ​​exceed this threshold are identified as formal collaborative base station pairs and grouped together to form a collaborative base station pair set. Each collaborative base station pair in the set contains two spatially correlated base station identifiers and corresponding normalized directional consistency parameters, which clearly demonstrates which base stations have a high degree of detection direction consistency.

[0085] Step S135: For each base station pair in the collaborative base station pair set, extract the signal strength fluctuation parameters in the time-aligned abnormal signal set, calculate the signal strength difference between the two base stations in the same monitoring period, and generate a signal strength attenuation gradient in combination with the spatial distance parameter between the base stations, where the spatial distance parameter is calculated based on the base station geographic location parameter.

[0086] For each base station pair in the coordinated base station pair set, the signal strength fluctuation parameters of the two base stations within each identical monitoring period are extracted from the time-aligned abnormal signal set. Then, for each monitoring period, the difference between the signal strength fluctuation parameters of the two base stations is calculated to obtain the signal strength difference. Simultaneously, the spatial distance parameter between the two base stations is calculated based on their geographic locations. The signal strength difference and the spatial distance parameter are combined to generate a signal strength attenuation gradient.

[0087] Step S1351: a base station pair is selected from the coordinated base station pair set, denoted as a first base station and a second base station, and base station identifiers of the first base station and the second base station are obtained.

[0088] Each base station pair is selected from the set of coordinated base station pairs. For the currently selected base station pair, one base station is designated as the first base station and the other as the second base station. The base station identifiers of these two base stations are obtained. Base station identifiers uniquely distinguish one base station from another. Using these identifiers, the corresponding base station and its associated data can be accurately located.

[0089] Step S1352: extracting geographic location parameters of the first base station and the second base station from the base station geographic location distribution parameters according to the base station identifier, wherein the geographic location parameters include a longitude parameter, a latitude parameter, and an altitude parameter.

[0090] Based on the base station identifiers of the first base station and the second base station, the geographical location parameters of the two base stations are extracted from a database storing base station geographical location distribution parameters. These geographical location parameters specifically include longitude parameters, latitude parameters, and altitude parameters, which can accurately describe the spatial location of the base stations.

[0091] Step S1353: Calculate the spatial distance parameter between the first base station and the second base station, which is calculated by the square root of the sum of squares of the longitude parameter difference, the latitude parameter difference and the altitude parameter difference.

[0092] When calculating the spatial distance parameter between the first base station and the second base station, the longitude parameter difference, the latitude parameter difference and the altitude parameter difference of the two base stations are calculated respectively. Then, the square of the longitude parameter difference, the square of the latitude parameter difference and the square of the altitude parameter difference are obtained by squaring the three differences respectively. Next, the sum of the squares is obtained by adding the three squares. Finally, the square root of the sum is calculated to obtain the spatial distance parameter between the first base station and the second base station.

[0093] Step S1354: Extract the signal strength fluctuation parameter of the first base station in each monitoring period from the time-aligned abnormal signal set to generate the first base station signal strength sequence.

[0094] In the time-aligned abnormal signal set, according to the base station identifier of the first base station, the signal strength fluctuation parameter of the base station in each monitoring period is extracted. The signal strength fluctuation parameters are arranged in the order of monitoring periods to form the first base station signal strength sequence. Each element in the first base station signal strength sequence corresponds to the signal strength fluctuation in a monitoring period.

[0095] Step S1355: Extract the signal strength fluctuation parameter of the second base station in each monitoring period from the time-aligned abnormal signal set to generate the second base station signal strength sequence.

[0096] Similarly, in the time-aligned abnormal signal set, according to the base station identifier of the second base station, the signal strength fluctuation parameter of the base station in each monitoring period is extracted, and the second base station signal strength sequence is generated by arranging in the order of monitoring periods.

[0097] Step S1356: Perform time dimension matching on the first base station signal strength sequence and the second base station signal strength sequence to make the signal strength fluctuation parameters corresponding to the same monitoring period one-to-one.

[0098] Since the first base station signal strength sequence and the second base station signal strength sequence are arranged according to the monitoring period, the time dimension matching can be performed by the time stamp of the monitoring period. The signal strength fluctuation parameters corresponding to the same monitoring period time stamp in the two sequences are associated to ensure that the signal strength fluctuation parameters of the first base station and the second base station in each monitoring period can be one-to-one corresponding, which prepares for the subsequent calculation of the signal strength difference in the same monitoring period.

[0099] Step S1357: Calculate the difference between the first base station signal strength parameter and the second base station signal strength parameter within the same monitoring period to generate a signal strength difference sequence.

[0100] For each monitoring period, subtract the signal strength fluctuation parameter for the corresponding period in the second base station signal strength sequence from the signal strength fluctuation parameter for the first base station signal strength sequence to obtain the signal strength difference for that monitoring period. The signal strength differences for all monitoring periods are arranged in chronological order to form a signal strength difference sequence.

[0101] Step S1358: Divide each difference in the signal strength difference sequence by the spatial distance parameter between the first base station and the second base station to generate a unit distance signal strength difference as a signal strength attenuation gradient.

[0102] Each signal strength difference in the signal strength difference sequence is divided by the spatial distance parameter between the first base station and the second base station to obtain the signal strength difference per unit distance. The difference value is determined as the signal strength attenuation gradient, which reflects the attenuation of the signal strength between the two base stations per unit distance.

[0103] Step S1359: performing sign processing on the signal strength attenuation gradient. If the first base station signal strength parameter is greater than the second base station signal strength parameter, the signal strength attenuation gradient is a positive value, otherwise it is a negative value.

[0104] The sign of the signal strength attenuation gradient is processed based on the magnitude relationship between the signal strength parameters of the first and second base stations. When the signal strength parameter of the first base station is greater than that of the second base station, the signal strength attenuation gradient takes a positive value; when the signal strength parameter of the first base station is less than that of the second base station, the signal strength attenuation gradient takes a negative value. The sign of the gradient can be used to intuitively determine the direction of signal strength attenuation.

[0105] Step S13510: The signal strength attenuation gradient is associated with the corresponding monitoring period timestamp and stored to generate a signal strength attenuation gradient sequence containing the time stamp.

[0106] Each signal strength attenuation gradient is associated with its corresponding monitoring period timestamp, so that each attenuation gradient value can be mapped to a specific monitoring time. This associated information is then stored in timestamp order to form a signal strength attenuation gradient sequence containing time stamps.

[0107] Step S136: extracting the timestamps of two base stations in the coordinated base station pair set receiving the same signal feature, calculating the timestamp difference, and generating the signal transmission delay difference between the base stations.

[0108] For each of the coordinated base station pairs, the timestamps of when they receive the same signal signature are calculated. The difference between these two timestamps is then calculated, representing the signal transmission delay difference between the two base stations. This delay difference can be used to determine the difference in signal transmission time between the two base stations.

[0109] Step S137: input the signal strength attenuation gradient and the signal transmission delay difference between base stations into the feature fusion layer of the multi-base station collaborative recognition model, perform spatiotemporal correlation modeling processing, and generate a cross-base station signal correlation vector.

[0110] Two features, signal strength attenuation gradient and inter-base station signal transmission delay differences, are input into the feature fusion layer of the multi-base station collaborative recognition model. The feature fusion layer processes these two features, exploring their spatiotemporal correlations and integrating them to form a cross-base station signal correlation vector. This cross-base station signal correlation vector contains information about the temporal and spatial correlations between signals from different base stations.

