CN110503229B

CN110503229B - Method, device and computing equipment for vehicle path optimization

Info

Publication number: CN110503229B
Application number: CN201810810590.2A
Authority: CN
Inventors: 同鲸渭; 向达; 王子卓; 王曦
Original assignee: Shanghai Shanshu Network Technology Co ltd; Shanshu Science And Technology Suzhou Co ltd; Shanshu Science And Technology Beijing Co ltd
Current assignee: Shanghai Shanshu Network Technology Co ltd; Shanshu Science And Technology Suzhou Co ltd; Shanshu Science And Technology Beijing Co ltd
Priority date: 2018-07-23
Filing date: 2018-07-23
Publication date: 2022-04-22
Anticipated expiration: 2038-07-23
Also published as: CN110503229A

Abstract

The invention relates to a method and a device for vehicle path optimization, the method comprising: assembling the cargo transportation tasks to be completed into at least one transportation group; clustering cargo delivery tasks included in any delivery group into at least one task set of the any delivery group based on a first optimization objective; adjusting the cargo shipment task between the plurality of task sets of any of the one or more shipment groups based on the constraint information and based on a second optimization objective if there is one or more shipment groups having a plurality of task sets in the at least one shipment group; based on the task sets each of the at least one delivery group has, at least the specific vehicles and the travel routes of each of the specific vehicles required to complete the cargo delivery tasks each of the at least one delivery group includes are determined. By using the method and the device, the solving precision and the solving speed of the vehicle path problem can be improved, and the vehicle path problem solving algorithm covers various service scenes and constraint conditions.

Description

Method, device and computing equipment for vehicle path optimization

Technical Field

The invention relates to a method, a device and a computing device for vehicle path optimization.

Background

Vehicle Routing Problem (VRP) is a Problem of optimizing route combination in logistics transportation and the like, which means that in a case where a plurality of customers need to transport goods from a pickup location to the customers, the customers are transported with a Vehicle fleet via appropriately organized driving routes from the pickup location to the customers, so as to achieve the purposes of shortest distance, minimum cost, minimum time consumption and the like under certain constraints (for example, demand for goods, delivery volume, delivery time window, Vehicle capacity limit, driving mileage limit, driving time limit and the like).

The VRP is a large-scale combination optimization and integer programming problem, and has large calculation amount and high requirement on solving precision. However, many of the existing VRP solving algorithms adopted by enterprises facing the VRP problem have insufficient capability to cope with such large amount of calculation and such high precision requirement, so that the solving precision and the solving speed cannot meet the business requirement. Moreover, these solution algorithms are typically only applicable to a single business scenario and constraint.

Disclosure of Invention

In view of the above problems of the prior art, embodiments of the present invention provide a method, an apparatus, and a computing device for vehicle path optimization, which can improve the solving speed and the solving precision of a vehicle path problem solving algorithm and enable the vehicle path problem solving algorithm to cover various service scenarios and constraints.

A method for vehicle path optimization according to an embodiment of the invention, comprising: assembling the cargo transferring tasks to be completed into at least one transferring group, wherein each transferring group comprises at least one cargo transferring task which can be transferred together by loading, and the distance between the unloading place of a specific cargo transferring task and the unloading places of other cargo transferring tasks in the at least one cargo transferring task is smaller than a distance threshold value; clustering cargo carrying tasks included in any one of the at least one carrying groups into at least one task set of the any one carrying group based on a first optimization objective, wherein a total cargo amount of each task set of the at least one task set of the any one carrying group is not larger than a maximum cargo capacity of an available maximum vehicle, and a value of the first optimization objective is minimum when the at least one cargo carrying task of the any one carrying group is completed in a manner that each task set of the at least one task set of the any one carrying group is completed by one vehicle; adjusting the cargo shipment task among the plurality of task sets of any of the one or more shipment groups based on the second optimization objective and in accordance with the constraint information if there are one or more shipment groups in the at least one shipment group each having a plurality of task sets; and after the adjustment, determining at least specific vehicles and a driving route of each specific vehicle required for completing the cargo transportation task respectively included in the at least one transportation group based on the task set respectively included in the at least one transportation group.

