Tail end distribution path planning method based on historical trajectory

By constructing historical trajectory data for logistics terminal distribution and generating distribution network connectivity tables, the efficiency and quality problems in terminal distribution path planning are solved, effective utilization of road network changes and experience is achieved, and distribution efficiency and quality are improved.

CN119067552AActive Publication Date: 2024-12-03CENT SOUTH UNIV
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411298217.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-12-03
Estimated Expiration
2044-09-18

AI Technical Summary

Technical Problem

In the terminal distribution path planning, the existing technology has problems such as long path planning time, lack of traffic network data, fast route changes and difficult to record and inherit experience, which makes it difficult to ensure distribution efficiency and quality.

Method used

By obtaining and preprocessing the express delivery address and trajectory data of the logistics terminal distribution track section, building a set of delivery nodes and resident nodes, establishing an association relationship, splitting the closed path section, generating a distribution network connection table, and using historical trajectory data to plan appropriately delivery path.

Benefits of technology

Effectively utilize historical experience to adapt to urban construction and road network changes, improve the planning efficiency and quality of distribution paths, and is suitable for a variety of complex scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067552A_ABST
    Figure CN119067552A_ABST
Patent Text Reader

Abstract

The invention discloses a terminal distribution path planning method based on a historical track. The method comprises the following steps: acquiring all express addresses and distribution track point data in a preset statistical period; constructing a logistics tail end delivery node total set according to all express addresses; obtaining closed delivery tracks based on the delivery track point data, and constructing a resident node set corresponding to each closed delivery track; establishing an association relationship between a delivery node and a resident node of each collection and delivery operation in a preset statistical period, and endowing starting time and ending time for the delivery node; acquiring a closed collection and delivery path of a single collection and delivery operation, splitting the closed collection and delivery path into a plurality of delivery path sections and storing the delivery path sections until the delivery path sections of all collection and delivery operations are stored, and acquiring a delivery network communication table according to the stored data; and planning a tail end distribution path based on the distribution network communication table. According to the invention, the distribution knowledge accumulated by the collection and delivery staff for a long time can be used for planning the tail-end distribution path, and the distribution efficiency and quality can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of logistics management and spatial big data processing, and in particular relates to a terminal delivery path planning method based on historical trajectories. Background Art

[0002] At present, modern logistics business has become the basic support of e-commerce, deeply integrated into modern production and social life, and has greatly changed people's shopping methods. In order to continuously improve the quality of logistics and customer experience, fast and accurate delivery has become the goal pursued by logistics companies. However, due to the huge volume of express delivery business, numerous customer locations, complex delivery road conditions, imperfect or even missing road networks required for terminal delivery, and rapid changes in transportation conditions, the terminal delivery from logistics service outlets or stations to the "last mile" of customers is the section with the largest workload and the most arduous delivery task, and it directly affects the quality of express delivery services. In order to facilitate management and improve delivery efficiency, a logistics service outlet usually divides the service scope into multiple fixed delivery sections (or delivery fences), and each section is usually delivered by a deliveryman. In the delivery operation, the deliveryman must first quickly plan the delivery order, that is, the delivery route, according to the address of the express to be delivered in the section and its spatial location, and then load the express in reverse order of delivery, and finally start the delivery operation according to the planned delivery route.

[0003] Although spatial information technology (such as geographic information technology) and logistics distribution have been highly integrated, and delivery personnel can use modern navigation systems to plan delivery routes, this delivery route planning model still faces many challenges and difficulties. These difficulties include: (1) When the service outlets modify the electronic fence or adjust the delivery personnel, the delivery personnel need to go through a long period of exploration to become familiar with the distribution status of the customers in the section, the surrounding traffic environment, and other conditions, so as to efficiently arrange the delivery route; (2) When the section lacks traffic network data or the customers are far away from the traffic route or the road changes rapidly, it is difficult for the navigation system to plan a suitable delivery route; (3) The delivery route experience accumulated by the end delivery personnel is difficult to record and pass on. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a terminal delivery path planning method based on historical trajectories to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a terminal delivery path planning method based on historical trajectories, comprising:

[0006] Obtain all express delivery addresses and delivery track point data of the final delivery route pick-up and delivery personnel during the preset statistical period;

[0007] After preprocessing all the express addresses, spatial aggregation is performed, and a total set of logistics terminal delivery nodes is constructed based on the aggregation results; a closed delivery trajectory is obtained based on the delivery trajectory point data, and a resident node set corresponding to each closed delivery trajectory is constructed;

[0008] Establish the relationship between the delivery node and the resident node for each delivery operation within the preset statistical period, and assign the start time and end time to the delivery node;

[0009] Obtain the closed delivery path of a single delivery operation, split the closed delivery path into several delivery path segments and store them until the delivery path segments of all delivery operations are stored, obtain the path segment data table, and obtain the distribution network connection table based on the path segment data table;

[0010] The terminal delivery path is planned based on the delivery network connection table.

