A method and system for mining and retrieving container truck transport routes based on GPS and industry characteristics

Abstract

The present invention proposes a method and system for mining and retrieving container truck transport routes based on GPS and industry characteristics, which achieves significant optimization and improvement in response to the unique needs of the container truck transport industry. The present invention adopts geo-fence technology and constructs a Cartesian set method independent of the waybill to extract empirical routes, thereby enhancing the coverage of the empirical routes. The solution is designed to meet the needs of container transportation for specific road conditions, including but not limited to height restrictions, weight restrictions, special road conditions, and special charging modes. The present invention specially designs a highly adaptable route planning strategy, which effectively improves the safety and efficiency of the transportation process, and at the same time has a high-coverage route retrieval capability. Compared with the existing technology, the solution accurately mines and constructs a public transportation trajectory model by deeply integrating the geo-fence information of the terminal and yard and rich historical GPS trajectory data.

Description

Technical Field

[0001] The present invention relates to the field of traffic data mining based on GPS technology, and in particular to a method and system for mining and retrieving container truck transportation routes based on GPS and industry characteristics. Background Art

[0002] With the rapid development of the logistics industry, container trailer transport efficiency and cost control have become key competitive advantages for businesses. However, current navigation software on the market exhibits significant limitations when planning container transport routes, severely hindering improvements in transport efficiency and cost reductions. Existing navigation software often overlooks the unique requirements of container transport, such as vehicle size, load limits, road conditions, and toll collection methods. This results in significant discrepancies between the routes drivers actually take. In particular, the distances of the routes they navigate are often longer than the actual routes, increasing transport time and costs while also potentially leading to illegal driving or traffic on roads unsuitable for large vehicles. While previous studies have attempted to improve route planning through algorithm optimization, these studies often lack industry specificity and practical application validation. Furthermore, these algorithms often fail to fully consider factors such as road conditions and driver habits, requiring further optimization for their effectiveness in practice. Patent CN202011620267.2 uses a combination of algorithms such as DBSCAN, LCSS, Dijkstra and aprior to calculate the vehicle's frequently traveled routes, thereby improving the performance indicators in the field of commercial vehicle frequently traveled routes. However, it does not combine actual application scenarios to perform optimal route planning for specific areas. Existing path planning technology is difficult to obtain the optimal planning and navigation path in the field of container trailers. Summary of the Invention

[0003] To meet the route planning needs of container trailers, address the irrationality of current general navigation software in route planning, and avoid inaccurate mileage calculations during mileage metering, this paper proposes a method and system for mining and retrieving container truck transport routes based on GPS and industry characteristics, incorporating the characteristics of the container transport industry. By focusing on operational scenarios such as docks and storage yards involved in the mission's starting point, the system uses the trailer's GPS trajectory to conduct pattern mining, and draws on empirical routes for more reasonable route planning.

[0004] The specific plan is as follows:

[0005] A method for mining and retrieving container truck transport routes based on GPS and industry characteristics.

[0006] S1: Collect and access container trailer trajectory data, surrounding environment data, and truck transport task data: including container trailer trajectory data formed by the container trailer's GPS data, terminal and yard geo-fence data, and truck transport task data;

[0007] S2: Preprocess the data in S1 and construct a Cartesian set of candidate ODs that are separated from the waybill:

[0008] 1) Mining the stop points that exceed the set stay time in the historical data of container trailer trajectories as key nodes of the transportation task, preliminarily filtering the stop points through the map service, and encoding the remaining stop points as potential customer door-to-door stop points;

[0009] 2) Truncate any container trailer track that enters or exits the geo-fenced area of ​​the terminal or yard, and split it into sub-tracks; the geo-fenced area of ​​the terminal or yard marks the logical starting point or end point of the transport task;

[0010] 3) constructing a Cartesian set of candidate ODs that are separated from the waybill based on each of the split container trailer sub-trajectories;

[0011] 4) Screen candidate ODs based on actual business data so that the control route body is consistent with historical transportation experience as a candidate trajectory;

[0012] S3: Mining and extracting common sub-trajectories: In the candidate OD Cartesian set, trajectory similarity evaluation and cluster analysis are performed for a group of transportation task trajectories with the same starting and ending points. Trajectory distances are calculated using the Hausdoriff method and then clustered. The density of trajectory points within each cluster is calculated for optimal selection. The trajectory with the shortest transportation time is selected as the benchmark trajectory. The common sub-trajectories are then verified and restored based on the number of Geohash blocks to obtain an effective empirical route.