[0111] Step S138: Call the pattern recognition layer of the multi-base station collaborative recognition model to perform spatiotemporal consistency verification on the cross-base station signal correlation vector, extract the signal pattern with continuous monitoring period correlation, and generate a target signal correlation pattern including the signal transmission delay difference and signal strength attenuation gradient between base stations.

[0112] The pattern recognition layer of the multi-base station collaborative recognition model analyzes cross-base station signal correlation vectors, verifying their temporal and spatial consistency. By analyzing signal correlations over consecutive monitoring periods, it extracts signal patterns that demonstrate consistent correlation. These signal patterns incorporate information such as inter-base station signal transmission delay differences and signal strength attenuation gradients, ultimately forming the target signal correlation pattern.

[0113] Step S140: Based on the target signal association pattern and the base station geographic location distribution parameters, a triangulation positioning algorithm is used to deduce the real-time trajectory parameters of the low-altitude target, where the real-time trajectory parameters include a position coordinate sequence and a moving speed vector.

[0114] Using the various information contained in the target signal correlation pattern, combined with the base station's geographic distribution parameters, a triangulation algorithm is used to infer the real-time trajectory parameters of low-altitude targets. These parameters primarily consist of a position coordinate sequence and a velocity vector. These parameters provide information about the target's path and velocity.

[0115] Step S141: extracting a set of coordinated base station pairs, a signal transmission delay difference between base stations, and a signal strength attenuation gradient from the target signal association pattern.

[0116] Key information such as the set of coordinated base station pairs, the difference in signal transmission delay between base stations, and the signal strength attenuation gradient is extracted from the target signal correlation pattern. The set of coordinated base station pairs determines the base station combination involved in positioning, while the difference in signal transmission delay between base stations and the signal strength attenuation gradient provide the basic data for positioning.

[0117] Step S142: extracting the geographic location parameters of each base station in the coordinated base station pair set from the base station geographic location distribution parameters to generate a base station positioning coordinate set, wherein the geographic location parameters include longitude parameters, latitude parameters and altitude parameters.

[0118] Based on the base station identifiers in the coordinated base station pair set, the geographic location parameters of each base station are extracted from the base station geographic location distribution parameters. These geographic location parameters include longitude, latitude, and altitude. These parameters are combined to form a base station positioning coordinate set, which clearly defines the specific location of each participating base station in space.

[0119] Step S143: For each coordinated base station pair, the distance difference between the target and the two base stations is calculated based on the signal transmission delay difference between the base stations and the electromagnetic wave propagation speed parameter to generate a distance difference parameter.

[0120] For each coordinated base station pair, the difference in signal transmission delay between the base stations and the electromagnetic wave propagation speed parameter are used to calculate the distance difference between the low-altitude target and the two base stations. Specifically, the difference in signal transmission delay between the base stations is multiplied by the electromagnetic wave propagation speed parameter. The result is the distance difference between the target and the two base stations, which is used as the distance difference parameter.

[0121] Step S144: constructing a hyperbola positioning equation based on the base station positioning coordinate set and the distance difference parameter, wherein the hyperbola positioning equation takes the geographic location parameters of the two base stations as the focus and the distance difference parameter as the real axis length.

[0122] A hyperbola positioning equation is constructed using the geographic locations of two base stations in the base station positioning coordinate set as the two foci of a hyperbola, and the distance difference parameter as the real axis length of the hyperbola. This hyperbola positioning equation describes the trajectory of points whose distance difference from the two foci is equal to the real axis length. This hyperbola positioning equation can be used to determine the possible location range of low-altitude targets.

[0123] Step S1441: Select a collaborative base station pair from the base station positioning coordinate set, recorded as the first focus and the second focus, the geographic location parameters of the first focus are the first longitude parameter, the first latitude parameter, and the first altitude parameter, and the geographic location parameters of the second focus are the second longitude parameter, the second latitude parameter, and the second altitude parameter.

[0124] A coordinated base station pair is selected from the base station positioning coordinate set, one of the base stations is set as a first focus, and the other is set as a second focus. The geographic location parameters of the first focus include a first longitude parameter, a first latitude parameter, and a first altitude parameter, and the geographic location parameters of the second focus include a second longitude parameter, a second latitude parameter, and a second altitude parameter.

[0125] Step S1442: Assume that the position coordinates of the low-altitude target are the target longitude parameter, the target latitude parameter, and the target altitude parameter, the distance from the target to the first focus is the first distance parameter, and the distance from the target to the second focus is the second distance parameter.

[0126] Assume that the position coordinates of a low-altitude target are composed of the target longitude, latitude, and altitude parameters. The distance from the target to the first focal point is set as the first distance parameter, and the distance to the second focal point is set as the second distance parameter. These parameters are the basic variables for constructing the hyperbolic positioning equation.

[0127] Step S1443: Calculate a distance difference parameter according to the electromagnetic wave propagation speed parameter and the signal transmission delay difference between base stations, where the distance difference parameter is equal to the first distance parameter minus the second distance parameter.

[0128] The distance difference parameter is calculated using the electromagnetic wave propagation speed parameter and the difference in signal transmission delay between base stations. The difference in signal transmission delay between base stations is multiplied by the electromagnetic wave propagation speed parameter. The result is the difference between the first and second distance parameters, which is also known as the distance difference parameter.

[0129] Step S1444: According to the distance calculation formula, the first distance parameter is the spatial distance between the target position coordinates and the first focus geographic location parameter, and the second distance parameter is the spatial distance between the target position coordinates and the second focus geographic location parameter.

[0130] According to the spatial distance calculation method, the first distance parameter is the spatial distance between the low-altitude target location coordinates and the first focal point location parameter, and the second distance parameter is the spatial distance between the low-altitude target location coordinates and the second focal point location parameter. When calculating spatial distance, it is necessary to comprehensively consider the differences in parameters such as longitude, latitude, and altitude.

[0131] Step S1445: Substitute the first distance parameter and the second distance parameter into the expression of the distance difference parameter to obtain an equation including the target longitude parameter and the target latitude parameter.

[0132] Substituting the first and second distance parameters into the distance difference parameter expression, we obtain an equation that includes the target longitude and latitude parameters. This equation reflects the distance relationship between the target location and the two base station locations.

[0133] Step S1446: Set the altitude parameter to a constant, simplify the three-dimensional space problem to a two-dimensional plane problem, and obtain a hyperbola positioning equation that only contains the target longitude parameter and the target latitude parameter; the standard form of the hyperbola positioning equation is the trajectory of points on the plane whose distance difference to the two foci is a constant, where the constant is the distance difference parameter, the distance between the two foci is the focal length parameter, and the focal length parameter is calculated based on the geographic location parameters of the first focus and the second focus.

[0134] To simplify the calculation, the altitude parameter is temporarily set to a constant, thus transforming the positioning problem in three-dimensional space into a two-dimensional problem. The resulting hyperbolic positioning equation now contains only the target longitude and latitude parameters. The standard form of this equation represents the trajectory of points on a plane whose distance difference from two foci is a constant. The constant is the distance difference parameter, and the distance between the two foci is the focal length parameter, which can be calculated based on the geographic location parameters of the first and second foci.