[0011] Optionally, the process of spatially aggregating all the express delivery addresses after preprocessing includes:

[0012] The express delivery address is converted into geographic coordinates, and an express delivery feature set is constructed; the interest surface of the logistics terminal distribution section is obtained, and the express delivery addresses of each interest surface are merged into a delivery node; the express delivery addresses that are not covered by the interest surface and are spatially adjacent are merged into a delivery node using a spatial clustering algorithm, and the geographic coordinates of each delivery node are calculated based on the express delivery feature set.

[0013] Optionally, the process of constructing a set of resident nodes corresponding to each closed delivery trajectory includes:

[0014] All trajectory points of each closed delivery trajectory are spatially clustered, and the trajectory points that meet the density requirements are classified into one category to form a resident trajectory sub-segment. The trajectory points of each resident trajectory sub-segment are merged into a resident node, and the center coordinates of the trajectory points of each resident trajectory sub-segment are calculated as the coordinates of the resident node to obtain the resident node set.

[0015] Optionally, the process of establishing the association relationship between the delivery node and the resident node for each pickup and delivery operation within a preset statistical period includes:

[0016] The express address set of the collection and delivery operation is read, and based on the express address set and the total set of logistics terminal delivery nodes, the delivery node subset of the collection and delivery operation is obtained; based on the resident node set corresponding to the collection and delivery operation, the start time and end time are assigned to each delivery node in the delivery node subset according to the resident node set.

[0017] Optionally, the process of assigning a start time and an end time to each delivery node in the delivery node subset includes:

[0018] Extract the delivery nodes and resident nodes that belong to the same interest surface from the delivery node subset and the resident node set, and assign the start time and end time of the resident node to the corresponding delivery node; if there is no resident node in the interest surface where a single delivery node is located, find the nearest resident node, and assign the start time and end time of the resident node to the corresponding delivery node; if there is no matching resident node, assign the start time and end time of the trajectory point in the distribution trajectory that is closest to the delivery node to the corresponding delivery node.

[0019] Optionally, the process of obtaining a closed delivery path includes:

[0020] Taking the station for the delivery operation as the starting point, the delivery nodes in the delivery node subset are connected in sequence according to the chronological order of the starting time, and the last delivery node is connected to the station to obtain a closed delivery path.

[0021] Optionally, the process of obtaining the path segment data table includes:

[0022] Taking the station as the starting point, extract two consecutive delivery nodes of the closed delivery path of a single delivery operation in turn, calculate the time difference between the end time of the previous delivery node and the start time of the next delivery node, and obtain the path segment time cost. Based on the path segment starting node number, the next node number and the path segment time cost, form the delivery path segment data and store it until the delivery path segment storage of all delivery operations is completed to obtain the path segment data table.

[0023] Optionally, the process of obtaining the distribution network connectivity table includes: traversing the delivery path segment data in the path segment data table, calculating the average time cost value of the delivery path segment whose starting node number is exactly the same as the next node number, and judging whether the delivery path segment already exists in the distribution network connectivity table; if so, updating the path segment time cost in the distribution network connectivity table according to the average time cost value; if not, storing the delivery path segment data directly in the distribution network connectivity table, wherein the structure of the distribution network connectivity table is exactly the same as that of the path segment data table.

[0024] Compared with the prior art, the present invention has the following advantages and technical effects:

[0025] The present invention mines the delivery paths of terminal delivery personnel on the basis of sorting out the historical delivery trajectory data of terminal delivery personnel, constructs a delivery network, and then uses the constructed delivery network to plan a suitable path for the delivery of terminal logistics express. This method uses historical delivery trajectories to construct a delivery network, which can map the delivery experience accumulated by delivery personnel over a long period of time in the distribution network. The planned delivery path can give full play to the role of historical experience, and can also adapt to various scenarios such as rapid urban construction, inaccurate road networks, and missing road networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0027] Figure 1 A schematic diagram of a method flow of an embodiment of the present invention;

[0028] Figure 2 This is an example diagram of the express address and AOI of an embodiment of the present invention;

[0029] Figure 3 This is an example diagram of the track points of the delivery section according to an embodiment of the present invention;

[0030] Figure 4 An example diagram of a closed delivery trajectory and its trajectory points according to an embodiment of the present invention;