[0013] S4: Optimize empirical trajectories and enhance processing: Use intelligent denoising algorithms to automatically identify and delete redundant trajectory segments within a preset range around the OD; use third-party route planning services to supplement the remaining trajectory information;

[0014] S5: Trajectory retrieval for nearby transport tasks: Target OD is used as the center to find the OD experience trajectory and use it as the main part of the planned trajectory. Third-party route planning services are used to solve the problem of missing heads and tails near the starting and ending points of the trajectory, thereby improving the experience trajectory and forming a complete route that conforms to historical business experience.

[0015] Preferably, the method for collecting and accessing container trailer data, surrounding environment data, and container truck transport task data is:

[0016] S11: The location data sent by the truck connected to the GPS signal box. The collection interval between each two GPS points is between 2-10 minutes, including the vehicle's real-time latitude and longitude, sending timestamp, direction, and speed;

[0017] S12: The dock geo-fence data is manually maintained static basic data. The shape of the geo-fence is the actual geographical shape of the dock.

[0018] S13: Truck transport task data includes: transport start and end terminals, customer location, transport task required time, and trailer license plate information.

[0019] Preferably, the preprocessing method in S2 is:

[0020] S21: Stop point mining and location standardization: The Traj-DBSCAN algorithm is used to mine significant stop points in the historical trajectory of the container truck as key nodes of the transportation task, and the Geohash technology is used to encode the location of each stop point;

[0021] S22: Task Boundary Definition and Trajectory Screening: Based on the conventional business model of container truck transportation, the actual geographical fence of the terminal is set as the logical starting point or end point of the transportation task. By setting a 48-hour sliding window, the trajectory data crossing the fences of two terminals is searched within this time period. The OD pairs formed by the Geohash of the stop points in these trajectories are marked and a candidate set of historical sub-trajectories is constructed.

[0022] S23: Trajectory quality control and optimization: Double filter the candidate trajectories to exclude trajectories with abnormal transportation time; and eliminate trajectories with insufficient GPS data points, that is, less than the set value.

[0023] Preferably, the method for mining and extracting common sub-trajectories in S3 is: for a group of transport task trajectories with the same starting point and end point Geohash, if the number of the group of transport trajectories is greater than or equal to 3, then mining common sub-trajectories is performed.

[0024] Preferably, the method for mining and extracting common sub-tracks in S3 is:

[0025] S31: Trajectory similarity assessment and clustering: Use Hausdorff distance to calculate the similarity between each trajectory in the same group; cluster the trajectories based on trajectory similarity using the DBSCAN algorithm, obtain clusters based on distance similarity, remove isolated points, and select the top 5 clusters containing the most transport trajectories for analysis;

[0026] S32: Track density screening and determination of reference tracks: Calculate the track density within each cluster, where the track density is the track transport time divided by the number of GPS points, and prioritize tracks with higher density. If there are less than three high-density tracks, gradually relax the density restriction. Among the eligible clusters, select the track with the shortest transport time as the reference track.

[0027] S33: Geohash-based trajectory comparison and common segment extraction: Perform Geohash encoding on all trajectories, compare each trajectory encoding with the reference trajectory encoding one by one, retain the Geohash blocks that are the same or adjacent to the reference trajectory encoding, and construct the encoding framework of potential common sub-trajectories;

[0028] S34: Verify and restore the common sub-trajectory: Ensure that the first and last Geohash blocks of the common coding result are consistent with the reference trajectory, and automatically supplement them if they are inconsistent. At the same time, check the number of Geohash blocks in the common coding result for verification. If the verification passes, use the reference trajectory and the verified Geohash coding result to restore the common sub-trajectory. Based on the number of GPS points in the restored common sub-trajectory, determine whether it is a valid empirical route.

[0029] Preferably, the verification requirement in S34 is: there are at least 3 Geohash blocks and they cover more than 30% of the reference trajectory code; the method for judging the valid empirical route is: if the number of GPS points in the restored common sub-trajectory is not less than 5, it is judged to be a valid empirical route.

[0030] Preferably, the method for optimizing the experience trajectory and enhancing the processing in S4 is:

[0031] S41: After obtaining the empirical route described in S3, an intelligent denoising algorithm is used to eliminate unnecessary factors due to pathfinding and temporary stops near the start and end points, and redundant trajectory segments within a preset range around the OD are automatically identified and deleted;

[0032] S42: Use a third-party route planning service to supplement the trajectory information, including supplementing trajectory points, calculating trajectory distance, counting the number of trajectory GPS points, and transportation time;

[0033] Preferably, the method for retrieving the trajectory of the adjacent transport task in S5 is:

[0034] S51: When performing trajectory retrieval, the search radius is set and the search area is drawn with the target OD as the center to find out whether there is an existing and settled OD experience trajectory; if an experience trajectory that meets the conditions is retrieved, it is used as the main part of the planned trajectory;

[0035] S52: Improve the experience trajectory: Use third-party route planning services to solve the problem of missing heads and tails near the starting and ending points of the trajectory, and finally form a complete route that conforms to historical business experience.