An apparatus for vehicle path optimization according to an embodiment of the present invention includes: the cargo conveying system comprises a gathering module, a control module and a control module, wherein the gathering module is used for gathering cargo conveying tasks to be completed into at least one conveying group, each conveying group comprises at least one cargo conveying task which can be carried by loading together, and the distance between the unloading place of a specific cargo conveying task in the at least one cargo conveying task and the unloading place of each other cargo conveying task is smaller than a distance threshold value; a clustering module for clustering cargo carrying tasks included in any one of the at least one carrying group into at least one task set of the any one carrying group based on a first optimization objective, wherein a total cargo amount of each of the at least one task set of the any one carrying group is not more than a maximum cargo capacity of an available maximum vehicle, and a value of the first optimization objective is minimum when the at least one cargo carrying task of the any one carrying group is completed in a manner that each of the at least one task set of the any one carrying group is completed by one vehicle; an adjustment module for adjusting the cargo shipment task between the plurality of task sets of any of the one or more shipment groups based on the constraint information and based on a second optimization objective if there are one or more of the at least one shipment group each having a plurality of task sets; and a determining module for determining at least specific vehicles and a driving route of each specific vehicle required for completing the cargo transportation task included in each of the at least one transportation group based on the task set included in each of the at least one transportation group after the adjustment.

A computing unit according to an embodiment of the invention, comprising: a processor; and a memory having executable instructions stored thereon, wherein the executable instructions, when executed, cause the processor to perform the aforementioned method.

A machine-readable storage medium according to an embodiment of the invention has stored thereon executable instructions, wherein the executable instructions, when executed, cause a machine to perform the aforementioned method.

The solution of the embodiment of the present invention solves the vehicle path problem by first grouping the sets of cargo carrying tasks to be completed into at least one carrying group and clustering the cargo carrying tasks included in each carrying group into at least one task set as an initial solution based on the optimization goal of total cost, and then adjusting the cargo carrying tasks among the task sets included in the carrying groups having a plurality of task sets based on the optimization goal of total time consumption, and determining the vehicles and the like required to complete the cargo carrying tasks to be completed according to the task sets each of the at least one carrying group after the adjustment is made, so that the solution of the embodiment of the present invention has sufficient capacity to face the calculation amount and the solution difficulty of the vehicle path problem and does not limit the type of traffic to which the cargo carrying tasks belong and can specify the constraint conditions as needed, therefore, compared with the prior art, the scheme of the embodiment of the invention can improve the solving speed and the solving precision of the vehicle path problem solving algorithm and can cover various service scenes and constraint conditions.

Drawings

The features, characteristics, advantages and benefits of the present invention will become apparent from the following detailed description taken in conjunction with the accompanying drawings.

FIG. 1A shows a general flow diagram of a method for vehicle path optimization according to one embodiment of the invention.

Fig. 1B shows a schematic view explaining a cargo conveying task in which a detour phenomenon exists.

FIG. 1C shows a schematic diagram of optimizing a travel route.

FIG. 2 shows a flow diagram of a method for vehicle path optimization according to one embodiment of the invention.

Fig. 3 shows a schematic view of an arrangement for vehicle path optimization according to an embodiment of the invention.

FIG. 4 shows a schematic diagram of a computing unit, according to an embodiment of the invention.

Detailed Description

The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thereby implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as needed. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with respect to some examples may also be combined in other examples.

As used herein, the term "include" and its variants mean open-ended terms in the sense of "including, but not limited to. The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first," "second," and the like may refer to different or the same object. Other definitions, whether explicit or implicit, may be included below. The definition of a term is consistent throughout the specification unless the context clearly dictates otherwise.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1A shows a general flow diagram of a method for vehicle path optimization according to one embodiment of the invention. The method 100 shown in FIG. 1A may be implemented by a general purpose computer, server, or other computing device having computing capabilities.

As shown in fig. 1A, at block 102, a distance matrix, a time matrix, station information, each cargo transportation task to be completed, vehicle type information, maximum iteration number, constraint information, and optimization objective information are read in.

The distance matrix represents the distance between each site in the region R involved in the shipment of the goods (e.g., a city, all regions under a province jurisdiction, all regions of a country, etc.) and the other various sites to which it is directly connected. For example, assuming that any one location a in region R is directly connected to three other locations B1, B2, and B3, the distance matrix includes the distance between location a and location B1, the distance between location a and location B2, and the distance between location a and location B3.

