A method and system for filtering abnormal trajectory data of a cross-regional muck truck

Abstract

The invention provides a method and system for filtering abnormal trajectory data of a muck truck traveling across regions, and relates to the technical field of muck truck trajectory data. The abnormal trajectory data filtering method comprises the following steps: S0: forming a target region chain according to a preset driving route of the muck truck; S1: regularly obtaining a trajectory data set generated by the muck truck traveling along the preset driving route; S2: sequentially connecting the region blocks where the vehicle trajectory points are located according to the uploading time point in the trajectory data set to form a trajectory region chain; S3: performing a cross-region determination, and when it is determined that a cross-region phenomenon occurs, obtaining the vehicle trajectory information causing the cross-region phenomenon and transferring to S4; S4: performing an abnormal determination on two consecutive average speed values ​​between the vehicle trajectory information causing the cross-region phenomenon and the vehicle trajectory information before and after it according to the variation range of the average speed value, and if it is determined that the variation range of the two consecutive average speed values ​​is abnormal, filtering the vehicle trajectory information causing the cross-region phenomenon in the trajectory data set.

Description

Technical Field

[0001] The present invention relates to the technical field of track data of a muck truck, and in particular to a method and system for filtering abnormal track data of a muck truck traveling across regions. Background Art

[0002] In modern urban construction and maintenance, muck trucks play an important role. Muck trucks are responsible for transporting and disposing of construction waste, engineering slag and other transport items. In actual application, muck trucks generally transport items in one administrative area to another administrative area for disposal.

[0003] When a dump truck transports construction waste, engineering debris and other items from one administrative region to another administrative region for disposal, it can be determined that the dump truck has crossed regions based on the two continuous trajectory data located by the GPS device in the dump truck. However, due to the noise of the Internet of Things system, transmission anomalies, system anomalies and other reasons, the GPS monitoring of the dump truck may have many abnormal points and trajectory deviation, causing the trajectory data located at a certain point in time to shift to another administrative region, resulting in a false cross-region phenomenon. At present, there is no processing of the abnormal trajectory data caused by the false cross-region phenomenon to avoid inaccurate supervision of the transportation process of the dump truck by staff. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for filtering abnormal trajectory data of a muck truck traveling across regions, which mainly uses the trajectory data set of the muck truck to judge whether it has a cross-region phenomenon. When a cross-region phenomenon occurs, the authenticity of the cross-region phenomenon is determined by continuous average speed values. Therefore, the abnormal trajectory data can be filtered to avoid inaccurate supervision of the transportation process of the muck truck by staff.

[0005] In order to solve the above technical problems, the present invention adopts the following solutions:

[0006] A method for filtering abnormal trajectory data of a muck truck traveling across regions, the method specifically comprising the following steps:

[0007] S0: Obtain a map divided into multiple area blocks, map the preset driving route of the muck truck on the map, and connect different area blocks in sequence along the preset driving route to form a target area chain;

[0008] S1: Regularly obtain the trajectory data set generated by the muck truck driving along the preset driving route;

[0009] The trajectory data set includes a plurality of vehicle trajectory information uploaded by the GPS positioning device in the muck truck, and the vehicle trajectory information includes the vehicle trajectory point and the upload time point;

[0010] S2: Map the vehicle trajectory points in the trajectory data set to the regional blocks, and connect the regional blocks where the vehicle trajectory points are located in sequence according to the upload time point to form a trajectory regional chain;

[0011] S3: performing cross-region determination on the area blocks where the vehicle trajectory points in the trajectory area chain are located in turn according to the target area chain. When it is determined that a cross-region phenomenon occurs, obtaining the vehicle trajectory information causing the cross-region phenomenon, and proceeding to S4;

[0012] S4: Calculate the average speed value between two consecutive vehicle trajectory information according to the trajectory data set, and make an abnormality determination on the two consecutive average speed values ​​between the vehicle trajectory information causing the cross-zone phenomenon and the vehicle trajectory information before and after it according to the variation range of the average speed value. If it is determined that the variation range of the two consecutive average speed values ​​is abnormal, filter the vehicle trajectory information causing the cross-zone phenomenon in the trajectory data set.

[0013] Furthermore, the target area chain is used to represent the area block sequence of the preset driving route passing through the area blocks in sequence, and then two consecutive area blocks in the target area chain are different area blocks;

[0014] The trajectory region chain is used to indicate that the region blocks where the vehicle trajectory points in the trajectory data set are located are sequentially sorted according to their respective upload time points, and two consecutive region blocks in the trajectory region chain are the same region blocks or different region blocks.