[0036] A truck transport route mining and retrieval system based on GPS and industry characteristics, including

[0037] Data collection module: used to collect container trailer trajectory data formed by GPS data of container trailers, terminal and yard geo-fence data, and container truck transportation task data;

[0038] Preprocessing module: used to process the container trailer trajectory data, terminal and yard geo-fence data, and truck transportation task data in the data acquisition module: including: mining the stay points that exceed the set stay time in the historical data of container trailer trajectory as key nodes of the transportation task, preliminarily filtering the stay points through the map service, and encoding the remaining stay points as potential customer door-point stay points; a location coding sub-module that truncates any container trailer trajectory that enters and exits the geo-fence of the terminal and yard, and splits it into container trailer sub-trajectories; a candidate OD sub-module that constructs a Cartesian set of candidate ODs that are separated from the waybill based on each split container trailer sub-trajectory; a candidate trajectory sub-module that screens candidate ODs based on actual business data so that the control route body conforms to historical transportation experience as the candidate trajectory;

[0039] The module for mining and extracting common sub-trajectories includes: a cluster analysis sub-module that evaluates and clusters the trajectory similarity of a group of transport task trajectories with the same starting and ending geohash, calculates the trajectory distance using Hausdoriff, calculates the density of trajectory points within each cluster, and selects the trajectory with the shortest transport time as the benchmark trajectory, and then verifies and restores the common sub-trajectories based on the number of geohash blocks to obtain a valid empirical route sub-module;

[0040] Optimize empirical trajectory and enhance processing module: including: a redundancy removal submodule that uses an intelligent denoising algorithm to automatically identify and delete redundant trajectory segments within a preset range around the OD; a trajectory enhancement submodule that uses a third-party route planning service to supplement trajectory information;

[0041] The trajectory retrieval module for the adjacent transport task includes: a planned trajectory submodule that searches for the OD empirical trajectory centered on the target OD and uses it as the main part of the planned trajectory; an empirical route submodule that uses a third-party route planning service to resolve the problem of missing heads and tails near the start and end points of the trajectory, thereby improving the empirical trajectory and forming a transport route that conforms to historical business experience; and a route display submodule that displays the transport route that conforms to historical experience.

[0042] Beneficial effects:

[0043] The present invention proposes a method and system for mining and retrieving container truck transport routes based on GPS and industry characteristics, which achieves significant optimization and improvement in response to the unique needs of the container truck transport industry. The present invention adopts geo-fence technology and constructs a Cartesian set method independent of the waybill to extract empirical routes, thereby enhancing the coverage of the empirical routes. The solution is designed to meet the needs of container transportation for specific road conditions, including but not limited to height restrictions, weight restrictions, special road conditions, and special charging modes. The present invention specially designs a highly adaptable route planning strategy, which effectively improves the safety and efficiency of the transportation process, and at the same time has a high-coverage route retrieval capability. Compared with the existing technology, the solution accurately mines and constructs a public transportation trajectory model by deeply integrating the geo-fence information of the terminal and yard and rich historical GPS trajectory data.

[0044] First, based on the fact that terminals and yards are limited, all tasks need to start or end at the terminal / yard. The present invention is based on finding all transportation tasks by cutting off the trajectory through geo-fences.

[0045] Secondly, the present invention uses AOI truncation technology to construct a Cartesian set independent of the waybill. Since trajectories between two yards or terminals inevitably involve at least one transport task, the present invention directly identifies transport tasks from these trajectories and constructs a Cartesian set, rather than relying on order information maintained in the system. This allows all potential transport task routes to be extracted for subsequent analysis. This solution addresses the frequent inaccuracies in waybill information in the container shipping industry. For example, a driver may be assigned two transport tasks simultaneously, but the order in which they are actually carried out may not correspond to the instructions on the waybill. A designated empty yard on the waybill may be redirected to another yard due to queues or a shortage of containers. Manual updates to waybill information may not yet be reflected in the system. Typically, trajectory segments not related to transport routes are excluded from the subsequent cluster analysis. Test results show that this method achieves over 90% coverage of empirical routes, compared to less than 70% for routes generated using waybill information, demonstrating its effectiveness and reliability in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Flowchart of a method for mining and retrieving container truck transport routes based on GPS and industry characteristics.

