A multi-vehicle loading and unloading path planning method, device, equipment and storage medium

Abstract

The embodiments of the present application provide a multi-vehicle loading and unloading route planning method, apparatus, device, and storage medium. The method includes: a server obtains multiple order information; each order information includes a loading location and an unloading location; the server obtains service information of all path nodes corresponding to the multiple order information; the service information of each path node includes a service time window and a closed time window of each path node, where the closed time window is the time of suspension of service within the service time window, and each path node is a loading location or an unloading location; the server performs planning based on the multiple order information and the service information of all path nodes to obtain planning information. The embodiments of the present application simultaneously consider the service time window and closed time window of each path node to improve the user service experience.

Description

Technical Field

[0001] The present application relates to the field of path planning, and in particular to a method, device, equipment and storage medium for multi-vehicle loading and unloading path planning. Background Art

[0002] With the rapid development of the manufacturing industry, the logistics of manufacturing material supply are facing enormous challenges. Improving logistics efficiency and reducing production and logistics costs are key to achieving intelligent logistics and intelligent manufacturing.

[0003] In the context of manufacturing logistics, manufacturers and raw material suppliers need to frequently load and unload goods. At the same time, most loading and unloading orders are characterized by small batches and high frequencies. The common pickup and delivery problem with time windows (PDPTW) can be described as follows: after receiving pickup and delivery orders with different requirements, the distribution center plans the vehicle's driving route and pickup and delivery information based on the order information. Then, it dispatches a fleet from the distribution center to pick up goods from various suppliers along the planned route, deliver them to the corresponding factories, and finally return to the distribution center.

[0004] The classic PDPTW model and the vehicle routing planning solution for the PDPTW problem have the following shortcomings: unreasonable time and route planning, resulting in long delivery times; unbalanced vehicle planning; and low order delivery efficiency. Summary of the Invention

[0005] The embodiments of the present application disclose a multi-vehicle loading and unloading path planning method, device, equipment and storage medium, which solve the shortcomings of the existing technology, avoid unnecessary time consumption, improve delivery efficiency, and enhance service quality.

[0006] In a first aspect, an embodiment of the present application provides a method for planning a path for loading and unloading multiple vehicles, comprising: a server obtains multiple order information; wherein each order information includes a loading location and an unloading location; the server obtains service information of all path nodes corresponding to the multiple order information; wherein the service information of each path node includes a service time window and a closed time window of each path node, wherein the closed time window is the time of suspension of service within the service time window, and each path node is the loading location or the unloading location; the server performs planning based on the multiple order information and the service information of all path nodes to obtain planning information, wherein the planning information includes indication information of the path corresponding to each vehicle among multiple vehicles to be assigned, at least one order information corresponding to the path, and a vehicle stay time window of each path node among multiple path nodes on the path; wherein all path nodes are distributed on multiple paths corresponding to the multiple vehicles to be assigned, and the path nodes on each path are different; the vehicle stay time window is composed of the time when the vehicle arrives at a path node and the time when the vehicle leaves the path node.

[0007] Among them, all path nodes refer to all loading locations and all unloading locations included in multiple (all) order information. For example, all order information includes: A→C, B→D, A→D, where order information A→C refers to from loading location A to unloading location C. Similarly, order information B→D refers to from loading location B to unloading location D, and order information A→D refers to from loading location A to unloading location D. In other words, all order information includes loading locations A and B, and unloading locations C and D, or all path nodes in all order information include A, B, C, and D.

[0008] The service time window is the time during which a route node provides service, or the hours during which a route node is open. For example, a route node's service hours are 8:00-20:00. Within this service time window, 12:00-14:00, 10:00-10:10, and 18:00-18:30 are periods of suspension (due to lunch breaks, temporary rest periods, or meals). Therefore, 12:00-14:00, 10:00-10:10, and 18:00-18:30 are called the route node's closed time window. The vehicle dwell time window is composed of the time a vehicle arrives at a route node and the time it leaves it. For example, if a vehicle arrives at a route node at 14:00 and leaves at 14:30, the vehicle dwell time window at that route node is 14:00-14:30.

[0009] Planning in this application can be understood as performing both path and time planning based on known order information (including multiple loading and unloading path nodes) and service information (primarily time information). Path and time planning are not performed separately, but rather complement and constrain each other. The planning process essentially involves using one or more algorithms to arrange path nodes so that the ordered set of nodes that make up the path satisfies both the service information and the constraints (the constraints are calculated based on the service information).

[0010] It can be seen that in the embodiment of the present application, the service time windows and closed time windows of the loading and unloading locations are taken into consideration. The server plans according to the order information and the service time windows and closed time windows of each loading location and each unloading location in the order information, and obtains the indication information of the path corresponding to each vehicle among the multiple vehicles to be assigned, at least one order information corresponding to the path, and the vehicle stay time window of each path node on the path. The implementation of the embodiment of the present application can avoid the problem of ignoring the closed time windows of the loading and unloading locations in the prior art, avoid the problem of low distribution efficiency due to unreasonable time and path arrangement, improve user service quality, and at the same time reduce the time cost of cargo transportation and vehicle consumption cost.

[0011] Based on the first aspect, in a possible embodiment, the service information of all path nodes also includes the earliest loading time of each loading location and the latest unloading time of each unloading location in all path nodes; before the server performs planning based on the multiple order information and the service information of all path nodes, the method further includes: the server processes the loading location and the unloading location in each order information to obtain the transportation time from the loading location to the unloading location in each order information; the server obtains the transportation time of each loading location based on the transportation time, the earliest loading time, the latest unloading time and the preset loading and unloading service time in each order information. the latest loading time and the earliest unloading time of each unloading location; the server obtains the loading time window of each loading location and the unloading time window of each unloading location based on the first information; the first information includes the earliest loading time and the latest loading time of each loading location, the earliest unloading time and the latest unloading time of each unloading location; accordingly, the server performs planning based on the multiple order information and the service information of all path nodes, and obtains planning information, including: the server performs planning based on the multiple order information, the service information of all path nodes, the loading time window of each loading location, and the unloading time window of each unloading location, and obtains planning information.

[0012] Among them, the loading time window is the optimal time range for loading, and the unloading time window is the optimal time range for unloading. It should be noted that the loading time window here may not include the loading service time, that is, loading has started but loading is not necessarily completed, or it may include the loading service time, that is, loading has started and loading is completed. Similarly, the unloading time window may not include the unloading service time, that is, unloading has started but unloading is not necessarily completed, or it may include the unloading service time, that is, unloading has started and unloading is completed. The loading and unloading service time can be set according to the actual application scenario, for example, it can be 10 minutes or 30 minutes.

[0013] As can be seen, the server can also obtain the earliest loading time at each loading location and the latest unloading time at each unloading location. After a series of calculations, the loading time window at each loading location and the unloading time window at each unloading location are obtained. The server then performs planning based on the order information, the service information of each path node, the loading time window at each loading location, and the unloading time window at each unloading location to obtain planning information. In this embodiment, by solving the loading time window at the loading location and the unloading time window at the unloading location in the order information, the loading time window and the unloading time window are referenced during implementation to plan the route and the time when the vehicle arrives at and leaves the path node, making the plan more reasonable, while reducing planning time and improving planning efficiency.

[0014] Based on the first aspect, in a possible embodiment, after obtaining the loading time window of each loading location and the unloading time window of each unloading location, the method also includes: the server divides the multiple order information into multiple transportation time periods according to the earliest loading time of the loading location in the each order information, wherein each transportation time period includes part of the multiple order information; accordingly, the server plans according to the multiple order information and the service information of all path nodes to obtain planning information, including: the server processes according to the second information to obtain third information; the second information includes the part of the order information in each transportation time period, the service information of the multiple path nodes corresponding to the part of the order information, the loading time window in the part of the order information, and the unloading time window in the part of the order information; the third information includes the pre-planned path corresponding to the part of the order information in each transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the pre-planned path; the server processes the third information to obtain the planning information.

[0015] As can be seen, the server can also divide multiple order information into multiple transportation time periods based on the earliest loading time. The server then processes the order information within each transportation time period separately to obtain the pre-planned route for each transportation time period and the vehicle dwell time window at each node on the pre-planned route. The server then simultaneously processes the pre-planned route for each transportation time period and the vehicle dwell time window at each node on the pre-planned route to obtain planning information. By implementing this embodiment, orders are distributed or transported according to the transportation time period, reducing the transportation pressure on delivery personnel or drivers.

[0016] Based on the first aspect, in a possible embodiment, the server processes the second information to obtain third information, including: the server uses the insertion method to process the second information to obtain fourth information; the fourth information includes the initial path corresponding to the partial order information in the each transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the initial path; the server uses a preset large neighborhood search algorithm to process the fourth information to obtain third information.

[0017] It is understood that the server first processes the second information using an insertion algorithm to obtain the initial path and the vehicle dwell time windows at each node on the initial path. The server then further processes the initial path and the vehicle dwell time windows at each node on the initial path using a preset large neighborhood search algorithm to obtain the third information. The preset large neighborhood search algorithm is an improvement on the traditional large neighborhood search algorithm and is used to iteratively optimize the initial path.

[0018] Based on the first aspect, in a possible embodiment, the large neighborhood search algorithm includes at least one deletion operator and at least one insertion operator, the deletion operator being used to perform a deletion operation on at least one path node among the multiple path nodes on the initial path during the processing of the large neighborhood search algorithm, and the insertion operator being used to perform an insertion operation on the at least one deleted path node after the deletion operation during the processing of the large neighborhood search algorithm.