[0015] Furthermore, in S3, the cross-region determination is specifically as follows:

[0016] The area block where the current vehicle trajectory point is located in the trajectory area chain is compared with the area block where the next vehicle trajectory point is located. If the area blocks are different, a to-be-determined area block sequence is established according to the area block sequence of the current vehicle trajectory point and the area block where the next vehicle trajectory point is located, and the area block sequence contained in the target area chain is matched with the to-be-determined area block sequence. If the match is successful, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block where the next vehicle trajectory point is located is used as the vehicle trajectory information causing the cross-area phenomenon.

[0017] Furthermore, in S3, the cross-region determination is specifically as follows:

[0018] Compare the area block where the current vehicle trajectory point is located with the area block where the next vehicle trajectory point is located in the trajectory area chain. If the area blocks are different, the area block where the next vehicle trajectory point is located is used as the area block to be confirmed;

[0019] Then compare the area block to be confirmed with the area block where the next vehicle trajectory point is located after the area block to be confirmed. If the area blocks are different, establish an area block sequence to be determined based on the area block where the current vehicle trajectory point is located, the area block to be confirmed, and the area block where the next vehicle trajectory point is located after the area block to be confirmed. Match the area block sequence to be determined with the target area chain for similarity. If they are not similar, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block to be confirmed is used as the vehicle trajectory information causing the cross-area phenomenon.

[0020] Furthermore, in S1, the trajectory data set is composed of vehicle trajectory information arranged in sequence according to respective upload time points, and the vehicle trajectory points in the vehicle trajectory information are the latitude and longitude of the vehicle located by the GPS positioning device in the muck truck.

[0021] Furthermore, the S4 specifically includes the following steps:

[0022] S41: sequentially calculating the average speed value between two consecutive vehicle trajectory information in the trajectory data set;

[0023] S42: Count all average speed values ​​in the trajectory data set, and perform mean difference calculation on all average speed values ​​to obtain the mean and standard deviation corresponding to each average speed value;

[0024] S43: traverse all average speed values ​​in the trajectory data set in turn, calculate the difference between each average speed value and the mean, and determine whether the difference is greater than a preset multiple of the standard deviation. If so, determine that the average speed value is abnormal data;

[0025] S44: When two consecutive average speed values ​​are both abnormal data, it is determined that the change range of the two consecutive average speed values ​​is abnormal, and the vehicle trajectory information causing the cross-zone phenomenon is filtered out in the trajectory data set.

[0026] Furthermore, in S41, the specific process of calculating the average speed value between two consecutive vehicle trajectory points is as follows:

[0027] According to the arrangement order of the vehicle trajectory information in the trajectory data set, the latitude and longitude of the vehicle in the current vehicle trajectory information and the latitude and longitude of the vehicle in the next vehicle trajectory information are calculated to obtain the distance difference. At the same time, the upload time point in the current vehicle trajectory information and the upload time point in the next vehicle trajectory information are calculated to obtain the time difference. Then, the average speed value between two consecutive vehicle trajectory information is calculated based on the corresponding distance difference and time difference.

[0028] A system for filtering abnormal trajectory data of a cross-regional muck truck, comprising:

[0029] Target area chain acquisition module: obtains a map divided into multiple area blocks, maps the preset driving route of the muck truck on the map, and connects different area blocks in sequence along the preset driving route to form a target area chain;

[0030] Track data set acquisition module: regularly obtains the track data set generated by the muck truck driving along the preset driving route; the track data set includes a number of vehicle track information uploaded by the GPS positioning device in the muck truck, and the vehicle track information includes the vehicle track point and the upload time point;

[0031] Track area chain acquisition module: maps the vehicle track points in the track data set to the area blocks, and connects the area blocks where the vehicle track points are located in sequence according to the upload time point to form a track area chain;

[0032] Cross-region data judgment module: according to the target area chain, the area blocks where the vehicle trajectory points in the trajectory area chain are located are judged in turn across the area;

[0033] Abnormal trajectory data filtering module: Calculate the average speed value between two consecutive vehicle trajectory information based on the trajectory data set, and make an abnormal judgment on the two consecutive average speed values ​​between the vehicle trajectory information causing the cross-zone phenomenon and the vehicle trajectory information before and after it based on the change range of the average speed value. If it is determined that the change range of the two consecutive average speed values ​​is abnormal, filter the vehicle trajectory information causing the cross-zone phenomenon in the trajectory data set.