[0047] Figure 2 Flowchart of the algorithm for searching the OD pairs of the stay point hash within the time period.

[0048] Figure 3Flowchart for obtaining the experience route in the embodiment.

[0049] Figure 4 A truck transport route mining and retrieval system based on GPS and industry characteristics. DETAILED DESCRIPTION

[0050] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0051] The present invention uses the GPS data of container trailers, terminal geo-fence data and container truck transport task data, performs calculation and analysis according to relevant calculation methods, and finally obtains one or more empirical routes for an OD (origin to destination) pair.

[0052] like Figure 1 and 3 As shown, the present invention is mainly divided into the following steps:

[0053] A method for mining and retrieving container truck transport routes based on GPS and industry characteristics.

[0054] S1: Collect and access container trailer trajectory data, surrounding environment data, and truck transport task data: including container trailer trajectory data formed by the container trailer's GPS data, terminal and yard geo-fence data, and truck transport task data;

[0055] S2: Preprocess the data in S1 and construct a Cartesian set of candidate ODs that are separated from the waybill:

[0056] 1) Mining the stop points that exceed the set stay time in the historical data of container trailer trajectories as key nodes of the transportation task, preliminarily filtering the stop points through the map service, and encoding the remaining stop points as potential customer door-to-door stop points;

[0057] 2) Truncate any container trailer track that enters or exits the geo-fenced area of ​​the terminal or yard, and split it into sub-tracks; the geo-fenced area of ​​the terminal or yard marks the logical starting point or end point of the transport task;

[0058] 3) constructing a Cartesian set of candidate ODs that are separated from the waybill based on each of the split container trailer sub-trajectories;

[0059] 4) Screen candidate ODs based on actual business data so that the control route body is consistent with historical transportation experience as a candidate trajectory;

[0060] S3: Mining and extracting common sub-trajectories: In the candidate OD Cartesian set, trajectory similarity evaluation and cluster analysis are performed for a group of transportation task trajectories with the same starting and ending points. Trajectory distances are calculated using the Hausdoriff method and then clustered. The density of trajectory points within each cluster is calculated for optimal selection. The trajectory with the shortest transportation time is selected as the benchmark trajectory. The common sub-trajectories are then verified and restored based on the number of Geohash blocks to obtain an effective empirical route.

[0061] S4: Optimize empirical trajectories and enhance processing: Use intelligent denoising algorithms to automatically identify and delete redundant trajectory segments within a preset range around the OD; use third-party route planning services to supplement the remaining trajectory information;

[0062] S5: Trajectory retrieval for nearby transport tasks: Target OD is used as the center to find the OD experience trajectory and use it as the main part of the planned trajectory. Third-party route planning services are used to solve the problem of missing heads and tails near the starting and ending points of the trajectory, thereby improving the experience trajectory and forming a complete route that conforms to historical business experience.

[0063] The detailed details are as follows:

[0064] S1: Collect and access container trailer trajectory data, surrounding environment data, and truck transport task data: The data required by this algorithm includes container trailer GPS data, terminal geo-fence data, and truck transport task data:

[0065] a. The location data sent by the container truck connected to the GPS signal box is collected with an interval of 2-10 minutes between each two GPS points, including the vehicle's real-time latitude and longitude, sending timestamp, direction, speed, etc.

[0066] b. The dock geo-fence data is manually maintained static basic data. The shape of the geo-fence is a polygon, which can be understood as the actual geographical shape of the dock.

[0067] c. Truck transport task data includes the starting and ending terminals of the transport, customer location, required time of the transport task, trailer license plate number information, etc.

[0068] S2: Preprocessing the container trailer trajectory data, surrounding environment data, and truck transport mission data described in S1: Stop point mining and location standardization: First, the Traj-DBSCAN algorithm is used to deeply explore significant stop points in the truck's historical trajectory. These stop points often mark key nodes in the transport mission. Subsequently, Geohash technology is used to positionally encode each stop point to facilitate subsequent comparison and analysis.

