Path matching method and device, storage medium and electronic device

Abstract

The present disclosure relates to a path matching method, device, storage medium and electronic equipment, and belongs to the technical field of data processing. The method comprises: acquiring a first position point in the process of a moving object moving from a starting point to an ending point, and a plurality of candidate paths from the starting point to the ending point, each candidate path comprising a plurality of second position points; determining a probability that the first position point belongs to each candidate path based on motion data of the first position point and position data of the second position points comprised by each candidate path, the motion data comprising position data and travel data used to determine a motion distance of the moving object; and determining a target path matched with the motion process of the moving object from the plurality of candidate paths according to the probability. The method can improve the accuracy of path matching of the moving object.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more specifically, to a path matching method, apparatus, storage medium, and electronic device. Background Technology

[0002] Vehicles typically use GPS devices to acquire location data while driving. Combined with maps, this allows the vehicle's trajectory to be matched and displayed against a path on the map. However, because GPS positioning data often contains errors, low location sampling frequencies can lead to incorrect path matching on the map. Summary of the Invention

[0003] The purpose of this disclosure is to provide a path matching method, apparatus, storage medium, and electronic device to improve the accuracy of path matching.

[0004] To achieve the above objectives, in a first aspect, this disclosure provides a path matching method, comprising:

[0005] The first position point of the moving object during its movement from the starting point to the end point and multiple candidate paths from the starting point to the end point are obtained, and each candidate path includes multiple second position points;

[0006] Based on the motion data of the first location point and the location data of the second location points included in each candidate path, the probability that the first location point belongs to each candidate path is determined. The motion data includes location data and driving data used to determine the movement distance of the moving object.

[0007] Based on the probability, a target path matching the motion process of the moving object is determined from the plurality of candidate paths.

[0008] Optionally, determining the probability that the first location point belongs to each of the candidate paths based on the motion data of the first location point and the location data of the second location points included in each candidate path includes:

[0009] For any candidate path, based on the location data of the first location point and the location data of the second location points included in the candidate path, a third location point associated with each of the first location points is determined from the second location points of the candidate path, wherein the number of second location points in the candidate path is greater than the number of first location points, and the associated first location points and third location points satisfy a preset distance condition and a preset direction condition.

[0010] Based on the motion data of the first location point and the location data of the third location point on the candidate path, the probability that the first location point belongs to the candidate path is determined.

[0011] Optionally, determining the probability that the first location point belongs to the candidate path based on the motion data of the first location point and the location data of the third location point on the candidate path includes:

[0012] For any candidate path, based on the driving data of the first position point and the position data of the third position point on the candidate path, a first accuracy rate is determined to match the total movement distance of the moving object before the last first position point with the total path distance before the target third position point on the candidate path, wherein the target third position point is a third position point associated with the last first position point.

[0013] Based on the location data of the first location point and the location data of the third location point on the candidate path, the vertical distance error probability between the first location point and the third location point on the candidate path is determined.

[0014] Based on the driving data of the first location point and the location data of the third location point on the candidate path, a second accuracy rate is determined to match the movement distance of the moving object during the turning process with the path distance of the turning segment in the candidate path.

[0015] Based on the first accuracy, the vertical distance error probability, and the second accuracy, the probability that the first location point belongs to the candidate path is obtained.

[0016] Optionally, determining the vertical distance error probability between the first location point and the third location point on the candidate path based on the location data of the first location point and the location data of the third location point on the candidate path includes:

[0017] For the r-th first position point, based on the position data of the third position point associated with the r-th first position point in the candidate path and the position data of the third position point associated with the (r-1)-th first position point in the candidate path, the first line segment associated with the r-th first position point is determined;

[0018] Based on the position data of the third position point associated with the r-th first position point in the candidate path and the position data of the third position point associated with the (r+1)-th first position point in the candidate path, the second line segment associated with the r-th first position point is determined.

[0019] Determine the first perpendicular distance between the r-th first position point and the first line segment, and determine the second perpendicular distance between the r-th first position point and the second line segment;

[0020] Based on the first vertical distance and the second vertical distance, determine the sub-vertical distance error probability corresponding to the r-th first position point;

[0021] Based on the sub-vertical distance error probability corresponding to each first position point, the vertical distance error probability between the first position point and the third position point on the candidate path is obtained.

[0022] Optionally, determining the second accuracy rate for matching the distance traveled by the moving object during a turn with the path distance of the turning segment in the candidate path, based on the driving data from the first location point and the location data from the third location point on the candidate path, includes:

[0023] Based on the driving data of the first location point and the location data of the third location point on the candidate path, a first sub-accuracy and a second sub-accuracy corresponding to each third location point are determined. The first sub-accuracy represents the accuracy of matching between the total movement distance of the moving object during the turning and the total path distance during the change of direction of the road segment in the candidate path. The second sub-accuracy represents the accuracy of matching between a first ratio and a second ratio. The first ratio is the ratio between the movement distances of the moving object before and after the turning, and the second ratio is the ratio between the path distances of the moving object before and after the change of direction of the road segment in the candidate path.

[0024] Based on the first and second sub-accuracy rates corresponding to the same third position point, the third sub-accuracy rate of that position point is obtained.

[0025] The second accuracy is obtained based on the third sub-accuracy corresponding to each third position point.

[0026] Optionally, determining the first sub-accuracy and the second sub-accuracy corresponding to each third location point based on the driving data of the first location point and the location data of the third location points on the candidate path includes:

[0027] For the i-th third location point, if there is a change in road direction between the i-th third location point and the (i+1)-th third location point, based on the driving data of the first location point, obtain the first movement distance of the moving object from the i-th sampling time to the turning time, the second movement distance of the moving object from the turning time to the (i+1)-th sampling time, and, based on the position data of the third location points on the candidate path, obtain the first path distance between the i-th third location point and the path turning point, and the second path distance between the path turning point and the (i+1)-th third location point, wherein the i-th sampling time is the sampling time of the first location point associated with the i-th third location point, i is greater than or equal to 1 and less than or equal to N-1, and N represents the total number of first location points;

[0028] Based on the first movement distance, the second movement distance, the first path distance, and the second path distance, determine the first sub-accuracy and the second sub-accuracy corresponding to the i-th third position point.