[0034] Beneficial effects of the present invention:

[0035] The present invention provides a method and system for filtering abnormal trajectory data of a muck truck traveling across regions. The abnormal trajectory data filtering method mainly judges whether a cross-region phenomenon occurs by using a trajectory data set of the muck truck. When a cross-region phenomenon occurs, the authenticity of the cross-region phenomenon is determined by using continuous average speed values. Thus, the abnormal trajectory data can be filtered to avoid inaccurate supervision of the transportation process of the muck truck by staff.

[0036] In addition, for the authenticity judgment of the cross-zone phenomenon, the continuous average speed value is calculated based on the distance and time difference, and the trajectory data is judged whether it is abnormal according to the change amplitude of the continuous average speed value. This method is simple, easy to implement, and has high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The figure is a flow chart of a method for filtering abnormal trajectory data of a cross-regional muck truck in Embodiment 1 of the present invention.

[0038] Figure 2 This is a schematic diagram of a preset driving route in Example 1 of the present invention.

[0039] Figure 3 This is a schematic diagram of a vehicle uploading a trajectory in Example 1 of the present invention.

[0040] Figure 4 Schematic diagram of the actual trajectory of the vehicle in Example 1 of the present invention. DETAILED DESCRIPTION

[0041] 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, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. 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.

[0042] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0043] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0044] Additionally, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness.One of ordinary skill in the art will recognize that various changes and modifications may be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0045] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0046] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0047] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments:

[0048] Example 1

[0049] like Figure 1 As shown, a method for filtering abnormal trajectory data of a muck truck traveling across regions, the method specifically comprises the following steps:

[0050] S0: Obtain a map divided into multiple area blocks, map the preset driving route of the muck truck on the map, and connect different area blocks in sequence along the preset driving route to form a target area chain;

[0051] S1: Regularly obtain the trajectory data set generated by the muck truck driving along the preset driving route;

[0052] The trajectory data set includes a plurality of vehicle trajectory information uploaded by the GPS positioning device in the muck truck, and the vehicle trajectory information includes the vehicle trajectory point and the upload time point;

[0053] S2: Map the vehicle trajectory points in the trajectory data set to the regional blocks, and connect the regional blocks where the vehicle trajectory points are located in sequence according to the upload time point to form a trajectory regional chain;

[0054] S3: performing cross-region determination on the area blocks where the vehicle trajectory points in the trajectory area chain are located in turn according to the target area chain. When it is determined that a cross-region phenomenon occurs, obtaining the vehicle trajectory information causing the cross-region phenomenon, and proceeding to S4;

[0055] S4: Calculate the average speed value between two consecutive vehicle trajectory information according to the trajectory data set, and make an abnormality determination on the two consecutive average speed values ​​between the vehicle trajectory information causing the cross-zone phenomenon and the vehicle trajectory information before and after it according to the variation range of the average speed value. If it is determined that the variation range of the two consecutive average speed values ​​is abnormal, filter the vehicle trajectory information causing the cross-zone phenomenon in the trajectory data set.

[0056] Preferably, the target area chain is used to represent the area block sequence of the preset driving route passing through the area blocks in sequence, and then two consecutive area blocks in the target area chain are different area blocks;

[0057] The trajectory region chain is used to indicate that the region blocks where the vehicle trajectory points in the trajectory data set are located are sequentially sorted according to their respective upload time points, and two consecutive region blocks in the trajectory region chain are the same region blocks or different region blocks.

[0058] Preferably, in S3, the cross-region determination is specifically:

[0059] The area block where the current vehicle trajectory point is located in the trajectory area chain is compared with the area block where the next vehicle trajectory point is located. If the area blocks are different, a to-be-determined area block sequence is established according to the area block sequence of the current vehicle trajectory point and the area block where the next vehicle trajectory point is located, and the area block sequence contained in the target area chain is matched with the to-be-determined area block sequence. If the match is successful, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block where the next vehicle trajectory point is located is used as the vehicle trajectory information causing the cross-area phenomenon.

[0060] Preferably, in S3, the cross-region determination is specifically:

[0061] Compare the area block where the current vehicle trajectory point is located with the area block where the next vehicle trajectory point is located in the trajectory area chain. If the area blocks are different, the area block where the next vehicle trajectory point is located is used as the area block to be confirmed;

[0062] Then compare the area block to be confirmed with the area block where the next vehicle trajectory point is located after the area block to be confirmed. If the area blocks are different, establish an area block sequence to be determined based on the area block where the current vehicle trajectory point is located, the area block to be confirmed, and the area block where the next vehicle trajectory point is located after the area block to be confirmed. Match the area block sequence to be determined with the target area chain for similarity. If they are not similar, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block to be confirmed is used as the vehicle trajectory information causing the cross-area phenomenon.