[0069] a. Task boundary definition and trajectory screening: Based on the conventional business model of container truck transportation, we set the actual geographical fence of the terminal as the logical starting point or end point of the transportation task. By setting a 48-hour sliding window, we search for trajectory data that spans the fences of two terminals within this time period, focusing on the OD pairs formed by the Geohash of the stop points in these trajectories. We construct a series of potential candidate sets of historical sub-trajectories with practical business significance. (e.g. Figure 2 , pre-process the GPS data, use every 48 hours as a sliding window, and search for the OD pair of the stay point Hash within the time period)

[0070] b. Trajectory Quality Control and Optimization: To ensure the quality of the constructed empirical routes, candidate trajectories are double-filtered. On the one hand, trajectories with unusually long (over 48 hours) or short (less than 30 minutes) transit times are excluded, as these may be unrepresentative due to special reasons (such as failures, detours, etc.). On the other hand, trajectories with insufficient GPS data points (e.g., fewer than 10) are eliminated, as these may be incomplete due to signal issues, affecting the accuracy of the analysis results.

[0071] And eliminate the tracks with insufficient GPS data points, that is, those with less than the set value.

[0072] The candidate ODs include:

[0073] Sub-trajectory set = {T1, T2}

[0074] The set of stop points of sub-trajectory T1 = {pier 1, stop point 1, stop point 2, pier 2}

[0075] The set of stop points of sub-trajectory T2 = {Pier 3, Stop Point 3, Pier 4}

[0076] Through Cartesian product, all possible OD combinations of T1 are obtained:

[0077] T1 candidate OD combination = {(terminal 1, stop point 1), (stop point 1, stop point 2), (stop point 2, terminal 2), (terminal 1, stop point 2), (terminal 1, terminal 2), (stop point 2, terminal 2)}

[0078] T2 candidate OD combination = {(terminal 3, stop point 3), (stop point 3, terminal 4), (terminal 3, stop point 4)}

[0079] Then all possible OD combinations are:

[0080] Candidate OD combination = T1 candidate OD combination × T2 candidate OD combination = {(terminal 1, stop point 1), (stop point 1, stop point 2), (stop point 2, terminal 2), (terminal 1, stop point 2), (terminal 1, terminal 2), (stop point 2, terminal 2), (terminal 3, stop point 3), (stop point 3, terminal 4), (terminal 3, stop point 4)}.

[0081] S3: Mining and extracting common sub-trajectories: For a group of transport task trajectories with the same starting and ending geohash, if the number of transport trajectories in the group is greater than or equal to 3, the common sub-trajectory mining is performed according to the following process:

[0082] a. Trajectory Similarity Assessment and Clustering: Hausdorff distance is used to calculate the similarity between each trajectory in the set. Trajectories are clustered based on their similarity using the DBSCAN algorithm. Clusters are generated based on distance similarity, and outliers are removed. The top five clusters containing the most transport trajectories are selected for further analysis.

[0083] b. Trajectory density screening and baseline trajectory determination: Calculate the density of trajectories within each cluster (trajectory transport time divided by the number of GPS points), prioritizing those with higher density to ensure compactness and representativeness. If there are fewer than three high-density trajectories, gradually relax the density restriction (for example, first to ≤150, then to ≤300, and finally to no restriction) to expand the candidate pool. Among the eligible clusters, select the trajectory with the shortest transport time as the baseline trajectory, which will be used as a reference for subsequent analysis.

[0084] a. Geohash-based trajectory comparison and common segment extraction: All trajectories are Geohash-encoded to facilitate efficient spatial position comparison. Each trajectory code is individually compared with the baseline trajectory code, retaining Geohash blocks that are identical or adjacent to the baseline trajectory code to construct a coding framework for potential common sub-trajectories.

[0085] b. Verification and restoration of public sub-trajectory: Ensure that the first and last Geohash blocks of the public coding result are consistent with the reference trajectory. If they are inconsistent, they will be automatically supplemented to ensure the integrity of the trajectory. At the same time, check the number of Geohash blocks in the public coding result. It is required to be at least 3 blocks and cover more than 30% of the reference trajectory coding to ensure the significance and practicality of the public sub-trajectory. If the verification passes, the reference trajectory and the verified Geohash coding results are used to restore the specific public sub-trajectory. If the number of GPS points in the restored trajectory is not less than 5, it is considered a valid empirical route.

[0086] It can be used for path planning and optimization of subsequent transportation tasks.

[0087] S4: Optimize experience trajectory and enhance processing:

[0088] a. After obtaining the initial empirical route, to eliminate detours caused by unnecessary factors such as pathfinding and temporary stops near the start and end points, we use an intelligent denoising algorithm to automatically identify and delete redundant trajectory segments within a preset range around the OD.