[0029] Optionally, determining the target path that matches the motion process of the moving object from the plurality of candidate paths based on the probability includes:

[0030] Based on the probability that the first location point belongs to each of the candidate paths, the first path selection result is determined from the plurality of candidate paths;

[0031] Based on the first accuracy corresponding to each candidate path, a second path selection result is determined from the plurality of candidate paths;

[0032] Based on the vertical distance error probability between the target first location point and the third location point on each candidate path, the third sub-path selection result corresponding to the target first location point is obtained, where the target first location point is any first location point;

[0033] Based on the third sub-path selection results corresponding to each first position point, the third path selection result is obtained;

[0034] The candidate path that appears most frequently in the first path selection result, the second path selection result, and the third path selection result is determined as the target path.

[0035] Secondly, embodiments of this disclosure provide a path matching device, comprising:

[0036] The acquisition module is used to acquire the first position point of the moving object during its movement from the starting point to the end point, as well as multiple candidate paths from the starting point to the end point, each candidate path including multiple second position points;

[0037] The first determining module is used to determine the probability that the first location point belongs to each of the candidate paths based on the motion data of the first location point and the location data of the second location points included in each candidate path. The motion data includes location data and driving data used to determine the movement distance of the moving object.

[0038] The second determining module is used to determine, based on the probability, a target path that matches the motion process of the moving object from the plurality of candidate paths.

[0039] Thirdly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0040] Fourthly, embodiments of this disclosure provide an electronic device, including:

[0041] A memory on which computer programs are stored;

[0042] A processor for executing the computer program in the memory to implement the steps of the method of any one of the first aspects.

[0043] The above technical solution first obtains the first position point of the moving object during its movement from the starting point to the ending point, as well as multiple candidate paths from the starting point to the ending point. Then, based on the motion data of the first position point and the position data of the second position points included in each candidate path, the probability that the first position point belongs to each candidate path can be determined. Subsequently, based on the probability, a target path matching the movement process of the moving object can be determined from the multiple candidate paths. Since the determination of the probability that the first position point belongs to each candidate path also takes into account the driving data used to determine the movement distance of the moving object, the combination of driving data can more realistically reflect the actual movement of the moving object, thereby improving the accuracy of path matching for the moving object.

[0044] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0045] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0046] Figure 1 This is a flowchart illustrating a path matching method as shown in an exemplary embodiment of this disclosure.

[0047] Figure 2 This is a block diagram of a path matching device shown in an exemplary embodiment of the present disclosure.

[0048] Figure 3 This is a block diagram of an electronic device shown in an exemplary embodiment of the present disclosure. Detailed Implementation

[0049] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0050] Figure 1 This is a flowchart illustrating a path matching method according to an exemplary embodiment of the present disclosure. The path matching method can be executed by an electronic device, specifically by a path matching apparatus, which can be implemented in software and / or hardware and configured within the electronic device. (Refer to...) Figure 1 The path matching method includes the following steps:

[0051] S101, obtain the first position point of the moving object during its movement from the starting point to the end point, as well as multiple candidate paths from the starting point to the end point, each candidate path including multiple second position points.

[0052] The moving object can be a vehicle, and the path matching method of this disclosure can be applied to vehicle navigation scenarios. The starting point and ending point of the moving object can be selected according to actual needs.

[0053] The first position point can be understood as a point obtained by sampling the position of the moving object during its movement from the starting point to the ending point. Optionally, the position of the moving object can be sampled at preset time intervals to obtain the first position point. For each first position point, there is corresponding motion data, which may include position data and travel data used to determine the distance traveled by the moving object. Optionally, the position data may include latitude and longitude and azimuth. Optionally, the travel data may include the speed, acceleration, steering wheel angle, and mileage of the moving object.

[0054] In some implementations, the first location point can be represented as Q = [Q1, Q2, ..., Q...]. N The sampling times are respectively T = [T1, T2, ..., T]. N The orientation angle corresponding to the first position point can be expressed as θ = [θ1, θ2, ..., θ]. N ].

[0055] Furthermore, in path matching tasks, multiple candidate paths from the starting point to the destination can be obtained in advance. The points on these candidate paths can be understood as secondary location points.

[0056] Taking two candidate paths as an example, in some implementations, the second position point in the first candidate path can be represented as R(1) = [R 11 ,R 12 ,...,R 1E The orientation angle corresponding to the second position point in the first candidate path can be expressed as θ(1)=[θ 11 ,θ 12 ,...,θ 1E The second position point in the second candidate path can be represented as R(2) = [R 21 ,R 22 ,...,R 2F The orientation angle corresponding to the second position point in the second candidate path can be expressed as θ(2)=[θ 21 ,θ 22 ,...,θ 2F ], where E and F can be equal or unequal.

[0057] S102, based on the motion data of the first position point and the position data of the second position points included in each candidate path, determine the probability that the first position point belongs to each candidate path.

[0058] S103, Based on probability, determine the target path that matches the motion process of the moving object from multiple candidate paths.

[0059] Using the above method, the first position point of the moving object during its movement from the starting point to the ending point, as well as multiple candidate paths from the starting point to the ending point, are first obtained. Then, based on the motion data of the first position point and the position data of the second position points included in each candidate path, the probability that the first position point belongs to each candidate path can be determined. Afterward, based on the probability, a target path matching the moving object's movement process can be determined from the multiple candidate paths. Because the determination of the probability that the first position point belongs to each candidate path also considers the travel data used to determine the moving object's distance, combining travel data can more realistically reflect the actual movement of the moving object, thereby improving the accuracy of path matching.

[0060] In some implementations, determining the probability that the first location point belongs to each candidate path based on the motion data of the first location point and the location data of the second location points included in each candidate path may include the following steps:

[0061] For any candidate path, based on the location data of the first location point and the location data of the second location points included in the candidate path, a third location point associated with each of the first location points is determined from the second location points of the candidate path, wherein the number of second location points in the candidate path is greater than the number of first location points, and the associated first location points and third location points satisfy a preset distance condition and a preset direction condition.

[0062] Based on the motion data of the first location point and the position data of the third location point on the candidate path, the probability that the first location point belongs to the candidate path is determined.

[0063] In this embodiment of the disclosure, for each first position point, a third position point that satisfies the preset distance condition and the preset direction condition can be found among the second position points of each candidate path. Then, for any candidate path, based on the motion data of the first position point and the position data of the third position point on the candidate path, the probability that the first position point belongs to the candidate path can be determined. Thus, the probability that the first position point belongs to each candidate path can be finally obtained.

[0064] In some implementations, when determining a third position point associated with a first position point from the second position points of the candidate path, candidate position points with the same orientation angle as the first position point can be selected from the second position points of the candidate path first. Then, the position point closest to the first position point can be found from the candidate position points as the third position point associated with the first position point.