[0063] Preferably, in S1, the trajectory data set is composed of vehicle trajectory information arranged in sequence according to respective upload time points, and the vehicle trajectory points in the vehicle trajectory information are the longitude and latitude of the vehicle located by the GPS positioning device in the muck truck.

[0064] Preferably, the S4 specifically includes the following steps:

[0065] S41: sequentially calculating the average speed value between two consecutive vehicle trajectory information in the trajectory data set;

[0066] S42: Count all average speed values ​​in the trajectory data set, and perform mean difference calculation on all average speed values ​​to obtain the mean and standard deviation corresponding to each average speed value;

[0067] S43: traverse all average speed values ​​in the trajectory data set in turn, calculate the difference between each average speed value and the mean, and determine whether the difference is greater than a preset multiple of the standard deviation. If so, determine that the average speed value is abnormal data;

[0068] S44: When two consecutive average speed values ​​are both abnormal data, it is determined that the change range of the two consecutive average speed values ​​is abnormal, and the vehicle trajectory information causing the cross-zone phenomenon is filtered out in the trajectory data set.

[0069] Preferably, in S41, the specific process of calculating the average speed value between two consecutive vehicle trajectory points is:

[0070] According to the arrangement order of the vehicle trajectory information in the trajectory data set, the latitude and longitude of the vehicle in the current vehicle trajectory information and the latitude and longitude of the vehicle in the next vehicle trajectory information are calculated to obtain the distance difference. At the same time, the upload time point in the current vehicle trajectory information and the upload time point in the next vehicle trajectory information are calculated to obtain the time difference. Then, the average speed value between two consecutive vehicle trajectory information is calculated based on the corresponding distance difference and time difference.

[0071] Based on the above principles, the present invention is further described:

[0072] The present invention is mainly used in cross-regional scenarios where supervisors supervise muck trucks transporting construction waste, engineering debris and other transport items from one administrative region to another administrative region for disposal through a supervision platform. The present invention mainly supervises the transportation process of muck trucks in this application scenario. The supervision of the transportation process of muck trucks is mainly carried out by comparing the preset trajectory of the muck truck with the actual trajectory data of the muck truck, analyzing whether the current muck truck is transporting according to the preset trajectory, thereby supervising the muck truck.

[0073] Currently, the trajectory data of muck trucks is generally located by the GPS device in the muck trucks. However, due to the noise of the Internet of Things system, transmission anomalies, system anomalies and other reasons, the GPS device in the muck trucks often produces position deviation during actual operation, causing the current located vehicle position to shift from the actual administrative area where the vehicle is located to another administrative area. In the corresponding trajectory data set, a cross-region phenomenon will be reflected, that is, a false cross-region phenomenon.

[0074] At present, when the trajectory data of a muck truck shows a cross-region phenomenon, supervisors need to actively analyze the cross-region phenomenon to determine whether it is caused by the trajectory of the muck truck or the positioning offset of the GPS device. By having the staff actively judge whether the cross-region phenomenon is correct, effective supervision of the muck truck can be achieved. The two different cross-region data will directly affect the supervisors' actual supervision behavior of the muck trucks. In addition, it is time-consuming for supervisors to actively analyze the transportation process of the muck truck, and human judgment is prone to errors.

[0075] Therefore, the present invention provides a method for filtering abnormal trajectory data of a muck truck traveling across regions. The abnormal trajectory data filtering method does not require supervisors to actively analyze the trajectory data, but directly filters the abnormal trajectory data that causes the false cross-region phenomenon, so as to avoid the abnormal trajectory data affecting the supervisors' actual supervision behavior of the muck trucks. Thus, the supervisors can supervise the accurate trajectory data through the supervision platform and perform effective operations on the accurate trajectory data.

[0076] Specifically, the abnormal trajectory data filtering method mainly judges whether the muck truck has a cross-region phenomenon through the trajectory data set of the muck truck. When the cross-region phenomenon occurs, the authenticity of the cross-region phenomenon is judged by the continuous average speed value. Among them, the authenticity judgment of the cross-region phenomenon adopts the calculation of the continuous average speed value based on the distance and time difference and judges whether the trajectory data is abnormal according to the change amplitude of the continuous average speed value. The method is simple, easy to implement and has high accuracy.

