A data-driven urban green freight new energy vehicle parking destination identification method

Abstract

The application relates to a data-driven city green freight new energy vehicle parking purpose identification method, which comprises the following steps: S1, acquiring an original vehicle positioning data sequence; S2, pre-processing and repairing the acquired original positioning data to obtain one or more target vehicle positioning data sequences; S3, based on the target vehicle positioning data sequence, comparing the distance and average speed of adjacent track points with pre-configured distance threshold and average speed threshold respectively, screening all vehicle stop points, and constructing continuous vehicle stop points into a vehicle stop point cluster; S4, judging whether each stop point set is a valid stop point set or a pending stop point set based on the time difference between the last stop point and the first stop point in the constructed stop point set; S5, for each pending stop point set, combining a turning angle and a travel chain analysis to determine whether each stop point set is a valid stop point set; and S6, determining the parking purpose of all valid stop point sets. Compared with the prior art, the application has the advantages of strong anti-interference capability and the like.

Description

Technical Field

[0001] This invention relates to the field of vehicle transportation, and in particular to a data-driven method for identifying the parking purpose of urban green freight new energy vehicles. Background Technology

[0002] Obtaining vehicle stopping points is a crucial basis for urban planning. Unlike traditional manual identification and survey methods, some existing technologies have proposed stopping point identification methods based on vehicle location data. For example, Chinese patent CN118469429A discloses a method for identifying truck stopping points based on the spatiotemporal characteristics of GPS data. This method includes: arranging each GPS trajectory data point in order from morning to night according to the timestamp; calculating the number of neighboring points of each trajectory point; segmenting the trajectory density distribution curve according to a dense interval division threshold to determine the dense intervals of trajectory points; using cluster analysis to identify spatial clusters in multiple sets of original GPS trajectory data of the same truck; obtaining multiple dense intervals of trajectory points contained in or intersecting each spatial cluster; determining whether the multiple dense intervals of trajectory points contained in or intersecting with the spatial cluster are temporally continuous to determine a set of candidate stopping points; if the vehicle displacement, vehicle dwell time, vehicle speed, and vehicle travel mode in the candidate stopping point set all meet preset conditions, then the candidate stopping point set is the final stopping point.

[0003] The above application allows for the identification of stop points using GPS data without the need for surveys, thus overcoming spatial constraints and enabling identification by specialized software tools.

[0004] However, firstly, given the increasing proportion of new energy trucks, the above method cannot distinguish between traditional stopping points and charging demand stopping points, resulting in data that has no application value. Secondly, when faced with situations such as interchange areas or poor vehicle positioning device networks that may lead to excessive data errors, the above method may suffer from interference from some smaller error data, resulting in a lower accuracy of the final identification result. Summary of the Invention

[0005] The purpose of this invention is to provide a data-driven method for identifying the parking purpose of urban green freight new energy vehicles.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A data-driven method for identifying the parking purpose of new energy vehicles used for urban green freight transport includes:

[0008] Step S1: Obtain the original vehicle positioning data sequence, wherein each trajectory point in the vehicle positioning data sequence includes latitude and longitude, timestamp, remaining battery percentage, charging status and instantaneous speed;

[0009] Step S2: Preprocess and repair the acquired raw positioning data to obtain one or more target vehicle positioning data sequences;

[0010] Step S3: Based on the target vehicle positioning data sequence, all vehicle stopping points are selected by comparing the distance and average speed of adjacent trajectory points with pre-configured distance thresholds and average speed thresholds, and consecutive vehicle stopping points are constructed into a vehicle stopping point cluster.

[0011] Step S4: Based on the time difference between the last stopping point and the first stopping point in the constructed stopping point set, determine whether each stopping point set is a valid stopping point set or a set of undetermined stopping points;

[0012] Step S5: For each set of undetermined stopping points, combine the turning angle and travel chain analysis to determine whether each set of stopping points is a valid set of stopping points;

[0013] Step S6: Determine the parking purpose of all valid stop point sets.