[0135] Step S1447: Arrange the hyperbolic positioning equation, move the terms containing the target longitude parameter and the target latitude parameter to the left side of the equation, and move the constant term to the right side of the equation, to generate a standard form of the hyperbolic positioning equation.

[0136] Arrange the equation by moving all the terms containing the target longitude and latitude parameters to the left side of the equation and the constant terms to the right side of the equation, so that the equation presents a standard hyperbolic equation form, which is convenient for subsequent solution and calculation.

[0137] Step S145: Solve the hyperbolic positioning equation to obtain the two-dimensional position coordinates of the low-altitude target in the current monitoring period, where the two-dimensional position coordinates include longitude coordinate parameters and latitude coordinate parameters.

[0138] By solving the sorted hyperbola positioning equation, the two-dimensional position coordinates of the low-altitude target in the current monitoring period can be obtained. The two-dimensional position coordinates are composed of longitude coordinate parameters and latitude coordinate parameters, reflecting the position of the target on the horizontal plane.

[0139] Step S146: Estimate the altitude parameter of the low-altitude target according to the signal strength attenuation gradient and the base station altitude parameter, and generate three-dimensional position coordinates in combination with the two-dimensional position coordinates.

[0140] The altitude parameter of the low-altitude target is determined based on the signal strength attenuation gradient and the base station's altitude parameter. The estimated altitude parameter is combined with the previously obtained two-dimensional position coordinates to form a three-dimensional position coordinate, which can more comprehensively reflect the low-altitude target's position in space.

[0141] Step S147: Arrange the three-dimensional position coordinates of each monitoring period in chronological order of the monitoring period to generate a position coordinate sequence.

[0142] The three-dimensional position coordinates obtained in each monitoring period are arranged in chronological order of the monitoring time to form a position coordinate sequence. Through the position coordinate sequence, the position change of the low-altitude target at different time points can be clearly seen.

[0143] Step S148: Calculate the spatial distance between adjacent three-dimensional position coordinates in the position coordinate sequence, and generate a movement distance parameter in combination with the time interval parameter of the monitoring period.

[0144] For two adjacent three-dimensional position coordinates in the position coordinate sequence, the spatial distance between them is calculated. At the same time, in combination with the time interval parameter of the monitoring period corresponding to the two three-dimensional position coordinates, a movement distance parameter is generated.

[0145] Step S1481: Select two adjacent three-dimensional position coordinates from the position coordinate sequence, denoted as the first position coordinate and the second position coordinate, the first position coordinate corresponding to the first timestamp, and the second position coordinate corresponding to the second timestamp.

[0146] In consecutive monitoring periods, the position coordinate sequence is arranged in chronological order, and two adjacent three-dimensional position coordinates are selected therefrom. For example, in a certain continuous monitoring process, the three-dimensional position coordinate that appears first is determined as the first position coordinate, and the three-dimensional position coordinate that appears immediately after is determined as the second position coordinate. At the same time, the first timestamp corresponding to the first position coordinate and the second timestamp corresponding to the second position coordinate are recorded, which are accurate to the smallest unit of the monitoring period, ensuring the accuracy of subsequent time interval calculation.

[0147] Step S1482: Extract the longitude parameter, latitude parameter and altitude parameter of the first position coordinate, denoted as the first longitude parameter, first latitude parameter and first altitude parameter.

[0148] The first position coordinate is analyzed to separate the various parameters used for positioning therefrom. The longitude parameter reflects the position information of the position in the east-west direction, the latitude parameter reflects the position information in the north-south direction, and the altitude parameter reflects the vertical height of the position relative to sea level. These parameters are denoted as the first longitude parameter, the first latitude parameter and the first altitude parameter, respectively, so as to be clearly distinguished and used in subsequent calculations.

[0149] Step S1483: Extract the longitude parameter, latitude parameter and altitude parameter of the second position coordinate, denoted as the second longitude parameter, second latitude parameter and second altitude parameter.

[0150] Similarly, the second location coordinates are parsed to extract the longitude, latitude, and altitude parameters contained therein, and are labeled as the second longitude parameter, the second latitude parameter, and the second altitude parameter, respectively. These parameters are identical in nature to the corresponding parameters of the first location coordinates, but their specific values ​​may vary depending on the location.

[0151] Step S1484: Calculate the longitude parameter difference, where the longitude parameter difference is the second longitude parameter minus the first longitude parameter.

[0152] Subtract the first longitude parameter from the second longitude parameter to get the longitude difference between the two. This longitude difference reflects the east-west offset of the two locations. If the difference is positive, the second location is east of the first location; if the difference is negative, the second location is west of the first location.

[0153] Step S1485: Calculate the latitude parameter difference, where the latitude parameter difference is the second latitude parameter minus the first latitude parameter.

[0154] Subtract the first latitude parameter from the second latitude parameter to get the latitude parameter difference. This latitude parameter difference reflects the north-south offset of the two locations. A positive difference indicates that the second location is north of the first location; a negative difference indicates that the second location is south of the first location.

[0155] Step S1486: Calculate the altitude parameter difference, where the altitude parameter difference is the second altitude parameter minus the first altitude parameter.

[0156] Subtract the first altitude parameter from the second altitude parameter to get the altitude difference. This difference reflects the vertical difference between the two locations. A positive difference indicates that the second location is higher than the first; a negative difference indicates that the second location is lower than the first.

[0157] Step S1487: performing square operations on the longitude parameter difference, latitude parameter difference and altitude parameter difference respectively to generate a longitude square difference parameter, a latitude square difference parameter and an altitude square difference parameter.

[0158] The longitude parameter difference is squared to obtain the longitude squared difference parameter. The purpose of the squaring operation is to eliminate the positive and negative effects of the difference, retaining only the numerical value to facilitate subsequent summation calculations. Similarly, the latitude parameter difference is squared to obtain the latitude squared difference parameter; the altitude parameter difference is squared to obtain the altitude squared difference parameter.

[0159] Step S1488: performing a sum operation on the longitude square difference parameter, the latitude square difference parameter, and the altitude square difference parameter to generate a total square difference parameter.

[0160] The total squared difference parameter is obtained by adding the squared longitude, latitude, and altitude parameters. This parameter combines the squared differences between two locations in longitude, latitude, and altitude, and is the intermediate data for calculating spatial distance.

[0161] Step S1489: performing a square root operation on the total square difference parameter to generate a spatial distance parameter between the first position coordinate and the second position coordinate.

[0162] By taking the square root of the total squared difference parameter, we obtain the spatial distance parameter between the first and second position coordinates. This spatial distance parameter accurately reflects the straight-line distance between two 3D position coordinates in space and is an important indicator for measuring the distance between two positions.

[0163] Step S14810: Calculate the difference between the second timestamp and the first timestamp to generate a time interval parameter.

[0164] Subtract the first timestamp from the second timestamp to obtain the difference, which is the time interval parameter. This time interval parameter represents the length of time from the appearance of the first location coordinate to the appearance of the second location coordinate. Its units are consistent with the timestamp units, ensuring compatibility when used in conjunction with the spatial distance parameter.

[0165] Step S14811: The spatial distance parameter is used as a moving distance parameter, and is associated with the time interval parameter and the corresponding timestamp for storage to generate a moving distance sequence.