[0019] It can be understood that the preset large neighborhood search algorithm includes at least one deletion operator and at least one insertion operator. During the processing of the large neighborhood search algorithm, the deletion operator is used to perform a deletion operation on at least one path node among multiple path nodes of the initial path, and the insertion operator is used to perform an insertion operation on the path obtained after performing the deletion operation, and reinsert the path node deleted in the deletion operator into the path to obtain a new path.

[0020] Based on the first aspect, in a possible embodiment, the at least one deletion operator includes at least one of an average node distance deletion operator, a shortest path deletion operator, a removal operator, a maximum cost deletion operator, a random path deletion operator, a preset node random proportion deletion operator, and a preset association deletion operator; the preset node random proportion deletion operator is used to delete multiple path nodes, and the number of deletions is related to the total number of path nodes; the preset association deletion operator is used to delete multiple path nodes according to an association evaluation function, and the association evaluation function is used to measure the distance index and time index between each path node.

[0021] It can be seen that the deletion operator in the preset large neighborhood search algorithm can include at least one of the above-mentioned deletion operators. Among them, the preset node random proportion deletion operator can also be called the improved node random proportion deletion operator. This operator improves the number of deleted path nodes. Specifically, φ path nodes are randomly selected from the entire path node set (these φ path nodes may correspond to one or several order information), and φ path nodes are deleted from the path. The number of deletions is calculated by multiplying the deletion ratio coefficient and the number of nodes. A new path structure is generated by removing a certain number of path nodes in proportion, so that the subsequent reinsertion can form a more diverse neighborhood path. The preset association deletion operator can also be called the improved association deletion operator. This operator deletes multiple path nodes according to the association evaluation function. The association evaluation function is used to measure the distance index and time index between each path node.

[0022] Based on the first aspect, in a possible embodiment, the vehicle stay time window is obtained based on the loading time window of the loading location and the closing time window of the loading location; or, the vehicle stay time window is obtained based on the unloading time window of the unloading location and the closing time window of the unloading location.

[0023] It can be understood that a vehicle's dwell time window is composed of the time a vehicle arrives at a route node and the time it leaves that route node. The time a vehicle arrives at a route node is the time loading or unloading begins, and the time a vehicle leaves a route node is the time loading or unloading is completed. If a vehicle encounters a closed time window at a loading location during loading, loading must be stopped and the vehicle must wait until the closed time expires before resuming loading. If a vehicle encounters a closed time window at a unloading location during unloading, unloading must also be stopped and the vehicle must wait until the closed time expires before resuming unloading. Therefore, the vehicle's dwell time window at each route node is actually derived from the loading and closed time windows of the loading location, or the unloading and closed time windows of the unloading location.

[0024] Based on the first aspect, in a possible embodiment, each order information also includes the cargo quantity; the planning information also includes the loading or unloading quantity of each vehicle at each path node of the corresponding path, and the total cargo quantity of each vehicle at multiple path nodes of the corresponding path does not exceed the vehicle load capacity.

[0025] It can be understood that each order information also includes the quantity of goods. When the server performs planning, the planning information obtained also includes the loading or unloading quantity of each vehicle at each path node on the corresponding path. It should be noted that the total cargo quantity of each vehicle at each path node does not exceed the vehicle load capacity.

[0026] Based on the first aspect, in a possible embodiment, the server sends the planning information to the vehicle terminals of the multiple vehicles to be assigned respectively.

[0027] It is understood that the server sends the planning information to the vehicle terminals of multiple vehicles to be assigned, so that each vehicle can deliver the goods according to the received route, the order information corresponding to the route, and the received vehicle dwell time windows at each node along the route. The vehicle terminal can be a display terminal on the vehicle, a driver's mobile phone terminal, or other terminal. Implementing this embodiment can reduce the delivery pressure on drivers, avoid unnecessary time consumption (such as waiting for unloading and loading), and improve delivery efficiency.

[0028] In a second aspect, an embodiment of the present application provides a multi-vehicle loading and unloading path planning device, comprising:

[0029] An acquisition unit, configured to acquire a plurality of order information; wherein each order information includes a loading location and an unloading location;

[0030] The acquisition unit is further configured to acquire service information of all path nodes corresponding to the plurality of order information; wherein the service information of each path node includes a service time window and a closed time window of each path node, wherein the closed time window is a time during which service is suspended within the service time window, and each path node is the loading location or the unloading location;

[0031] a planning unit, configured to perform planning based on the plurality of order information and the service information of all path nodes, and obtain planning information, the planning information including indication information of a path corresponding to each of the plurality of to-be-assigned vehicles, at least one order information corresponding to the path, and a vehicle dwelling time window for each of the plurality of path nodes on the path;

[0032] Among them, all the path nodes are distributed on multiple paths corresponding to the multiple vehicles to be assigned, and the path nodes on each path are different; the vehicle stay time window is composed of the time when the vehicle arrives at the path node and the time when it leaves the path node.

[0033] Based on the second aspect, in a possible embodiment, the service information of all path nodes also includes the earliest loading time of each loading location and the latest unloading time of each unloading location in the all path nodes; the device also includes a processing unit, which is used to: process the loading location and the unloading location in each order information to obtain the transportation time from the loading location to the unloading location in each order information; obtain the transportation time of each order information according to the transportation time, the earliest loading time, the latest unloading time and the preset loading and unloading service time. The latest loading time of the loading location and the earliest unloading time of each unloading location; based on the first information, the loading time window of each loading location and the unloading time window of each unloading location are obtained; the first information includes the earliest loading time and the latest loading time of each loading location, the earliest unloading time and the latest unloading time of each unloading location; accordingly, the planning unit is also used to plan according to the multiple order information, the service information of all path nodes, the loading time window of each loading location and the unloading time window of each unloading location to obtain planning information.

[0034] Based on the second aspect, in a possible embodiment, the processing unit is also used to divide the multiple order information into multiple transportation time periods according to the earliest loading time of the loading location in the each order information, wherein each transportation time period includes part of the order information in the multiple order information; accordingly, the planning unit is also used to: process according to the second information to obtain third information; the second information includes the part of the order information in each transportation time period, the service information of multiple path nodes corresponding to the part of the order information, the loading time window in the part of the order information and the unloading time window in the part of the order information; the third information includes the pre-planned path corresponding to the part of the order information in each transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the pre-planned path; the third information is processed to obtain the planning information.

[0035] Based on the second aspect, in a possible embodiment, the planning unit is specifically used to: use the insertion method to process the second information to obtain fourth information; the fourth information includes the initial path corresponding to the partial order information in the each transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the initial path; use a preset large neighborhood search algorithm to process the fourth information to obtain third information.

[0036] Based on the second aspect, in a possible embodiment, the large neighborhood search algorithm includes at least one deletion operator and at least one insertion operator, the deletion operator is used to perform a deletion operation on at least one path node among the multiple path nodes on the initial path during the processing of the large neighborhood search algorithm, and the insertion operator is used to perform an insertion operation on the at least one deleted path node after the deletion operation during the processing of the large neighborhood search algorithm.

[0037] Based on the second aspect, in a possible embodiment, the at least one deletion operator includes at least one of an average node distance deletion operator, a shortest path deletion operator, a removal operator, a maximum cost deletion operator, a random path deletion operator, a preset node random proportion deletion operator and a preset association deletion operator; the preset node random proportion deletion operator is used to delete multiple path nodes, and the number of deletions is related to the total number of path nodes; the preset association deletion operator is used to delete multiple path nodes according to an association evaluation function, and the association evaluation function is used to measure the distance index and time index between each path node.

[0038] Based on the second aspect, in a possible embodiment, the vehicle stay time window is obtained based on the loading time window of the loading location and the closing time window of the loading location; or, the vehicle stay time window is obtained based on the unloading time window of the unloading location and the closing time window of the unloading location.

[0039] Based on the second aspect, in a possible embodiment, each order information also includes the cargo quantity; the planning information also includes the loading or unloading quantity of each vehicle at each path node of the corresponding path, and the total cargo quantity of each vehicle at multiple path nodes of the corresponding path does not exceed the vehicle load capacity.

[0040] Based on the second aspect, in a possible embodiment, the device further includes a sending unit, configured to send the planning information to the vehicle terminals of the plurality of vehicles to be assigned respectively.

[0041] Each functional unit in the apparatus of the second aspect is used to implement the method described in the first aspect and any embodiment of the first aspect.

[0042] In a third aspect, an embodiment of the present application provides a server comprising a memory and a processor, wherein the memory is used to store instructions, and the processor is used to call instructions in the memory to execute the method described in the first aspect or any embodiment of the first aspect.

[0043] In a fourth aspect, an embodiment of the present application provides a non-volatile storage medium for storing program instructions. When the program instructions are applied to a server, they can be used to implement the method described in the first aspect or any possible embodiment of the first aspect.

[0044] In a fifth aspect, embodiments of the present application provide a computer program product comprising program instructions. When the computer program product is executed by a server, the server performs the method described in the first aspect. The computer program product may be a software installation package. When the method provided by any possible design of the first aspect is required, the computer program product may be downloaded and executed on the server to implement the method described in the first aspect or any possible embodiment of the first aspect.