[0031] Figure 5 An example diagram of the resident nodes and their start and end times extracted from the delivery trajectory of an embodiment of the present invention;

[0032] Figure 6 This is an example diagram of a delivery node and a track resident node of a pickup and delivery operation according to an embodiment of the present invention;

[0033] Figure 7 This is an example of a delivery path according to an embodiment of the present invention;

[0034] Figure 8 A network connectivity diagram of an embodiment of the present invention;

[0035] Fig. 9 This is an example diagram of a delivery route according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0037] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] Embodiment 1

[0039] like Figure 1 As shown, this embodiment provides a terminal delivery path planning method based on historical trajectories, including:

[0040] (1) Set a statistical period, read all the express delivery addresses of the last section of the statistical period, and use the geocoding tool to convert the express delivery addresses into geographic coordinates to obtain the express delivery element set C = {c1, c2, ..., c i ,...}, where c i is the i-th express element, expressed as c i =<id,name,address,lon,lat> , id is the express customer number, name is the customer name, address is the express address, lon and lat are the longitude and latitude coordinates of the express address. Figure 2 The middle triangle shows the geographic location of all express delivery addresses in the section, where the triangle is the express delivery address and the polygon is the AOI.

[0041] (2) Using the Area of ​​Interest (AOI) data in the terminal section of the logistics, the express addresses of the same AOI are merged into one delivery node. If there are express addresses that are not covered by the AOI, the DBSCAN spatial clustering algorithm is used to merge spatially adjacent express addresses into one delivery node.

[0042] (3) Calculate the center coordinates of the express address contained in each delivery node, set the center coordinates as the geographical coordinates of the delivery node, and obtain the terminal segment delivery node set D = {d1, d2, ..., d i ,...}, where d i is the i-th delivery node, expressed as d i =<id,lon,lat> , where id is the delivery node number, lon and lat are the longitude and latitude coordinates of the delivery node.

[0043] Step 3: Construct the delivery track nodes, including:

[0044] (1) Collect the trajectory point data P = {p1, p2, ..., p i ,...}, where the i-th trajectory point p i =<t,lon,lat,h,d,s> , t represents the timestamp of the trajectory point, lon represents the longitude, lat represents the latitude, h represents the elevation value, d represents the moving direction, and s represents the moving speed. Figure 3 A segment delivery trajectory point dataset is shown.

[0045] (2) Extract the closed delivery trajectory point set. The delivery person at the end of the route signs for the parcels from the express delivery station and loads the parcels to be delivered in reverse order according to the delivery path. He completes the delivery of the parcels in sequence and then returns to the station, forming a closed delivery trajectory, such as Figure 4 As shown in Figure 2, a delivery trajectory consists of multiple ordered trajectory points.

[0046] (3) Extracting the resident nodes of the delivery trajectory. A delivery trajectory consists of a resident trajectory subsegment of the delivery vehicle and a transport trajectory subsegment. Each trajectory subsegment consists of a number of ordered trajectory points. The vehicle resident trajectory subsegment includes the trajectory points uploaded when the vehicle is stationed to load express mail, and the trajectory points uploaded when the vehicle stops on the road or delivers express mail. The distance between the trajectory points of the resident trajectory subsegment is small, and the spatial density is large. The transport trajectory subsegment is the trajectory point generated when the delivery vehicle moves from one resident position to the next resident position. The distance between these trajectory points is large, and the spatial density is small. This embodiment uses the DBSCAN spatial clustering algorithm to spatially cluster all the trajectory points of a delivery trajectory, cluster multiple high-density trajectory points into one category, and form a resident trajectory subsegment. In this embodiment, the following is used: distance = 10m, the minimum number of points is 3; then, the trajectory points of each resident subsegment are merged into a resident node, the center coordinates of the trajectory points of each resident trajectory subsegment are calculated, and assigned to the resident node, to obtain the resident node set of the delivery trajectory. The set of resident nodes of the kth delivery trajectory is expressed as: S k ={s1,s2,...s i ,...}, where s i is the i-th resident node, denoted by s i =<id,lon,lat,start_time,end_time> , where id is the resident node number, lon and lat are the longitude and latitude coordinates of the resident node, start_time and end_time are the start time and end time of the resident node, that is, the first trajectory point time and the last trajectory point time of the resident node. Figure 5 The dwell nodes extracted from the delivery trajectory are shown.

[0047] Step 4: Build a distribution network, including:

[0048] (1) Establishing the relationship between the delivery node and the resident node of the distribution track, including:

[0049] Read all the express addresses of the i-th delivery operation, and obtain the set of all delivery nodes D for this delivery operation based on the correspondence between the express addresses and the delivery nodes. i .