[0077] In this embodiment, for a supervision platform for a muck truck, the supervisor can obtain a map divided into multiple area blocks on the supervision platform in advance. The area block can be an administrative area in a city, or it can be divided into multiple small area blocks by the supervisor according to the actual transportation area of ​​the muck truck. Then, a corresponding map is generated for the actual transportation area of ​​the muck truck, and the preset driving route of the muck truck is mapped to the map. The preset driving route will pass through multiple area blocks along the forward direction. The multiple area blocks are connected in sequence to form a target area chain for indicating the order in which the preset driving route passes through the area blocks in sequence, such as Figure 2 As shown, the dump truck transports construction waste, engineering debris and other transport items from the preset starting point area block A to the preset end point area block C for disposal, and the preset driving route passes through area block A, area block B and area block C in the map in sequence, forming a target area chain {A, B, C}.

[0078] Then, the muck truck will transport according to the preset driving route, and the trajectory data set of the muck truck will be regularly acquired through the GPS device in the muck truck. In this embodiment, the trajectory data of the muck truck for one hour is acquired, that is, the vehicle trajectory information of the muck truck within one hour of transportation is sorted in sequence according to the upload time point to form a trajectory data set. Therefore, in this embodiment, the current trajectory data set {X1, X2, X3, X4, X5} is acquired, wherein "X1, X2, X3, X4, X5" respectively represent a vehicle trajectory information, and the vehicle trajectory information includes vehicle trajectory points. The actual position of the vehicle is mapped to the area block through the vehicle trajectory points. According to the vehicle trajectory points mapped on the area block, the vehicle upload trajectory of the muck truck can be formed on the supervision platform of the muck truck, such as Figure 3 As shown, the area blocks where the vehicle trajectory points are located are connected in sequence according to the upload time point to form a trajectory area chain {A,A,D,B,C}, and "A,A,D,B,C" corresponds to "X1,X2,X3,X4,X5" one by one.

[0079] In another embodiment, the vehicle trajectory information may further include a vehicle identification, which may be a license plate number, and the trajectory data of the same muck truck may be grouped according to the license plate number.

[0080] In addition, in order to ensure the accuracy of the trajectory data set, you can also choose to pre-process the vehicle trajectory information. Specifically, you can remove sampling outliers based on the vehicle trajectory points. The vehicle trajectory points are the longitude and latitude of the vehicle located by the GPS positioning device in the dump truck. You can choose to remove the vehicle trajectory information with a longitude and latitude of 0 or exceeding the longitude and latitude limits.

[0081] Then, the cross-region determination is performed sequentially on the region blocks where the vehicle trajectory points in the trajectory region chain are located according to the target region chain. In this embodiment, there are two determination methods for cross-region determination, which are as follows:

[0082] The first determination method is as follows:

[0083] Compare the area block where the current vehicle trajectory point is located with the area block where the next vehicle trajectory point is located in the trajectory area chain. If the area blocks are not the same, the area block where the next vehicle trajectory point is located is used as the area block to be confirmed; then compare the area block to be confirmed with the area block where the next vehicle trajectory point is located after the area block to be confirmed. If the area blocks are not the same, establish an area block sequence to be determined according to the area block sequence of the area block where the current vehicle trajectory point is located, the area block to be confirmed, and the area block where the next vehicle trajectory point is located after the area block to be confirmed, and perform similarity matching between the area block sequence to be determined and the target area chain. If they are not similar, the area block to be confirmed is determined to be cross-area data;

[0084] In summary, the first determination method is mainly used to determine whether the cross-region phenomenon is caused by the positioning offset of the GPS device. Based on the first determination method, the trajectory area chain {A, A, D, B, C} is determined in sequence. If the area block where the current vehicle trajectory point is located is A, it is compared with the area block where the next vehicle trajectory point is located, that is, area block A is compared with area block D. If the two area blocks are not the same, area block D is used as the area block to be confirmed; then the area block D to be confirmed is compared with the area block where the next vehicle trajectory point is located, that is, the area block D to be confirmed is compared with area block B. If the two area blocks are not the same, a to-be-determined area block sequence {A, D, B} is established according to the area block sequence of area block A, to-be-determined area block D, and area block B, and the to-be-determined area block sequence {A, D, B} is matched with the target area chain {A, B, C} for similarity. If they are not similar, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the to-be-determined area block D is used as the vehicle trajectory information causing the cross-area phenomenon. In addition, it can be obtained that the muck truck recorded in the trajectory data set crosses the area from area block A to area block D and then to area block B, which does not conform to the preset trajectory route.