[0045] It can be seen that the embodiment of the present application provides a multi-vehicle loading and unloading route planning method, including: first, the server obtains the loading time window and unloading time window corresponding to each order based on the earliest loading time and the latest unloading time in each order information; then, all order information is divided into multiple transportation time periods, and each transportation time period includes at least one order information; thirdly, the order information in each transportation time period is planned separately, and then optimized at the same time to obtain planning information, and each vehicle delivers or transports according to the planned route, thereby improving transportation efficiency, reducing the delivery pressure of delivery personnel or drivers, and improving service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a system architecture provided in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of a multi-vehicle loading and unloading path planning method provided in an embodiment of the present application;

[0048] Figure 3 An example diagram of the relationship between the service time window and the closed time window of a certain path node provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram of planning information provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of another type of planning information provided in an embodiment of the present application;

[0051] Figure 6A schematic diagram of a multi-vehicle loading and unloading path planning method provided in an embodiment of the present application;

[0052] Figure 7 An example diagram of the relationship between the loading time window, unloading time window, loading service time, and unloading service time provided in an embodiment of the present application;

[0053] Figure 8 A schematic diagram of a loading time window and a unloading time window in a certain order information provided in an embodiment of the present application;

[0054] Figure 9 A schematic diagram of a vehicle monitoring interface provided in an embodiment of the present application;

[0055] Figure 10 A schematic diagram of a multi-vehicle loading and unloading path planning method provided in an embodiment of the present application;

[0056] Figure 11 A schematic diagram of a portion of the process flow corresponding to a multi-vehicle loading and unloading path planning method provided in an embodiment of the present application;

[0057] Figure 12 A schematic diagram of a multi-vehicle loading and unloading path planning method provided in an embodiment of the present application;

[0058] Figure 13 Schematic diagram of some scenarios provided in the embodiments of this application;

[0059] Figure 14 A schematic diagram of a portion of the process flow corresponding to a multi-vehicle loading and unloading path planning method provided in an embodiment of the present application;

[0060] Figure 15 A schematic diagram of the application results provided by the embodiment of the present application;

[0061] Figure 16 A schematic diagram of a multi-vehicle loading and unloading path planning device provided in an embodiment of the present application;

[0062] Figure 17 A schematic diagram of a server structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be noted that the terms used in the embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0064] It should be noted that when used in this specification and the appended claims, the terms "comprise" and "include" and any variations thereof are intended to cover non-exclusive inclusions. For example, a system, product, or device comprising a series of units / components is not limited to the listed units / components but may optionally include units / components not listed, or other units / components inherent to the product or device.

[0065] It will also be understood that the term “in the event of” may be interpreted as “when” or “upon” or “in response to determining” or “in response to detecting” or “if” depending on the context.

[0066] It should also be noted that the terms "first", "second", "third", "fourth", etc. in this specification and claims are used to distinguish different objects, rather than to describe a specific order.

[0067] refer to Figure 1 , Figure 1 This is a schematic diagram of a system architecture provided in an embodiment of the present application. The system architecture includes a server and vehicles to be assigned, including vehicle 1, vehicle 2, ..., vehicle n. The vehicles to be assigned can be any vehicle capable of transporting goods, such as electric vehicles, vans, and trucks. This application does not limit the vehicle type.

[0068] The server is configured to obtain all order information and service information for all path nodes. Each order information includes a loading location and an unloading location, and each path node is either a loading location or an unloading location. The server is also configured to perform a plan based on the obtained order information and service information for all path nodes, and transmit the plan information to multiple vehicles to be assigned. Each vehicle to be assigned is configured to receive the plan information transmitted by the server, wherein the received plan information for each vehicle includes the corresponding route information, at least one order information corresponding to the route, and the vehicle dwell time window for each path node on the route. The server generates a corresponding route based on the corresponding route information and displays the route, at least one order information corresponding to the route, and the vehicle dwell time window for each path node on the route. The driver or delivery person of each vehicle to be assigned delivers or transports the goods according to the displayed route information and time information.

[0069] It should be noted that the server can send the planning information to the vehicle terminals of multiple vehicles to be assigned respectively. After each vehicle terminal receives the corresponding planning information, it generates a corresponding path according to the corresponding path indication information, and displays the corresponding path, at least one order information corresponding to the path, and the vehicle stay time window of each path node on the path through the display of the vehicle terminal; or, the server can also send the planning information to the terminal device (for example, a mobile phone, tablet computer, notebook, etc.) of the driver or delivery person of each vehicle respectively. The terminal device generates a corresponding path according to the path indication information in the received planning information, and displays the corresponding path, at least one order information corresponding to the path, and the vehicle stay time window of each path node on the path.

[0070] It should also be noted that the planning information obtained by the server planning can be in the form of Figure 1 The form shown can also be Figure 5 For details, please refer to the form shown in Figure 5 The description, similarly, Figure 5 The information shown is the planning information of a vehicle to be assigned, while the planning information obtained by the server is the planning information of multiple vehicles to be assigned, that is, there are multiple Figure 5 The planning information in the server can also be in the form of Figure 4 For details, please refer to the form shown in Figure 4 The description is different Figure 4While the planning information shown is for a single vehicle to be assigned, the planning information obtained by the server represents the planning information for multiple vehicles to be assigned. Specifically, the planning information in the server includes multiple routes, each of which corresponds to at least one order, and each node in each route is marked with the time the vehicle arrived at and left the node. The planning information in the server can also be in other formats, which are not specifically limited in this application.

[0071] It should also be noted that each vehicle to be assigned receives the planning information sent by the server in the form of Figure 1 In the form of Figure 4 or Figure 5 or Figure 9 This application does not make any specific limitation.

[0072] Based on the above system architecture, the present application embodiment provides a multi-vehicle loading and unloading path planning method, referring to Figure 2 , the method includes but is not limited to the description in the following S101 to S103.

[0073] S101. The server obtains multiple order information.

[0074] The server obtains multiple order information, each order information includes a loading location and an unloading location, so the multiple order information includes multiple loading locations and multiple unloading locations. It should be noted that the multiple order information may have the same loading location or the same unloading location.

[0075] S102: The server obtains the service time window and the closing time window of each path node in all path nodes corresponding to the multiple order information.

[0076] Each order information includes two path nodes, where each path node is a loading location or an unloading location. The server obtains the service information of all path nodes corresponding to multiple order information. The service information of each path node includes the service time window and the closing time window of each path node. The service time window of each path node is the time when the path node (loading location or unloading location) is open to the public or the time when service is provided, and the closing time window of each path node is the time when service is suspended within the service time window of the path node.

[0077] For example, refer to Figure 3 As shown, Figure 3An example diagram of the relationship between the service time window and the closed time window of a certain path node provided in an embodiment of the present application, for this path node, the time when service can be provided is 8:00-20:00, that is, the service time window of the path node is 8:00-20:00, wherein, within the service time window, 12:00-14:00, 10:00-10:10 and 18:00-18:30 are the times when service is suspended (due to lunch break, temporary rest or meal suspension), then 12:00-14:00, 10:00-10:10 and 18:00-18:30 are called the closed time windows of the path node.

[0078] S103. The server performs planning based on the multiple order information, the service time window and the closing time window of each path node, and obtains planning information.

[0079] The server plans the service time windows and closing time windows of each path node among all the path nodes corresponding to the multiple order information and the multiple order information, obtaining planning information. The planning information includes route information corresponding to each of the multiple vehicles to be assigned, at least one order information corresponding to the route, and the vehicle dwell time window for each path node along the route. The route information can be a path trajectory or path node information. All path nodes are distributed along the multiple paths corresponding to the multiple vehicles to be assigned, and the path nodes on each path are different. The vehicle dwell time window for each path node is composed of the time when the vehicle arrives at the path node and the time when the vehicle leaves the path node. For a loading location, the time when the vehicle arrives at the path node is the time when loading begins, and the time when the vehicle leaves the path node is the time when loading ends. For an unloading location, the time when the vehicle arrives at the path node is the time when unloading begins, and the time when the vehicle leaves the path node is the time when unloading ends.

[0080] In one embodiment, an algorithm can be performed based on multiple order information and the service information of all path nodes to obtain planning information. For example, the algorithm can be a large neighborhood search algorithm and the Solomon algorithm used to generate its initial solution. During the algorithm implementation, an objective function can be set based on the multiple order information, and constraints can be set based on the service information of each path node. The objective function can be constrained by the constraints. The value of the objective function can be changed by adjusting the values of the decision variables in the objective function. When the decision variables take a certain value, the objective function reaches an optimal value, and the planned path is obtained based on the optimal value of the objective function. The objective function can be, for example, to minimize the total time cost, minimize the total number of vehicles, or minimize the total distance.

[0081] In one embodiment, the planning information generated by the server may be the indication information of the path corresponding to each vehicle in the plurality of vehicles to be assigned, at least one order information corresponding to the path, and the vehicle stay time window of each path node on the path. The planning information may be in the form of a plurality of path node information corresponding to each vehicle in the plurality of vehicles to be assigned, for reference. Figure 4 As shown, Figure 4 This is an example diagram of the planning information of a vehicle provided in this application. The multiple path node information corresponding to the vehicle includes: multiple path nodes arranged in a certain order, the time when the vehicle arrives and leaves each path node, and order information. It should be noted that in Figure 4 In the example, an order information corresponds to an order ID, and an order ID corresponds to a loading path node and an unloading path node ( Figure 4 In the operation, the same number is used to represent the same path node, and different numbers are used to represent different path nodes). PICKUP in the operation represents loading, and DELIVERY represents unloading.

