Intelligent dispatching distance matrix generation method and device based on vehicle trajectory

Abstract

The present application discloses a method and device for generating an intelligent scheduling distance matrix based on vehicle trajectories. The method and device analyze vehicle operation information such as mileage and operating time between all stations based on vehicle trajectory data and station information, and use the information as elements of an OD matrix for path planning to generate an OD matrix. The present application can effectively overcome the defect of large errors in the method of generating an OD matrix using Euclidean distance, and does not require map navigation, thereby overcoming the technical problems existing in the prior art when generating an OD matrix.

Description

Technical Field

[0001] The present application belongs to the technical field of vehicle path planning, and in particular, relates to a method and device for generating an intelligent scheduling distance matrix based on vehicle trajectories. Background Art

[0002] The Vehicle Routing Problem (VRP) is one of the most complex problems in the field of supply chain, operations research and management science. In the new retail scenario, the rapid growth of real-time orders for hourly delivery has brought great challenges to finding the optimal path for warehouse distribution. The problem itself is to organize appropriate driving routes for a series of loading and unloading points so that trucks can pass through them in an orderly manner, and achieve the goals of minimum total mileage and cost under the constraints of cargo volume, loading and unloading time windows, vehicle capacity restrictions, mileage restrictions, and operating time restrictions. For the entire path planning, generating the distance and time matrix between all points is the most important step in data preparation.

[0003] There are many ways to generate a distance matrix. The first is to use Euclidean distance, and the time is converted according to the speed threshold. The distance matrix obtained by this method has a large error. It can still be used for medium and long-distance transportation (over 200km), but it is completely unusable for urban distribution when the distance between stations is small. The second is to use map navigation. For each station, Gaode / Baidu driving navigation is used to obtain mileage and time to form an OD (Origin-Destination) matrix. The biggest problem with this method is that the cost is too high. For example, if there are 1,000 stations, navigation will be required 1 million times, and if there are 10,000 stations, navigation will need to be called 100 million times. The free map interface service is completely unable to support it and the efficiency is very low.

[0004] Therefore, it is very necessary in the art to propose a new solution to the OD matrix generation problem in path planning to overcome the technical problems existing in the existing technology. Summary of the invention

[0005] In view of this, the present application provides a method and device for generating an intelligent scheduling distance matrix based on vehicle trajectories, which are used to overcome the technical problems existing in the prior art when generating an OD matrix.

[0006] The specific technical solutions are as follows:

[0007] A method for generating an intelligent dispatching distance matrix based on vehicle trajectories, comprising:

[0008] Obtain vehicle operation trajectory data and station information;

[0009] Based on the obtained vehicle running track data and station information, the vehicle running track and the station are matched to obtain the matching result of the vehicle running track and the station;

[0010] According to the matching result, extracting a vehicle operation information set corresponding to each two stations in the two-station pair; the vehicle operation information set corresponding to the two stations includes the vehicle operation information corresponding to each vehicle operation track between the two stations;

[0011] According to the vehicle operation information set corresponding to every two stations, the statistical operation information corresponding to the OD section to which every two stations belong is determined respectively.

[0012] According to the statistical operation information corresponding to each OD segment, an OD matrix for path planning is generated, so that the path optimization engine performs vehicle path optimization based on the OD matrix.

[0013] Optionally, the obtaining of vehicle running track data and station information includes:

[0014] At least obtain the vehicle identification and the position and time information corresponding to each track point on the vehicle running track;

[0015] Get the site identification and location information of each site.

[0016] Optionally, the matching process of the vehicle running track and the site based on the obtained vehicle running track data and site information to obtain the matching result of the vehicle running track and the site includes:

[0017] Each track point on the vehicle running track is matched with the station that is closest and does not exceed the preset distance threshold, and a matching result is obtained that each track point on the vehicle running track matches the corresponding station or does not match the station.

[0018] Optionally, extracting the vehicle operation information set corresponding to every two stations in the pairwise order according to the matching result includes:

[0019] Remove the track points on the vehicle running track that are not matched to the station;

[0020] According to the position and time information of each track point on the vehicle running track, the running time and running mileage between two consecutive stations corresponding to each track point retained for the same vehicle data are calculated;

[0021] The two consecutive stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and the running time and mileage corresponding to the running trajectories of each vehicle between the same OD segment are summarized to obtain the vehicle running information set corresponding to the two stations in the same OD segment.