The time matrix represents the regular travel time of each point in the region R to the other respective points directly connected thereto in the case where the road condition is normal (e.g., the road is not in a maintenance state, there is no traffic jam, etc.). For example, assuming that any one of the sites a in the region R is directly connected with three other sites B1, B2, and B3, the time matrix includes a regular travel time from the site a to the site B1, a regular travel time from the site a to the site B2, and a regular travel time from the site a to the site B3.

Each cargo delivery task that needs to be completed includes: a pickup location, a discharge location, a time window for pickup required, a time window for delivery required, a cargo name, a cargo quantity, a cargo volume, a cargo gross weight, and the like.

The vehicle type information indicates the vehicle type (e.g., 2-ton, 5-ton, etc.) of each vehicle available for cargo conveyance, the maximum cargo capacity and the maximum cargo capacity, and whether or not it belongs to a special function vehicle (e.g., whether it is a refrigerator vehicle, etc.), and the like.

The site information comprises the area (including an administrative area, a custom area and the like) to which the site belongs, the fixed service time of the site, the working time and the like. And the station information is used for calculating the distance and auditing a time window and an area limiting condition in the optimization process.

The constraint information CF indicates a constraint condition to be observed in the cargo transportation and vehicle path problem solving process and the like. In the present embodiment, the constraint information CF includes road condition estimation (for example, a travel time for a certain road section that is 3 hours longer than a normal travel time due to traffic congestion), a time required for unloading (for example, 30 minutes), a driver working time (for example, a rest time of 1 hour per 8 hours of work), and vehicle use cost (a daily rental fee per vehicle, a bridge fee per bridge, a toll fee per expressway, and the like).

The optimization objective information indicates an optimization objective that needs to be taken by the vehicle path problem solving process, such as total distance, total cost, total time consumed, and the like. In the present embodiment, the optimization target information includes the total cost and the total elapsed time.

At block 104, two or more cargo conveyance tasks of the various cargo conveyance tasks to be completed, which have the same pickup location and discharge location, the same pickup time windows and the same intersection, and which do not require separate conveyance, are combined into a single cargo conveyance task to obtain a plurality of combined cargo conveyance tasks. Wherein the total cargo volume of the consolidated single cargo movement mission is no greater than the maximum cargo volume of the maximum available vehicle.

If the cargo conveying tasks to be completed have the same pick-up and drop-off locations, the pick-up time windows have an intersection, the drop-off time windows have an intersection and the total cargo quantity of all the cargo conveying tasks not requiring separate conveying is larger than the maximum cargo quantity of the available maximum vehicle, the cargo conveying tasks are combined into a plurality of cargo conveying tasks, and each cargo conveying task in the plurality of cargo conveying tasks is not larger than the maximum cargo quantity of the available maximum vehicle.

At block 106, the merged plurality of cargo transferring tasks are assembled into at least one transferring group PGP, each transferring group includes at least one cargo transferring task that can be transferred together by loading, and the distance between the unloading place of a specific cargo transferring task and the unloading place of each other cargo transferring task in the at least one cargo transferring task is smaller than the distance threshold.

Specifically, first, density-based assembly is performed. In the density-based assembly, the number of tasks of each of the merged plurality of cargo carrying tasks EVi is counted, wherein the number of tasks of a cargo carrying task EVi represents the number of those cargo carrying tasks of the merged plurality of cargo carrying tasks EVi which can be carried on-board with the cargo carrying task EVi and whose place of discharge is at a distance from the place of discharge of the cargo carrying task EVi which is smaller than a first distance threshold. Here, the cargo carrying task that can be carried on-vehicle together with the cargo carrying task EVi refers to a cargo carrying task that has the same article attribute (for example, but not limited to, general articles, dangerous articles, etc.) as the cargo carrying task EVi. Then, whether the cargo transportation tasks with the task number larger than the number threshold exist in the combined cargo transportation tasks or not is judged. And if the judgment result shows that at least one cargo transporting task with the task number larger than the number threshold exists in the merged plurality of cargo transporting tasks, aiming at any cargo transporting task in the at least one cargo transporting task, integrating those cargo transporting tasks which can be transported by loading together with the any cargo transporting task and of which the distance between the unloading place and the unloading place of the any cargo transporting task is smaller than the first distance threshold and the any cargo transporting task into a transporting group.