[0082] In another possible embodiment, the planning information may also be in the form of the indication information of the path corresponding to each vehicle in the plurality of vehicles to be assigned, the vehicle arrival time and departure time of each path node on each path, and the order information corresponding to each path. Figure 5 As shown, Figure 5 This is a schematic diagram of the path and order information corresponding to a vehicle provided in this application. The vehicle departs from the distribution center and returns to the distribution center after delivering the goods. The path corresponding to the vehicle is represented by arrows indicating directions and multiple path nodes connected in a certain order. Figure 5 The path node O in represents the vehicle distribution center. Each vehicle is sent out from the vehicle distribution center and finally returns to the distribution center O.

[0083] It can be seen that the embodiment of the present application provides a multi-vehicle loading and unloading path planning method. First, multiple order information and service information of each path node in the multiple order information are obtained, wherein the service information of each path node includes the service time window and closed time window of each path node. Then, planning is performed based on the multiple order information and the service time window and closed time window of each path node to obtain planning information. In the embodiment of the present application, the order allocation problem is converted into a path planning problem of multiple path nodes, taking into account the service time window and closed time window of each loading location and each unloading location, which can more reasonably arrange the delivery time and delivery path, and avoid the increase in consumption costs (consumption costs include time costs, vehicle usage costs, labor costs, etc.) caused by unreasonable paths and unreasonable delivery time arrangements. Therefore, in actual applications, multiple vehicles directly deliver goods according to the corresponding paths in the planning information and the vehicle stay time windows of each path node on the path, which can improve delivery efficiency, reduce consumption costs, and enhance user service experience.

[0084] The present application also provides a method for planning a multi-vehicle loading and unloading path. Figure 6 , this method includes but is not limited to the contents described in the following S201 to S207.

[0085] S201. The server obtains multiple order information.

[0086] Please refer to the description in S101, which will not be repeated here for the sake of brevity.

[0087] S202: The server obtains service information of all path nodes corresponding to multiple order information.

[0088] Based on multiple order information, the server obtains the service information of all path nodes. The service information of all path nodes includes: the service time window of each path node corresponding to the multiple order information, the closing time window of each path node, the earliest loading time of each loading location in the multiple order information, and the latest unloading time of each unloading location in the multiple order information. Among them, the service time window of each path node is the time when the path node (loading location or unloading location) is open to the public or provides services, and the closing time window of each path node is the time when the service is suspended within the service time window of the path node. The latest unloading time refers to the latest unloading time allowed for an order, and the earliest loading time refers to the earliest loading time allowed for an order. As shown in Reference Table 1, Table 1 lists the service information that needs to be obtained for each order information.

[0089] Table 1

[0090]

[0091] S203. The server obtains a loading time window of each loading location and a unloading time window of each unloading location according to the earliest loading time of each loading location and the latest unloading time of each unloading location.

[0092] First, each order information includes a loading location and an unloading location. The server processes the loading and unloading locations in each order information to obtain the transportation time from the loading location to the unloading location for each vehicle in the order information. For example, the processing method may be to input the corresponding loading and unloading locations in each order information into a certain mapping software with computing capabilities. The mapping software calculates the transportation time from the loading location to the unloading location based on the input loading and unloading locations and a locally stored map.

[0093] Then, based on the first information, the server obtains the latest loading time of each loading location and the earliest unloading time of each unloading location in multiple order information. The first information includes the transportation time from the loading location to the unloading location, the earliest loading time, the latest unloading time and the preset loading and unloading service time in the multiple order information. The preset loading and unloading service time is the time required for loading or the time required for unloading or the total time required for loading and unloading. The preset loading and unloading service time is a parameter and can be set specifically according to the actual application scenario; the latest loading time refers to the latest loading time for an order, and the earliest loading time refers to the earliest unloading time for an order.

[0094] Finally, based on the earliest loading time and latest loading time at each loading location and the earliest unloading time and latest unloading time at each unloading location in the multiple order information, the loading time window for each loading location and the unloading time window for each unloading location in the multiple order information are obtained. In each order information, the earliest loading time and the latest loading time at the loading location constitute the loading time window for that loading location, and the earliest unloading time and the latest unloading time at the unloading location constitute the unloading time window for that unloading location. It should be noted that in this application, the loading time window and the unloading time window are the optimal loading time and optimal unloading time calculated based on the known earliest loading time and the latest unloading time.

[0095] It should be noted that the loading time window in this application may include the loading service time (refer to Figure 7 (a) in the figure), that is, the loading time window includes the time from the start of loading to the end of loading; it may also not include the loading service time (refer to Figure 7(b) in the figure), that is, loading can be started within the loading time window, and the loading process may not be completed. This situation can also be called the loading start time window (loading can be started within the loading start time window). Similarly, the unloading time window in this application can include the unloading service time (refer to Figure 7 (c) in the figure), that is, the unloading time window includes the time from the start of unloading to the end of unloading; it may also not include the unloading service time (refer to Figure 7 (d) in the figure), that is, unloading can be started within the unloading time window, and the unloading process may not be completed. This situation can also be called the start unloading time window (unloading can be started within the start unloading time window).

[0096] In order to more clearly understand the method of obtaining the loading time window and the unloading time window in this step, the following describes the process by taking one of the multiple order information as an example.

[0097] Given the earliest loading time EPT of the loading location and the latest unloading time LDT of the unloading location in a certain order information, the latest loading time LPT is:

[0098] LPT=Max{EPT,LDT-d(p,d)-ST} (1)

[0099] The earliest unloading time EDT is:

[0100] EDT=Min{LDT,EPT+d(p,d)+ST} (2)

[0101] According to the earliest loading time EPT and the latest loading time LPT, the loading time window of the order is determined. According to the earliest unloading time EDT and the latest unloading time LDT, the unloading time window of the order is determined. Therefore, we get Figure 8 The loading time window and unloading time window are shown in the diagram, where d(p,d) represents the transportation time from the loading location to the unloading location in the order, and ST is the loading service time.

[0102] S204. The server performs planning based on the multiple order information, the service information of all path nodes, the loading time window of each loading location, and the unloading time window of each unloading location to obtain planning information.

[0103] The server performs planning based on multiple order information, service information for all path nodes, loading time windows for each loading location, and unloading time windows for each unloading location. This planning information includes information indicating the path corresponding to each of the multiple vehicles to be assigned, at least one order corresponding to the path, and the vehicle dwell time window for each path node along the path. All path nodes are distributed along the multiple paths corresponding to the multiple vehicles to be assigned, and the path nodes on each path are different. The vehicle dwell time window for each path node is composed of the time when the vehicle arrives at the path node and the time when the vehicle leaves the path node. For a loading location, the time when the vehicle arrives at the path node is the time when loading begins, and the time when the vehicle leaves the path node is the time when loading ends. For an unloading location, the time when the vehicle arrives at the path node is the time when unloading begins, and the time when the vehicle leaves the path node is the time when unloading ends.

[0104] In this embodiment, the format of the planning information can refer to the description of the format of the planning information in S103. For the sake of brevity, this embodiment will not be repeated here.

[0105] S205. The server sends the planning information to the multiple vehicles to be assigned.

[0106] The server sends the planning information to multiple vehicles to be assigned respectively. Correspondingly, each vehicle to be assigned receives the planning information corresponding to the vehicle sent by the server. The planning information corresponding to the vehicle includes the indication information of the path corresponding to the vehicle, the order information corresponding to the path, and the vehicle stay time window of each path node on the path.

[0107] In one possible embodiment, the planning information may also be in the form of a route corresponding to each vehicle, at least one order information corresponding to the route, and the vehicle's dwell time window at each node along the route. In this case, after the server sends the planning information to multiple vehicles to be assigned, each vehicle can directly deliver or transport the goods based on the received planning information.

[0108] S206 : Each of the multiple vehicles to be assigned generates a corresponding route according to the route indication information.

[0109] After the vehicle terminal or device terminal of each of the multiple vehicles to be assigned receives the corresponding planning information, it generates the corresponding path according to the path indication information in the planning information. The method of generating the corresponding path is not specifically limited in this application.

[0110] S207: Each of the multiple vehicles to be assigned displays the corresponding route, the order information corresponding to the route, and the vehicle stay time window of each route node on the route.

[0111] It should be noted that a display is installed on the vehicle terminal of each vehicle to be assigned, and the display is used to display the path corresponding to the vehicle, the order information corresponding to the path, and the vehicle stay time window at each node on the path, so that the driver or delivery person can deliver the goods according to the displayed path. Alternatively, the path corresponding to the vehicle, the order information corresponding to the path, and the vehicle stay time window at each node on the path can also be displayed through the terminal device of the driver or delivery person corresponding to each vehicle (which can be a mobile phone, tablet, notebook or other electronic device that can be used for display), so that the driver or delivery person can deliver the goods according to the path displayed by the terminal device. Among them, the display results of the corresponding path, the order information corresponding to the path, and the vehicle stay time window at each node on the path refer to Figure 9 shown.

[0112] It should be noted that, compared to Figure 2 For the corresponding embodiment, the factors considered in this embodiment are increased: the loading time window of each loading location and the unloading time window of each unloading location in multiple order information. In actual application, the rest time of the goods purchaser and the rest time of the supplier (i.e., the closed time window) are taken into consideration, so that the vehicle stay time window of each vehicle at each path node in the planning information does not overlap with the closed time window of the path node or the overlap is as small as possible.

