Real-time behavior trajectory big data analysis and processing method based on Beidou positioning

Abstract

The present invention discloses a real-time behavior trajectory big data analysis and processing method based on Beidou positioning. The present invention relates to the field of trajectory data analysis technology, and solves the technical problem that the positioning of a vehicle under different circumstances is biased, further affecting the subsequent control of the vehicle and affecting the experimental results. The present invention analyzes the real-time trajectory of the vehicle according to Beidou positioning coordinates and the actual position of the vehicle to determine whether there is a positioning error. For the situation where the positioning is abnormal, the real-time trajectory is segmented and the real-time trajectory of different segments is analyzed to determine the specific cause of the deviation. Then the deviation is corrected according to the specific cause to improve the accuracy of the overall positioning. Secondly, the overall path of the vehicle is predicted according to the obtained correction information, and displayed to the corresponding control personnel, so that the control personnel can make timely adjustments to the vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of trajectory data analysis, and in particular to a real-time behavior trajectory big data analysis and processing method based on Beidou positioning. Background Art

[0002] With the popularization of vehicle-mounted positioning terminals and the installation of data collection equipment on the road, it has become possible to manage different types of vehicles in the city and refine the optimization methods of traffic. The trajectory data of vehicle-mounted positioning is a spatial point with attached time and motion characteristics, and the trajectory data of road data collection equipment is a fixed spatial point with attached time and graphic characteristics. The combination of the two types of information can basically describe all the states of the vehicle, and can analyze and infer a large amount of relevant behavior information and personnel information.

[0003] According to the publication number CN117975178B, a taxi trajectory data analysis method based on big data analysis is disclosed, which relates to the field of big data analysis technology, including collecting trajectory data of taxis, and mapping trajectory points onto a two-dimensional plane to form a trajectory image; applying an improved convolutional network to process the trajectory image, extracting spatial features of the trajectory, and extracting temporal features of the trajectory based on an LSTM network; fusing the spatial features and the temporal features, and establishing a destination prediction model; evaluating and optimizing the trained destination prediction model, and predicting the destination of the taxi based on the optimized destination prediction model.

[0004] The above patent can help taxi companies and drivers to dispatch vehicles more effectively and reduce empty driving rate by accurately predicting the destination of taxis, and help adjust traffic lights, plan detour routes, and adjust traffic control measures when necessary in real time, thereby effectively alleviating traffic congestion. However, some existing trajectory analysis systems have deviations in the positioning of vehicles under different circumstances when used, which further leads to inaccurate positioning of the vehicle, thereby affecting the control personnel of the vehicle, and further affecting the overall experimental results. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a real-time behavior trajectory big data analysis and processing method based on Beidou positioning, which solves the problem that the positioning of the vehicle under different circumstances is biased, further affecting the subsequent control of the vehicle and affecting the experimental results.

[0006] To achieve the above objectives, the present invention is implemented by the following technical scheme: a real-time behavior trajectory big data analysis and processing method based on Beidou positioning, the method specifically comprises the following steps:

[0007] Step 1: Acquire the real-time trajectory of the scheduled vehicle, and judge the accuracy of the real-time trajectory according to the actual position of the scheduled vehicle, and generate a judgment result, and the judgment result includes a normal trajectory result and an abnormal trajectory result;

[0008] Step 2: Analyze the generated trajectory anomaly results by segmenting the real-time behavior trajectory to obtain real-time trajectory segments, and analyze the trajectory points corresponding to the real-time trajectory segments to obtain the environmental impact difference;

[0009] Step 3: Processing the obtained real-time trajectory segment to be analyzed, performing specific abnormality analysis on the abnormal trajectory points in the real-time trajectory segment to be analyzed, and generating correction information in combination with normal trajectory points;

[0010] Step 4: predicting the real-time trajectory of the scheduled vehicle based on the obtained correction information, predicting the driving trajectory based on the actual terrain, and drawing the obtained driving trajectory to generate trajectory prediction information;

[0011] Step 5: Display the obtained trajectory prediction information to the corresponding monitoring personnel.