[0166] The calculated spatial distance parameter is determined as the movement distance parameter, which is then associated with the time interval parameter and the corresponding first and second timestamps. This association and storage creates a chronological movement distance sequence that fully records the distance information of the low-altitude target during different time intervals.

[0167] Step S149: Calculate the moving direction angle according to the difference in the longitude coordinate parameters and the latitude coordinate parameters of the adjacent three-dimensional position coordinates, and generate a moving speed vector in combination with the moving distance parameter and the time interval parameter. The moving speed vector includes a speed magnitude parameter and a speed direction angle parameter.

[0168] After obtaining the longitude coordinate parameter difference and the latitude coordinate parameter difference of the adjacent three-dimensional position coordinates, the moving direction angle is calculated based on the two differences. The calculation of the moving direction angle needs to be combined with the positive and negative situations of the two differences to determine the specific direction of the low-altitude target movement. For example, according to the longitude coordinate parameter difference, it is determined whether to move east or west, and according to the latitude coordinate parameter difference, it is determined whether to move north or south, and the moving direction angle is obtained by combining the two direction information.

[0169] After calculating the moving direction angle, the moving speed vector is generated by combining the moving distance parameter and the time interval parameter obtained before. The speed size parameter is obtained by dividing the moving distance parameter by the time interval parameter, which reflects the distance moved by the low-altitude target in unit time. The speed direction angle parameter is the moving direction angle calculated before, which is used to indicate the direction of the low-altitude target movement. The speed size parameter and the speed direction angle parameter are integrated to form a complete moving speed vector.

[0170] Step S1410: The position coordinate sequence and the moving speed vector are stored in association to generate a real-time trajectory parameter, and each record of the real-time trajectory parameter contains a time stamp, a three-dimensional position coordinate and a moving speed vector.

[0171] The position coordinate sequence and the moving speed vector are associated in time sequence, so that each three-dimensional position coordinate corresponding to a time point has a corresponding moving speed vector matched therewith. In the storage process, each record contains a time stamp, a three-dimensional position coordinate corresponding to the time stamp and a moving speed vector. Through the above associated storage, a real-time trajectory parameter is formed, which completely records the position and movement of the low-altitude target at different times.

[0172] Step S150: The real-time trajectory parameter is matched with the preset security control region data in spatial relationship to generate a low-altitude security situation assessment report containing a target intrusion risk level, and the low-altitude security situation assessment report is pushed to a regional security command platform.

[0173] Step S151: Obtain the preset security control region data, which contains the region identifier, the region boundary coordinate sequence and the corresponding risk level threshold value of each control region.

[0174] The required data is retrieved from a database or storage medium storing the preset security control region data. These data are classified according to the control regions, and each control region has a unique region identifier. The region boundary coordinate sequence is composed of a series of consecutive coordinate points, which can accurately represent the boundary range of the control region when connected in order. The corresponding risk level threshold value is set according to the importance and security requirements of different control regions, which contains multiple parameters such as speed threshold value and intrusion duration threshold value.

[0175] Step S152: parsing the position coordinate sequence in the real-time trajectory parameters, extracting the three-dimensional position coordinates of each monitoring period, and generating a coordinate set to be evaluated.

[0176] The position coordinate sequence in the real-time trajectory parameters is arranged in chronological order. During the parsing process, the 3D position coordinates corresponding to each monitoring period are extracted one by one. Each 3D position coordinate contains three parameters: longitude, latitude, and altitude. After these parameters are fully extracted, they are assembled into a set of coordinates to be evaluated in the order in which they were extracted. Each 3D position coordinate in the set of coordinates to be evaluated corresponds to a specific monitoring period, ensuring that its time information can be accurately traced in subsequent spatial relationship judgments.

[0177] Step S153: For each three-dimensional position coordinate in the coordinate set to be evaluated, determine the spatial relationship with each control area in the preset security control area data.

[0178] The first 3D position coordinate is extracted from the set of coordinates to be evaluated. This coordinate is then compared to the first control area in the pre-set security control area data. After the first control area is evaluated, the second control area is evaluated, and so on, until all control areas are evaluated. The second 3D position coordinate is then extracted from the set of coordinates to be evaluated, and the above process is repeated, comparing it to each control area in turn. This one-by-one comparison ensures that each 3D position coordinate has been spatially compared to all control areas.

[0179] Step S1531: Compare the longitude and latitude parameters of the three-dimensional position coordinates with the regional boundary coordinate sequence of the control area to determine whether the three-dimensional position coordinates are within the two-dimensional plane range of the control area.

[0180] For each 3D location coordinate, its longitude and latitude parameters are extracted and compared with the region boundary coordinate sequence of the control area. Each coordinate point in the region boundary coordinate sequence contains longitude and latitude information. Using the ray method, it can be determined whether the point determined by the longitude and latitude parameters of the 3D location coordinate is within the 2D plane enclosed by the region boundary coordinate sequence.

[0181] Step S1532: If it is within the two-dimensional plane range, further compare the altitude parameter of the three-dimensional position coordinate with the altitude limit range of the control area to determine whether it is within the altitude limit range.

[0182] When the longitude and latitude parameters of the three-dimensional position coordinate are within the two-dimensional plane range of the control area, the altitude parameter of the three-dimensional position coordinate is extracted, and the altitude limit range of the control area is obtained from the preset security control area data. The altitude parameter is compared with the upper limit and the lower limit of the altitude limit range, and if the altitude parameter is greater than the lower limit and less than the upper limit, it means that the three-dimensional position coordinate is within the altitude limit range.

[0183] Step S1533: If the three-dimensional position coordinate is within both the two-dimensional plane range and the altitude limit range, mark the three-dimensional position coordinate as a region intrusion coordinate, and record the corresponding control area identifier and intrusion timestamp.

[0184] When a three-dimensional position coordinate is within both the two-dimensional plane range and the altitude limit range of a control area, the three-dimensional position coordinate is marked as a region intrusion coordinate. At the same time, the region identifier of the control area and the monitoring period timestamp corresponding to the three-dimensional position coordinate are recorded as the intrusion timestamp.

[0185] Step S154: According to the control area identifier corresponding to the region intrusion coordinate, extract the risk level threshold of the control area from the preset security control area data.

[0186] After obtaining the control area identifier corresponding to the region intrusion coordinate, the control area identifier is searched in the preset security control area data to find the corresponding control area information, and the risk level threshold of the control area is extracted therefrom. The risk level threshold includes a plurality of specific parameters, such as a speed threshold, an intrusion duration threshold, an intrusion frequency threshold, etc. The above parameters are set according to the safety importance of the control area, and the risk level thresholds of different control areas may be different.

[0187] Step S155: Compare the moving speed vector in the real-time trajectory parameter with the risk level threshold, and if the speed parameter of the moving speed vector exceeds the speed threshold in the risk level threshold, the risk level is increased.

[0188] The moving speed vector corresponding to the region intrusion coordinate is obtained from the real-time trajectory parameter, and the speed parameter in the moving speed vector is extracted. The speed parameter is compared with the speed threshold in the risk level threshold, and if the speed parameter is greater than the speed threshold, it means that the low-altitude target moves faster when intruding the control area, which may have higher danger. At this time, the risk level is increased according to the preset rule. For example, the originally evaluated risk level is a certain level, and after increasing, it becomes a higher level.