[0113] It can be seen that in this embodiment, the service time window and the closed time window of each path node in multiple order information are taken into consideration, and the loading time window of the loading location and the unloading time window of the unloading location in each of the multiple order information are obtained. In actual application, according to the time requirements of the purchaser and the time requirements of the supplier, the route and delivery time can be planned more reasonably, the service quality can be improved, and the user service quality can be enhanced.

[0114] The present application also provides a method for planning a multi-vehicle loading and unloading path. Figure 10 As shown, the method includes but is not limited to the contents described in the following S301 to S307.

[0115] S301. The server obtains multiple order information.

[0116] Please refer to the description in S201, which will not be repeated here for the sake of brevity.

[0117] S302: The server obtains service information of all path nodes corresponding to multiple order information.

[0118] Please refer to the description in S202, which will not be repeated here for the sake of brevity.

[0119] S303. The server obtains a loading time window of each loading location and a unloading time window of each unloading location according to the earliest loading time of each loading location and the latest unloading time of each unloading location.

[0120] Refer to the description in S203, which will not be repeated here for the sake of brevity.

[0121] S304. The server divides the multiple order information into multiple transportation time periods according to the earliest loading time of each loading location in the multiple order information.

[0122] The server divides multiple order information into multiple transportation time periods according to the earliest loading time of the loading location in each order information. Each transportation time period includes part of the order information in the multiple order information. In this way, when there are many orders, all orders can be divided into multiple time periods in chronological order and delivered separately, reducing the delivery pressure of the delivery staff or drivers.

[0123] For example, all orders are divided into two transportation time periods according to the earliest loading time. One transportation time period is 8:30-18:00 (also known as the daytime transportation time period), and the other transportation time period is 20:30-6:00 (also known as the nighttime transportation time period). If the earliest loading time of an order is within the range of 8:30-18:00, the order is divided into the daytime transportation time period. If the earliest loading time of an order is within the range of 20:30-6:00, the order is divided into the nighttime transportation time period. Refer to Table 2, which is an example table of the division results provided in an embodiment of the present application.

[0124] Table 2 Example of order division results

[0125]

[0126] S305: The server processes the second information to obtain third information.

[0127] The server processes the second information to obtain third information, wherein the second information includes order information in each transport time period in each transport time period, service information of multiple path nodes corresponding to the order information in each transport time period, loading time windows of multiple loading locations in the order information in each transport time period, and unloading time windows of multiple unloading locations; wherein the service information includes the service time window and the closed time window of each path node (and may also include the earliest loading time of the loading location and the latest unloading time of the unloading location); the third information includes the pre-planned path corresponding to the order information in each transport time period in each transport time period and the vehicle stay time window of each path node among the multiple path nodes on the pre-planned path.

[0128] That is to say, the server processes the order information in each transportation time period respectively, and then obtains the pre-planned path corresponding to the order information in each transportation time period and the vehicle stay time window of each path node on the pre-planned path.

[0129] S306: The server processes the third information to obtain planning information.

[0130] After obtaining the pre-planned path corresponding to the order information in each transportation time period and the vehicle stay time window of each path node on the pre-planned path, the pre-planned path of each transportation time period and the vehicle stay time window of each path node on the pre-planned path are optimized simultaneously to obtain the planning information of all orders. The planning information includes the indication information of the path corresponding to each vehicle among multiple vehicles to be assigned, at least one order information corresponding to the path and the vehicle stay time window of each path node.

[0131] It should be noted that the planning information output after the final optimization is output according to the transportation time period. Therefore, when delivering or transporting, it is also delivered according to the transportation time period.

[0132] S307: The server sends the planning information to the multiple vehicles to be assigned.

[0133] Please refer to the description in S205, which will not be repeated here for the sake of brevity.

[0134] In actual applications, each of the multiple vehicles to be assigned generates a corresponding path based on the path indication information, and displays the corresponding path, the order information corresponding to the path, and the vehicle stay time window of each path node on the path. For details, please refer to the description in S206 and S207. For the sake of brevity of the specification, it will not be repeated here.

[0135] In order to understand this embodiment more clearly, this application provides some flow charts, refer to Figure 11 shown. Figure 11 Orders 100 For all order information, all order information is divided into four transportation time periods according to the earliest loading time. The four transportation time periods are the first transportation time period 111 , Second transportation time period 112 , the third transportation time period 113 and the fourth transport section 114 , so that there is at least one order information in each transportation time period, and then the order information in these four transportation time periods is processed separately to obtain the pre-planning information corresponding to the order information in each transportation time period: pre-planning information 121 , Pre-planning information 122 , Pre-planning information123 and pre-planning information 124 The pre-planning information here includes the pre-planning path and the vehicle stay time window of each path node corresponding to the pre-planning path. Finally, the pre-planning information within these four transportation time periods (pre-planning information 121 , Pre-planning information 122 , Pre-planning information 123 and pre-planning information 124 ) Optimize at the same time to obtain the final planning information 130 .

[0136] It can be seen that in this embodiment, all order information is divided into multiple transport time periods, and each transport time period includes part of the order information. In this way, the order information in each transport time period is planned by the algorithm, and the pre-planned path corresponding to the order information in each transport time period and the vehicle stay time window of each path node are obtained respectively. Then, the pre-planned path of each transport time period and the vehicle stay time window of each path node are optimized together to obtain the final planning information. By implementing this embodiment, all orders are divided into multiple transport time periods in chronological order. During delivery, they can be delivered in an orderly manner according to the divided time periods, avoiding congestion during delivery time and reducing the pressure on drivers or delivery personnel. At the same time, it can also balance vehicle demand and reduce the number of vehicles used and consumption costs.

[0137] The present application also provides a method for planning a multi-vehicle loading and unloading path. Figure 12 As shown, the method includes but is not limited to the following contents of S401 to S408.

[0138] S401. The server obtains multiple order information.

[0139] Please refer to the description in S301, which will not be repeated here for the sake of brevity.

[0140] S402: The server obtains service information of all path nodes corresponding to multiple order information.

[0141] Please refer to the description in S302, which will not be repeated here for the sake of brevity.

[0142] S403. The server obtains a loading time window of each loading location and a unloading time window of each unloading location according to the earliest loading time of each loading location and the latest unloading time of each unloading location.

[0143] Please refer to the description in S303, which will not be repeated here for the sake of brevity.

[0144] S404. The server divides the multiple order information into multiple transportation time periods according to the earliest loading time of each loading location in the multiple order information.

[0145] Please refer to the description in S304, which will not be repeated here for the sake of brevity.

[0146] S405: The server processes the second information using an insertion method to obtain fourth information.

[0147] The server processes the second information using an interpolation method to obtain fourth information. The second information includes the order information for each transport time period, service information for multiple path nodes corresponding to the order information, and the loading and unloading time windows in the order information. The fourth information includes the initial path corresponding to the order information for each transport time period and the vehicle dwell time windows for each path node on the initial path. In other words, the server processes the order information for each transport time period using an interpolation method to obtain the initial path corresponding to the order information for each transport time period and the vehicle dwell time windows for each of the multiple path nodes on the initial path.

[0148] In a specific embodiment, the Solomon insertion method can be used to process the order information in each transportation time period separately. The Solomon insertion method is used to process the order information in a certain transportation time period. The general steps are as follows: 1) Initialize the path corresponding to the order information in the transportation time period; 2) Set the set of path nodes that are not routed in the transportation time period as U; 3) Find the optimal insertion position for the current path; 4) Select the path node with the lowest incremental cost from U and insert it into the optimal insertion position; 5) If a feasible insertion position that meets the constraints cannot be found, create a new path and select the path node with the longest distance or the highest cost from U and insert it into the current path; 6) Delete the path node that has just been inserted from U; 7) If U is empty, terminate; otherwise, return to step 3). Finally, the initial path corresponding to the order information in the transportation time period and the vehicle dwell time window of each path node on the initial path are obtained. The vehicle dwell time window is composed of the time when the vehicle arrives at the path node and the time when the vehicle leaves the path node. The order information in each transportation time period is processed using the Solomon insertion method to obtain the fourth information.

[0149] Among them, the size of the increased cost can be measured by the objective function, which is:

[0150]

[0151] Min K (4)

[0152] The objective function (3) represents minimizing the total transportation time cost, including vehicle travel time and vehicle waiting time. The objective function (4) represents minimizing the number of vehicles K, where the decision variables are:

[0153]

[0154]

[0155] The constraints are:

[0156]

[0157]

[0158]

[0159]

[0160]

[0161]

[0162]

[0163]

[0164] Formula (7) indicates that the loading volume of vehicle k when leaving node i does not exceed the vehicle's load capacity. Formula (8) indicates that each node is served by only one vehicle and only once. Formula (9) indicates that each node is served only once. Formula (10) indicates that each node satisfies the flow conservation rule. Formula (11) indicates that the loading point and unloading point of each order are served by the same vehicle. Formula (12) indicates that all vehicles return to the depot for shift handover. Formula (13) indicates the time window constraint for vehicle k to arrive at node i. Formula (14) indicates the time window constraint for loading point i and unloading point L+i.

[0165] The definitions of the variables in the above objective function and constraints are shown in Table 3.

[0166] Table 3 Variable definition table

[0167]

[0168]

[0169] It should be noted that during the implementation of the insertion algorithm, when the path node to be inserted is the same as the previous path node or the next path node, they are merged and the same time is set to start loading or unloading, so as to merge the orders and achieve the effect of loading / unloading together.