[0085] The second determination method is as follows:

[0086] Compare the area block where the current vehicle trajectory point is located with the area block where the next vehicle trajectory point is located in the trajectory area chain. If the area blocks are different, establish an area block sequence to be determined according to the area block sequence of the current vehicle trajectory point and the area block where the next vehicle trajectory point is located, and match the area block sequence contained in the target area chain with the area block sequence to be determined. If the match is successful, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block where the next vehicle trajectory point is located is used as the vehicle trajectory information causing the cross-area phenomenon;

[0087] In summary, the second determination method can quickly determine whether the trajectory of the muck truck is caused by the preset trajectory route of the muck truck. Based on the second determination method, the trajectory area chain {A, A, D, B, C} is determined in sequence. If the area block where the current vehicle trajectory point is located is B, it is compared with the area block where the next vehicle trajectory point is located, that is, area block B is compared with area block C. If the two area blocks are not the same, the area block sequence to be determined {B, C} is established according to the area block sequence of area block B and area block C, and the area blocks contained in the target area chain {A, B, C} are compared. The domain block sequence is matched with the region block sequence {B, C} to be determined, and the target region chain {A, B, C} contains the region block sequence {A, B} and the region block sequence {B, C}. It can be seen that if the region block sequence {B, C} to be determined is matched successfully, it is determined that a cross-region phenomenon occurs, and the vehicle trajectory information corresponding to the region block C is used as the vehicle trajectory information causing the cross-region phenomenon. In addition, it can be obtained that the muck truck recorded in the trajectory data set crosses the region from the region block B to the region block C in accordance with the preset trajectory route. However, it cannot be ruled out that the offset caused by the GPS device is a possibility.

[0088] Therefore, after obtaining the cross-region data, it is necessary to calculate the continuous average speed value based on the distance and time difference and make a secondary judgment on whether the cross-region data is abnormal based on the change amplitude of the continuous average speed value, so as to improve the accuracy of filtering abnormal trajectory data.

[0089] In this embodiment, the vehicle trajectory information causing the cross-zone phenomenon obtained by the first determination method and the second determination method can be calculated, and the calculation method is specifically as follows:

[0090] The latitude and longitude of the vehicle and the upload time point of each vehicle trajectory information in the trajectory data set {X1, X2, X3, X4, X5} are obtained. According to the Haversine algorithm, the distance difference and time difference between X1 and X2, X2 and X3, X3 and X4, and X4 and X5 can be calculated in sequence. Then, the average speed value {V1, V2, V3, V4} between two consecutive vehicle trajectory information can be calculated based on the corresponding distance difference and time difference.

[0091] Then, the average speed values ​​{V1, V2, V3, V4} are calculated to obtain their mean and standard deviation, and then all the average speed values ​​in the trajectory data set are traversed in turn, the difference between each average speed value and the gas average value is calculated, and it is determined whether the difference is greater than the preset multiple of the standard deviation. If the average speed value V2 and the average speed value V3 are greater than the preset multiple of the standard deviation, the average speed value V2 and the average speed value V3 are determined to be abnormal data, and the average speed value V2 and the average speed value V3 are two consecutive average speed values, then the change amplitude of the two consecutive average speed values ​​is determined to be abnormal, and the vehicle trajectory information that causes the cross-region phenomenon is filtered out in the trajectory data set, that is, the vehicle trajectory information X3 corresponding to the area block D is eliminated. Then, the actual vehicle trajectory can be formed on the supervision platform of the muck truck according to the corrected trajectory data set {X1, X2, X4, X5}, as shown in FIG. Figure 4 As shown, the staff can directly see that the dump truck is running according to the preset trajectory route, which is convenient for the staff to carry out supervision work and avoids the staff from making manual judgments on abnormal trajectory points, which affects the staff's supervision work.