[0014] Step S2 includes:

[0015] Step S2-1: Delete all data points in the vehicle positioning data sequence with a longitude or latitude of 0, as well as data points that exceed the longitude or latitude threshold range;

[0016] Step S2-2: Delete all data points in the vehicle location data sequence whose timestamps remain unchanged;

[0017] Step S2-3: Calculate the average speed between adjacent data points. If the average speed between adjacent data points is greater than the pre-configured maximum speed, delete the corresponding data point.

[0018] Step S2-4: When the timestamp difference between adjacent data points exceeds the pre-configured duration threshold, the vehicle positioning data sequence is segmented to obtain multiple target vehicle positioning data sequences.

[0019] Step S3 includes:

[0020] Step S3-1: Configure distance threshold and average speed threshold;

[0021] Step S3-2: Calculate the distance and average speed between each adjacent data point in the target vehicle positioning data sequence. If the distance between adjacent data points is less than the distance threshold and the average speed is less than the average speed threshold, then the previous data point among the adjacent data points is determined as the vehicle stopping point.

[0022] Step S3-3: Construct all consecutive vehicle stop points into a vehicle stop point cluster.

[0023] The distance threshold is determined in the following way: based on the target vehicle positioning data sequence, a logarithmic distribution curve of the distance between two adjacent trajectory data points is constructed. The logarithmic distribution curve shows a bimodal mixed distribution, and the target point with the mixed distribution is used as the distance threshold.

[0024] The average speed threshold is determined as follows: based on the target vehicle positioning data sequence, an average speed logarithmic distribution curve of two adjacent trajectory data points is constructed. The logarithmic distribution curve presents a bimodal mixed distribution, and the target point with the mixed distribution is used as the average speed threshold.

[0025] Step S4 includes:

[0026] Step S4-1: Determine a first parking duration threshold and a second parking duration threshold by fitting a power law distribution on a double logarithmic axis, wherein the first parking duration threshold is greater than the second parking duration threshold;

[0027] Step S4-2: Determine whether the time difference between the last parking point and the first parking point in the vehicle stopping point cluster exceeds the first parking duration threshold. If yes, the vehicle stopping point cluster is a valid stopping point set; otherwise, proceed to step S4-3.

[0028] Step S4-3: Determine whether the time difference between the last parking point and the first parking point in the vehicle stopping point cluster exceeds the second parking duration threshold. If yes, then the vehicle stopping point cluster is a set of undetermined stopping points.

[0029] In step S4-1, the process of fitting a power law distribution on the double logarithmic axis is divided into four segments.

[0030] Step S5 includes:

[0031] Step S5-1: For each set of undetermined stopping points, determine whether the charging status of each stopping point is charging or charging is complete. If yes, calculate whether the remaining power percentage of the last stopping point is greater than the remaining power percentage of the first stopping point. If yes, mark the set of undetermined stopping points as a valid stopping point set. Otherwise, proceed to step S5-2.

[0032] Step S5-2: Calculate the turning angle of each set of undetermined stopping points. If the turning angle is greater than the pre-configured angle threshold, mark the set of undetermined stopping points as a valid parking point set; otherwise, proceed to step S5-3.

[0033] Step S5-3: Based on the travel chain analysis, determine whether the set of undetermined stopping points is the start or end point of the travel chain. If yes, mark the set of undetermined stopping points as a valid stopping point set; otherwise, proceed to step S5-4.

[0034] Step S5-4: Determine whether the set of undetermined stopping points is located after the set of valid stopping points for charging purposes. If yes, mark the set of undetermined stopping points as a valid stopping point set; otherwise, proceed to step S5-5.

[0035] Step S5-5: Determine whether the location of the set of undetermined stopping points has been identified as a valid parking point set in the historical determination. If so, mark the set of undetermined stopping points as a valid parking point set.