After the density-based stitching is performed, it is determined whether a cargo shipping task that has not yet been stitched to a shipping group exists among the merged plurality of cargo shipping tasks. And if the judgment result shows that at least two goods delivery tasks which are not assembled to the delivery group exist in the combined goods delivery tasks, performing distance-based assembly.

In distance-based rendezvous, the rendezvous is performed at least once such that the at least two cargo conveyance tasks that have not yet been rendezvoused into a conveyance group are both rendezvoused into a conveyance group. Wherein, in each of the at least one collage, for a not yet collaged cargo transfer task of the at least two cargo transfer tasks, any of the seed cargo transfer tasks and those of the not yet collaged cargo transfer tasks that can be transferred truck-mounted with the seed cargo transfer task and whose discharge location is at a distance from the discharge location of the seed cargo transfer task that is furthest from its pickup location is ganged into a transfer group.

At block 108, based on the optimization objective of total cost, the cargo carrying tasks included in any one of the at least one shipping group PGP obtained by grouping the at least one shipping group PGP into at least one task set of the shipping group PGPi, wherein the total cargo volume of each of the at least one task set of the shipping group PGPi is not greater than the maximum cargo volume of the available maximum vehicles, and the total cost is minimized when the cargo carrying tasks included in the shipping group PGPi are completed by one vehicle in accordance with the completion of each of the at least one task set of the shipping group PGPi.

In the following, how to cluster the task sets will be described in detail by taking an example in which the shipping group PGPi has five cargo shipping tasks a1, a2, a3, a4, and a 5.

First, five cargo carrying tasks a1, a2, A3, a4, and a5 carrying a group PGPi are placed in task sets a1, a2, A3, a4, and a5, respectively. Then, an attempt is made to merge task sets A1 and A2 into one task set A12. A total cost P11 of completing the task sets a12, A3, a4, and a5 with the vehicles each completing one task set is calculated, and a total cost P12 of completing the task sets a1, a2, A3, a4, and a5 with the vehicles each completing one task set is calculated. Here, the total cost takes into account not only the distance of the travel route that the vehicle has traveled to complete the task set, but also the vehicle use cost in the read-in constraint information. If P11 is less than P12, task sets A1 and A2 may be merged into one task set, otherwise task sets A1 and A2 may not be merged into one task set. Here, it is assumed that the task sets a1 and a2 can be merged into a task set a 12.

Next, an attempt is made to merge task sets A12 and A3 into a task set A123. The total cost P21 of completing the task sets a123, a4, and a5 with vehicles each completing one task set is calculated, and the total cost P22 of completing the task sets a12, A3, a4, and a5 with vehicles each completing one task set is calculated. If P21 is less than P22, task sets A12 and A3 may be merged into one task set, otherwise task sets A12 and A3 may not be merged into one task set. Here, it is assumed that the task sets a12 and A3 cannot be merged into one task set, and that neither the task sets a12 and a4, nor the task sets a12 and a5, can be merged into one task set.

Next, an attempt is made to merge task sets A3 and A4 into one task set A34. A total cost P31 of completing the task sets a12, a34, and a5 with vehicles each completing one task set is calculated, and a total cost P32 of completing the task sets a12, A3, a4, and a5 with vehicles each completing one task set is calculated. If P31 is less than P32, task sets A3 and A4 may be merged into one task set, otherwise task sets A12 and A3 may not be merged into one task set. Here, it is assumed that the task sets A3 and a4 may be merged into one task set a34, but the task sets a34 and a5 may not be merged into one task set.

Finally, three task sets a12, a34 and a5 of the clustered shipping group PGPi, wherein task set a12 includes cargo shipping tasks a1 and a2, task set a34 includes cargo shipping tasks A3 and a4, and task set a5 includes cargo shipping task a 5.

Those skilled in the art will appreciate that after clustering, each of the at least one shipping group PGP may have either multiple task sets or only one task set.

At block 110, if there are one or more shipping groups G in the at least one shipping group PGP each having a plurality of task sets, the plurality of task sets TS for each of the one or more shipping groups G is set to the plurality of task sets TP adjusted for the last iteration of the shipping group Gi.

At block 112, the current iteration number IT is set to zero.