[0022] Optionally, the determining, according to the vehicle operation information set corresponding to each two stations, the statistical operation information corresponding to the OD section to which each two stations belong includes:

[0023] The running time and the running mileage in the vehicle running information set corresponding to the OD segment are averaged to obtain the average time and the average mileage as the running time and the running mileage of the OD segment;

[0024] The generating of the OD matrix of the path planning according to the statistical operation information corresponding to each OD segment includes:

[0025] The running time and mileage of each OD segment are converted into an OD matrix between different stations.

[0026] A device for generating an intelligent dispatching distance matrix based on vehicle trajectories, comprising:

[0027] An acquisition module is used to obtain vehicle running track data and station information;

[0028] A matching module is used to match the vehicle running track with the station based on the obtained vehicle running track data and station information to obtain a matching result between the vehicle running track and the station;

[0029] An extraction module, configured to extract a vehicle operation information set corresponding to each of the two stations in pairs according to the matching result; the vehicle operation information set corresponding to the two stations includes vehicle operation information corresponding to each vehicle operation track between the two stations;

[0030] The determination module is used to determine the statistical operation information corresponding to the OD section to which each two stations belong according to the vehicle operation information set corresponding to each two stations.

[0031] The generation module is used to generate an OD matrix for path planning according to the statistical operation information corresponding to each OD segment, so that the path optimization engine can perform vehicle path optimization based on the OD matrix.

[0032] Optionally, the acquisition module is specifically used to:

[0033] At least obtain the vehicle identification and the position and time information corresponding to each track point on the vehicle running track;

[0034] Get the site identification and location information of each site.

[0035] Optionally, the matching module is specifically used to:

[0036] Each track point on the vehicle running track is matched with the station that is closest and does not exceed the preset distance threshold, and a matching result is obtained that each track point on the vehicle running track matches the corresponding station or does not match the station.

[0037] Optionally, the extraction module is specifically used to:

[0038] Remove the track points on the vehicle running track that are not matched to the station;

[0039] According to the position and time information of each track point on the vehicle running track, the running time and running mileage between two consecutive stations corresponding to each track point retained for the data of the same vehicle are calculated;

[0040] The two consecutive stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and the running time and mileage corresponding to the running trajectories of each vehicle between the same OD segment are summarized to obtain the vehicle running information set corresponding to the two stations in the same OD segment.

[0041] Optionally, the determination module is specifically used to: average the running time and the running mileage in the vehicle running information set corresponding to the OD segment to obtain the average time and the average mileage as the running time and the running mileage of the OD segment;

[0042] The generation module is specifically used to convert the running time and running mileage of each OD segment into an OD matrix between different sites.

[0043] It can be seen from the above technical scheme that the method and device for generating an intelligent scheduling distance matrix based on vehicle trajectory disclosed in the present application analyze the vehicle operation information such as mileage and running time between all stations based on vehicle trajectory data and station information, and use it as an element of the OD matrix of path planning to realize the generation of the OD matrix. The present application can effectively overcome the defect of large error in the method of generating the OD matrix by Euclidean distance, and does not require the use of map navigation, thereby overcoming the technical problems existing in the existing technology when generating the OD matrix. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A flow chart of the method for generating a distance matrix for intelligent scheduling based on vehicle trajectories provided in this application;

[0046] Figure 2 The technical implementation logic diagram for generating the OD matrix provided in this application;

[0047] Figure 3 A schematic diagram of the structure of the vehicle trajectory-based intelligent scheduling distance matrix generation device provided in this application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The present application provides a method and device for generating an intelligent scheduling distance matrix based on vehicle trajectories. The method analyzes vehicle operation information such as mileage and operating time between all stations based on vehicle trajectory data and station information, and uses it as an element of the OD matrix of path planning to achieve the generation of the OD matrix, thereby overcoming the technical problems existing in the existing technology when generating the OD matrix.

[0050] First, the special terms, English abbreviations, etc. involved in the embodiments of the present application are explained as follows:

[0051] Table 1

[0052]

[0053] The processing flow of the method for generating a distance matrix for intelligent scheduling based on vehicle trajectories provided in this application is as follows: Figure 1 As shown, specifically including:

[0054] Step 101: Obtain vehicle running track data and station information.