[0036] The calculation process for the turning angle of the set of undetermined stopping points includes:

[0037] Step S5-2-1: Determine the actual stopping positions of the set of undetermined stopping points;

[0038] Step S5-2-2: Based on the location of the set of pending stopping points, extract from the target vehicle positioning data sequence the cluster of forward moving points that is located before and adjacent to the set of pending stopping points, and the cluster of backward moving points that is located after and adjacent to the set of pending stopping points;

[0039] Step S5-2-3: Based on the forward and backward movement point clusters, and combined with the actual stopping positions of the set of undetermined stopping points, determine the turning angle of the set of undetermined stopping points:

[0040]

[0041] Where: α(s) c ) represents the turning angle of the set of undetermined stopping points, K represents the number of individual moving points selected for calculation, and w k The weight of the moving point, Let m be the point to move forward. i-k Actual parking position, last moving point m I+k The turning angle, dis(m) i-k ,m I+k ) represents the previous movement point m i-k and the point to move back m I+k The distance is given by I1, where I is the index of the last moving point in the moving point cluster, I is the index of the last stopping point in the set of undetermined stopping points, and I0 is the index of the first moving point in the moving point cluster.

[0042] Step S5-2-1 specifically includes:

[0043] Step S5-2-1-1: Determine whether the number of stopping points in the set of undetermined stopping points is 1 or 2. If it is, calculate the average latitude and longitude based on time weighting based on all stopping points, and use it as the actual docking position of the set of undetermined stopping points. Otherwise, execute step S5-2-1-2.

[0044] Step S5-2-1-2: Determine whether the number of stopping points in the set of undetermined stopping points is 3. If yes, then take the latitude and longitude of the second stopping point as the actual docking position of the set of undetermined stopping points. Otherwise, execute step S5-2-1-3.

[0045] Step S5-2-1-3: Based on the second to second-to-last stop points in the set of undetermined stop points, calculate the average latitude and longitude using time weighting, and use it as the actual docking location for the set of undetermined stop points;

[0046] In steps S5-2-1-1 and S5-2-1-3, the weight of the k-th stop point in the set of undetermined stop points participating in the calculation is:

[0047]

[0048] Where: t k+1 Let t be the timestamp of the (k+1)th stopping point. k The timestamp of the k-th stopping point The timestamp of the last stop point in the set of stop points. This is the timestamp of the first stop point in the set of stop points.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] 1. By taking charging demand into account, it can identify effective stopping point clusters of charging demand, thereby improving the accuracy and amount of information in the identification.

[0051] 2. Based on the aforementioned specially designed turning angles and other criteria, effective stopping point clusters are identified. This avoids interference from smaller local errors when facing situations such as grade-separated areas or poor vehicle positioning device networks that may lead to excessive data errors, thereby improving the accuracy of effective stopping point cluster identification. Attached Figure Description

[0052] Figure 1 This is a schematic diagram of the main steps of the method of the present invention;

[0053] Figure 2 A schematic diagram illustrating the data-driven method for identifying the parking purpose of new energy urban green freight vehicles in this application.

[0054] Figure 3 This is a schematic diagram showing the distance between two adjacent trajectory points in this application;

[0055] Figure 4 The diagram shows a logarithmic distribution, where (a) is a logarithmic distribution diagram of the distance between adjacent trajectories, and (b) is a logarithmic distribution diagram of the average velocity of adjacent trajectories.

[0056] Figure 5 This is a schematic diagram showing the cumulative stopping time distribution of the stopping point cluster in this application;

[0057] Figure 6 This is a flowchart illustrating the effective stopping point identification process for new energy freight vehicles based on the trip chain in this application.

[0058] Figure 7 The diagrams are for identifying actual stopping positions, where (a) is a diagram for identifying stopping points without turning angles; (b) is a diagram for identifying stopping points with turning angles; and (c) is a diagram for calculating turning angles with distance weighting.