[0189] Step S156: Count the number and duration of region intrusion coordinates in the same control area, and generate a target intrusion risk level in combination with the risk level threshold.

[0190] The number of regional intrusion coordinates belonging to the same control area is counted to obtain the number of regional intrusion coordinates. Simultaneously, based on the intrusion timestamps corresponding to the regional intrusion coordinates, the duration of the low-altitude target's presence in the control area is calculated (i.e., the interval from the timestamp of the first regional intrusion coordinate to the timestamp of the last regional intrusion coordinate). The number of regional intrusion coordinates and the duration of the intrusion are compared with the intrusion count threshold and intrusion duration threshold, respectively, in the risk level threshold. Combined with previous risk level increases, a comprehensive assessment is made to determine the target's intrusion risk level. For example, if the number of regional intrusion coordinates exceeds the intrusion count threshold, the duration exceeds the intrusion duration threshold, and the movement speed also exceeds the speed threshold, the target's intrusion risk level will be assessed as higher.

[0191] Step S157: Integrate the target intrusion risk level, area intrusion coordinates, intrusion timestamp and corresponding real-time trajectory parameters to generate a low-altitude safety situation assessment report, which includes situation assessment time, target identification, intrusion area information, risk level and real-time trajectory data.

[0192] The target intrusion risk level, all regional intrusion coordinates, corresponding intrusion timestamps, and related real-time trajectory parameters are collected and integrated according to a predefined format. The situation assessment time is the time the report is generated, the target identifier uniquely identifies the low-altitude target, the intrusion area information includes the intrusion control area identifier and area description, the risk level is the target intrusion risk level, and the real-time trajectory data is the position coordinate sequence and movement velocity vector associated with the low-altitude target. By integrating this information, a complete low-altitude security situation assessment report is generated.

[0193] Step S158: Push the low-altitude safety situation assessment report to the regional safety command platform.

[0194] The generated low-altitude security situation assessment report is transmitted to the regional security command platform via a dedicated communication link or network transmission method. Data integrity and security are ensured during transmission to prevent information leakage or loss. After receiving the report, the regional security command platform allows relevant personnel to promptly review the intrusion status and risk level of low-altitude targets so that appropriate prevention and control measures can be implemented.

[0195] For example, step S15331: select a three-dimensional position coordinate from the coordinate set to be evaluated, record it as the current evaluation coordinate, and extract the longitude parameter, latitude parameter and altitude parameter of the current evaluation coordinate.

[0196] In the coordinate set to be evaluated, a three-dimensional position coordinate is selected as the current evaluation coordinate in sequence. The current evaluation coordinate is analyzed to extract the longitude parameter, latitude parameter and altitude parameter contained therein. These parameters are key data for spatial relationship judgment, the longitude parameter and latitude parameter are used to judge whether the current evaluation coordinate is within the two-dimensional plane range of the control area, and the altitude parameter is used to judge whether it is within the altitude limit range.

[0197] Step S15332: Select a control area from the preset safety control area data, denoted as the current control area, and extract the region boundary coordinate sequence of the current control area, which contains a plurality of boundary point coordinates arranged in clockwise or counterclockwise order, each boundary point coordinate contains longitude boundary parameter and latitude boundary parameter.

[0198] From the preset safety control area data, a control area is selected as the current control area according to the set order. The information of the current control area is analyzed to extract its region boundary coordinate sequence. The region boundary coordinate sequence is composed of a plurality of boundary point coordinates arranged in clockwise or counterclockwise order, forming a closed polygon, each boundary point coordinate contains longitude boundary parameter and latitude boundary parameter, accurately determining the two-dimensional boundary of the control area.

[0199] Step S15333: Determine whether the longitude parameter and latitude parameter of the current evaluation coordinate are within the two-dimensional plane range of the current control area using the ray method.

[0200] A horizontal right ray is drawn with the point determined by the longitude parameter and latitude parameter of the current evaluation coordinate as the starting point. The intersection of the ray and the polygon formed by the region boundary coordinate sequence of the current control area is judged, and the number of intersection points of the ray and the boundary line segments is counted.

[0201] Step S153331: Draw a horizontal ray to the right from the current evaluation coordinate, and count the number of intersection points of the horizontal ray and each boundary line segment in the region boundary coordinate sequence.

[0202] Two adjacent boundary point coordinates are extracted from the region boundary coordinate sequence to form a boundary line segment. For each boundary line segment, it is judged whether the horizontal ray intersects it. When judging, the longitude parameter and latitude parameter of the two endpoints of the boundary line segment are first determined, and then according to the direction and position of the horizontal ray, it is analyzed whether there is an intersection point. If there is an intersection point and the intersection point is not at the endpoint of the boundary line segment, the number of intersection points is increased by one. According to the above method, all boundary line segments in the region boundary coordinate sequence are traversed to complete the counting of the number of intersection points.

[0203] Step S153332: If the number of intersection points is odd, the current evaluation coordinate is in the two-dimensional plane range.

[0204] After the number of intersection points of the horizontal ray and all boundary line segments is counted, the counting result is checked. When the number of intersection points is odd, it indicates that the point determined by the longitude parameter and the latitude parameter of the current evaluation coordinate is in the two-dimensional plane range of the control region. At this time, the judgment result is recorded, preparing for the subsequent altitude parameter judgment.

[0205] Step S153333: If the number of intersection points is even, the current evaluation coordinate is not in the two-dimensional plane range.

[0206] When the number of intersection points counted is even, it indicates that the point determined by the longitude parameter and the latitude parameter of the current evaluation coordinate is not in the two-dimensional plane range of the control region. In this case, there is no need to perform subsequent altitude parameter judgment, and the result is directly recorded, and then the spatial relationship judgment for the next control region is continued.

[0207] Step S1534: If the current evaluation coordinate is in the two-dimensional plane range, extract the altitude height limit range of the current control region, which includes the minimum altitude parameter and the maximum altitude parameter.

[0208] After determining that the current evaluation coordinate is in the two-dimensional plane range, the altitude height limit range corresponding to the current control region is retrieved from the preset safety control region data. The altitude height limit range is composed of the minimum altitude parameter and the maximum altitude parameter, which clearly defines the restriction interval of the control region in the vertical direction. The extracted minimum altitude parameter and maximum altitude parameter are stored for comparison with the altitude parameter of the current evaluation coordinate.

[0209] Step S1535: Compare the altitude parameter of the current evaluation coordinate with the minimum altitude parameter and the maximum altitude parameter. If the altitude parameter is greater than the minimum altitude parameter and less than the maximum altitude parameter, the current evaluation coordinate is in the altitude height limit range.

[0210] The altitude parameter of the current evaluation coordinate is taken out and compared with the extracted minimum altitude parameter and maximum altitude parameter. When the altitude parameter is greater than the minimum altitude parameter and less than the maximum altitude parameter, it indicates that the current evaluation coordinate is in the altitude height limit range of the control region. The comparison result is recorded, and combined with the two-dimensional plane range judgment result, it is determined whether the current evaluation coordinate belongs to the region intrusion coordinate.

[0211] Step S1536: If the three-dimensional position coordinate is within the two-dimensional plane range and the altitude height limit range at the same time, mark the three-dimensional position coordinate as a regional intrusion coordinate, record the corresponding control area identifier and intrusion timestamp.