[0012] As a further solution of the present invention: the specific method of generating the judgment result in step 1 is:

[0013] Determine the scheduled vehicle and obtain the real-time moving trajectory of the scheduled vehicle, then obtain multiple trajectory points on the real-time moving trajectory, and obtain the coordinates corresponding to the trajectory points, and at the same time obtain the actual coordinates of the scheduled vehicle corresponding to the trajectory point n, and compare the trajectory point coordinates with the actual coordinates of the scheduled vehicle, calculate the coordinate difference between the trajectory coordinates and the actual coordinates of the scheduled vehicle, and then compare the coordinate difference with the preset value.

[0014] As a further solution of the present invention: the specific method of comparing the coordinate difference with the preset value in step 1 is:

[0015] When the coordinate difference is greater than the preset value, the corresponding trajectory point is marked as an abnormal trajectory point. When the coordinate difference is less than the preset value, the corresponding trajectory point is marked as a normal trajectory point. Then all abnormal trajectory points are obtained, and the number ratio of abnormal trajectory points is calculated as the abnormal ratio, and the abnormal ratio is compared with the threshold.

[0016] If the anomaly ratio is greater than the threshold, an abnormal trajectory result is generated. Otherwise, if the anomaly ratio is less than the threshold, a normal trajectory result is generated.

[0017] As a further solution of the present invention: the specific method of analyzing the abnormal trajectory results in step 2 is:

[0018] The real-time behavior trajectory is obtained, and the motion environment corresponding to the real-time behavior trajectory is obtained, and the real-time behavior trajectory is segmented with the motion environment as the segmentation point to obtain the real-time trajectory segment denoted as a, and a=1, 2, ..., b, where b represents the number of real-time trajectory segments, and then the trajectory point corresponding to the real-time trajectory segment a is obtained, and the abnormal situation of the trajectory point is judged at the same time.

[0019] As a further solution of the present invention: the method for determining the abnormal situation of the trajectory point in step 2 is:

[0020] Take any real-time trajectory segment as the analysis object, and analyze the trajectory points in the analysis object. If the trajectory points in the analysis object include normal trajectory points and abnormal trajectory points, the analysis object is recorded as the real-time trajectory segment to be analyzed. If the trajectory points in the analysis object are all abnormal trajectory points, an environmental impact analysis signal is generated and analyzed.

[0021] As a further solution of the present invention: the specific method of analyzing the environmental impact analysis signal in step 2 is:

[0022] All abnormal trajectory points in the analysis object are obtained, and the differences between the abnormal trajectory points and the actual coordinates are calculated in turn. At the same time, all the calculated differences are averaged to obtain the difference mean, and then the difference mean is calculated with the difference mean under normal driving conditions to obtain the impact difference.

[0023] As a further solution of the present invention: the specific method of processing the real-time trajectory segment to be analyzed in step 3 is:

[0024] Take any group of real-time trajectory segments to be analyzed as the analysis target, then mark the abnormal trajectory points in the analysis target as o, and o=1, 2, ..., p, mark the normal trajectory points as n, and n=1, 2, ..., m, where p and m represent the number of abnormal trajectory points and normal trajectory points respectively, and at the same time, obtain the positioning environment corresponding to the abnormal trajectory point o and the normal trajectory point n, record them as abnormal positioning environment and normal positioning environment respectively, and compare the abnormal positioning environment with the normal positioning environment to obtain the positioning environment to be analyzed, and at the same time, analyze and calculate the environmental impact difference between the positioning environment to be analyzed and the positioning environment of the normal real-time trajectory segment, and generate correction information according to the environmental impact difference.

[0025] As a further solution of the present invention: the specific method of generating the trajectory prediction information in step 4 is:

[0026] Acquire the driving information of the scheduled vehicle, and at the same time acquire the corresponding actual terrain, and correct the actual terrain according to the correction information, then acquire the driving direction in the driving information of the scheduled vehicle, acquire the driving route corresponding to the actual terrain based on the driving direction and generate a driving trajectory, and at the same time generate trajectory prediction information according to the driving trajectory.