[0059] Figure 8 This is a schematic diagram of the turning angle distribution of the stopping point cluster in this application. Detailed Implementation

[0060] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0061] Explanation of technical terms in this application:

[0062] (1) Vehicle trajectory: The vehicle's location trajectory on day d (generally using GPS data, but data from BeiDou or other positioning systems can also be used) is represented as G. d {(x1,y1,t1),(x2,y2,t2),...,(x i ,y i ,t i ),...,(x I ,y I ,t I )},t1<t2,...,<t I , t I -t1=T d Where (x) i ,y i ,t i ) for t i The GPS trajectory point at time p i ;x i ,y i t i The latitude and longitude of the moment; I represents the number of trajectory points; T d This represents the time span of day d, where d = 1, 2, ..., D, and D is the number of days in the trajectory data.

[0063] (2) Distance traveled: trajectory point p i and p i+1Geographical distance d between i+1 The value is obtained by formula (1), where R is the average radius of the Earth, which is approximately 6371 kilometers.

[0064] d i+1 =R·arc cos(sin(y) i )·sin(y i+1 )+cos(y i )·cos(y i+1 )·cos(x i+1 -x i )) (1)

[0065] (3) Average velocity: between two adjacent trajectory points p i and p i+1 The average velocity v between i+1 =d i+1 / (t i+1 -t i );

[0066] (4) Stopping point and stopping cluster: If the vehicle is at t i If time is stationary, then the stationary point s i Defined as Stopping the cluster is defined as S i ={s i ,s i+1 ,...,s I}, The number of trajectory points included is

[0067] (5) Set of stopping points: The set of all clusters of stopping points;

[0068] (6) Mobility Points and Mobility Clusters: If the vehicle is at t i If time is moving, then the moving point m i Defined as The mobile point cluster is defined as M i ={m i ,m i+1 ,...,m I}, The number of trajectory points included is

[0069] (7) Cumulative distance traveled: The total distance traveled by all trajectory points in the movement point cluster;

[0070] (8) Stop point cluster range: The maximum distance between pairs of stop points in the stop point cluster;

[0071] (9) Actual stopping position: The representative point in the stopping point cluster, which may be the first or last stopping point in the stopping point cluster;

[0072] (10) Stop the cumulative time: Stop cluster S i The cumulative stopping time is expressed as

[0073] (11) Turning angle: p i The turning angle at the point is defined as in This is a function for calculating the angle between points on the trajectory.

[0074] A data-driven method for identifying the parking purpose of new energy vehicles used for urban green freight transport, such as Figure 1 and Figure 2 As shown, it includes:

[0075] Step S1: Obtain the original vehicle positioning data sequence, wherein each trajectory point in the vehicle positioning data sequence includes latitude and longitude, timestamp, remaining battery percentage, charging status and instantaneous speed;

[0076] The specific data format is shown in Table 1:

[0077] Table 1

[0078]

[0079]

[0080] Among them, the charging status is 1, 3, and 4, which represent charging while parked, not charging, and charging completed, respectively, and PDATime represents the timestamp.

[0081] Step S2: Preprocess and repair the acquired raw positioning data to obtain one or more target vehicle positioning data sequences, including:

[0082] Step S2-1: Delete all data points in the vehicle positioning data sequence with a longitude or latitude of 0, as well as data points that exceed the longitude or latitude threshold range;

[0083] Step S2-2: Delete all data points in the vehicle location data sequence whose timestamps remain unchanged;

[0084] Step S2-3: Calculate the average speed between adjacent data points. If the average speed between adjacent data points is greater than the pre-configured maximum speed, delete the corresponding data point.

[0085] Step S2-4: When the timestamp difference between adjacent data points exceeds the pre-configured duration threshold, the vehicle positioning data sequence is segmented to obtain multiple target vehicle positioning data sequences.

[0086] Step S3: Based on the target vehicle positioning data sequence, compare the distance and average speed of adjacent trajectory points with pre-configured distance thresholds and average speed thresholds respectively to filter out all vehicle stopping points, and construct a vehicle stopping point cluster from consecutive vehicle stopping points, including:

[0087] Step S3-1: Configure distance threshold and average speed threshold;

[0088] Among them, such as Figure 4 As shown in part (a), the distance threshold is determined as follows: Based on the target vehicle positioning data sequence, a logarithmic distribution curve of the distance between two adjacent trajectory data points is constructed. The logarithmic distribution curve exhibits a bimodal mixed distribution. The target point with the mixed distribution is used as the distance threshold. In this embodiment, the distance threshold L0 = 14.7m.