[0212] When the three-dimensional position coordinate is within the two-dimensional plane range and the altitude height limit range at the same time, mark the three-dimensional position coordinate as a regional intrusion coordinate. At the same time, obtain the identifier information of the control area from the preset safety control area data, and record the monitoring period timestamp corresponding to the three-dimensional position coordinate, that is, the intrusion timestamp.

[0213] Step S1537: If the three-dimensional position coordinate is not within the two-dimensional plane range or not within the altitude height limit range, do not mark it as a regional intrusion coordinate, and continue to perform spatial relationship judgment on the next control area.

[0214] When the three-dimensional position coordinate does not satisfy the conditions of being within the two-dimensional plane range and the altitude height limit range at the same time, do not mark it as a regional intrusion coordinate. At this time, according to the preset order, select the next control area, and repeat the above spatial relationship judgment process until the judgment of all control areas is completed.

[0215] Step S154: According to the control area identifier corresponding to the regional intrusion coordinate, extract the risk level threshold of the control area from the preset safety control area data.

[0216] After obtaining the regional intrusion coordinate and its corresponding control area identifier, search for the risk level threshold corresponding to the control area in the preset safety control area data. The risk level threshold usually contains multiple parameters, such as speed threshold, duration threshold, etc., which will be used as important reference standards for evaluating the target intrusion risk level.

[0217] Step S155: Compare the moving speed vector in the real-time trajectory parameter with the risk level threshold, if the speed size parameter of the moving speed vector exceeds the speed threshold in the risk level threshold, then the risk level is increased.

[0218] Extract the moving speed vector corresponding to the regional intrusion coordinate from the real-time trajectory parameter, which contains the speed size parameter and the speed direction angle parameter. Compare the speed size parameter with the speed threshold in the risk level threshold. When the speed size parameter exceeds the speed threshold, it means that the moving speed of the target is fast, which may bring higher safety risk, so the corresponding risk level needs to be increased. According to the preset increase rule, adjust the initially determined risk level, and record the adjusted result.

[0219] Step S156: Count the number of regional intrusion coordinates and duration in the same control area, and generate a target intrusion risk level based on the risk level threshold.

[0220] Count all regional intrusion coordinates belonging to the same controlled area to obtain the number of regional intrusion coordinates. Simultaneously, based on the intrusion timestamps corresponding to these regional intrusion coordinates, calculate the duration of the target's presence in the controlled area—the difference between the earliest and latest intrusion timestamps. Compare the number and duration of regional intrusion coordinates to the corresponding thresholds in the risk level threshold. For example, if the number of regional intrusion coordinates exceeds the number threshold or the duration exceeds the time threshold, the risk level is increased according to the risk level threshold. The comprehensive comparison results are used to determine the target's intrusion risk level.

[0221] Step S157: Integrate the target intrusion risk level, area intrusion coordinates, intrusion timestamp and corresponding real-time trajectory parameters to generate a low-altitude safety situation assessment report, which includes situation assessment time, target identification, intrusion area information, risk level and real-time trajectory data.

[0222] This information is collected, along with the target's intrusion risk level, all intrusion coordinates for each area, corresponding intrusion timestamps, and relevant real-time trajectory parameters, including the position coordinate sequence and velocity vector. This information is consolidated according to a pre-set format, adding the situation assessment time and the unique target identifier assigned to the target. The intrusion area information includes the control area identifier and the coordinate sequence of the area boundary. Once consolidated, a low-altitude security situation assessment report is generated, which comprehensively reflects the intrusion situation and security status of the low-altitude target.

[0223] Step S160: Push the low-altitude safety situation assessment report to the regional safety command platform.

[0224] The generated low-altitude safety situation assessment report is sent to the regional security command platform via a pre-set communication protocol and transmission path. During transmission, encryption technology is used to protect the report content and prevent information leakage. Once the regional security command platform receives the report, relevant personnel can promptly monitor the low-altitude safety situation and take appropriate countermeasures.

[0225] Figure 2 A schematic diagram illustrates exemplary hardware and software components of a data processing system 100 for low-altitude safety situation analysis based on 5G base station towers, which can implement the concepts of the present invention, according to some embodiments of the present invention. For example, processor 120 can be used in data processing system 100 for low-altitude safety situation analysis based on 5G base station towers to perform the functions of the present invention.

[0226] For example, the data processing system 100 for low-altitude safety situation analysis based on 5G base station towers may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and storage media 140 in different forms, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the data processing system 100 for low-altitude safety situation analysis based on 5G base station towers may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present invention can be implemented according to these program instructions. The data processing system 100 for low-altitude safety situation analysis based on 5G base station towers also includes an I / O interface 150 between the computer and other input and output devices.

[0227] In addition, an embodiment of the present invention also provides a readable storage medium, in which computer-executable instructions are preset. When the processor executes the computer-executable instructions, the above-mentioned data processing method for low-altitude safety situation analysis based on 5G base station towers is implemented.

[0228] It should be noted that in order to simplify the description of the present invention and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present invention, multiple features are sometimes combined into one embodiment, figure or description thereof.

Claims

1. A data processing method for low-altitude safety situation analysis based on 5G base station towers, characterized in that: The method comprises: Obtaining original signal feature sequences collected from distributed 5G base station towers during a continuous monitoring period, wherein the original signal feature sequences include signal strength fluctuation parameters and signal arrival direction parameters of each base station; A dynamic baseline model is constructed based on the historical signal feature library of each 5G base station tower, and baseline comparison processing is performed on the original signal feature sequence to generate an abnormal signal feature set including a signal deviation parameter; Calling a pre-trained multi-base station collaborative recognition model to perform cross-base station correlation analysis on the abnormal signal feature set and base station spatial relationship data, and extracting a target signal correlation pattern with spatiotemporal consistency, wherein the target signal correlation pattern includes the signal transmission delay difference and signal strength attenuation gradient between base stations; According to the target signal association pattern and the base station geographic location distribution parameters, a triangulation positioning algorithm is used to deduce the real-time trajectory parameters of the low-altitude target, wherein the real-time trajectory parameters include a position coordinate sequence and a moving speed vector; The real-time trajectory parameters are spatially matched with the preset security control area data to generate a low-altitude security situation assessment report including the target intrusion risk level, and the low-altitude security situation assessment report is pushed to the regional security command platform.

2. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 1 is characterized in that: The method of constructing a dynamic baseline model based on the historical signal feature library of each 5G base station tower, performing baseline comparison processing on the original signal feature sequence, and generating an abnormal signal feature set including a signal deviation parameter includes: Extracting a historical signal feature sequence within a preset time period in the past from a historical signal feature library of each 5G base station tower, wherein the historical signal feature sequence includes a signal strength fluctuation parameter and a signal arrival direction parameter under a normal communication environment; Performing time segmentation processing on the historical signal feature sequence, dividing the historical data segments according to the same daily monitoring period, and calculating the statistical distribution range of the signal strength fluctuation parameter and the probability distribution characteristics of the signal arrival direction parameter within each monitoring period; Building a dynamic baseline model based on the statistical distribution range and probability distribution characteristics, the dynamic baseline model includes a signal strength benchmark interval and a signal arrival direction benchmark distribution for each time period; Comparing the signal strength fluctuation parameter in the original signal feature sequence with the signal strength reference interval of the corresponding time period in the dynamic baseline model, calculating the strength deviation value exceeding the reference interval, and generating a signal strength deviation; Comparing the signal arrival direction parameter in the original signal feature sequence with the signal arrival direction reference distribution of the corresponding period in the dynamic baseline model, calculating the direction probability density deviation value, and generating the signal direction deviation degree; Performing weighted fusion of the signal strength deviation and the signal direction deviation to generate a comprehensive signal deviation parameter, wherein the weight of the weighted fusion is determined based on the signal stability analysis results in the historical data; The original signal feature sequence fragments whose comprehensive signal deviation parameters exceed the preset threshold are screened out to generate an abnormal signal feature set containing the signal deviation parameters.

3. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 1 is characterized in that: The calling of the pre-trained multi-base station collaborative recognition model to perform cross-base station correlation analysis on the abnormal signal feature set and base station spatial relationship data, and extracting a target signal correlation pattern with spatiotemporal consistency, includes: Performing time alignment processing on the abnormal signal feature set, calibrating the time dimension of the abnormal signal feature segments of different base stations according to the monitoring period timestamp, and generating a time-aligned abnormal signal set; Call the base station spatial relationship database to obtain the geographic location parameters of each 5G base station tower, calculate the spatial relative azimuth of any two base stations, and generate a base station spatial orientation matrix. The geographic location parameters include longitude parameters, latitude parameters, and altitude parameters; Extracting the signal arrival direction parameter of each base station in the time-aligned abnormal signal set, calculating the direction deviation angle between the signal detection direction and the relative orientation of the base station in combination with the base station spatial orientation matrix, and generating a direction consistency parameter, which represents the degree of consistency of the detection directions of different base stations for the same target; Based on the directional consistency parameter, base station combinations whose directional consistency exceeds a preset threshold are screened out to generate a set of coordinated base station pairs, where each base station pair in the set of coordinated base station pairs includes two base station identifiers with spatial correlation and corresponding directional consistency parameters; For each base station pair in the set of coordinated base station pairs, extract the signal strength fluctuation parameter from the time-aligned abnormal signal set, calculate the signal strength difference between the two base stations within the same monitoring period, and generate the signal strength attenuation gradient in combination with the spatial distance parameter between the base stations, where the spatial distance parameter is calculated based on the base station geographic location parameter; Extracting timestamps of two base stations in the coordinated base station pair set receiving the same signal feature, calculating a timestamp difference, and generating a signal transmission delay difference between the base stations; Inputting the signal strength attenuation gradient and the signal transmission delay difference between base stations into the feature fusion layer of the multi-base station collaborative recognition model, performing spatiotemporal correlation modeling processing, and generating a cross-base station signal correlation vector; The pattern recognition layer of the multi-base station collaborative recognition model is called to perform spatiotemporal consistency verification on the cross-base station signal correlation vector, extract the signal pattern with continuous monitoring period correlation, and generate the target signal correlation pattern including the signal transmission delay difference and signal strength attenuation gradient between base stations.

4. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 3 is characterized in that: The step of extracting the signal arrival direction parameter of each base station in the time-aligned abnormal signal set, calculating the direction deviation angle between the signal detection direction and the relative direction of the base station in combination with the base station spatial orientation matrix, and generating a direction consistency parameter, wherein the direction consistency parameter represents the degree of consistency of the detection directions of different base stations for the same target, includes: Extracting signal arrival direction parameters of any two base stations in the same monitoring period from the time-aligned abnormal signal set, and recording them as a first base station signal direction parameter and a second base station signal direction parameter respectively; Extracting the spatial relative azimuth angles corresponding to the two base stations from the base station spatial azimuth matrix, and recording the relative azimuth angles as the theoretical azimuth angles between the base stations; Comparing the first base station signal direction parameter with a theoretical azimuth angle between base stations to calculate a first direction deviation angle, where the first direction deviation angle is an absolute value of a difference between the first base station signal direction parameter and the theoretical azimuth angle between base stations; Compare the second base station signal direction parameter with the reverse angle of the theoretical azimuth between base stations to calculate a second direction deviation angle, where the reverse angle is the angle value obtained by adding one hundred and eighty degrees to the theoretical azimuth between base stations; Performing arithmetic averaging on the first direction deviation angle and the second direction deviation angle to generate an average direction deviation angle; Calculating a direction consistency parameter according to the average direction deviation angle, wherein the direction consistency parameter is negatively correlated with the average direction deviation angle, and the smaller the average direction deviation angle, the larger the direction consistency parameter; Comparing the direction consistency parameter with a preset direction consistency threshold, and if the direction consistency parameter is greater than the direction consistency threshold, marking the base station pair as a potential cooperative base station pair; The direction consistency parameters of all potential coordinated base station pairs are normalized to generate direction consistency parameter values.

5. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 3 is characterized in that: For each base station pair in the set of coordinated base station pairs, extracting a signal strength fluctuation parameter from a time-aligned abnormal signal set, calculating a signal strength difference between two base stations within the same monitoring period, and generating a signal strength attenuation gradient in combination with a spatial distance parameter between the base stations, where the spatial distance parameter is calculated based on a geographic location parameter of the base stations, including: Selecting a base station pair from the set of coordinated base station pairs, denoted as a first base station and a second base station, and obtaining base station identifiers of the first base station and the second base station; Extracting a geographic location parameter of the first base station and a geographic location parameter of the second base station from the base station geographic location distribution parameters according to the base station identifier, the geographic location parameters including a longitude parameter, a latitude parameter, and an altitude parameter; Calculating a spatial distance parameter between the first base station and the second base station, where the spatial distance parameter is calculated by the square root of the sum of the squares of the longitude parameter difference, the latitude parameter difference, and the altitude parameter difference; Extracting a signal strength fluctuation parameter of the first base station in each monitoring period from the time-aligned abnormal signal set to generate a first base station signal strength sequence; Extracting a signal strength fluctuation parameter of the second base station in each monitoring period from the time-aligned abnormal signal set to generate a second base station signal strength sequence; Performing time dimension matching on the first base station signal strength sequence and the second base station signal strength sequence so that signal strength fluctuation parameters corresponding to the same monitoring period correspond one to one; Calculating the difference between the signal strength parameter of the first base station and the signal strength parameter of the second base station within the same monitoring period to generate a signal strength difference sequence; Dividing each difference in the signal strength difference sequence by a spatial distance parameter between the first base station and the second base station to generate a unit distance signal strength difference as a signal strength attenuation gradient; Performing sign processing on the signal strength attenuation gradient, if the first base station signal strength parameter is greater than the second base station signal strength parameter, the signal strength attenuation gradient is a positive value, otherwise it is a negative value; The signal strength attenuation gradient is associated with the corresponding monitoring period timestamp and stored to generate a signal strength attenuation gradient sequence containing the time stamp.

6. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 1 is characterized in that: The method of using a triangulation positioning algorithm to deduce real-time trajectory parameters of a low-altitude target based on the target signal association pattern and the base station geographic location distribution parameters includes: extracting a set of coordinated base station pairs, a signal transmission delay difference between base stations, and a signal strength attenuation gradient from the target signal association pattern; Extracting geographic location parameters of each base station in the cooperative base station pair set from the base station geographic location distribution parameters to generate a base station positioning coordinate set, wherein the geographic location parameters include a longitude parameter, a latitude parameter, and an altitude parameter; For each coordinated base station pair, the distance difference between the target and the two base stations is calculated based on the signal transmission delay difference between the base stations and the electromagnetic wave propagation speed parameters, and a distance difference parameter is generated; Constructing a hyperbola positioning equation based on the base station positioning coordinate set and the distance difference parameter, wherein the hyperbola positioning equation takes the geographic location parameters of the two base stations as the focus and the distance difference parameter as the real axis length; Solving the hyperbolic positioning equation to obtain the two-dimensional position coordinates of the low-altitude target in the current monitoring period, wherein the two-dimensional position coordinates include longitude coordinate parameters and latitude coordinate parameters; estimating the altitude parameter of the low-altitude target according to the signal strength attenuation gradient and the base station altitude parameter, and generating three-dimensional position coordinates by combining the two-dimensional position coordinates; Arrange the three-dimensional position coordinates of each period according to the time sequence of the monitoring period to generate a position coordinate sequence; Calculating the spatial distance between adjacent three-dimensional position coordinates in the position coordinate sequence, and generating a moving distance parameter in combination with a time interval parameter of a monitoring period; Calculating a moving direction angle according to a difference in longitude coordinate parameters and a difference in latitude coordinate parameters between the adjacent three-dimensional position coordinates, and generating a moving speed vector in combination with a moving distance parameter and a time interval parameter, wherein the moving speed vector includes a speed magnitude parameter and a speed direction angle parameter; The position coordinate sequence and the moving speed vector are associated and stored to generate real-time trajectory parameters, where each record of the real-time trajectory parameters includes a timestamp, three-dimensional position coordinates, and a moving speed vector.

7. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 6 is characterized in that: The constructing of a hyperbola positioning equation based on the base station positioning coordinate set and the distance difference parameter includes: Selecting a cooperative base station pair from the base station positioning coordinate set, denoted as a first focus and a second focus, where the geographic location parameters of the first focus are a first longitude parameter, a first latitude parameter, and a first altitude parameter, and the geographic location parameters of the second focus are a second longitude parameter, a second latitude parameter, and a second altitude parameter; Assume that the position coordinates of the low-altitude target are the target longitude parameter, target latitude parameter, and target altitude parameter, the distance from the target to the first focus is the first distance parameter, and the distance from the target to the second focus is the second distance parameter; Calculating a distance difference parameter based on an electromagnetic wave propagation speed parameter and a difference in signal transmission delay between base stations, wherein the distance difference parameter is equal to the first distance parameter minus the second distance parameter; According to the distance calculation formula, the first distance parameter is the spatial distance between the target position coordinates and the first focus geographic location parameter, and the second distance parameter is the spatial distance between the target position coordinates and the second focus geographic location parameter; Substituting the first distance parameter and the second distance parameter into the expression of the distance difference parameter, an equation including the target longitude parameter and the target latitude parameter is obtained; The altitude parameter is set as a constant, and the three-dimensional spatial problem is simplified to a two-dimensional plane problem, resulting in a hyperbola positioning equation containing only the target longitude parameter and the target latitude parameter. The standard form of the hyperbola positioning equation is the trajectory of points on the plane whose distance difference to the two foci is a constant, where the constant is the distance difference parameter, and the distance between the two foci is the focal length parameter, which is calculated based on the geographic location parameters of the first and second foci. The hyperbola positioning equation is sorted out by moving the terms containing the target longitude parameter and the target latitude parameter to the left side of the equation and the constant term to the right side of the equation to generate a standard form of the hyperbola positioning equation.

8. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 6 is characterized in that: The calculating the spatial distance between adjacent three-dimensional position coordinates in the position coordinate sequence and generating a moving distance parameter in combination with a time interval parameter of a monitoring period includes: Selecting two adjacent three-dimensional position coordinates from the position coordinate sequence, recording them as a first position coordinate and a second position coordinate, the first position coordinate corresponding to a first timestamp, and the second position coordinate corresponding to a second timestamp; Extracting the longitude parameter, latitude parameter, and altitude parameter of the first position coordinate, which are recorded as the first longitude, the first latitude, and the first altitude, respectively; Extracting the longitude parameter, latitude parameter, and altitude parameter of the second position coordinates, which are recorded as the second longitude, the second latitude, and the second altitude, respectively; Calculating a longitude parameter difference, where the longitude parameter difference is the second longitude minus the first longitude; Calculating a latitude parameter difference, where the latitude parameter difference is the second latitude minus the first latitude; Calculating an altitude parameter difference, where the altitude parameter difference is the second altitude minus the first altitude; Squaring the longitude parameter difference, the latitude parameter difference and the altitude parameter difference respectively to generate a longitude square difference parameter, a latitude square difference parameter and an altitude square difference parameter; performing a sum operation on the longitude square difference parameter, the latitude square difference parameter, and the altitude square difference parameter to generate a total square difference parameter; Performing a square root operation on the total square difference parameter to generate a spatial distance parameter between the first position coordinate and the second position coordinate; Calculate the difference between the second timestamp and the first timestamp to generate a time interval parameter; The spatial distance parameter is used as a moving distance parameter, associated with a time interval parameter and a corresponding timestamp and stored to generate a moving distance sequence.

9. The data processing method for low-altitude safety situation analysis based on 5G base station towers according to claim 1 is characterized in that: The real-time trajectory parameters are spatially matched with the preset security control area data to generate a low-altitude security situation assessment report including the target intrusion risk level, including: Acquire preset security control area data, wherein the preset security control area data includes area identifiers, area boundary coordinate sequences, and corresponding risk level thresholds of multiple control areas; Parsing the position coordinate sequence in the real-time trajectory parameters, extracting the three-dimensional position coordinates of each monitoring period, and generating a coordinate set to be evaluated; For each three-dimensional position coordinate in the coordinate set to be evaluated, determine the spatial relationship with each control area in the preset security control area data; The spatial relationship judgment includes: Compare the longitude and latitude parameters of the three-dimensional position coordinates with the regional boundary coordinate sequence of the control area to determine whether the three-dimensional position coordinates are within the two-dimensional plane range of the control area; If it is within the two-dimensional plane range, the altitude parameter of the three-dimensional position coordinate is further compared with the altitude limit range of the control area to determine whether it is within the altitude limit range; If the 3D position coordinates are within both the 2D plane range and the altitude limit, the 3D position coordinates are marked as regional intrusion coordinates, and the corresponding control area identifier and intrusion timestamp are recorded; According to the control area identifier corresponding to the regional intrusion coordinates, the risk level threshold of the control area is extracted from the preset security control area data; Comparing the moving speed vector in the real-time trajectory parameter with the risk level threshold, and if the speed magnitude parameter of the moving speed vector exceeds the speed threshold in the risk level threshold, raising the risk level; Count the number of regional intrusion coordinates and duration in the same control area, and generate the target intrusion risk level based on the risk level threshold; The target intrusion risk level, regional intrusion coordinates, intrusion timestamp and corresponding real-time trajectory parameters are integrated to generate a low-altitude safety situation assessment report, which includes situation assessment time, target identification, intrusion area information, risk level and real-time trajectory data.

10. A data processing system for low-altitude safety situation analysis based on 5G base station towers, characterized in that: It includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the data processing method for low-altitude safety situation analysis based on 5G base station towers as described in any one of claims 1 to 9.

Images