[0092] Example 2

[0093] A system for filtering abnormal trajectory data of a cross-regional muck truck, comprising:

[0094] Target area chain acquisition module: obtains a map divided into multiple area blocks, maps the preset driving route of the muck truck on the map, and connects different area blocks in sequence along the preset driving route to form a target area chain;

[0095] Track data set acquisition module: regularly obtains the track data set generated by the muck truck driving along the preset driving route; the track data set includes a number of vehicle track information uploaded by the GPS positioning device in the muck truck, and the vehicle track information includes the vehicle track point and the upload time point;

[0096] Track area chain acquisition module: maps the vehicle track points in the track data set to the area blocks, and connects the area blocks where the vehicle track points are located in sequence according to the upload time point to form a track area chain;

[0097] Cross-region data judgment module: according to the target area chain, the area blocks where the vehicle trajectory points in the trajectory area chain are located are judged in turn across the area;

[0098] Abnormal trajectory data filtering module: Calculate the average speed value between two consecutive vehicle trajectory information based on the trajectory data set, and make an abnormal judgment on the two consecutive average speed values ​​between the vehicle trajectory information causing the cross-zone phenomenon and the vehicle trajectory information before and after it based on the change range of the average speed value. If it is determined that the change range of the two consecutive average speed values ​​is abnormal, filter the vehicle trajectory information causing the cross-zone phenomenon in the trajectory data set.

[0099] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. According to the technical essence of the present invention, within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement made to the above embodiment still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for filtering abnormal trajectory data of a cross-regional muck truck, characterized in that: The method specifically comprises the following steps: S0: Obtain a map divided into multiple area blocks, map the preset driving route of the muck truck on the map, and connect different area blocks in sequence along the preset driving route to form a target area chain; Wherein, the target area chain is used to represent the area block sequence of the preset driving route passing through the area blocks in sequence, and two consecutive area blocks in the target area chain are different area blocks; S1: Regularly obtain the trajectory data set generated by the muck truck driving along the preset driving route; The trajectory data set includes a plurality of vehicle trajectory information uploaded by the GPS positioning device in the muck truck, and the vehicle trajectory information includes the vehicle trajectory point and the upload time point; S2: Map the vehicle trajectory points in the trajectory data set to the regional blocks, and connect the regional blocks where the vehicle trajectory points are located in sequence according to the upload time point to form a trajectory regional chain; The trajectory region chain is used to indicate that the region blocks where the vehicle trajectory points in the trajectory data set are located are sequentially sorted according to their respective upload time points, and two consecutive region blocks in the trajectory region chain are the same region blocks or different region blocks; S3: performing cross-region determination on the area blocks where the vehicle trajectory points in the trajectory area chain are located in turn according to the target area chain. When it is determined that a cross-region phenomenon occurs, obtaining the vehicle trajectory information causing the cross-region phenomenon, and proceeding to S4; The cross-region determination includes the following two methods: The first determination method is specifically as follows: compare the area block where the current vehicle trajectory point is located in the trajectory area chain with the area block where the next vehicle trajectory point is located. If the area blocks are different, establish an area block sequence to be determined according to the area block sequence of the current vehicle trajectory point and the area block where the next vehicle trajectory point is located, and match the area block sequence contained in the target area chain with the area block sequence to be determined. If the match is successful, it is determined that the cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block where the next vehicle trajectory point is located is used as the vehicle trajectory information causing the cross-area phenomenon; The second determination method is specifically as follows: compare the area block where the current vehicle trajectory point is located with the area block where the next vehicle trajectory point is located in the trajectory area chain. If the area blocks are not the same, the area block where the next vehicle trajectory point is located is used as the area block to be confirmed; then compare the area block to be confirmed with the area block where the next vehicle trajectory point is located after the area block to be confirmed. If the area blocks are not the same, establish an area block sequence to be determined according to the area block sequence where the current vehicle trajectory point is located, the area block to be confirmed, and the area block where the next vehicle trajectory point is located after the area block to be confirmed, and perform similarity matching between the area block sequence to be determined and the target area chain. If they are not similar, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block to be confirmed is used as the vehicle trajectory information causing the cross-area phenomenon; S4: Calculate the average speed value between two consecutive vehicle trajectory information according to the trajectory data set, and make an abnormality determination on the two consecutive average speed values ​​between the vehicle trajectory information causing the cross-zone phenomenon and the vehicle trajectory information before and after it according to the variation range of the average speed value. If it is determined that the variation range of the two consecutive average speed values ​​is abnormal, filter the vehicle trajectory information causing the cross-zone phenomenon in the trajectory data set.

2. The method for filtering abnormal trajectory data of a cross-regional muck truck according to claim 1, characterized in that: In S1, the trajectory data set is composed of vehicle trajectory information arranged in sequence according to respective upload time points, and the vehicle trajectory points in the vehicle trajectory information are the latitude and longitude of the vehicle located by the GPS positioning device in the muck truck.