[0089] like Figure 4 As shown in part (b), the average speed threshold is determined in the following way: based on the target vehicle positioning data sequence, the average speed logarithmic distribution curve of two adjacent trajectory data points is constructed. The logarithmic distribution curve presents a bimodal mixed distribution. The target point with the mixed distribution is used as the average speed threshold. In this embodiment, the average speed threshold V0 = 1.33 km / h.

[0090] Step S3-2: As Figure 3 As shown, the distance and average speed between each adjacent data point in the target vehicle positioning data sequence are calculated respectively. If the distance between adjacent data points is less than the distance threshold and the average speed is less than the average speed threshold, then the previous data point among the adjacent data points is determined as the vehicle stopping point.

[0091] Step S3-3: Construct all consecutive vehicle stop points into a vehicle stop point cluster.

[0092] Step S4: Based on the time difference between the last stopping point and the first stopping point in the constructed stopping point set, determine whether each stopping point set is a valid stopping point set or a set of undetermined stopping points, including:

[0093] Step S4-1: Determine the first parking duration threshold and the second parking duration threshold by fitting a power law distribution on a double logarithmic axis, wherein the first parking duration threshold is greater than the second parking duration threshold;

[0094] Step S4-2: Determine whether the time difference between the last parking point and the first parking point in the vehicle stopping point cluster exceeds the first parking duration threshold. If yes, the vehicle stopping point cluster is a valid stopping point set; otherwise, proceed to step S4-3.

[0095] Step S4-3: Determine whether the time difference between the last parking point and the first parking point in the vehicle stopping point cluster exceeds the second parking duration threshold. If yes, then the vehicle stopping point cluster is a set of undetermined stopping points.

[0096] like Figure 5 As shown, in step S4-1, during the process of fitting a power law distribution on the double logarithmic axis, the data is divided into four segments.

[0097] The cumulative stopping time for each segment and the method for identifying valid stopping points are as follows:

[0098] The first segment, with a cumulative stop time of less than 2.16 minutes, is determined to be a brief stop point caused by traffic light waiting or traffic congestion, and is not a valid stop point, and is therefore excluded.

[0099] The second segment, with a cumulative stopping time greater than or equal to 2.16 minutes and less than 55.44 minutes, is determined to include both invalid and valid stopping points and is recorded as a short-term stop.

[0100] The third segment, with a cumulative stop time greater than 55.44 minutes but less than 7.35 hours, is determined to include invalid stop points, temporary stop points, and the end-of-trip stop point, and is recorded as an intermediate stop.

[0101] The fourth segment, with a cumulative stopping time greater than 7.35 hours, is judged as a valid stopping point.

[0102] That is, the second parking duration threshold is 55.44 minutes, and the first parking duration threshold is 7.35 hours.

[0103] Furthermore, in this embodiment, to eliminate stop point clusters with excessively large ranges, the maximum distance between each stop point in the cluster was calculated. In this application, the maximum distance between stop points in 99% of the stop point clusters is less than 312.36 meters. Therefore, stop point clusters with a range greater than 312.36 meters are marked as invalid stop points and excluded.

[0104] Step S5: For each set of undetermined stopping points, combine the turning angle and travel chain analysis to determine whether each set of stopping points is a valid set of stopping points, such as... Figure 6 As shown, it includes:

[0105] Step S5-1: For each set of undetermined stopping points, determine whether the charging status of each stopping point is charging or charging is complete. If yes, calculate whether the remaining power percentage of the last stopping point is greater than the remaining power percentage of the first stopping point. If yes, mark the set of undetermined stopping points as a valid stopping point set. Otherwise, proceed to step S5-2.