[0055] This step is a data preparation step, which is used to provide a data basis for subsequent processing.

[0056] The acquired vehicle running trajectory data at least includes the vehicle identification and the position and time information corresponding to each trajectory point on the vehicle running trajectory. In addition, optionally, the acquired vehicle running trajectory data may also include speed information of each trajectory point on the vehicle running trajectory.

[0057] The vehicle identification may be, but is not limited to, the vehicle number; the location information and time information corresponding to the track point may be, but are not limited to, the longitude and latitude information and GPS (Global Positioning System) time corresponding to the track point.

[0058] An example of the obtained vehicle running trajectory data is provided below through Table 2:

[0059] Table 2

[0060]

[0061]

[0062] The acquired site information includes at least a site identifier and location information of the site, wherein the site identifier may be but is not limited to a site number, and the location information of the site includes but is not limited to the latitude and longitude information corresponding to the site.

[0063] An example of the obtained site information is provided below through Table 3:

[0064] Table 3

[0065]

[0066] Step 102: Based on the obtained vehicle running track data and site information, the vehicle running track and the site are matched to obtain a matching result of the vehicle running track and the site.

[0067] After obtaining the vehicle running trajectory data and station information, this step further matches each trajectory point on the vehicle running trajectory with the nearest station that does not exceed the preset distance threshold, and obtains a matching result that each trajectory point on the vehicle running trajectory matches the corresponding station or does not match the station.

[0068] The value of the distance threshold can be flexibly set or adjusted according to actual conditions. For example, the distance threshold can be set to 100m according to actual conditions. This embodiment does not limit its specific value.

[0069] Step 103: extract the vehicle operation information set corresponding to each pair of stations according to the above matching results; the vehicle operation information set corresponding to the two stations includes the vehicle operation information corresponding to each vehicle operation track between the two stations.

[0070] Specifically, the trajectory points on the vehicle running trajectory that are not matched to the stations are first removed, and then the running time and running mileage between two temporally consecutive stations corresponding to each retained trajectory point are calculated for the data of the same vehicle according to the position and time information of each trajectory point on the vehicle running trajectory. On this basis, the two temporally consecutive stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and the running time and running mileage corresponding to the running trajectories of each vehicle between the same OD segment are summarized to obtain the vehicle running information set corresponding to the two stations in the same OD segment.

[0071] For the data examples in Tables 2 and 3 above, the results of calculating the running time and running mileage between two consecutive stations for the same vehicle are as follows:

[0072] Table 4

[0073]

[0074] Based on Table 4, the results of further combining the two consecutive stations corresponding to the running trajectory of each vehicle into an OD segment are as follows:

[0075] Table 5

[0076]

[0077] On the basis of forming the OD segments, the results of the previous step are summarized according to the OD segments, specifically summarizing the running time and running mileage corresponding to each vehicle running track between the same OD segments, and obtaining the vehicle running information set corresponding to the two stations in the same OD segment.

[0078] Step 104 : According to the vehicle operation information set corresponding to every two stations, the statistical operation information corresponding to the OD segment to which every two stations belong is determined respectively.

[0079] Afterwards, each running time in the vehicle running information set corresponding to the OD segment is averaged and each running mileage is averaged to obtain an average time and an average mileage, which are used as the running time and running mileage of the OD segment.

[0080] Preferably, in the implementation, before performing the above-mentioned averaging process, referring to Figure 2 First, data cleaning is performed to remove abnormal data in the vehicle operation information set corresponding to the same OD segment, such as removing the OD segment data whose running time and running mileage are not within the range of their mean value plus or minus 1 times the standard deviation (mean±sd). That is, the OD segment data whose running time and running mileage in the same OD segment seriously deviate from the mean are regarded as abnormal data.

[0081] On this basis, the average duration and average mileage of the remaining data in the vehicle operation information set corresponding to the same OD segment are further calculated, and the calculated average duration and average mileage are used as the operation duration and operation mileage of this OD segment (that is, the statistical operation information corresponding to this OD segment).

[0082] Step 105 : Generate an OD matrix for path planning according to the statistical operation information corresponding to each OD segment, so that the path optimization engine performs vehicle path optimization based on the generated OD matrix.