At block 114, a cargo shipment job SR is selected from each of the plurality of task sets TPi after the last iterative adjustment of the shipment group Gi that satisfies the condition CON. Wherein the condition CON may include: the cargo carrying task exceeding the time limit and the cargo carrying task exceeding the capacity limit, the cargo carrying task having a detour phenomenon, and the cargo carrying task having a small degree of task relevance in the task set TPi.

The cargo carrying tasks exceeding the time limit in the task set TPi refer to those cargo carrying tasks for which the delivery time for delivering the cargo cannot be met according to the requirements thereof, after considering the read time matrix and the influence of the road condition estimation, the unloading required time and the driver working time, which are included in the read constraint information, on the cargo carrying time, for the traveling route for completing each cargo carrying task in the task set TPi.

The cargo conveyance tasks exceeding the capacity limit in the task set TPi refer to those cargo conveyance tasks that need to be removed in order to make the total cargo amount in the task set TPi not greater than the maximum cargo amount in the case where the total cargo amount in the task set TPi is greater than the maximum cargo amount of the available maximum vehicle indicated by the read-in vehicle type information.

The cargo carrying tasks in which the detour phenomenon occurs refer to those cargo carrying tasks that require detour in order to complete each of the cargo carrying tasks in the task set TPi, among the travel routes for completing the cargo carrying tasks. For example, assume that the task set TPi includes a cargo carrying task ai with a pickup location a and a discharge location B, and a cargo carrying task ak with a pickup location a and a discharge location C. As shown in fig. 1B, the straight distance between the pickup location a and the discharge location B is AB, the straight distance between the pickup location a and the discharge location C is AC, the straight distance between the discharge locations B and C is CB, and, assuming that the travel route TR for completing the tasks ai and ak in the task set TPi with one vehicle is from a to C to B first, the detour ratio W of the task ai in the travel route TR is equal to (AC + CB-AB)/AB. If the detour ratio W is larger than the given allowable detour ratio threshold, it indicates that the task ai is a cargo carrying task in which a detour phenomenon exists, otherwise the task ai is not a cargo carrying task in which a detour phenomenon exists.

The task relevance of each cargo transferring task aj in the task set TPi is equal to the average value of the distance relevance of the task aj and other cargo transferring tasks in the task set TPi. The distance dependency of any two cargo transfer tasks is related to the distance between their pick-up and drop-off locations and is higher as their pick-up and drop-off locations are closer. If the pick-up location and the drop-off location of the two cargo transferring tasks are the same, the distance correlation thereof reaches a maximum.

At block 116, a plurality of evaluation-observation value pairs PC for each of the selected cargo-carrying tasks SR is calculated. Wherein the evaluation value of each evaluation value-observation value pair PCn of the task SRi is equal to one of the task sets TPj of the plurality of task sets TP assumed to put the cargo conveying task SRi into the last iterative adjustment, the travel time taken for completing the travel route whose travel time is the smallest among the respective feasible travel routes for the cargo-carrying task included in the task set TPj assuming that the task SRi has been put in, and, the observed value in the evaluation value-observed value pair PCn is equal to a difference between a total travel time required for completing the plurality of task sets TP after the previous iterative adjustment in such a manner that one task set is completed by one vehicle and a total travel time required for completing the plurality of task sets TP in such a manner that one task set is completed by one vehicle after assuming that the cargo-carrying task SRi is put into the task set TPj in the plurality of task sets TP after the previous iterative adjustment. Here, the calculation of the travel time takes into account the regular travel time included in the read time matrix, and the road condition estimation, the time required for unloading, and the driver operating time included in the read constraint information.