[0106] Step S5-2: Calculate the turning angle of each set of undetermined stopping points. If the turning angle is greater than the pre-configured angle threshold, mark the set of undetermined stopping points as a valid parking point set; otherwise, proceed to step S5-3.

[0107] like Figure 7 As shown, the calculation process for the turning angle of the set of undetermined stopping points includes:

[0108] Step S5-2-1: Determine the actual stopping positions of the set of undetermined stopping points, specifically including:

[0109] Step S5-2-1-1: Determine whether the number of stopping points in the set of undetermined stopping points is 1 or 2. If it is, calculate the average latitude and longitude based on time weighting based on all stopping points, and use it as the actual docking position of the set of undetermined stopping points. Otherwise, execute step S5-2-1-2.

[0110] Step S5-2-1-2: Determine whether the number of stopping points in the set of undetermined stopping points is 3. If yes, then take the latitude and longitude of the second stopping point as the actual docking position of the set of undetermined stopping points. Otherwise, execute step S5-2-1-3.

[0111] Step S5-2-1-3: Based on the second to second-to-last stop points in the set of undetermined stop points, calculate the average latitude and longitude using time weighting, and use it as the actual docking location for the set of undetermined stop points;

[0112] In steps S5-2-1-1 and S5-2-1-3, the weight of the k-th stop point in the set of undetermined stop points participating in the calculation is:

[0113]

[0114] Where: t k+1 Let t be the timestamp of the (k+1)th stopping point. k The timestamp of the k-th stopping point The timestamp of the last stop point in the set of stop points. This is the timestamp of the first stop point in the set of stop points.

[0115] The specific location calculation formula is shown in equation (2):

[0116]

[0117] Where: x c The coordinates of the actual docking location are: This represents the number of stopping points.

[0118] Step S5-2-2: Based on the location of the set of pending stopping points, extract from the target vehicle positioning data sequence the cluster of forward moving points that is located before and adjacent to the set of pending stopping points, and the cluster of backward moving points that is located after and adjacent to the set of pending stopping points;

[0119] Step S5-2-3: Based on the forward and backward movement point clusters, and combined with the actual stopping positions of the set of undetermined stopping points, determine the turning angle of the set of undetermined stopping points.

[0120] The turning angle at the stopping point cluster is calculated based on the truck's actual stopping position and its forward and backward movement points. Due to the influence of data recording time and vehicle speed, the forward and backward movement points may be far from the truck's actual stopping position. To address this issue, a distance-weighted method is used to calculate the turning angle.

[0121]

[0122] Where: α(s) c ) represents the turning angle of the set of undetermined stopping points, K represents the number of individual moving points selected for calculation, and w k The weight of the moving point, Let m be the point to move forward. i-k Actual parking position, last moving point m I+k The turning angle, dis(m) i-k ,m I+k ) represents the previous movement point m i-k and the point to move back m I+k The distance is given by I1, where I is the index of the last moving point in the moving point cluster, I is the index of the last stopping point in the set of undetermined stopping points, and I0 is the index of the first moving point in the moving point cluster.

[0123] Among them, the greater the distance between paired moving points, the smaller the weight.

[0124] like Figure 7 As shown in (c), the turning angle calculated for each pair of forward and backward movement points is less reliable and has a smaller weight as the distance between them increases.

[0125] like Figure 8 As shown, the turning angles at each stop point cluster are modeled and their probability distribution is shown. This distribution is interrupted at 84.45°, with each part representing a different turning field. The angle threshold is determined to be 84.45°.

[0126] Step S5-3: Based on the travel chain analysis, determine whether the set of undetermined stopping points is the start or end point of the travel chain. If yes, mark the set of undetermined stopping points as a valid stopping point set; otherwise, proceed to step S5-4.

[0127] Step S5-4: Determine whether the set of undetermined stopping points is located after the set of valid stopping points for charging purposes. If yes, mark the set of undetermined stopping points as a valid stopping point set; otherwise, proceed to step S5-5.