[0089] b. To further improve the completeness and accuracy of the empirical trajectory, use third-party route planning services (such as Baidu Eagle Eye) to supplement the trajectory information. The supplementary content includes supplementing trajectory points, calculating trajectory distance, counting the number of trajectory GPS points, transportation time, and other information.

[0090] S5: Trajectory retrieval of nearby transport tasks:

[0091] When performing trajectory retrieval, a reasonable search radius is set with the target OD as the center, and a search area is drawn to find whether there are already existing and accumulated OD experience trajectories. Once an experience trajectory that meets the conditions is retrieved, it is used as the main part of the planned trajectory.

[0092] a. To further refine this trajectory, we use a third-party route planning service to address potential missing beginnings and endings near the start and end points, ultimately creating a complete route consistent with historical business experience.

[0093] This example uses the trajectory of an OD as an example. In this example, we extract a single, most frequently used route from multiple transport trajectories. Public subtrajectories are primarily used to ensure that the main route conforms to historical experience. Missing points in the OD perimeter and public trajectories are forcibly supplemented by third-party route planning services to reduce detours.

[0094] When searching for trajectories, draw a circle with a certain radius to find out whether there are any accumulated OD experience trajectories in the surrounding POIs.

[0095] like Figure 4 As shown, the present invention also protects a truck transport route mining and retrieval system based on GPS and industry characteristics, comprising:

[0096] Data collection module: used to collect container trailer trajectory data formed by GPS data of container trailers, terminal and yard geo-fence data, and container truck transportation task data;

[0097] Preprocessing module: used to process the container trailer trajectory data, terminal and yard geo-fence data, and truck transportation task data in the data acquisition module: including: mining the stay points that exceed the set stay time in the historical data of container trailer trajectory as key nodes of the transportation task, preliminarily filtering the stay points through the map service, and encoding the remaining stay points as potential customer door-point stay points; a location coding sub-module that truncates any container trailer trajectory that enters and exits the geo-fence of the terminal and yard, and splits it into container trailer sub-trajectories; a candidate OD sub-module that constructs a Cartesian set of candidate ODs that are separated from the waybill based on each split container trailer sub-trajectory; a candidate trajectory sub-module that screens candidate ODs based on actual business data so that the control route body conforms to historical transportation experience as the candidate trajectory;

[0098] The module for mining and extracting common sub-trajectories includes: a cluster analysis sub-module that evaluates and clusters the trajectory similarity of a group of transport task trajectories with the same starting and ending geohash, calculates the trajectory distance using Hausdoriff, calculates the density of trajectory points within each cluster, and selects the trajectory with the shortest transport time as the benchmark trajectory, and then verifies and restores the common sub-trajectories based on the number of geohash blocks to obtain a valid empirical route sub-module;

[0099] Optimize empirical trajectory and enhance processing module: including: a redundancy removal submodule that uses an intelligent denoising algorithm to automatically identify and delete redundant trajectory segments within a preset range around the OD; a trajectory enhancement submodule that uses a third-party route planning service to supplement trajectory information;

[0100] The trajectory retrieval module for the adjacent transport task includes: a planned trajectory submodule that searches for the OD empirical trajectory centered on the target OD and uses it as the main part of the planned trajectory; an empirical route submodule that uses a third-party route planning service to resolve the problem of missing heads and tails near the start and end points of the trajectory, thereby improving the empirical trajectory and forming a transport route that conforms to historical business experience; and a route display submodule that displays the transport route that conforms to historical experience.

[0101] The above specific implementation manner is a preferred embodiment of the present invention and does not limit the present invention. Any other changes or other equivalent replacement methods that do not deviate from the technical solution of the present invention are included in the protection scope of the present invention.