For example, assume that a task set TPj into which a task SRi has been put includes three cargo conveying tasks SRi, a23 and a25, wherein the task SRi has a pick-up location a and a discharge location B1, the task a23 has a pick-up location a and a discharge location B2, and the task a25 has a pick-up location a and a discharge location B3. Assume that the time matrix read in represents: the regular travel time from the point a to the point B1 is 1 hour, the regular travel time from the point a to the point B2 is 2 hours, the regular travel time from the point a to the point B3 is 1 hour, the regular travel time from the point B1 to the point B2 is 1.5 hours, the regular travel time from the point B1 to the point B3 is 2 hours, and the regular travel time from the point B2 to the point B3 is 1.5 hours. It is assumed that the road condition estimation in the read-in constraint information indicates that traffic jam occurs in the section from the location B1 to the location B3, resulting in an increase in the travel time from the location B1 to the location B3 by 4 hours more than the normal travel time, the time required for unloading in the read-in constraint information indicates that the time required for unloading is 0.5 hours on average in each location, and the driver operating time in the read-in constraint information indicates that the driver has to rest for 0.8 hours every 8 hours of operation. Possible travel routes for completing the cargo conveying task included in the task set TPj assuming that the task SRi has been put include 6 travel routes TR1, TR2, TR3, TR4, TR5, and TR6, respectively, wherein the travel route TR1 is a → B1 → B2 → B3, the travel route TR2 is a → B1 → B3 → B2, the travel route TR3 is a → B2 → B1 → B3, the travel route TR4 is a → B2 → B3 → B1, the travel route TR5 is a → B3 → B1 → B2, and the travel route TR6 is a → B3 → B2 → B1. In the case of a rest time of the driver, the travel time of the travel route TR1 is equal to 1+0.5+1.5+0.5+1.5+ 0.5-5.5 hours, the travel time of the travel route TR2 is equal to 1+0.5+2+4+0.5+1.5+ 0.5-10 hours, the travel time of the travel route TR3 is equal to 2+0.5+1.5+0.5+2+4+ 0.5-11 hours, the travel time of the travel route TR4 is equal to 2+0.5+1.5+0.5+2+4+ 0.5-11 hours, the travel time of the travel route TR5 is equal to 1+0.5+2+ 0.5+1.5+ 0.5-10 hours, and the travel time of the travel route TR6 is equal to 1+0.5+1.5+ 0.5-5 + 0.5-10 hours. Taking into account the rest time of the driver, the travel time of the travel route TR1 is equal to 5.5 hours, the travel time of the travel route TR2 is equal to 10+ 0.8-10.8 hours, the travel time of the travel route TR3 is equal to 11+ 0.8-11.8 hours, the travel time of the travel route TR4 is equal to 11+ 0.8-11.8 hours, the travel time of the travel route TR5 is equal to 10+ 0.8-10.8 hours, and the travel time of the travel route TR6 is equal to 5.5 hours. Thus, of the 6 possible travel routes TR1-TR6, the travel route with the least travel time is TR1 and TR6, both 5.5 hours. Therefore, the evaluation value in the evaluation value-observation value pair PCn of the mission SRi is equal to 5.5 hours, i.e., the travel time taken for the travel route to be TR1 or TR 6.

At block 118, a regret value is calculated for each of the selected cargo-carrying tasks SR that is equal to the difference between the next-to-smallest and the smallest of the calculated multiple evaluation-observation values for the respective evaluation value of the task SRi in PC. For example, assuming that the plurality of evaluation-observation pairs PC of the task SRi include 5 evaluation values, which are 1 hour, 1.5 hours, 1.8 hours, 0.8 hours, and 3 hours, respectively, the minimum evaluation value of the task SRi is 0.8 hours, and the next minimum evaluation value of the task SRi is 1 hour, so that the regret value of the task SRi is equal to 1-0.8 — 0.2.

At block 120, a composite value for each of the selected cargo-carrying tasks SR is calculated that is equal to the regret value of the task SRi and a weighted sum of pairs of evaluation-observation values of the task SRi to the respective observations in the PC.

For example, assume that: the regret value and the weighted value of the regret value of the task Sri are h and w0 respectively, the multiple pairs of evaluation value-observation value pairs PC of the task Sri comprise m observation values which are sv1, sv2, sv3, … and svm respectively, and the weighted values of the m observation values sv1, sv2, sv3, … and svm of the task Sri are w1, w2, w3, … and wm respectively, so that the comprehensive value ZH of the task SRi is: ZH w0+ sv1 w1+ sv2 w2+ sv3 w3+ … + svm wm.

At block 122, the cargo conveyance task SRj having the largest combined value is found from the selected cargo conveyance tasks SR.

At block 124, the found cargo transporting task SRj is taken out from the task set where the task SRj in the plurality of task sets TP after the last iterative adjustment is currently located, and is placed into the task set TPx corresponding to the minimum evaluation value of the cargo transporting task SRj in the plurality of task sets TP after the last iterative adjustment, so as to obtain the plurality of task sets TP after the current iterative adjustment of the transporting group Gi. Here, the minimum evaluation value of the task SRj is calculated assuming that the SRj is put in the task set TPx.