[0065] In some implementations, for ease of understanding, two candidate paths are still used as an example. In the first candidate path, the first position point Q = [Q1, Q2, ..., Q...]. N The third position point associated with each of them can be represented as Q(R1) = [Q 11 Q 12 ,...,Q 1N In the second candidate path, the first position point Q = [Q1, Q2, ..., Q] is... N The third position point associated with each of them can be represented as Q(R2) = [Q 21 Q 22 ,...,Q 2N ].

[0066] By determining the third position points associated with each first position point from the second position points of the candidate path, and then determining the probability that the first position point belongs to the candidate path based on the motion data of the first position points and the position data of the third position points on the candidate path, the computational load can be reduced and the computational efficiency can be improved while ensuring the accuracy of probability calculation.

[0067] In some implementations, determining the probability that the first location point belongs to the candidate path based on the motion data of the first location point and the location data of the third location point on the candidate path may include the following steps:

[0068] For any candidate path, based on the driving data of the first position point and the position data of the third position point on the candidate path, determine the first accuracy of matching the total movement distance of the moving object before the last first position point with the total path distance before the target third position point on the candidate path, where the target third position point is the third position point associated with the last first position point;

[0069] Based on the location data of the first location point and the location data of the third location point on the candidate path, determine the vertical distance error probability between the first location point and the third location point on the candidate path;

[0070] Based on the driving data of the first location point and the location data of the third location point on the candidate path, a second accuracy is determined to match the distance of the moving object during the turning process with the path distance of the turning segment in the candidate path.

[0071] Based on the first accuracy, the vertical distance error probability, and the second accuracy, the probability that the first location point belongs to the candidate path is obtained.

[0072] In this embodiment of the disclosure, the probability that a first location point belongs to the candidate path can be determined from multiple dimensions as a whole. These dimensions may include: the total path distance difference, the path point difference, and the path segment distance difference. Each dimension will be described in detail below.

[0073] In some implementations, the difference in total path distance can be expressed by the first accuracy rate of matching the total distance traveled by the moving object before the last first position point with the total path distance before the target third position point on the candidate path. Here, when there is a one-to-one correspondence between the first and third position points, the target third position point can be the last third position point.

[0074] In some implementations, the total distance traveled by the moving object within the sampling time period corresponding to the first position point can be determined by cumulatively summing discrete data such as driving speed and acceleration during the sampling time period corresponding to the first position point, or by using mileage records. Here, the sampling time period can be the time period between sampling the first first position point and sampling the last first position point.

[0075] In some implementations, the segmented distance can be calculated between every two adjacent third location points based on the latitude and longitude data of the third location point, and then the multiple segmented distances can be accumulated to obtain the total path distance corresponding to the third location point on the candidate path.

[0076] In some implementations, after obtaining the total movement distance of the moving object within the sampling time period corresponding to the first position point, and the total path distance corresponding to the third position point on the candidate path, the first accuracy can be calculated using the following formula:

[0077]

[0078] Where πc represents the first accuracy calculated for the c-th candidate path, dc represents the total path distance before the third position point of the target on the c-th candidate path, D represents the total movement distance of the moving object before the last first position point, and z is a very small positive value, for example, it can be set to 0.05.

[0079] For example, assuming the total movement distance D = 500 meters of the moving object within the sampling time period corresponding to the first position point, and the total path distance d1 = 530 meters corresponding to the third position point on the first candidate path, then the first accuracy of the calculation for the first candidate path is...

[0080] In some implementations, the path point difference dimension can be expressed by the vertical distance error probability between the first location point and the third location point on the candidate path.

[0081] In some implementations, determining the vertical distance error probability between the first location point and the third location point on the candidate path based on the location data of the first location point and the location data of the third location point on the candidate path may include the following steps:

[0082] For the r-th first position point, based on the position data of the third position point Qcr associated with the r-th first position point in the candidate path c and the position data of the third position point Qc(r-1) associated with the (r-1)-th first position point in the candidate path c, determine the first line segment associated with the r-th first position point.

[0083] Based on the position data of the third position point associated with the r-th first position point in the candidate path and the position data of the third position point associated with the (r+1)-th first position point in the candidate path, the second line segment associated with the r-th first position point is determined.

[0084] Determine the first perpendicular distance between the r-th first position point and the first line segment, and determine the second perpendicular distance between the r-th first position point and the second line segment;

[0085] Based on the first vertical distance and the second vertical distance, determine the sub-vertical distance error probability corresponding to the r-th first position point;

[0086] Based on the sub-vertical distance error probability corresponding to each first position point, the vertical distance error probability between the first position point and the third position point on the candidate path is obtained.

[0087] In this embodiment of the disclosure, for the c-th candidate path, the third position point associated with the (r-1)-th first position point is the (r-1)-th third position point, the third position point associated with the r-th first position point is the r-th third position point, and the third position point associated with the (r+1)-th first position point is the (r+1)-th third position point. Furthermore, the line connecting the r-th third position point and the (r-1)-th third position point can be considered as the first line segment associated with the r-th first position point, and the line connecting the r-th third position point and the (r+1)-th third position point can be considered as the second line segment associated with the r-th first position point. Then, the perpendicular distance between the r-th first position point and the first line segment can be determined as the first perpendicular distance, denoted as d(Q). c(r-1) Q cr Let the perpendicular distance between the r-th first position point and the second line segment be defined as the second perpendicular distance, denoted as d(Q). cr Q c(r+1) ).

[0088] In some implementations, after obtaining the first perpendicular distance between the r-th first position point and the first line segment, and the second perpendicular distance between the r-th first position point and the second line segment, the first perpendicular distance and the second perpendicular distance can be processed using the following formula to obtain the sub-perpendicular distance error probability corresponding to the r-th first position point:

[0089]

[0090] Where p(Q) r Q cr ) represents the sub-vertical distance error probability of the r-th first position point on the c-th candidate path, d(Q) r Q cr )=min[d(Q c(r-1) Q cr ),d(Q cr Q c(r+1) )], where σ is the standard deviation parameter, which can be set based on experience, 1≤r≤N.

[0091] In some implementations, after obtaining the sub-vertical distance error probabilities corresponding to each first location point, the sub-vertical distance error probabilities corresponding to each first location point can be processed using the following formula to obtain the vertical distance error probability between the first location point and the third location point on the candidate path:

[0092] pc1 = p(Q1, Q) c1 )*p(Q2,Q c2 )*...*p(Q N-1 Q c(N-1) )*p(Q N Q cN )

[0093] Where pc1 represents the vertical distance error probability between the first position point and the third position point on the c-th candidate path, and Q cN This represents the Nth third position point on the c-th candidate path.