[0128] Step S5-5: Determine whether the location of the set of undetermined stopping points has been identified as a valid parking point set in the historical determination. If so, mark the set of undetermined stopping points as a valid parking point set.

[0129] Step S6: Determine the parking purpose of all valid stop point sets.

[0130] Specifically, on the one hand, if the remaining battery percentage of the last stop point in the set of valid stop points is greater than that of the first stop point, and the charging status is charging or charging complete, then the charging demand for that parking purpose in the set of valid stop points is determined. Other parking purposes can be determined by combining existing methods.

[0131] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A data-driven method for identifying the parking purpose of urban green freight new energy vehicles, characterized in that, include: Step S1: Obtain the original vehicle positioning data sequence, wherein each trajectory point in the vehicle positioning data sequence includes latitude and longitude, timestamp, remaining battery percentage, charging status and instantaneous speed; Step S2: Preprocess and repair the acquired raw positioning data to obtain one or more target vehicle positioning data sequences; Step S3: Based on the target vehicle positioning data sequence, all vehicle stopping points are selected by comparing the distance and average speed of adjacent trajectory points with pre-configured distance thresholds and average speed thresholds, and consecutive vehicle stopping points are constructed into a vehicle stopping point cluster. Step S4: Based on the time difference between the last stopping point and the first stopping point in the constructed stopping point set, determine whether each stopping point set is a valid stopping point set or a set of undetermined stopping points; Step S5: For each set of undetermined stopping points, combine the turning angle and travel chain analysis to determine whether each set of stopping points is a valid set of stopping points; Step S6: Determine the parking purpose of all valid stop point sets; Step S4 includes: Step S4-1: Determine a first parking duration threshold and a second parking duration threshold by fitting a power law distribution on a double logarithmic axis, wherein the first parking duration threshold is greater than the second parking duration threshold; Step S4-2: Determine whether the time difference between the last parking point and the first parking point in the vehicle stopping point cluster exceeds the first parking duration threshold. If yes, the vehicle stopping point cluster is a valid stopping point set; otherwise, proceed to step S4-3. Step S4-3: Determine whether the time difference between the last parking point and the first parking point in the vehicle stopping point cluster exceeds the second parking duration threshold. If yes, the vehicle stopping point cluster is a set of undetermined stopping points. Step S5 includes: Step S5-1: For each set of undetermined stopping points, determine whether the charging status of each stopping point is charging or charging is complete. If yes, calculate whether the remaining power percentage of the last stopping point is greater than the remaining power percentage of the first stopping point. If yes, mark the set of undetermined stopping points as a valid stopping point set. Otherwise, proceed to step S5-2. Step S5-2: Calculate the turning angle of each set of undetermined stopping points. If the turning angle is greater than the pre-configured angle threshold, mark the set of undetermined stopping points as a valid parking point set; otherwise, proceed to step S5-3. Step S5-3: Based on the travel chain analysis, determine whether the set of undetermined stopping points is the start or end point of the travel chain. If yes, mark the set of undetermined stopping points as a valid stopping point set; otherwise, proceed to step S5-4. Step S5-4: Determine whether the set of undetermined stopping points is located after the set of valid stopping points for charging purposes. If yes, mark the set of undetermined stopping points as a valid stopping point set; otherwise, proceed to step S5-5. Step S5-5: Determine whether the location of the set of undetermined stopping points has been identified as a set of valid parking points in the historical determination. If yes, mark the set of undetermined stopping points as a set of valid parking points. The calculation process for the turning angle of the set of undetermined stopping points includes: Step S5-2-1: Determine the actual stopping positions of the set of undetermined stopping points; Step S5-2-2: Based on the location of the set of pending stopping points, extract from the target vehicle positioning data sequence the cluster of forward moving points that is located before and adjacent to the set of pending stopping points, and the cluster of backward moving points that is located after and adjacent to the set of pending stopping points; Step S5-2-3: Based on the forward and backward movement point clusters, and combined with the actual stopping positions of the set of undetermined stopping points, determine the turning angle of the set of undetermined stopping points: in: The turning angle of the set of undetermined stopping points. K To select the number of individual movement points to calculate, The weight of the moving point, Forward movement point Actual parking location, repositioning point The turning angle, Forward movement point and the point of relocation distance, This is the sequence number of the last mover in the mover cluster. The index of the last stop point in the set of undetermined stop points. This is the sequence number of the first forward mover in the forward mover cluster.