[0050] Read all the resident nodes of the i-th delivery trajectory and get the resident node set S i .

[0051] From D i and S iFind the delivery nodes and resident nodes in the same AOI, and assign the start and end times of the resident nodes in the same AOI to the corresponding delivery nodes; then, find the nearest resident nodes for all unassociated delivery nodes, and assign the start and end times of the resident nodes to the corresponding delivery nodes; finally, find the nearest track point in the distribution track for the unassociated delivery nodes, and assign the time of the track point to the start and end times of the delivery node. Figure 6 The delivery nodes (diamonds), track residence nodes (solid large circles), and track points of a distribution operation are shown.

[0052] Repeat the above steps until the matching of delivery nodes of all pickup and delivery operations in the statistical period is completed.

[0053] (2) Build a distribution network, including:

[0054] Read all delivery nodes of the i-th pickup and delivery operation.

[0055] Taking the station as the starting point, connect the delivery nodes of the i-th delivery operation in the order of the starting time, and then connect the last delivery node to the station, thus forming the i-th closed delivery path, which is expressed as: s→d1→d2→...→d k →...d n →e, where s represents the station station node for the i-th pickup and delivery operation, d k represents the kth delivery node, e represents the resident node after the i-th pick-up and delivery operation is completed and returns to the station, and n represents the number of delivery nodes for the i-th pick-up and delivery operation. Figure 7 This is an example of a delivery route.

[0056] For the i-th delivery path, starting from s, take two consecutive nodes in turn, calculate the time difference between the end time of the previous node and the start time of the next node, and form a delivery path segment<id,source,target,cost,reserve_cost> , id is the path segment number, source is the starting node number, target is the next node number directly connected to source, and cost is the path segment weight. The cost of this embodiment is expressed as the time difference between the two nodes, representing the transportation time from source to target. The reserve_cost value of the path segment represents the transportation time from target to source. This patent sets reserve_cost to "-1", indicating that the path segment is a one-way line segment, that is, target cannot reach source. This embodiment stores all path segments of the i-th delivery path in the path segment data table.

[0057] Repeat the above steps until all the path segments of the delivery path are stored in the path segment data table.

[0058] Create a distribution network connection table, the structure of which is consistent with the path segment table. Search for all source→target identical path segments, and calculate the average time of source→target transportation as the path segment cost weight. When storing in the network connection table, first check whether there is a source→target path segment in the network connection table. If so, update the newly calculated cost to the corresponding path segment; if not, store the path segment data in the network connection table. Figure 8 The network connectivity graph created in this example is shown.

[0059] Step 5: Use the constructed network connectivity table to plan the express delivery route, including:

[0060] (1) Read all the addresses of the express parcels to be delivered, map the parcels to the express parcel nodes, and obtain the set of express parcel nodes to be delivered.

[0061] (2) Using the Dijkstra shortest path search algorithm, with the station as the starting and end point of the distribution, the express node as the path passing point, and the distribution network connection table, the distribution path with the shortest transportation time is planned. Fig. 9 The delivery path planned in this example is shown using bold lines.

[0062] The present invention first spatially aggregates the express addresses within a certain period of time in the logistics terminal distribution route, and merges the express addresses with the same interest surface (area) or adjacent addresses into a delivery node; secondly, collects and organizes the route distribution trajectory data within the statistical period, analyzes the closed distribution trajectory from the station to each express address and then back to the station, extracts the resident trajectory sub-segment from each distribution trajectory, and merges all the trajectory points of the resident trajectory sub-segment into a resident node, and sets the start time and end time for each resident node; then, reads all the express parcels of each collection and delivery operation, maps the express parcels to the delivery nodes, associates the delivery nodes to the delivery nodes of the collection and delivery, obtains the connection path of the delivery nodes of this collection and delivery, and uses these connection paths to construct a distribution network; finally, uses the Dijkstra algorithm to plan the distribution path from the constructed distribution network. The present invention extracts the terminal distribution semantic path that implies the distribution experience from the spatiotemporal big data of the terminal distribution trajectory and the express address, and then constructs the distribution network data for planning the later express delivery path. The present invention can use the delivery knowledge accumulated by delivery personnel over a long period of time for terminal delivery route planning, which can effectively improve delivery efficiency and quality.