At block 126, the current iteration number IT is incremented by 1.

At block 128, a determination is made as to whether the current iteration number IT is greater than the maximum number of iterations read in.

If the determination at block 128 is negative, flow returns to block 114. If the determination result in the block 128 is positive, the iteratively adjusted task sets TP of the transport group Gi at this time are the finally adjusted task sets TP of the transport group Gi.

Block 114-.

At block 130, if the determination at block 128 is positive, the specific vehicles and the total number of vehicles required to complete the delivery group PGPi, the loading rate of each specific vehicle, and the travel route of each specific vehicle are determined according to the task set that each delivery group PGPi of the at least one delivery group PGP has.

Wherein the total number of vehicles required to complete the shipping of the group PGPi is equal to the total number of task sets the shipping group PGPi has. The specific vehicles used to complete each task set of shipping group PGPi are determined based on the principle that each task set of shipping group PGPi is completed using the smallest vehicle that can complete it, resulting in the specific vehicles needed to complete shipping group PGPi. The loading rate of each particular vehicle is equal to the ratio of the amount of cargo actually loaded to its nominal load.

At block 132, the travel route of each particular vehicle of each of the at least one shipping groups PGP is further optimized using a traveler problem (TSP) optimization principle to reduce the travel distance of the vehicle.

How to optimize the travel route using the TSP optimization principle is explained below with reference to fig. 1C. Firstly, a starting station t1 is randomly found out in a driving route, a next station t2 of t1 in the driving route, a demand station t3 closest to t2 in the driving route and a next station t4 of t3 in the driving route are found out, corresponding adjacent stations t5 and t6 are found out, t 1-t 2, t 3-t 4 and t 5-t 6 respectively form original sides x1, x2 and x3, and t 2-t 3, t 4-t 5 and t 6-t 1 respectively form candidate sides y1, y2 and y3, then the original sides x1, x2 and x3 are removed, and whether the driving distance of the driving route after the original sides x1, x2 and x3 is removed is reduced or not is checked. If the optimal station driving sequence is reduced, the optimized station driving sequence is reserved for the driving route. And in the same way, circulating each station in the driving route to reduce the driving distance of the vehicle.

At block 134, the travel time and the travel distance of the travel route of each specific vehicle completing the transportation group PGPi, and the total travel time and the total travel distance of the transportation group PGPi are calculated based on the optimized travel route of each specific vehicle completing the transportation group PGPi.

At block 136, the total number of the specific vehicles and the vehicles required to complete the at least one transportation group PGP, the loading rate of each specific vehicle, the travel route of each specific vehicle, the travel time and the travel distance of the travel route of each specific vehicle, and the total travel time and the total travel distance of the completed transportation group PGPi are calculated and displayed, and the total travel time and the total travel distance of the at least one transportation group PGP are completed.

As can be seen from the above description, the solution of the present embodiment first clusters the cargo shipping tasks included in each shipping group into at least one task set as an initial solution by grouping the cargo shipping tasks that need to be completed into at least one shipping group and based on the optimization goal of the total cost, the cargo delivery mission is then adjusted among a plurality of mission sets included in a delivery group having a plurality of mission sets based on the optimization objective of total elapsed time, and, determining the vehicles and the like required for completing the cargo transportation task required to be completed according to the task set respectively possessed by the at least one transportation group after adjustment is carried out, solving a vehicle path problem, therefore, the solution of the embodiment has enough capacity to face the calculation amount and the solving difficulty of the vehicle path problem, therefore, the solution of the embodiment can improve the solving speed and the solving precision of the vehicle path problem solving algorithm. In addition, the scheme of the embodiment does not limit the service types to which the cargo transportation tasks belong and can specify the constraint conditions according to needs, so that the scheme of the embodiment can cover various service scenarios and constraint conditions.