[0094] In some implementations, the difference in path segment distances can be expressed by a second accuracy rate that matches the distance traveled by the moving object during a turn with the path distance of the turning segment in the candidate path.

[0095] In some implementations, determining a second accuracy rate for matching the distance traveled by the moving object during a turn with the path distance of the turning segment in the candidate path, based on the driving data of the first location point and the location data of the third location point on the candidate path, may include the following steps:

[0096] Based on the driving data of the first position point and the position data of the third position point on the candidate path, a first sub-accuracy and a second sub-accuracy are determined for each third position point. The first sub-accuracy represents the accuracy of matching between the total distance traveled by the moving object during the turning and the total path distance during the change of direction of the road segment in the candidate path. The second sub-accuracy represents the accuracy of matching between the first ratio and the second ratio. The first ratio is the ratio between the distances traveled by the moving object before and after the turning, and the second ratio is the ratio between the path distances traveled by the moving object before and after the change of direction of the road segment in the candidate path.

[0097] Based on the first and second sub-accuracy rates corresponding to the same third position point, the third sub-accuracy rate of that position point is obtained.

[0098] The second accuracy is obtained based on the third sub-accuracy corresponding to each third position point.

[0099] In this embodiment of the disclosure, the movement distance of the path object during the turning process can include the total movement distance during the turning process, as well as the movement distances before and after the turning. The path distance of the turning segment in the candidate path can include the total path distance during the period when the direction of the segment in the candidate path changes, as well as the path distances before and after the change of direction of the segment in the candidate path. Furthermore, a first sub-accuracy corresponding to a certain third position point can be determined based on the total movement distance of the moving object during the turning process and the total path distance during the period when the direction of the segment in the candidate path changes. A second sub-accuracy corresponding to a certain third position point can be determined based on the movement distance of the moving object before and after the turning process, as well as the path distances before and after the change of direction of the segment in the candidate path.

[0100] Here, for the i-th third position point in the c-th candidate path, the third sub-accuracy of that position point can be obtained based on the first sub-accuracy and the second sub-accuracy corresponding to that third position point. The specific calculation method is as follows:

[0101] p(Q ci Q c(i+1) )=βp a +(1-β)p b

[0102]

[0103] Where p(Q) ci Q c(i+1) ) represents the third sub-accuracy corresponding to the i-th third position point in the c-th candidate path, p a p represents the accuracy of the first sub-sub. b The second sub-accuracy is represented by D3, which represents the distance the moving object traveled before turning, and D4 represents the distance the moving object traveled after turning. d3 represents the path distance before the road segment direction changed, and d4 represents the path distance after the road segment direction changed. z is a very small positive value, which can be set to 0.1. β can be adjusted according to the actual situation, for example, it can be set to 0.5.

[0104] For example, suppose the moving object is at T i To T i+1 Within the time frame, the actual distance traveled before the turn is D3 = 20 meters, and the actual distance traveled after the turn is D4 = 30 meters. The i-th third position point Q in the first candidate path... 1i The distance d3 before the road segment turns is 22 meters, and the distance to the (i+1)th third position point Q in the first candidate path after the road segment turns is... 1(i+1) If the distance d4 = 24 meters, then:

[0105]

[0106] In some implementations, after obtaining the third sub-accuracy corresponding to each third location point, the third sub-accuracy corresponding to each third location point can be processed by the following formula to obtain the second accuracy matching the movement distance of the moving object during the turning period and the path distance of the turning segment in the candidate path:

[0107] pc2=p(Q c1 Q c2 )*p(Q c2 Q c3 )*...*p(Q c(N-1) Q cN )

[0108] Where pc2 represents the second accuracy of matching the distance traveled by the moving object during the turn with the path distance of the turning segment in the c-th candidate path, Q cN This represents the Nth third position point on the c-th candidate path.

[0109] In some implementations, determining a first sub-accuracy and a second sub-accuracy corresponding to each third location point based on the driving data of the first location point and the location data of the third location points on the candidate path may include the following steps:

[0110] For the i-th third location point, if there is a change in road direction between the i-th third location point and the (i+1)-th third location point, based on the driving data of the first location point, obtain the first movement distance of the moving object from the i-th sampling time to the turning time, the second movement distance of the moving object from the turning time to the (i+1)-th sampling time, and based on the position data of the third location points on the candidate path, obtain the first path distance between the i-th third location point and the path turning point, and the second path distance between the path turning point and the (i+1)-th third location point. Here, the i-th sampling time is the sampling time of the first location point Qi associated with the i-th third location point, i is greater than or equal to 1 and less than or equal to N-1, and N represents the total number of first location points.

[0111] Based on the first motion distance, the second motion distance, the first path distance, and the second path distance, determine the first sub-accuracy and the second sub-accuracy corresponding to the i-th third position point.

[0112] In this embodiment of the disclosure, when determining the first sub-accuracy and the second sub-accuracy corresponding to the i-th third position point, there are two cases: one where the road segment direction has changed, and the other where the road segment direction has not changed. Optionally, the relationship between the direction angle difference between two adjacent first position points and a preset threshold can be used to determine whether the moving object has changed direction between these two first position points. Similarly, the relationship between the direction angle difference between two adjacent third position points in the candidate path and a preset threshold can be used to determine whether the moving object has changed direction between these two third position points.

[0113] In this embodiment of the disclosure, for the i-th third position point, when there is a change in road segment direction between the i-th third position point and the (i+1)-th third position point, the following can be obtained based on the driving data of the i-th first position point and the (i+1)-th first position point: the first movement distance of the moving object from the i-th sampling time to the turning time, i.e., the movement distance of the moving object before the turning; the second movement distance of the moving object from the turning time to the (i+1)-th sampling time, i.e., the movement distance of the moving object after the turning; and the first path distance between the i-th third position point and the path turning point, i.e., the path distance before the change in road segment direction, based on the position data of the i-th third position point and the (i+1)-th third position point; and the second path distance between the path turning point and the (i+1)-th third position point, i.e., the path distance after the change in road segment direction.

[0114] After obtaining the first movement distance, the second movement distance, the first path distance, and the second path distance, we can then use the aforementioned formula... as well as Determine the first and second sub-accuracy rates corresponding to the i-th third position point. Here, d3+d4 represents the total path distance during the change of road segment direction, and D3+D4 represents the total distance the moving object travels during the turning process.