[0027] The present invention provides a real-time behavior trajectory big data analysis and processing method based on Beidou positioning. Compared with the prior art, it has the following beneficial effects:

[0028] The present invention analyzes the real-time trajectory of the vehicle according to the Beidou positioning coordinates and the actual position of the vehicle to determine whether there is a positioning error. For abnormal positioning, the real-time trajectory is segmented and the real-time trajectories of different segments are analyzed to determine the specific cause of the deviation. The deviation is then corrected according to the specific cause to improve the accuracy of the overall positioning. Secondly, the overall path of the vehicle is predicted according to the obtained correction information and displayed to the corresponding control personnel, so that the control personnel can make timely adjustments to the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a method diagram of the present invention;

[0030] Figure 2 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] See also Figure 1 and Figure 2 The present application provides a real-time behavior trajectory big data analysis and processing method based on Beidou positioning, which specifically includes the following steps:

[0033] Step 1: The real-time trajectory of the scheduled vehicle is obtained, and the accuracy of the real-time trajectory is judged according to the actual position of the scheduled vehicle, and a judgment result is generated at the same time, and the judgment result includes a normal trajectory result and an abnormal trajectory result. The specific method of generating the judgment result is:

[0034] The scheduled vehicle is determined, and the real-time moving track of the scheduled vehicle is obtained by using positioning technologies such as Beidou or GPS+camera. Then, multiple track points on the real-time moving track are obtained, and the coordinates corresponding to the track points are obtained. Specifically, the multiple track points are labeled as n, and n=1, 2, ..., m, where m represents the number of track points n, and the track points are selected randomly. The coordinates corresponding to the track point n are further obtained, and the coordinates obtained here are geographic coordinates. At the same time, the actual coordinates of the scheduled vehicle corresponding to the track point n are obtained, and the actual coordinates here represent the actual geographic coordinates corresponding to the track point passed by the vehicle during driving. The coordinates of the trajectory point are compared with the actual coordinates of the scheduled vehicle, and the comparison and judgment here is judged by calculating the difference between the coordinates. The coordinate difference between the trajectory coordinates and the actual coordinates of the scheduled vehicle is calculated, and the geographical coordinates are expressed in longitude and latitude. For example, the geographical coordinates of trajectory point 1 are (118.765432°E, 32.045678°N), and when the scheduled vehicle travels to the trajectory point, the actual geographical coordinates actually measured are (118.765428°E, 32.045680°N). Then, the judgment is made by calculating the difference between the coordinates of the trajectory point and the actual coordinates of the scheduled vehicle. For example, for the above-mentioned trajectory point 1, the longitude difference is |118.765432-118.765428|=0.000004°E, and the latitude difference is |32.045678-32.045680|=0.000002°N. Then, the coordinate difference is compared with the preset value, and the specific value of the preset value is set by the operator. At the same time, the value of the preset value is a range value. For example, the preset value can be set to a longitude difference within ±0.00001°E and a latitude difference within ±0.00001°N.

[0035] When the coordinate difference is greater than the preset value, it means that the deviation between the trajectory point coordinates and the actual coordinates is too large, and the corresponding trajectory point is marked as an abnormal trajectory point. When the coordinate difference is less than the preset value, it means that the deviation between the trajectory point coordinates and the actual coordinates is within the allowable range, and the corresponding trajectory point is marked as a normal trajectory point. Then all abnormal trajectory points are obtained, and the number of abnormal trajectory points is calculated as the abnormal proportion. For example, there are 50 trajectory points in total, of which 10 are abnormal trajectory points, then the abnormal proportion is 10÷50=0.2. At the same time, the abnormal proportion is compared with the threshold, where the specific value of the threshold is set by the operator. If the abnormal proportion is greater than the threshold, it means that the number of abnormal trajectory points is large, and the trajectory abnormal result is generated at the same time. On the contrary, if the abnormal proportion is less than the threshold, it means that the number of abnormal trajectory points is small, and the trajectory normal result is generated at the same time. Assuming that the operator sets the threshold to 0.15. If the abnormal proportion is greater than the threshold, it means that the number of abnormal trajectory points is large, and the trajectory abnormal result should be generated at this time. As in the above example, the abnormal proportion is 0.2, which is greater than the threshold 0.15, indicating that there are many abnormal situations in the trajectory.

[0036] Step 2: Analyze the generated trajectory anomaly results by segmenting the real-time behavior trajectory to obtain real-time trajectory segments, and analyze the trajectory points corresponding to the real-time trajectory segments to obtain the environmental impact difference. The specific method of generating the environmental impact difference is:

[0037] Acquire the real-time behavior trajectory and the motion environment corresponding to the real-time behavior trajectory. The motion environment here may include different road types (such as expressways, urban main roads, rural roads, etc.), different traffic conditions (smooth, congested, construction, etc.) and different geographical areas (mountainous areas, plains, urban areas, etc.), and segment the real-time behavior trajectory using the motion environment as a segmentation point to obtain real-time trajectory segments denoted as a, and a=1, 2, ..., b, where b represents the number of real-time trajectory segments, then acquire the trajectory points corresponding to the real-time trajectory segment a, and judge the abnormality of the trajectory points at the same time;