[0170] It should also be noted that if the loading or unloading time of a vehicle falls within the closed time window of the route node, the service must be postponed until the end of the closed time window to complete the unfinished service. Therefore, during the implementation of the insertion method, the actual arrival and departure times of the vehicle at the route node are corrected. The correction formula is as follows:

[0171]

[0172] Among them, t i is the time when the vehicle actually arrives at the path node i, RBT i is the closing time of path node i, RET i represents the closing time of path node i. The vehicle arrival time is corrected by function (15) to obtain the actual arrival time.

[0173] Based on the actual arrival time of the vehicle and taking into account the closing time windows of the route nodes, the actual departure time is calculated:

[0174]

[0175] Among them, ST is the loading service time or unloading service time, te i is the actual departure time after reaching path node i. For ease of understanding, the present application embodiment provides the following application scenario, refer to Figure 13 As shown, the black boxes represent the arrival and departure times before correction, and the white boxes represent the actual arrival and departure times after correction. The specific description is as follows:

[0176] (1) In scenario 1, before correction, the time from arrival to departure is outside the off-time window, so the arrival and departure times are the actual arrival and departure times; (2) In scenario 2, before correction, the arrival time is outside the off-time window, but after arrival, during the loading or unloading process, the off-time window of the path node is encountered, and loading or unloading needs to be suspended until the end of the break, and then loading or unloading is continued until completion. Referring to formula (16), it can be seen that the actual departure time is te in scenario 2 i , the actual arrival time remains unchanged; (3) In scenario three, before correction, the arrival time is within the rest time window of the path node, and it is necessary to wait for the rest time to end before loading or unloading can begin. As shown in the reference formula (15), the actual arrival time is t in scenario three i The actual arrival time is the time of loading or unloading, and the actual departure time is the time of completion of loading or unloading, such as the te in scenario 3. i(4) In scenario 4, before correction, the time between arrival and departure is outside the closed time window, so the arrival and departure times are the actual arrival and departure times. S406: The server processes the fourth information using a preset large neighborhood search algorithm to obtain the third information.

[0177] The server uses a preset large neighborhood search algorithm to process the initial path corresponding to the order information in each transport time period and the vehicle dwell time window at each node on the initial path, obtaining third information. The third information includes the pre-planned path corresponding to the order information in each transport time period and the vehicle dwell time window at each node on the pre-planned path. It should be noted that, in essence, the fourth information is equivalent to the initial path of the order information in each transport time period, and the third path is equivalent to optimizing the initial path in the fourth information, thereby obtaining the optimized path for the order information in each transport time period.

[0178] Among them, the preset large neighborhood search algorithm can also be called an improved large neighborhood search algorithm, and the improved technical points include: 1) at least one deletion operator is adopted. In each round of iteration, the deletion operator is selected according to the roulette strategy based on the weight probability η of each operator for operation; 2) at least one deletion operator includes a preset node random proportion deletion operator and a preset association deletion operator; the preset node random proportion deletion operator can also be called an improved node random proportion deletion operator. This deletion operator improves the number of path nodes deleted in the traditional node random proportion deletion operator, see the description below for details; the preset association deletion operator can also be called an improved association deletion operator. This deletion operator comprehensively considers the distance factor, time factor, and cargo volume factor, and defines an association evaluation function. The association evaluation function is used to measure the distance, time, and cargo volume cost between each path node; 3) at least one insertion operator is adopted. In each round of iteration, the insertion operator is selected according to the roulette strategy based on the weight probability η of each operator for operation.

[0179] The preset large neighborhood search algorithm is used to process the initial path within each transportation time period and the vehicle dwell time windows at each node on the initial path. The following describes the main steps of the preset large neighborhood search algorithm using order information within a certain transportation time period as an example:

[0180] 1) Set the number of iterations ItrMax;

[0181] 2) Initialize the deletion ratio The value of is 0.1, where m represents the total number of deleted operators;

[0182] 3) selecting a deletion operator from at least one deletion operator according to a roulette wheel strategy based on the weight probability η of each operator (initialized weights are equal), and performing an operator operation on the initial path of the transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the initial path; the deletion operator is used to perform a deletion operation on at least one path node among the multiple path nodes on the initial path; wherein the at least one deletion operator includes an average node distance deletion operator (averageDistanceRemoval), a shortest path deletion operator (shortestRemoval), a shawRemoval operator, a maximum cost deletion operator (worstRemoval), a random path deletion operator (tourRemoval), an improved node random ratio deletion operator (randomRemoval), and an improved related deletion operator (improveRelatedRemoval);

[0183] 4) Based on the weighted probability η of each operator (initialized with equal weights), select an insertion operator from at least one insertion operator using a roulette wheel strategy to reinsert the recently deleted path node to form a complete new solution. The at least one insertion operator includes a greedy insertion operator, a regret-2 insertion operator, and a regret-3 insertion operator. In this process, feasible insertion points are traversed, and the priority insertion position is selected according to the rules of each operator. The new solution obtained after insertion is judged to see if it meets the constraints. If not, the next possible insertion point is found. If it does, a new solution is obtained.

[0184] 5) Choose whether to accept the new solution and update the relevant parameters according to the simulated annealing principle.

[0185] A. According to the new solution (the result obtained in this iteration is the new solution), change the weight probability η of the solution being accepted in the next iteration. The formula is as follows:

[0186]

[0187] Among them w1, w2, w3, w4 are parameters, The higher the value, the better the optimization effect of the operator. Generally, w1≥w2≥w3≥w4≥0. The attenuation parameter λ∈[0,1] is introduced to balance Compared with the original weight, which is generally set to 0.5, the final weight update formula for each operator is as follows:

[0188]

[0189] The weights of operators not used in the iteration remain unchanged. This adaptive weight adjustment method increases the weight of operators that produce optimal solutions, thereby increasing their probability of selection. For operators that do not produce optimal solutions, a low value is assigned to w4 to reduce the impact of the weight. The final ratio of each operator's weight to the total weight is the operator's selection probability. The following formula shows the selection probability of a deleted operator, |Ω - | represents the total set of deletion operators, and the same applies to insertion operators.

[0190]

[0191] B. If the new solution is not accepted, the deletion ratio of the deletion operator must be increased. The formula is as follows: i represents the current number of iterations, k represents the currently used deletion operator, and delta represents the increase ratio.

[0192]

[0193] 6) The execution ends when the number of iterations reaches IterMax;

[0194] 7) Output the iterative search results.

[0195] The following describes the preset node random proportional deletion operator and the preset improved association deletion operator.

[0196] The preset node random ratio deletion operator randomly selects φ path nodes from the entire path node set U (these φ path nodes correspond to one or several order information), deletes φ path nodes from the path, and the number of deletions is determined by the deletion ratio coefficient The product of the number of nodes U is calculated. A new path structure is generated by removing a certain number of path nodes in proportion, so that the subsequent reinsertion can form a more diverse neighborhood path.

[0197] The preset improved association deletion operator defines an association evaluation function that takes into account the distance, time, and cargo volume between each path node. The evaluation indicators are defined as follows:

[0198]

[0199]

[0200] Among them, P i Indicates the pickup point, D i Indicates the delivery point, T irepresents the earliest time for point i, qi represents the demand for pickup points, and Γ represents the set of removed points. The execution strategy of this operator is as follows: initially, a path node is randomly selected from the current solution S and added to the set Γ. The similarity r(i, j) between this point and all path nodes in the set Γ is then calculated for each non-Γ path node in S. The similarity between this point and the set Γ is then averaged. The path node with the smallest similarity is then added to the set Γ. This process is repeated until the required number of nodes are removed.

[0201] The following are descriptions of other operators:

[0202] Average node distance deletion operator, the calculation formula is as follows:

[0203]

[0204] Dis(i) represents the total distance of the planned path i, Node(i) represents the total number of path nodes of path i, and the average node distance a(i) of each path is obtained through the operator. The path corresponding to the maximum value is selected and all nodes of the path are deleted, thereby reducing the path distance and the situation where the path passes through too many nodes and causes excessive costs, thereby achieving the goal of minimizing the number of routes.

[0205] The shortest path deletion operator calculates the distance value of each path, takes the shortest path as the path to be optimized, and removes all path nodes on the path to optimize the number of vehicles.

[0206] The maximum cost removal operator calculates the cost of each path, selects the path with the highest cost, and removes all path nodes of this path for the travel time target.

[0207] The random path deletion operator randomly removes all path nodes on a path to increase the range of neighborhood solutions.

[0208] S407: The server processes the third information using a preset large neighborhood search algorithm to obtain planning information.

[0209] The server uses a preset large neighborhood search algorithm to simultaneously optimize the pre-planned paths for each transportation time period and the vehicle stay time windows at each path node on the pre-planned paths to obtain final planning information. The planning information includes indication information of the path corresponding to each of the multiple vehicles to be assigned, at least one order information corresponding to the path, and the vehicle stay time windows at each path node on the path.

[0210] It should be noted that the planning information output after the final optimization is output according to the transportation time period. Therefore, when delivering or transporting, it is also delivered according to the transportation time period.

[0211] S408. The server sends the planning information to the multiple vehicles to be assigned.

[0212] Please refer to the description in S307, which will not be repeated here for the sake of brevity.

[0213] In actual applications, each of the multiple vehicles to be assigned generates a corresponding path based on the path indication information, and displays the corresponding path, the order information corresponding to the path, and the vehicle stay time window of each path node on the path. For details, please refer to the description in S206 and S207. For the sake of brevity of the specification, it will not be repeated here.