[0115] In some implementations, for road segments whose direction has not changed, the corresponding third sub-accuracy can be set to a fixed value, such as 1.

[0116] In some implementations, after obtaining the first accuracy, vertical distance error probability, and second accuracy of the c-th candidate path, the first accuracy, vertical distance error probability, and second accuracy can be processed using the following formula to obtain the probability that the first location point belongs to the candidate path:

[0117] pc=πc*pc1*pc2=πc*p(Q1,Q c1 )*p(Q c1 Qc2 )*p(Q2,Q c2 )*p(Q c2 Q c3 )*...*p(Q N-1 Q c(N-1) )*p(Q c(N-1) Q cN )*p(Q N Q cN )

[0118] In some implementations, since pc is calculated using a multiplication operation, logarithmic form can be used to avoid the value being too small, i.e., gc = lg(pc).

[0119] Through the above process, the probability that the first position point belongs to any candidate path can be obtained. In some implementations, based on the probability, the target path that matches the movement process of the moving object is determined from multiple candidate paths. This can be done by determining the candidate path with the highest probability as the target path that matches the movement process of the moving object.

[0120] For example, suppose there are two candidate paths. The probability that the first position point belongs to each candidate path is represented by g1 and g2 respectively. If g1 > g2, the first candidate path is matched; if g1 < g2, the second candidate path is matched; if the two are the same, a random match is made.

[0121] In some implementations, to further improve path matching accuracy, determining a target path that matches the motion process of the moving object from multiple candidate paths based on probability may include the following steps:

[0122] Based on the probability that the first position point belongs to each candidate path, the first path selection result is determined from multiple candidate paths;

[0123] Based on the first accuracy corresponding to each candidate path, determine the second path selection result from multiple candidate paths;

[0124] Based on the vertical distance error probability between the target first location point and the third location point on each candidate path, the third sub-path selection result of the corresponding target first location point is obtained, where the target first location point is any first location point;

[0125] Based on the third sub-path selection results corresponding to each first position point, the third path selection result is obtained;

[0126] The candidate path that appears most frequently in the first, second, and third path selection results is determined as the target path.

[0127] In this embodiment, instead of using the probability of the first position point belonging to each candidate path alone to determine the target path that matches the movement process of the moving object from multiple candidate paths, the probability is used as the first path selection result. Then, the second path selection result and the third path selection result are combined to jointly determine the final target path. That is, the candidate path that appears most frequently in the first path selection result, the second path selection result, and the third path selection result is determined as the target path. In this way, the influence of random errors caused by special sampling points can be avoided, and the accuracy of path matching can be further improved.

[0128] In some implementations, a second path selection result can be determined from multiple candidate paths based on a first accuracy corresponding to each candidate path. Optionally, the candidate path corresponding to the highest first accuracy can be determined as the second path selection result.

[0129] In some implementations, the third sub-path selection result for the target first location point can be obtained firstly based on the vertical distance error probability between the target first location point and the third location point on each candidate path. Then, the third path selection result can be obtained based on the third sub-path selection results for each first location point. Optionally, for the target first location point, the candidate path corresponding to the maximum vertical distance error probability can be determined as the third sub-path selection result for the target first location point. Then, the candidate path that appears most frequently can be selected from the third sub-path selection results for each first location point as the third path selection result.

[0130] The path matching method of this disclosure embodiment will now be described with reference to an example.

[0131] 1. During vehicle operation, the vehicle's position data is collected using a GPS device, and the sampling time is recorded; the vehicle's azimuth angle data is collected using a magnetometer device, and the sampling time is recorded; the vehicle's speed, acceleration, steering wheel angle, and other data are collected using a CAN bus, and the sampling time is recorded; the sampling frequency of the magnetometer and CAN bus must be higher than the GPS sampling frequency and be an integer multiple of the GPS sampling frequency.

[0132] 2. Suppose that there are N points in the GPS location data collected, denoted as Q = [Q1, Q2, ..., Q...]. N The corresponding sampling time is T = [T1, T2, ..., T]. N Based on the driving azimuth angle and sampling time collected by the magnetometer device, the driving azimuth angle corresponding to the above time is found and denoted as θ=[θ1,θ2,...,θ N ];

[0133] 3. For two candidate paths that may match in the map, assume that the location data points in the two candidate paths are: R(1)=[R 11 ,R 12 ,...,R 1E ], R(2)=[R 21 ,R 22 ,...,R 2F The direction of each data point is set as θ(1)=[θ 11 ,θ 12 ,...,θ 1E ],θ(2)=[θ 21 ,θ 22 ,...,θ 2F Based on the above data, the path matching problem can be summarized as: which candidate path has the highest probability of the location point Q collected by GPS belonging to, that is, matching it with it;

[0134] 4. For the N location points Q collected by GPS, in each candidate path, find the N path location points that are closest to it, and denote them as Q(R1) = [Q 11 Q 12 ,...,Q 1N ]、Q(R2)=[Q 21 Q 22 ,...,Q 2N ], and their directions are respectively set as φ(1)=[φ 11 ,φ 12 ,...,φ 1N ] and φ(2)=[φ 21 ,φ 22 ,...,φ 2N ], where Q 1i ∈R(1),φ 1i ∈θ(1), 1≤i≤N, Q 2j ∈R(2),φ 2j ∈θ(2), 1≤j≤N;

[0135] 5. It should be noted that in step 4, for each GPS location point, when searching for the nearest path location point in each candidate path, the direction data of the two must be consistent (i.e., θ and φ1, θ and φ2). This can be achieved by comparing the absolute value of the difference between the driving azimuth angle θ and the path direction θ1 (or θ2) and whether it is less than the set threshold.

[0136] 6. Let p1 be the probability that GPS location point Q belongs to candidate path R1 and p2 be the probability that it belongs to candidate path R2. These two probabilities can be calculated using the following formula:

[0137] p1=π1*p(Q1,Q 11 )*p(Q 11 Q 12 )*p(Q2,Q 12 )*p(Q 12 Q 13 )*...*p(Q N-1 Q 1(N-1) )*p(Q 1(N-1) Q 1N )*p(Q N Q 1N )

[0138] p2=π2*p(Q1,Q 21 )*p(Q 21 Q 22 )*p(Q2,Q 22 )*p(Q 22 Q 23 )*...*p(Q N-1 Q 2(N-1) )*p(Q 2(N-1) Q 2N )*p(Q N Q 2N )

[0139] 7. The calculation of π1 and π2 follows these rules: the distance to candidate path Q(R1) is calculated and denoted as d1; the distance to candidate path Q(R2) is calculated and denoted as d2. d1 and d2 can be obtained by calculating segmented distances based on the pairwise GPS location latitude and longitude and then summing them; the distance to the vehicle in T = [T1, T2, ..., T...] is calculated. N Let D be the actual distance traveled within the specified time period. D can be calculated by accumulating discrete data such as vehicle speed and acceleration collected by the CAN bus during this time period (or by using an odometer). Where z is a very small positive value, which can be set to 0.05; π1 and π2 represent the accuracy of matching between the total distance traveled by the vehicle in time T and the distance of the candidate path.