[0038] Get any real-time trajectory segment as the analysis object, and then analyze the trajectory points in the analysis object. If the trajectory points in the analysis object include normal trajectory points and abnormal trajectory points, for example, there are 5 trajectory points in the analysis object, and there are two abnormal trajectory points among the 5 trajectory points, further indicating that the motion environment will affect the overall positioning, then it means that the motion environment corresponding to the analysis object has no effect on the overall positioning, and at the same time mark the analysis object as a real-time trajectory segment to be analyzed. If the trajectory points in the analysis object are all abnormal trajectory points, for example, there are 3 trajectory points in the analysis object, and the corresponding 3 trajectory points are all abnormal trajectory points, then in this case it also means that the motion environment affects the positioning, then it means that the motion environment corresponding to the analysis object affects the overall positioning, further analyze the motion environment corresponding to the analysis object, and generate an environmental impact analysis signal. If the trajectory points in the analysis object are all normal trajectory points, then the analysis object is not analyzed.

[0039] Processing the generated environmental impact analysis signal, obtaining all abnormal trajectory points in the analysis object, and calculating the difference between the abnormal trajectory points and the actual coordinates in turn, and averaging all the calculated differences to obtain the difference mean, and then performing difference calculation between the difference mean and the difference mean under normal driving state to obtain the impact difference;

[0040] By analogy, all real-time trajectory segments are analyzed to obtain corresponding impact differences, and real-time trajectory segments without impact are not processed here.

[0041] For example, there are three abnormal trajectory points, whose coordinates are (118.765432°E, 32.045678°N), (118.765435°E, 32.045682°N), and (118.765438°E, 32.045685°N). The corresponding actual coordinates are (118.765428°E, 32.045680°N), (118.765425°E, 32.045684°N), and (118.765422°E, 32.045687°N). The longitude difference between the first abnormal trajectory point and the actual coordinates is 0.000004°E, and the latitude difference is 0.000002°N; the longitude difference between the second abnormal trajectory point is 0.00001°E, and the latitude difference is 0.000002°N; the longitude difference between the third abnormal trajectory point is 0.000016°E, and the latitude difference is 0.000002°N.

[0042] Next, all the calculated differences are averaged to obtain the mean of the differences. In the above example, the total longitude difference is 0.000004°E+0.00001°E+0.000016°E=0.00003°E, and the total latitude difference is 0.000002°N+0.000002°N+0.000002°N=0.000006°N. Assuming there are three abnormal trajectory points, the mean longitude difference is 0.00003°E÷3=0.00001°E, and the mean latitude difference is 0.000006°N÷3=0.000002°N. Assuming that the mean longitude difference under normal driving conditions is 0.000005°E, and the mean latitude difference is 0.000001°N, the difference between the two is further calculated to obtain an impact difference of 0.000001.

[0043] Step 3: Process the obtained real-time trajectory segment to be analyzed, perform specific abnormal analysis on the abnormal trajectory points in the real-time trajectory segment to be analyzed, and generate correction information in combination with normal trajectory points. The specific method of generating the correction information is as follows:

[0044] Take any group of real-time trajectory segments to be analyzed as the analysis target, then mark the abnormal trajectory points in the analysis target as o, and o=1, 2, ..., p, mark the normal trajectory points as n, and n=1, 2, ..., m, where p and m represent the number of abnormal trajectory points and normal trajectory points respectively, and at the same time obtain the positioning environment corresponding to the abnormal trajectory point o and the normal trajectory point n, and record them as abnormal positioning environment and normal positioning environment respectively, and the positioning environment here represents the specific sampling conditions corresponding to the sampling of the abnormal trajectory points, such as signal transmission speed, signal strength and signal The abnormal positioning environment is compared with the normal positioning environment to obtain the positioning environment to be analyzed. The positioning environment to be analyzed here means the positioning environment that is different from the normal positioning environment. For example, the signal transmission speed of an abnormal trajectory point o1 is 200kbps, the signal strength is -80dBm, and the signal delay is 500ms; while the signal transmission speed of a normal trajectory point is 500kbps, the signal strength is -60dBm, and the signal delay is 200ms. By comparison, it is found that the signal strength is less than -70dBm and the signal delay is greater than 3 The positioning environment of 00ms is the positioning environment to be analyzed, and the positioning environment to be analyzed and the positioning environment of the normal real-time trajectory segment are analyzed and calculated to obtain the difference in environmental impact, and correction information is generated according to the difference in environmental impact. The specific calculation method here is based on the big data algorithm for analysis and calculation. The specific calculation method is obtained by numerically quantifying the environment and calculating the difference in quantified values ​​of different environments. For example, the signal strength in the positioning environment is quantified to obtain the signal strength value, and the corresponding signal delay value and signal transmission speed value are obtained in the same way. For example, the signal strength in the positioning environment is quantified to obtain the signal strength value. Assuming that the signal strength quantization value of the normal positioning environment is 80, the signal strength quantization value of the positioning environment to be analyzed is 60, and the difference between the two is 20. Similarly, the corresponding signal delay value and signal transmission speed value can be obtained for similar calculations. If the signal delay quantization value in the normal positioning environment is 100, the signal delay quantization value in the positioning environment to be analyzed is 150, and the difference is 50; the signal transmission speed quantization value in the normal positioning environment is 400, and the signal transmission speed quantization value in the positioning environment to be analyzed is 300, and the difference is 100.

[0045] Step 4: Predict the real-time trajectory of the scheduled vehicle based on the obtained correction information, and predict the driving trajectory based on the actual terrain. At the same time, draw the obtained driving trajectory to generate trajectory prediction information. The specific method of generating the trajectory prediction information is as follows:

[0046] Acquire the driving information of the scheduled vehicle, and the driving information here includes: driving direction, driving speed and driving environment. At the same time, obtain the corresponding actual terrain according to Beidou positioning, and correct the actual terrain according to the correction information. Then obtain the driving direction in the driving information of the scheduled vehicle, obtain the driving route corresponding to the actual terrain based on the driving direction and generate a driving trajectory, and generate trajectory prediction information according to the driving trajectory.

[0047] Assume that a scheduled vehicle is traveling. The driving information of the vehicle is obtained through sensors and positioning devices on the vehicle.

[0048] The driving direction is due east. The driving speed is 60 kilometers per hour. The driving environment is sunny and the road is relatively flat with moderate traffic volume.

[0049] At the same time, the Beidou positioning system is used to obtain the corresponding actual terrain. Assuming that the actual terrain of the area shows some small hills and a river, according to the pre-set correction information, for example, it is known that there is a newly built bridge in the area that can cross the river, the actual terrain is corrected to remove the obstruction of the river to the driving route.

[0050] Next, after obtaining that the scheduled vehicle's driving direction is due east, the corresponding driving route is searched in the corrected actual terrain based on this direction. If there is a highway connecting two cities in the due east direction and the vehicle's current position is near this highway, then this highway is determined as the driving route and a driving trajectory is generated. Assuming that the vehicle's current position is the coordinate (119.56789°E, 30.45678°N), the vehicle's position change in the future is predicted based on the driving route and driving speed, thereby generating trajectory prediction information. For example, at the current speed, the vehicle may reach the coordinate (119.61234°E, 30.47890°N) in 10 minutes.

[0051] Step 5: Display the obtained trajectory prediction information to the corresponding monitoring personnel.

[0052] Some of the data in the above formulas are numerically calculated by removing their dimensions. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0053] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A real-time behavior trajectory big data analysis and processing method based on Beidou positioning, characterized in that: The method specifically comprises the following steps: Step 1: Acquire the real-time trajectory of the scheduled vehicle, and judge the accuracy of the real-time trajectory according to the actual position of the scheduled vehicle, and generate a judgment result, and the judgment result includes a normal trajectory result and an abnormal trajectory result; Step 2: Analyze the generated trajectory anomaly results, divide the real-time behavior trajectory into real-time trajectory segments, and analyze the trajectory points corresponding to the real-time trajectory segments to obtain the environmental impact difference. The specific processing method is as follows: Taking any real-time trajectory segment as the analysis object, and analyzing the trajectory points in the analysis object, if the trajectory points in the analysis object include normal trajectory points and abnormal trajectory points, the analysis object is recorded as the real-time trajectory segment to be analyzed, if the trajectory points in the analysis object are all abnormal trajectory points, then generating an environmental impact analysis signal, and analyzing the environmental impact analysis signal; Obtain all abnormal trajectory points in the analysis object, and calculate the difference between the abnormal trajectory points and the actual coordinates in turn, and then perform mean calculation on all the calculated differences to obtain the mean of the differences, and then perform difference calculation on the mean of the differences and the mean of the differences under the normal driving state to obtain the impact difference; Step 3: Processing the obtained real-time trajectory segment to be analyzed, performing specific abnormality analysis on the abnormal trajectory points in the real-time trajectory segment to be analyzed, and generating correction information in combination with normal trajectory points; Step 4: predicting the real-time trajectory of the scheduled vehicle based on the obtained correction information, predicting the driving trajectory based on the actual terrain, and drawing the obtained driving trajectory to generate trajectory prediction information; Step 5: Display the obtained trajectory prediction information to the corresponding monitoring personnel.