Claims

1. A method for mining and retrieving container truck transport routes based on GPS and industry characteristics, characterized in that: S1: Collect and access container trailer trajectory data, surrounding environment data, and truck transport task data: including container trailer trajectory data formed by the container trailer's GPS data, terminal and yard geo-fence data, and truck transport task data; S2: Preprocess the data in S1 and construct a Cartesian set of candidate ODs that are separated from the waybill: 1) Mining the stop points that exceed the set stay time in the historical data of container trailer trajectories as key nodes of the transportation task, preliminarily filtering the stop points through the map service, and encoding the remaining stop points as potential customer door-to-door stop points; 2) Truncate any container trailer track that enters or exits the geo-fenced area of ​​the terminal or yard, and split it into sub-tracks; the geo-fenced area of ​​the terminal or yard marks the logical starting point or end point of the transport task; 3) constructing a Cartesian set of candidate ODs that are separated from the waybill based on each of the split container trailer sub-trajectories; 4) Screen candidate ODs based on actual business data so that the control route body is consistent with historical transportation experience as a candidate trajectory; S3: Mining and extracting common sub-trajectories: In the candidate OD Cartesian set, trajectory similarity evaluation and cluster analysis are performed for a group of transportation task trajectories with the same starting and ending points. Trajectory distances are calculated using the Hausdoriff method and then clustered. The density of trajectory points within each cluster is calculated for optimal selection. The trajectory with the shortest transportation time is selected as the benchmark trajectory. The common sub-trajectories are then verified and restored based on the number of Geohash blocks to obtain an effective empirical route. S4: Optimize empirical trajectories and enhance processing: Use intelligent denoising algorithms to automatically identify and delete redundant trajectory segments within a preset range around the OD; Use third-party route planning services to supplement the remaining trajectory information; S5: Trajectory retrieval for the adjacent transport task: search for the OD empirical trajectory centered on the target OD and use it as the main part of the planned trajectory; Use third-party route planning services to solve the problem of missing heads and tails near the starting and ending points of the trajectory, thereby improving the empirical trajectory and forming a complete route that conforms to historical business experience.

2. A method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 1, characterized in that: The method for collecting and accessing container trailer data, surrounding environment data, and container truck transport task data is as follows: S11: The location data sent by the truck connected to the GPS signal box. The collection interval between each two GPS points is between 2-10 minutes, including the vehicle's real-time latitude and longitude, sending timestamp, direction, and speed; S12: The dock geo-fence data is manually maintained static basic data. The shape of the geo-fence is the actual geographical shape of the dock. S13: Truck transport task data includes: transport start and end terminals, customer location, transport task required time, and trailer license plate information.

3. A method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 1, characterized in that: The preprocessing method in S2 is: S21: Stop point mining and location standardization: The Traj-DBSCAN algorithm is used to mine significant stop points in the historical trajectory of the container truck as key nodes of the transportation task, and the Geohash technology is used to encode the location of each stop point; S22: Task Boundary Definition and Trajectory Screening: Based on the conventional business model of container truck transportation, the actual geographical fence of the terminal is set as the logical starting point or end point of the transportation task. By setting a 48-hour sliding window, the trajectory data crossing the fences of two terminals is searched within this time period. The OD pairs formed by the Geohash of the stop points in these trajectories are marked and a candidate set of historical sub-trajectories is constructed. S23: Trajectory quality control and optimization: Double filter the candidate trajectories to exclude trajectories with abnormal transportation time; and eliminate trajectories with insufficient GPS data points, that is, less than the set value.

4. A method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 1, characterized in that: In S2, the candidate ODs include: Sub-trajectory set = {T1, T2} The set of stop points of sub-trajectory T1 = {pier 1, stop point 1, stop point 2, pier 2} The set of stop points of sub-trajectory T2 = {Pier 3, Stop Point 3, Pier 4} Through Cartesian product, all possible OD combinations of T1 are obtained: T1 candidate OD combination = {(terminal 1, stop point 1), (stop point 1, stop point 2), (stop point 2, terminal 2), (terminal 1, stop point 2), (terminal 1, terminal 2), (stop point 2, terminal 2)} T2 candidate OD combination = {(terminal 3, stop point 3), (stop point 3, terminal 4), (terminal 3, stop point 4)} Then all possible OD combinations are: Candidate OD combination = T1 candidate OD combination × T2 candidate OD combination = {(terminal 1, stop point 1), (stop point 1, stop point 2), (stop point 2, terminal 2), (terminal 1, stop point 2), (terminal 1, terminal 2), (stop point 2, terminal 2), (terminal 3, stop point 3), (stop point 3, terminal 4), (terminal 3, stop point 4)}.

5. The method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 1 is characterized in that: The method of mining and extracting common sub-trajectories in S3 is as follows: for a group of transport task trajectories with the same starting and ending point Geohash, if the number of transport trajectories in the group is greater than or equal to 3, common sub-trajectories are mined.