[0140] For example, if the actual distance traveled by the vehicle is D = 500 meters, and the distance of the candidate path Q(R1) is d1 = 530 meters, then...

[0141] 8. p(Q) r Q 1r ) and p(Q r Q 2r The calculation of (1≤r≤N) follows the following rules:

[0142]

[0143] d(Q r Q 1r )=min[d(Q 1(r-1) Q 1r ),d(Q 1r Q 1(r+1) )]

[0144] Wherein d(Q) 1(r-1) Q 1r ) represents GPS location point Q r Distance (Q) 1(r-1) Q 1r The perpendicular distance between the two points, d(Q) 1r Q 1(r+1) ) represents GPS location point Q r Distance (Q) 1r Q 1(r+1) The perpendicular distance between the lines connecting the two points; similarly, d(Q) r Q 2r )=min[d(Q 2(r-1) Q 2r ),d(Q 2r Q 2(r+1) )], where d(Q 2(r-1) Q 2r ) represents GPS location point Q r Distance (Q) 2(r-1) Q 2r The perpendicular distance between the two points, d(Q) 2r Q 2(r+1) ) represents GPS location point Q r Distance (Q) 2r Q 2(r+1) The perpendicular distance between the two points; σ is the standard deviation parameter, which can be set based on experience; the above probability can characterize the probability of error in the perpendicular distance between the GPS location point and the path location point.

[0145] 9. p(Q) 1i Q 1(i+1) ), p(Q 2i Q 2(i+1) The calculation of )(1≤i≤N-1) follows the rules to determine φ. 1i φ 1(i+1) (1≤i≤N-1) or φ 2i φ 2(i+1) (1≤i≤N-1) Whether the directions are consistent, if the absolute value of the direction difference is less than the set threshold, then p(Q) 1i Q 1(i+1) ) or p(Q 2i Q 2(i+1)If the absolute value of the direction difference is greater than the set threshold, it indicates that the direction of the road segment in the candidate path has changed, and the two location points belong to different road segments. p(Q) 1i Q 1(i+1) ), p(Q 2i Q 2(i+1) The calculation of (1≤i≤N-1) is shown in the process in number 10;

[0146] 10. Using p(Q) 1i Q 1(i+1) Taking (e.g.) as an example, calculate the candidate path Q. 1i Let d3 be the distance from the point to the road segment before the turn, and calculate the distance from the point to the candidate path Q after the turn. 1(i+1) Let the distance between the points be d4. Based on the vehicle's steering wheel angle, speed, and acceleration data from the CAN bus, calculate the actual distance traveled by the vehicle before turning (which can also be obtained using an odometer), and let this be denoted as D3. Then, calculate the actual distance traveled by the vehicle after turning, and let this be denoted as D4.

[0147] p(Q 1i Q 1(i+1) )=βp a +(1-β)p b , 0≤β≤1

[0148]

[0149] Wherein, β can be adjusted according to the actual situation; for example, it can be set to 0.5, representing p. a and p b The weights are the same; p a Indicates that the vehicle is at T i To T i+1 The accuracy of matching the distance traveled within a time period with the path distance; p b Indicates that the vehicle is at T i To T i+1 The accuracy of matching the ratio of the actual distance traveled between two road segments within a time period to the ratio of the distance between two road segments in the candidate path; z is a very small positive value, which can be set to 0.1;

[0150] For example, vehicles at T i To T i+1 Within the given time, the actual distance traveled before the turn is D3 = 20 meters, and the actual distance traveled after the turn is D4 = 30 meters. The candidate path Q... 1i The distance from the point to the road segment before the turn is d3 = 22 meters, and the distance from the point to Q after the turn is... 1(i+1) If the distance between the points is d4 = 24 meters, then:

[0151]

[0152] 11. Since the probabilities p1 and p2 in process number 6 are multiplied together, to avoid the values ​​being too small, this embodiment of the disclosure uses logarithmic form, that is:

[0153] g1 = lg(p1)

[0154] g2 = lg(p2)

[0155] 12. Compare g1 and g2 in process 11. If g1 > g2, then match candidate path 1; if g1 < g2, then match candidate path 2; if they are the same, then match randomly.

[0156] 13. To further improve matching accuracy, the result of process 12 is denoted as Result1, which reflects the sum of total probabilities. Compare the values ​​of π1 and π2 in process 7. If π1 > π2, then candidate path 1 is matched; otherwise, it is not. This result is denoted as Result2, which reflects the accuracy of matching the actual total distance traveled with the candidate path distance. Compare p(Q) in process 6... r Q 1r ) and p(Q r Q 2r Given a set of N values ​​(1≤r≤N), we match the class with the highest probability and the largest number of values ​​(e.g., if N=5, if p(Q) = 1, r ≤ N). r Q 1r )>p(Q r Q 2r When r=1, r=2, r=5, then candidate path 1 is matched), and this result is recorded as Result3. This result reflects that the GPS sampling points belong to a certain candidate path that is close and numerous. For the results of Result1, Result2, and Result3, the final decision can be given based on the voting rules. This method can avoid the influence of random errors caused by special sampling points.

[0157] Based on the same inventive concept, embodiments of this disclosure provide a path matching device. Figure 2 This is a block diagram of a path matching device 200 shown in an exemplary embodiment of this disclosure, with reference to... Figure 2 The path matching device 200 includes:

[0158] The acquisition module 201 is used to acquire the first position point of the moving object during its movement from the starting point to the ending point, and multiple candidate paths from the starting point to the ending point, wherein each candidate path includes multiple second position points;

[0159] The first determining module 202 is used to determine the probability that the first location point belongs to each of the candidate paths based on the motion data of the first location point and the location data of the second location points included in each candidate path. The motion data includes location data and driving data used to determine the movement distance of the moving object.

[0160] The second determining module 203 is used to determine, based on the probability, a target path that matches the motion process of the moving object from the plurality of candidate paths.