2. The data-driven method for identifying the parking purpose of urban green freight new energy vehicles according to claim 1, characterized in that, Step S2 includes: Step S2-1: Delete all data points in the vehicle positioning data sequence with a longitude or latitude of 0, as well as data points that exceed the longitude or latitude threshold range; Step S2-2: Delete all data points in the vehicle location data sequence whose timestamps remain unchanged; Step S2-3: Calculate the average speed between adjacent data points. If the average speed between adjacent data points is greater than the pre-configured maximum speed, delete the corresponding data point. Step S2-4: When the timestamp difference between adjacent data points exceeds the pre-configured duration threshold, the vehicle positioning data sequence is segmented to obtain multiple target vehicle positioning data sequences.

3. The data-driven method for identifying the parking purpose of urban green freight new energy vehicles according to claim 1, characterized in that, Step S3 includes: Step S3-1: Configure distance threshold and average speed threshold; Step S3-2: Calculate the distance and average speed between each adjacent data point in the target vehicle positioning data sequence. If the distance between adjacent data points is less than the distance threshold and the average speed is less than the average speed threshold, then the previous data point among the adjacent data points is determined as the vehicle stopping point. Step S3-3: Construct all consecutive vehicle stop points into a vehicle stop point cluster.

4. The data-driven method for identifying the parking purpose of urban green freight new energy vehicles according to claim 3, characterized in that, The distance threshold is determined in the following way: based on the target vehicle positioning data sequence, a logarithmic distribution curve of the distance between two adjacent trajectory data points is constructed. The logarithmic distribution curve shows a bimodal mixed distribution, and the target point with the mixed distribution is used as the distance threshold. The average speed threshold is determined as follows: based on the target vehicle positioning data sequence, an average speed logarithmic distribution curve of two adjacent trajectory data points is constructed. The logarithmic distribution curve presents a bimodal mixed distribution, and the target point with the mixed distribution is used as the average speed threshold.

5. The data-driven method for identifying the parking purpose of urban green freight new energy vehicles according to claim 1, characterized in that, In step S4-1, the process of fitting a power law distribution on the double logarithmic axis is divided into four segments.

6. The data-driven method for identifying the parking purpose of urban green freight new energy vehicles according to claim 1, characterized in that, Step S5-2-1 specifically includes: Step S5-2-1-1: Determine whether the number of stopping points in the set of undetermined stopping points is 1 or 2. If it is, calculate the average latitude and longitude based on time weighting based on all stopping points, and use it as the actual docking position of the set of undetermined stopping points. Otherwise, execute step S5-2-1-2. Step S5-2-1-2: Determine whether the number of stopping points in the set of undetermined stopping points is 3. If yes, then take the latitude and longitude of the second stopping point as the actual docking position of the set of undetermined stopping points. Otherwise, execute step S5-2-1-3. Step S5-2-1-3: Based on the second to second-to-last stop points in the set of undetermined stop points, calculate the average latitude and longitude using time weighting, and use it as the actual docking location for the set of undetermined stop points.

7. The data-driven method for identifying the parking purpose of urban green freight new energy vehicles according to claim 6, characterized in that, In steps S5-2-1-1 and S5-2-1-3, the set of undetermined stopping points involved in the calculation... l The weights of the stopping points are: in: t l+1 For the first l +1 timestamp of the stop point t l For the first l The timestamp of the stopping point The timestamp of the last stop point in the set of stop points. This is the timestamp of the first stop point in the set of stop points.

Images