[0063] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A terminal delivery path planning method based on historical trajectory, It is characterized in that The following steps are involved: Obtain all express delivery addresses and delivery track point data of the final delivery route pick-up and delivery personnel during the preset statistical period; After preprocessing all the express addresses, spatial aggregation is performed, and a total set of logistics terminal delivery nodes is constructed based on the aggregation results; a closed delivery trajectory is obtained based on the delivery trajectory point data, and a resident node set corresponding to each closed delivery trajectory is constructed; Establish the relationship between the delivery node and the resident node for each delivery operation within the preset statistical period, and assign the start time and end time to the delivery node; Obtain the closed delivery path of a single delivery operation, split the closed delivery path into several delivery path segments and store them until the delivery path segments of all delivery operations are stored, obtain the path segment data table, and obtain the distribution network connection table based on the path segment data table; The terminal delivery path is planned based on the delivery network connection table.

2. The terminal delivery path planning method based on historical trajectory according to claim 1, It is characterized in that The process of spatially aggregating all the express delivery addresses after preprocessing includes: The express delivery address is converted into geographic coordinates, and an express delivery feature set is constructed; the interest surface of the logistics terminal distribution section is obtained, and the express delivery addresses of each interest surface are merged into a delivery node; the express delivery addresses that are not covered by the interest surface and are spatially adjacent are merged into a delivery node using a spatial clustering algorithm, and the geographic coordinates of each delivery node are calculated based on the express delivery feature set.

3. The terminal delivery path planning method based on historical trajectory according to claim 1, It is characterized in that The process of constructing the set of resident nodes corresponding to each closed delivery trajectory includes: All trajectory points of each closed delivery trajectory are spatially clustered, and the trajectory points that meet the density requirements are classified into one category to form a resident trajectory sub-segment. The trajectory points of each resident trajectory sub-segment are merged into a resident node, and the center coordinates of the trajectory points of each resident trajectory sub-segment are calculated as the coordinates of the resident node to obtain the resident node set.

4. The terminal delivery path planning method based on historical trajectory according to claim 1, It is characterized in that The process of establishing the association relationship between the delivery node and the resident node for each pickup and delivery operation within the preset statistical period includes: The express address set of the collection and delivery operation is read, and based on the express address set and the total set of logistics terminal delivery nodes, the delivery node subset of the collection and delivery operation is obtained; based on the resident node set corresponding to the collection and delivery operation, the start time and end time are assigned to each delivery node in the delivery node subset according to the resident node set.

5. The terminal delivery path planning method based on historical trajectory according to claim 4, It is characterized in that The process of assigning a start time and an end time to each delivery node in the delivery node subset includes: Extract the delivery nodes and resident nodes that belong to the same interest surface from the delivery node subset and the resident node set, and assign the start time and end time of the resident node to the corresponding delivery node; if there is no resident node in the interest surface where a single delivery node is located, find the nearest resident node, and assign the start time and end time of the resident node to the corresponding delivery node; if there is no matching resident node, assign the start time and end time of the trajectory point in the distribution trajectory that is closest to the delivery node to the corresponding delivery node.

6. The terminal delivery path planning method based on historical trajectory according to claim 4, It is characterized in that The process of obtaining a closed delivery path includes: Taking the station for the delivery operation as the starting point, the delivery nodes in the delivery node subset are connected in sequence according to the chronological order of the starting time, and the last delivery node is connected to the station to obtain a closed delivery path.

7. The terminal delivery path planning method based on historical trajectory according to claim 1, It is characterized in that The process of obtaining the path segment data table includes: Taking the station as the starting point, extract two consecutive delivery nodes of the closed delivery path of a single delivery operation in turn, calculate the time difference between the end time of the previous delivery node and the start time of the next delivery node, and obtain the path segment time cost. Based on the path segment starting node number, the next node number and the path segment time cost, form the delivery path segment data and store it until the delivery path segment storage of all delivery operations is completed to obtain the path segment data table.

8. The terminal delivery path planning method based on historical trajectory according to claim 7, It is characterized in that The process of obtaining the distribution network connection table includes: traversing the delivery path segment data in the path segment data table, calculating the average time cost value of the delivery path segment whose starting node number is exactly the same as the next node number, and judging whether the delivery path segment already exists in the distribution network connection table. If so, the path segment time cost in the distribution network connection table is updated by the average time cost value; if not, the delivery path segment data is directly stored in the distribution network connection table, wherein the structure of the distribution network connection table is exactly the same as that of the path segment data table.

Citation Information

Patent Citations

  • Method, device and equipment for displaying parcel pre-delivery route and storage medium

    CN112488623A

  • Distribution range generation method and device, electronic equipment and storage medium

    CN116433128A

  • Track clustering-based mining method, system and equipment for frequent route of take-out delivery in different periods

    CN118071238A