[0161] Optionally, the first determining module 202 includes:

[0162] The first determining submodule is used to determine, for any candidate path, a third location point associated with each of the first location points from the second location points of the candidate path, based on the location data of the first location point and the location data of the second location points included in the candidate path, wherein the number of second location points in the candidate path is greater than the number of first location points, and the associated first location points and third location points satisfy a preset distance condition and a preset direction condition.

[0163] The second determining submodule is used to determine the probability that the first position point belongs to the candidate path based on the motion data of the first position point and the position data of the third position point on the candidate path.

[0164] Optionally, the second determining submodule includes:

[0165] The first determining unit is configured to, for any candidate path, based on the driving data of the first position point and the position data of the third position point on the candidate path, determine a first accuracy rate for matching the total movement distance of the moving object before the last first position point with the total path distance before the target third position point on the candidate path, wherein the target third position point is a third position point associated with the last first position point.

[0166] The second determining unit is used to determine the vertical distance error probability between the first location point and the third location point on the candidate path based on the location data of the first location point and the location data of the third location point on the candidate path.

[0167] The third determining unit is used to determine a second accuracy rate for matching the movement distance of the moving object during the turning process with the path distance of the turning segment in the candidate path based on the driving data of the first position point and the position data of the third position point on the candidate path.

[0168] The fourth determining unit is used to determine the probability that the first location point belongs to the candidate path based on the first accuracy, the vertical distance error probability, and the second accuracy.

[0169] Optionally, the second determining unit includes:

[0170] The first determining subunit is used to determine, for the r-th first position point, a first line segment associated with the r-th first position point based on the position data of the third position point associated with the r-th first position point in the candidate path and the position data of the third position point associated with the (r-1)-th first position point in the candidate path.

[0171] The second determining subunit is used to determine the second line segment associated with the r-th first position point based on the position data of the third position point associated with the r-th first position point in the candidate path and the position data of the third position point associated with the (r+1)-th first position point in the candidate path.

[0172] The third determining subunit is used to determine the first vertical distance between the r-th first position point and the first line segment, and to determine the second vertical distance between the r-th first position point and the second line segment;

[0173] The fourth determining subunit is used to determine the sub-vertical distance error probability corresponding to the r-th first position point based on the first vertical distance and the second vertical distance;

[0174] The fifth determining subunit is used to obtain the vertical distance error probability between the first position point and the third position point on the candidate path based on the sub-vertical distance error probability corresponding to each first position point.

[0175] Optionally, the third determining unit includes:

[0176] The sixth determining subunit is used to determine a first sub-accuracy and a second sub-accuracy corresponding to each third position point based on the driving data of the first position point and the position data of the third position points on the candidate path. The first sub-accuracy represents the accuracy of matching between the total movement distance of the moving object during the turning and the total path distance during the change of direction of the road segment in the candidate path. The second sub-accuracy represents the accuracy of matching between a first ratio and a second ratio. The first ratio is the ratio between the movement distances of the moving object before and after the turning, and the second ratio is the ratio between the path distances of the road segment in the candidate path before and after the change of direction.

[0177] The seventh determining sub-unit uses the first sub-accuracy and the second sub-accuracy based on the corresponding third position point to obtain the third sub-accuracy of that position point;

[0178] The eighth determination sub-unit uses the third sub-accuracy corresponding to each third position point to obtain the second accuracy.

[0179] Optionally, the sixth determining subunit is further configured to, for the i-th third position point, when there is a change in road direction between the i-th third position point and the (i+1)-th third position point, obtain, based on the driving data of the first position point, a first movement distance of the moving object from the i-th sampling time to the turning time, a second movement distance of the moving object from the turning time to the (i+1)-th sampling time, and, based on the position data of the third position points on the candidate path, obtain a first path distance between the i-th third position point and the path turning point, and a second path distance between the path turning point and the (i+1)-th third position point, wherein the i-th sampling time is the sampling time of the first position point associated with the i-th third position point, i is greater than or equal to 1 and less than or equal to N-1, and N represents the total number of first position points; and, based on the first movement distance, the second movement distance, the first path distance, and the second path distance, determine a first sub-accuracy and a second sub-accuracy corresponding to the i-th third position point.

[0180] Optionally, the second determining module 203 includes:

[0181] The third determining submodule is used to determine the first path selection result from the multiple candidate paths based on the probability that the first location point belongs to each of the candidate paths;

[0182] The fourth determining submodule is used to determine the second path selection result from the plurality of candidate paths based on the first accuracy corresponding to each candidate path;

[0183] The fifth determining submodule is used to obtain the third sub-path selection result corresponding to the target first position point based on the vertical distance error probability between the target first position point and the third position point on each candidate path, wherein the target first position point is any first position point;

[0184] The sixth determination submodule is used to obtain the third path selection result based on the third sub-path selection result corresponding to each first position point;

[0185] The seventh determination submodule is used to determine the candidate path that appears most frequently among the first path selection result, the second path selection result, and the third path selection result as the target path.

[0186] Regarding the path matching device 200 in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0187] Based on the same inventive concept, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the path matching method described in any embodiment of this disclosure.

[0188] Based on the same inventive concept, this disclosure also provides an electronic device, including:

[0189] A memory on which computer programs are stored;

[0190] A processor is configured to execute the computer program in the memory to implement the steps of the path matching method described in any embodiment of the present disclosure.

[0191] Figure 3 This is a block diagram illustrating an electronic device 300 according to an exemplary embodiment. Figure 3 As shown, the electronic device 300 may include a processor 301 and a memory 302. The electronic device 300 may also include one or more of a multimedia component 303, an input / output (I / O) interface 304, and a communication component 305.

[0192] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps in the path matching method described above. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 302 or transmitted via communication component 305. The audio component also includes at least one speaker for outputting audio signals. I / O interface 304 provides an interface between processor 301 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 305 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0193] In an exemplary embodiment, the electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the path matching method described above.

[0194] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the path matching method described above. For example, the computer-readable storage medium may be the memory 302 including the program instructions described above, which may be executed by the processor 301 of the electronic device 300 to complete the path matching method described above.

[0195] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the path matching method described above when executed by the programmable device.