[0083] Finally, the running time and mileage of each OD segment are converted into an OD matrix between different stations. For the data examples provided in the above tables, the converted OD matrix is ​​as follows:

[0084] Table 6

[0085]

[0086] Subsequently, the generated OD matrix can be brought into the path optimization engine for use, so that the path optimization engine can perform vehicle path optimization based on the OD matrix. By performing vehicle path optimization based on the generated OD matrix, appropriate driving routes can be organized so that trucks and other vehicles can pass through them in an orderly manner, while meeting constraints such as cargo volume, loading and unloading time windows, vehicle capacity restrictions, mileage restrictions, and operating time restrictions, the total mileage and cost can be minimized.

[0087] It can be seen from the above technical solution that the method of the embodiment of the present application analyzes the vehicle operation information such as mileage and running time between all stations based on vehicle trajectory data and station information, and uses it as the element of the OD matrix of path planning to realize the generation of the OD matrix. The present application can effectively overcome the defect of large error in the method of generating the OD matrix using Euclidean distance, and there is no need to use map navigation, thereby overcoming the technical problems existing in the existing technology when generating the OD matrix.

[0088] Corresponding to the above method, the embodiment of the present application also discloses a device for generating an intelligent scheduling distance matrix based on vehicle trajectories, such as Figure 3 As shown, the device comprises:

[0089] The acquisition module 301 is used to acquire vehicle running track data and station information;

[0090] A matching module 302 is used to match the vehicle running track with the station based on the obtained vehicle running track data and station information to obtain a matching result between the vehicle running track and the station;

[0091] The extraction module 303 is used to extract the vehicle operation information set corresponding to each two stations in the two-station pair according to the matching result; the vehicle operation information set corresponding to the two stations includes the vehicle operation information corresponding to each vehicle operation track between the two stations;

[0092] The determination module 304 is used to determine the statistical operation information corresponding to the OD section to which each two stations belong according to the vehicle operation information set corresponding to each two stations.

[0093] The generation module 305 is used to generate an OD matrix for path planning according to the statistical operation information corresponding to each OD segment, so that the path optimization engine performs vehicle path optimization based on the OD matrix.

[0094] In one implementation, the acquisition module 301 is specifically configured to:

[0095] At least obtain the vehicle identification and the position and time information corresponding to each track point on the vehicle running track;

[0096] Get the site identification and location information of each site.

[0097] In one embodiment, the matching module 302 is specifically used to match each track point on the vehicle running track with the station that is closest and does not exceed a preset distance threshold, and obtain a matching result that each track point on the vehicle running track matches the corresponding station or does not match the station.

[0098] In one implementation, the extraction module 303 is specifically configured to:

[0099] Remove the track points on the vehicle running track that are not matched to the station;

[0100] According to the position and time information of each track point on the vehicle running track, the running time and running mileage between two consecutive stations corresponding to each track point retained for the same vehicle data are calculated;

[0101] The two consecutive stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and the running time and mileage corresponding to the running trajectories of each vehicle between the same OD segment are summarized to obtain the vehicle running information set corresponding to the two stations in the same OD segment.

[0102] In one embodiment, the determination module 304 is specifically configured to: average each running time and each running mileage in the vehicle running information set corresponding to the OD segment to obtain an average time and an average mileage as the running time and running mileage of the OD segment;

[0103] The generation module 305 is specifically used to convert the running time and running mileage of each OD segment into an OD matrix between different sites.

[0104] For the intelligent scheduling distance matrix generation device based on vehicle trajectory disclosed in the embodiment of the present application, since it corresponds to the intelligent scheduling distance matrix generation method based on vehicle trajectory disclosed in the above method embodiment, the description is relatively simple. For relevant similarities, please refer to the description of the corresponding method embodiment above, and it will not be described in detail here.

[0105] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0106] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0107] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0108] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating an intelligent dispatching distance matrix based on vehicle trajectories, characterized in that: include: Obtain vehicle operation trajectory data and station information; Based on the obtained vehicle running track data and station information, the vehicle running track and the station are matched to obtain the matching result of the vehicle running track and the station; According to the matching results, two time-continuous stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and a vehicle running information set corresponding to two stations in the same OD segment is extracted; The vehicle operation information set corresponding to the two stations includes the vehicle operation information corresponding to each vehicle operation track between the two stations; According to the vehicle operation information set corresponding to each two stations, the statistical operation information corresponding to the OD section to which each two stations belong is determined respectively; According to the statistical operation information corresponding to each OD segment, an OD matrix for path planning is generated, so that the path optimization engine performs vehicle path optimization based on the OD matrix.