6. A method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 1, characterized in that: The method for mining and extracting common sub-tracks in S3 is: S31: Trajectory similarity assessment and clustering: Use Hausdorff distance to calculate the similarity between each trajectory in the same group; cluster the trajectories based on trajectory similarity using the DBSCAN algorithm, obtain clusters based on distance similarity, remove isolated points, and select the top 5 clusters containing the most transport trajectories for analysis; S32: Track density screening and determination of reference tracks: Calculate the track density within each cluster, where the track density is the track transport time divided by the number of GPS points, and prioritize tracks with higher density. If there are less than three high-density tracks, gradually relax the density restriction. Among the eligible clusters, select the track with the shortest transport time as the reference track. S33: Geohash-based trajectory comparison and common segment extraction: Perform Geohash encoding on all trajectories, compare each trajectory encoding with the reference trajectory encoding one by one, retain the Geohash blocks that are the same or adjacent to the reference trajectory encoding, and construct the encoding framework of potential common sub-trajectories; S34: Verify and restore the common sub-trajectory: Ensure that the first and last Geohash blocks of the common coding result are consistent with the reference trajectory, and automatically supplement them if they are inconsistent. At the same time, check the number of Geohash blocks in the common coding result for verification. If the verification passes, use the reference trajectory and the verified Geohash coding result to restore the common sub-trajectory. Based on the number of GPS points in the restored common sub-trajectory, determine whether it is a valid empirical route.

7. A method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 6, characterized in that: The verification requirement in S34 is: at least 3 Geohash blocks must cover more than 30% of the reference trajectory code; the method for determining a valid empirical route is: if the number of GPS points in the restored common sub-trajectory is not less than 5, it is determined to be a valid empirical route.

8. The method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 1, characterized in that: The method for optimizing the experience trajectory and enhancing the processing in S4 is: S41: After obtaining the empirical route described in S3, an intelligent denoising algorithm is used to eliminate unnecessary factors due to pathfinding and temporary stops near the start and end points, and redundant trajectory segments within a preset range around the OD are automatically identified and deleted; S42: Use a third-party route planning service to supplement the trajectory information, including supplementing trajectory points, calculating trajectory distance, counting the number of trajectory GPS points, and transportation time.

9. The method for mining and retrieving container truck transport routes based on GPS and industry characteristics according to claim 1, characterized in that: The method for retrieving the trajectory of the adjacent transport task in S5 is: S51: When performing trajectory retrieval, the search radius is set and the search area is drawn with the target OD as the center to find out whether there is an existing and settled OD experience trajectory; if an experience trajectory that meets the conditions is retrieved, it is used as the main part of the planned trajectory; S52: Improve the experience trajectory: Use third-party route planning services to solve the problem of missing heads and tails near the starting and ending points of the trajectory, and finally form a complete route that conforms to historical business experience.

10. A system for mining and retrieving container truck transport routes based on GPS and industry characteristics according to any one of claims 1 to 8, characterized in that: include Data collection module: used to collect container trailer trajectory data formed by GPS data of container trailers, terminal and yard geo-fence data, and container truck transportation task data; Preprocessing module: used to process the container trailer trajectory data, terminal and yard geo-fence data, and truck transportation task data in the data acquisition module: including: mining the stay points that exceed the set stay time in the historical data of container trailer trajectory as key nodes of the transportation task, preliminarily filtering the stay points through the map service, and encoding the remaining stay points as potential customer door-point stay points; a location coding sub-module that truncates any container trailer trajectory that enters and exits the geo-fence of the terminal and yard, and splits it into container trailer sub-trajectories; a candidate OD sub-module that constructs a Cartesian set of candidate ODs that are separated from the waybill based on each split container trailer sub-trajectory; a candidate trajectory sub-module that screens candidate ODs based on actual business data so that the control route body conforms to historical transportation experience as the candidate trajectory; The module for mining and extracting common sub-trajectories includes: a cluster analysis sub-module that evaluates and clusters the trajectory similarity of a group of transport task trajectories with the same starting and ending geohash, calculates the trajectory distance using Hausdoriff, calculates the density of trajectory points within each cluster, and selects the trajectory with the shortest transport time as the benchmark trajectory, and then verifies and restores the common sub-trajectories based on the number of geohash blocks to obtain a valid empirical route sub-module; Optimize empirical trajectory and enhance processing module: including: a redundancy removal submodule that uses an intelligent denoising algorithm to automatically identify and delete redundant trajectory segments within a preset range around the OD; a trajectory enhancement submodule that uses a third-party route planning service to supplement trajectory information; The trajectory retrieval module for the adjacent transport task includes: a planned trajectory submodule that searches for the OD empirical trajectory centered on the target OD and uses it as the main part of the planned trajectory; an empirical route submodule that uses a third-party route planning service to resolve the problem of missing heads and tails near the start and end points of the trajectory, thereby improving the empirical trajectory and forming a transport route that conforms to historical business experience; and a route display submodule that displays the transport route that conforms to historical experience.

Images