[0214] In order to understand this embodiment more clearly, this application provides some flow charts, refer to Figure 14 shown. Figure 14 Orders 200 For all order information, all order information is divided into four transportation time periods according to the earliest loading time. The four transportation time periods are the first transportation time period 211 , Second transportation time period 212 , the third transportation time period 213 and the fourth transport section 214 , so that there is at least one order information in each transportation time period, and then the order information in these four transportation time periods is processed by insertion method to obtain the initial path information corresponding to the order information in each transportation time period: initial path information 221 , initial path information 222 , initial path information 223 and initial path information 224 The initial path information includes the initial path and the vehicle stay time window corresponding to each path node on the initial path. The initial path information of these four transportation time periods is then processed by the preset large neighborhood search algorithm to obtain pre-planning information: pre-planning information 231 , Pre-planning information 232 , Pre-planning information 233 and pre-planning information 234 The pre-planning information here includes the pre-planning path and the vehicle stay time window of each path node corresponding to the pre-planning path. Finally, the pre-planning information within these four transportation time periods (pre-planning information 231 , Pre-planning information 232 , Pre-planning information 233 and pre-planning information 234 ) Optimize through the preset large neighborhood search algorithm to obtain the final planning information 240 .

[0215] As can be seen, this embodiment employs mathematical modeling based on actual application scenarios, sets an objective function, changes the value of the objective function through the values of decision variables, and lists corresponding constraints based on the service information of each path node. These constraints are considered when solving for the optimal value of the objective function. In actual implementation, the objective function can be solved using an interpolation method to obtain an initial path. This initial path is then optimized using a preset large neighborhood search algorithm to obtain the optimal value of the objective function, ultimately obtaining planning information. Implementing this embodiment can improve vehicle loading rates and reduce transportation costs.

[0216] In one embodiment, in addition to the loading location and unloading location, each order information also includes the cargo volume, that is, the cargo volume transported from the loading location to the unloading location, and the planning information also includes the loading volume or unloading volume of each vehicle at each path node of the corresponding path, and the total cargo volume of each vehicle at multiple path nodes of the corresponding path does not exceed the vehicle load capacity.

[0217] The multi-vehicle loading and unloading path planning method proposed in the embodiment of this application has been applied to a certain logistics distribution scenario. The number of vehicles and the average loading rate optimized by the vehicle path planning algorithm under different logistics distribution task scales are calculated, and some data are displayed as follows Figure 15 As shown in the figure, the horizontal axis represents the logistics task volume, and the vertical axis has no specific unit. It can represent the number of vehicles or the average loading rate. Figure 15 As can be seen, when the logistics task volume is 139, the number of vehicles used is approximately 10, and the average loading rate of these vehicles is approximately 80%; when the logistics task volume is 245, the number of vehicles used is approximately 20, and the average loading rate of these vehicles exceeds 80%; when the logistics task volume is 398, the number of vehicles used is approximately 32, and the average loading rate of these vehicles is approximately 85%; when the logistics task volume is 441, the number of vehicles used is approximately 40, and the average loading rate of these vehicles also exceeds 80%. The loading rate = actual amount of cargo loaded / vehicle load. The results show that the algorithm can achieve relatively stable optimization results with an average loading rate above 80% in datasets of different sizes.

[0218] In addition, based on the above application, the embodiment of the present application was tested on the Li&Lim pdp100 standard data set. The results are shown in Table 4. Table 4 shows that the algorithm can obtain the optimal number of vehicles and the optimal journey time for all 29 standard examples, meeting the conditions for engineering application.

[0219] Table 4 Test results of Li&Lim standard test set

[0220]

[0221]

[0222] The present application embodiment provides a schematic diagram of a multi-vehicle loading and unloading path planning device 500, with reference to Figure 16 As shown, including:

[0223] The acquisition unit 501 is used to acquire a plurality of order information; wherein each order information includes a loading location and an unloading location;

[0224] The acquisition unit 501 is further configured to acquire service information of all path nodes corresponding to the plurality of order information; the service information of each path node includes a service time window and a closed time window of each path node, where the closed time window is the time during which service is suspended within the service time window, and each path node is a loading location or an unloading location;

[0225] A planning unit 502 is configured to perform planning based on the plurality of order information and the service information of all path nodes, and obtain planning information, wherein the planning information includes an indication of a path corresponding to each of the plurality of to-be-assigned vehicles, at least one order information corresponding to the path, and a vehicle dwell time window for each of the plurality of path nodes on the path;

[0226] Among them, all path nodes are distributed on multiple paths corresponding to multiple vehicles to be assigned, and the path nodes on each path are different; the vehicle stay time window is composed of the time when the vehicle arrives at the path node and the time when it leaves the path node.

[0227] In a possible embodiment, the service information of all path nodes also includes the earliest loading time of each loading location and the latest unloading time of each unloading location in all path nodes; the device also includes a processing unit 503, which is used to: process the loading location and unloading location in each order information to obtain the transportation time from the loading location to the unloading location in each order information; obtain the latest loading time of each loading location and the earliest unloading time of each unloading location based on the transportation time, earliest loading time, latest unloading time and preset loading and unloading service time in each order information; obtain the loading time window of each loading location and the unloading time window of each unloading location based on the first information; the first information includes the earliest loading time and latest loading time of each loading location, and the earliest unloading time and latest unloading time of each unloading location; accordingly, the planning unit 502 is also used to plan according to multiple order information, the service information of all path nodes, the loading time window of each loading location and the unloading time window of each unloading location to obtain planning information.

[0228] In a possible embodiment, the processing unit 503 is further used to divide the multiple order information into multiple transportation time periods according to the earliest loading time of the loading location in each order information, wherein each transportation time period includes part of the order information in the multiple order information; accordingly, the planning unit 502 is further used to: process according to the second information to obtain third information; the second information includes part of the order information in each transportation time period, service information of multiple path nodes corresponding to the part of the order information, loading time windows in the part of the order information, and unloading time windows in the part of the order information; the third information includes the pre-planned path corresponding to the part of the order information in each transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the pre-planned path; the third information is processed to obtain planning information.

[0229] In a possible embodiment, the planning unit 502 is specifically used to: use the insertion method to process the second information to obtain fourth information; the fourth information includes the initial path corresponding to part of the order information in each transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the initial path; use a preset large neighborhood search algorithm to process the fourth information to obtain third information.

[0230] In a possible embodiment, the large neighborhood search algorithm includes at least one deletion operator and at least one insertion operator. The deletion operator is used to perform a deletion operation on at least one path node among multiple path nodes on the initial path during the processing of the large neighborhood search algorithm. The insertion operator is used to perform an insertion operation on at least one deleted path node after the deletion operation during the processing of the large neighborhood search algorithm.

[0231] In a possible embodiment, at least one deletion operator includes at least one of an average node distance deletion operator, a shortest path deletion operator, a removal operator, a maximum cost deletion operator, a random path deletion operator, a preset node random proportion deletion operator, and a preset association deletion operator; the preset node random proportion deletion operator is used to delete multiple path nodes, and the number of deletions is related to the total number of path nodes; the preset association deletion operator is used to delete multiple path nodes according to an association evaluation function, and the association evaluation function is used to measure the distance index and time index between each path node.

[0232] In a possible embodiment, the vehicle stay time window is obtained based on the loading time window of the loading location and the closing time window of the loading location; or, the vehicle stay time window is obtained based on the unloading time window of the unloading location and the closing time window of the unloading location.

[0233] In a possible embodiment, each order information also includes the cargo quantity; the planning information also includes the loading or unloading quantity of each vehicle at each path node of the corresponding path, and the total cargo quantity of each vehicle at multiple path nodes of the corresponding path does not exceed the vehicle load capacity.

[0234] In a possible embodiment, the apparatus 500 further includes a sending unit 504, and the sending unit 504 is configured to send the planning information to vehicle terminals of a plurality of vehicles to be assigned respectively.

[0235] Each functional unit of the above-mentioned device 500 can be used to implement Figure 2 or Figure 7 or Figure 10 or Figure 12 The method described in the embodiment, the specific content can be referred to Figure 2 or Figure 7 or Figure 10 or Figure 12 For the sake of brevity, the descriptions in the relevant contents of the embodiments will not be repeated here.

[0236] See also Figure 17 , Figure 17 6 is a schematic diagram of another server 600 provided in an embodiment of the present application. The server 600 includes at least: a processor 610, a communication interface 620 and a memory 630. The processor 610, the transceiver 620 and the memory 630 are coupled via a bus 640.

[0237] The processor 610 calls the program code in the memory 630 to run Figure 16 The acquisition unit 501, planning unit 502, processing unit 503 and sending unit 504 in the embodiment of the present invention are shown in FIG. In practical applications, the processor 610 may include one or more general-purpose processors, wherein the general-purpose processor may be any type of device capable of processing electronic instructions, including a central processing unit (CPU), a microprocessor, a microcontroller, a main processor, a controller and an ASIC (Application Specific Integrated Circuit). The processor 610 reads the program code stored in the memory 630 and cooperates with the transceiver 620 to execute part or all of the steps of the method executed by the multi-vehicle loading and unloading path planning device 500 in the above embodiment of the present application.

[0238] The transceiver 620 may be a wired interface (e.g., an Ethernet interface) for communicating with other computing nodes or devices. When the transceiver 620 is a wired interface, the transceiver 620 may use a protocol suite above TCP / IP, such as RAAS, Remote Function Call (RFC), Simple Object Access Protocol (SOAP), Simple Network Management Protocol (SNMP), Common Object Request Broker Architecture (CORBA), and distributed protocols.