[0196] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0197] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0198] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A path matching method, characterized in that, include: The first position point of the moving object during its movement from the starting point to the end point and multiple candidate paths from the starting point to the end point are obtained, and each candidate path includes multiple second position points; Based on the motion data of the first location point and the location data of the second location points included in each candidate path, the probability that the first location point belongs to each candidate path is determined. The motion data includes location data and driving data used to determine the movement distance of the moving object. Based on the probability, a target path matching the motion process of the moving object is determined from the plurality of candidate paths; The determination of the probability that the first location point belongs to each candidate path based on the motion data of the first location point and the location data of the second location points included in each candidate path includes: For any candidate path, based on the driving data of the first position point and the position data of the third position point on the candidate path, a first accuracy rate is determined to match the total movement distance of the moving object before the last first position point with the total path distance before the target third position point on the candidate path, wherein the target third position point is a third position point associated with the last first position point; the third position point is determined based on the second position point. Based on the first accuracy, the motion data of the first location point, and the location data of the third location point on the candidate path, the probability that the first location point belongs to the candidate path is determined.

2. The method according to claim 1, characterized in that, The third position point is determined based on the second position point, specifically including: For any candidate path, based on the location data of the first location point and the location data of the second location points included in the candidate path, a third location point is determined from the second location points of the candidate path that is associated with each of the first location points respectively, wherein the number of second location points in the candidate path is greater than the number of first location points, and the associated first location points and third location points satisfy a preset distance condition and a preset direction condition.

3. The method according to claim 2, characterized in that, The step of determining the probability that the first location point belongs to the candidate path based on the first accuracy, the motion data of the first location point, and the location data of the third location point on the candidate path includes: Based on the location data of the first location point and the location data of the third location point on the candidate path, the vertical distance error probability between the first location point and the third location point on the candidate path is determined. Based on the driving data of the first location point and the location data of the third location point on the candidate path, a second accuracy rate is determined to match the movement distance of the moving object during the turning process with the path distance of the turning segment in the candidate path. Based on the first accuracy, the vertical distance error probability, and the second accuracy, the probability that the first location point belongs to the candidate path is obtained.

4. The method according to claim 3, characterized in that, The step of determining the vertical distance error probability between the first location point and the third location point on the candidate path based on the location data of the first location point and the location data of the third location point on the candidate path includes: For the r-th first position point, based on the position data of the third position point associated with the r-th first position point in the candidate path and the position data of the third position point associated with the (r-1)-th first position point in the candidate path, the first line segment associated with the r-th first position point is determined; Based on the position data of the third position point associated with the r-th first position point in the candidate path and the position data of the third position point associated with the (r+1)-th first position point in the candidate path, the second line segment associated with the r-th first position point is determined. Determine the first perpendicular distance between the r-th first position point and the first line segment, and determine the second perpendicular distance between the r-th first position point and the second line segment; Based on the first vertical distance and the second vertical distance, determine the sub-vertical distance error probability corresponding to the r-th first position point; Based on the sub-vertical distance error probability corresponding to each first position point, the vertical distance error probability between the first position point and the third position point on the candidate path is obtained.

5. The method according to claim 3, characterized in that, The determination of a second accuracy rate for matching the distance traveled by the moving object during a turn with the path distance of the turning segment in the candidate path, based on the driving data from the first location point and the location data from the third location point on the candidate path, includes: Based on the driving data of the first location point and the location data of the third location point on the candidate path, a first sub-accuracy and a second sub-accuracy corresponding to each third location point are determined. The first sub-accuracy represents the accuracy of matching between the total movement distance of the moving object during the turning and the total path distance during the change of direction of the road segment in the candidate path. The second sub-accuracy represents the accuracy of matching between a first ratio and a second ratio. The first ratio is the ratio between the movement distances of the moving object before and after the turning, and the second ratio is the ratio between the path distances of the moving object before and after the change of direction of the road segment in the candidate path. Based on the first and second sub-accuracy rates corresponding to the same third position point, the third sub-accuracy rate of that position point is obtained. The second accuracy is obtained based on the third sub-accuracy corresponding to each third position point.

6. The method according to claim 5, characterized in that, The determination of the first sub-accuracy and the second sub-accuracy corresponding to each third location point, based on the driving data of the first location point and the location data of the third location points on the candidate path, includes: For the i-th third location point, if there is a change in road direction between the i-th third location point and the (i+1)-th third location point, based on the driving data of the first location point, obtain the first movement distance of the moving object from the i-th sampling time to the turning time, the second movement distance of the moving object from the turning time to the (i+1)-th sampling time, and, based on the position data of the third location points on the candidate path, obtain the first path distance between the i-th third location point and the path turning point, and the second path distance between the path turning point and the (i+1)-th third location point, wherein the i-th sampling time is the sampling time of the first location point associated with the i-th third location point, i is greater than or equal to 1 and less than or equal to N-1, and N represents the total number of first location points; Based on the first movement distance, the second movement distance, the first path distance, and the second path distance, determine the first sub-accuracy and the second sub-accuracy corresponding to the i-th third position point.

7. The method according to any one of claims 3-6, characterized in that, The step of determining a target path that matches the motion process of the moving object from the plurality of candidate paths based on the probability includes: Based on the probability that the first location point belongs to each of the candidate paths, the first path selection result is determined from the plurality of candidate paths; Based on the first accuracy corresponding to each candidate path, a second path selection result is determined from the plurality of candidate paths; Based on the vertical distance error probability between the target first location point and the third location point on each candidate path, the third sub-path selection result corresponding to the target first location point is obtained, where the target first location point is any first location point; Based on the third sub-path selection results corresponding to each first position point, the third path selection result is obtained; The candidate path that appears most frequently in the first path selection result, the second path selection result, and the third path selection result is determined as the target path.

8. A path matching device, characterized in that, The device includes: The acquisition module is used to acquire the first position point of the moving object during its movement from the starting point to the end point, as well as multiple candidate paths from the starting point to the end point, each candidate path including multiple second position points; The first determining module is used to determine the probability that the first location point belongs to each of the candidate paths based on the motion data of the first location point and the location data of the second location points included in each candidate path. The motion data includes location data and driving data used to determine the movement distance of the moving object. The second determining module is used to determine a target path that matches the motion process of the moving object from the plurality of candidate paths based on the probability. The first determining module is further configured to, for any candidate path, determine a first accuracy rate for matching the total distance traveled by the moving object before the last first position point with the total path distance before the target third position point on the candidate path, based on the driving data of the first position point and the position data of the third position point on the candidate path, wherein the target third position point is a third position point associated with the last first position point; the third position point is determined based on the second position point; and determine the probability that the first position point belongs to the candidate path based on the first accuracy rate, the motion data of the first position point, and the position data of the third position point on the candidate path.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

Images