3. The method for filtering abnormal trajectory data of a cross-regional muck truck according to claim 2, characterized in that: The S4 specifically includes the following steps: S41: sequentially calculating the average speed value between two consecutive vehicle trajectory information in the trajectory data set; S42: Count all average speed values ​​in the trajectory data set, and perform mean difference calculation on all average speed values ​​to obtain the mean and standard deviation corresponding to each average speed value; S43: traverse all average speed values ​​in the trajectory data set in turn, calculate the difference between each average speed value and the mean, and determine whether the difference is greater than a preset multiple of the standard deviation. If so, determine that the average speed value is abnormal data; S44: When two consecutive average speed values ​​are both abnormal data, it is determined that the change range of the two consecutive average speed values ​​is abnormal, and the vehicle trajectory information causing the cross-zone phenomenon is filtered out in the trajectory data set.

4. The method for filtering abnormal trajectory data of a cross-regional muck truck according to claim 3 is characterized in that: In S41, the specific process of calculating the average speed value between two consecutive vehicle trajectory points is as follows: According to the arrangement order of the vehicle trajectory information in the trajectory data set, the latitude and longitude of the vehicle in the current vehicle trajectory information and the latitude and longitude of the vehicle in the next vehicle trajectory information are calculated to obtain the distance difference. At the same time, the upload time point in the current vehicle trajectory information and the upload time point in the next vehicle trajectory information are calculated to obtain the time difference. Then, the average speed value between two consecutive vehicle trajectory information is calculated based on the corresponding distance difference and time difference.

5. A system for filtering abnormal trajectory data of a cross-regional muck truck, characterized in that: include: Target area chain acquisition module: obtains a map divided into multiple area blocks, maps the preset driving route of the muck truck on the map, and connects different area blocks in sequence along the preset driving route to form a target area chain; Wherein, the target area chain is used to represent the area block sequence of the preset driving route passing through the area blocks in sequence, and two consecutive area blocks in the target area chain are different area blocks; Track data set acquisition module: regularly obtains the track data set generated by the muck truck driving along the preset driving route; the track data set includes a number of vehicle track information uploaded by the GPS positioning device in the muck truck, and the vehicle track information includes the vehicle track point and the upload time point; Track area chain acquisition module: maps the vehicle track points in the track data set to the area blocks, and connects the area blocks where the vehicle track points are located in sequence according to the upload time point to form a track area chain; The trajectory region chain is used to indicate that the region blocks where the vehicle trajectory points in the trajectory data set are located are sequentially sorted according to their respective upload time points, and two consecutive region blocks in the trajectory region chain are the same region blocks or different region blocks; Cross-region data judgment module: according to the target area chain, the area blocks where the vehicle trajectory points in the trajectory area chain are located are judged in turn across the area; The cross-region determination includes the following two methods: The first determination method is specifically as follows: compare the area block where the current vehicle trajectory point is located in the trajectory area chain with the area block where the next vehicle trajectory point is located. If the area blocks are different, establish an area block sequence to be determined according to the area block sequence of the current vehicle trajectory point and the area block where the next vehicle trajectory point is located, and match the area block sequence contained in the target area chain with the area block sequence to be determined. If the match is successful, it is determined that the cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block where the next vehicle trajectory point is located is used as the vehicle trajectory information causing the cross-area phenomenon; The second determination method is specifically as follows: compare the area block where the current vehicle trajectory point is located with the area block where the next vehicle trajectory point is located in the trajectory area chain. If the area blocks are not the same, the area block where the next vehicle trajectory point is located is used as the area block to be confirmed; then compare the area block to be confirmed with the area block where the next vehicle trajectory point is located after the area block to be confirmed. If the area blocks are not the same, establish an area block sequence to be determined according to the area block sequence where the current vehicle trajectory point is located, the area block to be confirmed, and the area block where the next vehicle trajectory point is located after the area block to be confirmed, and perform similarity matching between the area block sequence to be determined and the target area chain. If they are not similar, it is determined that a cross-area phenomenon occurs, and the vehicle trajectory information corresponding to the area block to be confirmed is used as the vehicle trajectory information causing the cross-area phenomenon; Abnormal trajectory data filtering module: Calculate the average speed value between two consecutive vehicle trajectory information based on the trajectory data set, and make an abnormal judgment on the two consecutive average speed values ​​between the vehicle trajectory information causing the cross-zone phenomenon and the vehicle trajectory information before and after it based on the change range of the average speed value. If it is determined that the change range of the two consecutive average speed values ​​is abnormal, filter the vehicle trajectory information causing the cross-zone phenomenon in the trajectory data set.

Images