[0239] The memory 630 can store program code and data information. The program code includes the code of the acquisition unit 501, the code of the planning unit 502, the code of the processing unit 503, and the code of the sending unit 504. The data information includes: order information, service information, planning information, etc. In actual applications, the memory 630 may include volatile memory (Volatile Memory), such as random access memory (Random Access Memory, RAM); the memory may also include non-volatile memory (Non-Volatile Memory), such as read-only memory (Read-Only Memory, ROM), flash memory (Flash Memory), hard disk drive (HDD) or solid-state drive (SSD). The memory may also include a combination of the above types of memory.

[0240] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by hardware (such as a processor, etc.) to implement part or all of the steps of any method executed by the server in an embodiment of the present application.

[0241] An embodiment of the present application also provides a computer program product. When the computer program product is read and executed by a computer, the server executes part or all of the steps of a multi-vehicle loading and unloading path planning method in an embodiment of the present application.

[0242] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (e.g., a floppy disk, a storage disk, or a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state disk, SSD). In the embodiments, the description of each embodiment has its own focus. For parts not described in detail in one embodiment, please refer to the relevant description of other embodiments.

[0243] In the several embodiments provided in this application, it should be understood that the disclosed devices can also be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0244] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0245] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0246] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0247] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A multi-vehicle loading and unloading path planning method, characterized in that: include: The server obtains a plurality of order information; wherein each order information includes a loading location and an unloading location; The server obtains service information for all path nodes corresponding to the plurality of order information; the service information for each path node includes a service time window and a closed time window for each path node, the closed time window being the time during which service is suspended within the service time window, and each path node being the loading location or the unloading location; the service information for all path nodes also includes the earliest loading time for each loading location and the latest unloading time for each unloading location in the path nodes; the earliest loading time refers to the earliest loading time allowed for an order, and the latest unloading time refers to the latest unloading time allowed for an order; The server obtains the latest loading time of each loading location and the earliest unloading time of each unloading location based on the transportation time from the loading location to the unloading location, the earliest loading time, the latest unloading time, and the preset loading and unloading service time in each order information; The server obtains, based on the first information, a loading time window for each loading location and an unloading time window for each unloading location; the first information includes the earliest loading time and the latest loading time for each loading location, and the earliest unloading time and the latest unloading time for each unloading location; The server divides the plurality of order information into a plurality of transport time periods according to the earliest loading time of the loading location in each order information, wherein each transport time period includes part of the plurality of order information; The server processes the second information to obtain third information; the second information includes the partial order information in each transportation time period, service information of multiple path nodes corresponding to the partial order information, loading time windows in the partial order information, and unloading time windows in the partial order information; the third information includes the pre-planned path corresponding to the partial order information in each transportation time period and the vehicle stay time window of each path node among the multiple path nodes on the pre-planned path; The server simultaneously optimizes the third information to obtain planning information; the planning information includes indication information of a path corresponding to each of a plurality of vehicles to be assigned, at least one order information corresponding to the path, and a vehicle dwell time window at each of a plurality of path nodes on the path; Among them, all the path nodes are distributed on multiple paths corresponding to the multiple vehicles to be assigned, and the path nodes on each path are different; the vehicle stay time window is composed of the time when the vehicle arrives at the path node and the time when the vehicle leaves the path node; the vehicle stay time window is obtained based on the loading time window of the loading location and the closing time window of the loading location; or, the vehicle stay time window is obtained based on the unloading time window of the unloading location and the closing time window of the unloading location.

2. The method according to claim 1, characterized in that The server processes the second information to obtain third information, including: The server processes the second information using an insertion method to obtain fourth information; the fourth information includes an initial path corresponding to the portion of order information in each transportation time period and a vehicle stay time window at each of a plurality of path nodes on the initial path; The server processes the fourth information using a preset large neighborhood search algorithm to obtain third information.

3. The method according to claim 2, characterized in that The large neighborhood search algorithm includes at least one deletion operator and at least one insertion operator. The deletion operator is used to perform a deletion operation on at least one path node among multiple path nodes on the initial path during the processing of the large neighborhood search algorithm. The insertion operator is used to perform an insertion operation on the at least one deleted path node after the deletion operation during the processing of the large neighborhood search algorithm.

4. The method according to claim 3, characterized in that The at least one deletion operator includes at least one of an average node distance deletion operator, a shortest path deletion operator, a remove operator, a maximum cost deletion operator, a random path deletion operator, a preset node random ratio deletion operator, and a preset association deletion operator; the preset node random ratio deletion operator is used to delete multiple path nodes, and the number of deletions is related to the total number of path nodes; The preset association deletion operator is used to delete multiple path nodes according to an association evaluation function, and the association evaluation function is used to measure the distance index and time index between each path node.

5. The method according to any one of claims 1 to 4, characterized in that Each order information also includes the cargo quantity; the planning information also includes the loading or unloading quantity of each vehicle at each path node of the corresponding path, and the total cargo quantity of each vehicle at multiple path nodes of the corresponding path does not exceed the vehicle load capacity.

6. A multi-vehicle loading and unloading path planning device, characterized in that: include: An acquisition unit, configured to acquire a plurality of order information; wherein each order information includes a loading location and an unloading location; The acquisition unit is further configured to acquire service information of all path nodes corresponding to the plurality of order information; wherein the service information of each path node includes a service time window and a closed time window of each path node, wherein the closed time window is a time during which service is suspended within the service time window, and each path node is the loading location or the unloading location; a planning unit, configured to perform planning based on the plurality of order information and the service information of all path nodes, and obtain planning information, the planning information including indication information of a path corresponding to each of the plurality of to-be-assigned vehicles, at least one order information corresponding to the path, and a vehicle dwelling time window for each of the plurality of path nodes on the path; Wherein, all the path nodes are distributed on the multiple paths corresponding to the multiple vehicles to be assigned, and the path nodes on each path are different; the vehicle stay time window is composed of the time when the vehicle arrives at the path node and the time when the vehicle leaves the path node; The service information of all path nodes also includes the earliest loading time of each loading location and the latest unloading time of each unloading location in all path nodes; the earliest loading time refers to the earliest loading time allowed for an order, and the latest unloading time refers to the latest unloading time allowed for an order; The apparatus further comprises a processing unit, wherein the processing unit is configured to: Processing the loading location and the unloading location in each order information to obtain the transportation time from the loading location to the unloading location in each order information; Obtaining the latest loading time at each loading location and the earliest unloading time at each unloading location based on the transportation time, the earliest loading time, the latest unloading time, and the preset loading and unloading service time in each order information; Obtaining, based on the first information, a loading time window for each loading location and an unloading time window for each unloading location; the first information includes the earliest loading time and the latest loading time for each loading location, and the earliest unloading time and the latest unloading time for each unloading location; Accordingly, the planning unit is further configured to perform planning based on the plurality of order information, the service information of all path nodes, the loading time windows of the respective loading locations, and the unloading time windows of the respective unloading locations to obtain planning information; The processing unit is further configured to divide the plurality of order information into a plurality of transport time periods according to the earliest loading time of the loading location in each order information, wherein each transport time period includes a portion of the plurality of order information; Accordingly, the planning unit is further configured to: Processing the second information to obtain third information; the second information includes the partial order information in each transportation time period, service information of multiple path nodes corresponding to the partial order information, loading time windows in the partial order information, and unloading time windows in the partial order information; the third information includes the pre-planned path corresponding to the partial order information in each transportation time period and a vehicle stop time window at each of the multiple path nodes on the pre-planned path; optimizing the third information simultaneously to obtain the planning information; The vehicle stay time window is obtained based on the loading time window of the loading location and the closing time window of the loading location; or the vehicle stay time window is obtained based on the unloading time window of the unloading location and the closing time window of the unloading location.

7. The device according to claim 6, characterized in that The planning unit is specifically used for: Processing the second information using an interpolation method to obtain fourth information; the fourth information includes an initial path corresponding to the portion of order information in each transportation time period and a vehicle stay time window at each of a plurality of path nodes on the initial path; The fourth information is processed using a preset large neighborhood search algorithm to obtain third information.

8. The device according to claim 7, characterized in that The large neighborhood search algorithm includes at least one deletion operator and at least one insertion operator. The deletion operator is used to perform a deletion operation on at least one path node among multiple path nodes on the initial path during the processing of the large neighborhood search algorithm. The insertion operator is used to perform an insertion operation on the at least one deleted path node after the deletion operation during the processing of the large neighborhood search algorithm.

9. The device according to claim 8, characterized in that The at least one deletion operator includes at least one of an average node distance deletion operator, a shortest path deletion operator, a remove operator, a maximum cost deletion operator, a random path deletion operator, a preset node random ratio deletion operator, and a preset association deletion operator; the preset node random ratio deletion operator is used to delete multiple path nodes, and the number of deletions is related to the total number of path nodes; The preset association deletion operator is used to delete multiple path nodes according to an association evaluation function, and the association evaluation function is used to measure the distance index and time index between each path node.

10. The device according to any one of claims 6 to 9, characterized in that: Each order information also includes the cargo quantity; the planning information also includes the loading or unloading quantity of each vehicle at each path node of the corresponding path, and the total cargo quantity of each vehicle at multiple path nodes of the corresponding path does not exceed the vehicle load capacity.

11. A server, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory to execute the method according to any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that The method comprises program instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 5.

Images