2. The method according to claim 1, characterized in that The obtaining of vehicle running track data and station information includes: At least obtain the vehicle identification and the position and time information corresponding to each track point on the vehicle running track; Get the site identification and location information of each site.

3. The method according to claim 2, characterized in that The matching process of the vehicle running track and the site based on the obtained vehicle running track data and site information to obtain the matching result of the vehicle running track and the site includes: Each track point on the vehicle running track is matched with the station that is closest and does not exceed the preset distance threshold, and a matching result is obtained that each track point on the vehicle running track matches the corresponding station or does not match the station.

4. The method according to claim 3, characterized in that: According to the matching result, two time-continuous stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and a vehicle running information set corresponding to two stations in the same OD segment is extracted, including: Remove the track points on the vehicle running track that are not matched to the station; According to the position and time information of each track point on the vehicle running track, the running time and running mileage between two consecutive stations corresponding to each track point retained for the data of the same vehicle are calculated; The two consecutive stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and the running time and mileage corresponding to the running trajectories of each vehicle between the same OD segment are summarized to obtain the vehicle running information set corresponding to the two stations in the same OD segment.

5. The method according to claim 4, characterized in that The step of determining the statistical operation information corresponding to the OD segment to which each two stations belong based on the vehicle operation information set corresponding to each two stations includes: The running time and the running mileage in the vehicle running information set corresponding to the OD segment are averaged to obtain the average time and the average mileage as the running time and the running mileage of the OD segment; The generating of the OD matrix of the path planning according to the statistical operation information corresponding to each OD segment includes: The running time and mileage of each OD segment are converted into an OD matrix between different stations.

6. A device for generating an intelligent dispatching distance matrix based on vehicle trajectories, characterized in that: include: An acquisition module is used to obtain vehicle running track data and station information; A matching module is used to match the vehicle running track with the site based on the obtained vehicle running track data and site information to obtain a matching result between the vehicle running track and the site; An extraction module, used for grouping two time-continuous stations corresponding to the running trajectory of each vehicle into an OD segment according to the matching result, and extracting a vehicle running information set corresponding to two stations in the same OD segment; The vehicle operation information set corresponding to the two stations includes the vehicle operation information corresponding to each vehicle operation track between the two stations; A determination module, used to determine the statistical operation information corresponding to the OD section to which each two stations belong, according to the vehicle operation information set corresponding to each two stations; The generation module is used to generate an OD matrix for path planning according to the statistical operation information corresponding to each OD segment, so that the path optimization engine can perform vehicle path optimization based on the OD matrix.

7. The device according to claim 6, characterized in that The acquisition module is specifically used for: At least obtain the vehicle identification and the position and time information corresponding to each track point on the vehicle running track; Get the site identification and location information of each site.

8. The device according to claim 7, characterized in that The matching module is specifically used for: Each track point on the vehicle running track is matched with the station that is closest and does not exceed the preset distance threshold, and a matching result is obtained that each track point on the vehicle running track matches the corresponding station or does not match the station.

9. The device according to claim 8, characterized in that The extraction module is specifically used for: Remove the track points on the vehicle running track that are not matched to the station; According to the position and time information of each track point on the vehicle running track, the running time and running mileage between two consecutive stations corresponding to each track point retained for the data of the same vehicle are calculated; The two consecutive stations corresponding to the running trajectory of each vehicle are grouped into an OD segment, and the running time and mileage corresponding to the running trajectories of each vehicle between the same OD segment are summarized to obtain the vehicle running information set corresponding to the two stations in the same OD segment.

10. The device according to claim 9, characterized in that: The determination module is specifically used to: average the running time and running mileage in the vehicle running information set corresponding to the OD segment to obtain the average time and average mileage as the running time and running mileage of the OD segment; The generation module is specifically used to convert the running time and running mileage of each OD segment into an OD matrix between different sites.

Images