2. The method for analyzing and processing real-time behavior trajectory big data based on Beidou positioning according to claim 1 is characterized in that: The specific method of generating the judgment result in step 1 is: Determine the scheduled vehicle and obtain the real-time moving trajectory of the scheduled vehicle, then obtain multiple trajectory points on the real-time moving trajectory, and obtain the coordinates corresponding to the trajectory points, and at the same time obtain the actual coordinates of the scheduled vehicle corresponding to the trajectory point n, and compare the trajectory point coordinates with the actual coordinates of the scheduled vehicle, calculate the coordinate difference between the trajectory coordinates and the actual coordinates of the scheduled vehicle, and then compare the coordinate difference with the preset value.

3. The method for analyzing and processing real-time trajectory big data based on Beidou positioning according to claim 2 is characterized in that: The specific method of comparing the coordinate difference with the preset value in step 1 is: When the coordinate difference is greater than the preset value, the corresponding trajectory point is marked as an abnormal trajectory point. When the coordinate difference is less than the preset value, the corresponding trajectory point is marked as a normal trajectory point. Then all abnormal trajectory points are obtained, and the number ratio of abnormal trajectory points is calculated as the abnormal ratio, and the abnormal ratio is compared with the threshold. If the anomaly ratio is greater than the threshold, an abnormal trajectory result is generated. Otherwise, if the anomaly ratio is less than the threshold, a normal trajectory result is generated.

4. The method for analyzing and processing real-time behavior trajectory big data based on Beidou positioning according to claim 1 is characterized in that: The specific method of analyzing the abnormal trajectory results in step 2 is: The real-time behavior trajectory is obtained, and the motion environment corresponding to the real-time behavior trajectory is obtained, and the real-time behavior trajectory is segmented with the motion environment as the segmentation point to obtain the real-time trajectory segment denoted as a, and a=1, 2, ..., b, where b represents the number of real-time trajectory segments, and then the trajectory point corresponding to the real-time trajectory segment a is obtained, and the abnormal situation of the trajectory point is judged at the same time.

5. The method for analyzing and processing real-time trajectory big data based on Beidou positioning according to claim 1 is characterized in that: The specific method of processing the real-time trajectory segment to be analyzed in step 3 is: Take any group of real-time trajectory segments to be analyzed as the analysis target, then mark the abnormal trajectory points in the analysis target as o, and o=1, 2, ..., p, mark the normal trajectory points as n, and n=1, 2, ..., m, where p and m represent the number of abnormal trajectory points and normal trajectory points respectively, and at the same time, obtain the positioning environment corresponding to the abnormal trajectory point o and the normal trajectory point n, record them as abnormal positioning environment and normal positioning environment respectively, and compare the abnormal positioning environment with the normal positioning environment to obtain the positioning environment to be analyzed, and at the same time, analyze and calculate the environmental impact difference between the positioning environment to be analyzed and the positioning environment of the normal real-time trajectory segment, and generate correction information according to the environmental impact difference.

6. The method for analyzing and processing real-time trajectory big data based on Beidou positioning according to claim 1, characterized in that: The specific method of generating trajectory prediction information in step 4 is: Acquire the driving information of the scheduled vehicle, and at the same time acquire the corresponding actual terrain, and correct the actual terrain according to the correction information, then acquire the driving direction in the driving information of the scheduled vehicle, acquire the driving route corresponding to the actual terrain based on the driving direction and generate a driving trajectory, and at the same time generate trajectory prediction information according to the driving trajectory.

Images