Other variants

It should be understood by those skilled in the art that although the constraint information includes the road condition estimation, the time required for unloading, the driver's working time, and the vehicle use cost in the above embodiment, the present invention is not limited thereto. In some other embodiments of the present invention, the constraint information may also include any one, any two or any three of the road condition estimate, the time required to unload, the driver operating time, and the vehicle usage cost, or the constraint information may also include at least one of the road condition estimate, the time required to unload, the driver operating time, and the vehicle usage cost and one or more other types of constraints (e.g., cargo demand, delivery volume, delivery time window, vehicle capacity limit, mileage limit, travel time limit, etc.), or the constraint information may include one or more other types of constraints in addition to the road condition estimate, the time required to unload, the driver operating time, and the vehicle usage cost.

It will be appreciated by those skilled in the art that although in the above embodiment the clustering of cargo shipments tasks in a shipping group PGPi into at least one task set of a shipping group PGPi at block 108 is based on a total cost, the invention is not so limited. In other embodiments of the present invention, the clustering of the cargo shipment tasks in the shipment group PGPi into at least one task set of the shipment group PGPi at block 108 may also be based on other types of optimization objectives, such as, but not limited to, total journey or total elapsed time, etc.

It should be understood by those skilled in the art that although in the above embodiment, the adjustment of the cargo transportation task among the plurality of task sets TP after the last iterative adjustment of the transportation group Gi realized at the block 114-128 is performed based on the total time consumption, the present invention is not limited thereto. In other embodiments of the present invention, the adjustment of the cargo shipping assignments among the plurality of task sets TP of the shipping group Gi obtained in block 114-128 after the last iterative adjustment may be performed based on other types of optimization objectives, such as, but not limited to, total distance or total cost.

It will be appreciated by those skilled in the art that although in the above embodiment the optimization objectives upon which the cargo conveyance tasks of the conveyance group PGPi are clustered into at least one task set of the conveyance group PGPi at block 108 are based are different from the optimization objectives upon which the cargo conveyance tasks are adjusted between the task sets TP of the conveyance group Gi that were adjusted at blocks 114-128 from the previous iteration, the invention is not limited thereto. In other embodiments of the invention, the optimization objectives on which both are based may also be the same.

It should be understood by those skilled in the art that although the items calculated at the block 136 include the specific vehicles and the total number of vehicles required to complete the at least one transportation group PGP, the loading rate of each specific vehicle, the travel route of each specific vehicle, the travel time and the travel distance of the travel route of each specific vehicle, and the total travel time and the total travel distance to complete the at least one transportation group PGP in the above embodiment, the present invention is not limited thereto. In some other embodiments of the present invention, the items calculated at the block 136 may also include only the specific vehicles and the travel routes of each specific vehicle required to complete the at least one transportation group PGP, or, in addition to the specific vehicles and the travel routes of each specific vehicle required to complete the at least one transportation group PGP, the items calculated at the block 136 may also include one or more of the total number of vehicles required to complete the at least one transportation group PGP, a loading rate of each specific vehicle, a travel time and a travel distance of the travel route of each specific vehicle, and a total travel time and a total travel distance of the at least one transportation group PGP.

It should be understood by those skilled in the art that although in the above embodiment, the iteration process is ended when the number of completed iterations reaches the maximum number of iterations in block 112-128, the invention is not limited thereto. In other embodiments of the present invention, for example, but not limited to, a cost function based on time, distance, or number of vehicles may be set, and then after each iteration, the value of the cost function is calculated and determined whether it reaches a predetermined threshold, if the determination result indicates that the predetermined threshold is not reached, the iteration is continued, otherwise, the iteration process is ended.

It should be understood by those skilled in the art that, although in the above embodiments, the integrated value of the task SRi is determined based on the regret value and the observed value of the task SRi, the present invention is not limited thereto. In other embodiments of the present invention, for example and without limitation, the regret value for task SRi may be determined as a composite value of task SRi, or a weighted sum of observations of task SRi may be determined as a composite value of task SRi. In the case where the regret value of the task SRi is determined as the integrated value of the task SRi, it is not necessary to calculate the observed value of the task SRi.

It will be appreciated by those skilled in the art that although in the above embodiment the further optimization of the travel route at block 126 is based on TSP optimization principles, the invention is not limited thereto. In other embodiments of the invention, the further optimization of the driving route may be based on any other suitable principle.

It should be understood by those skilled in the art that although in the above embodiment, the method 100 includes the block 132 to further optimize the process for the travel route, the present invention is not limited thereto. In other embodiments of the present invention, the method 100 may not include the block 132.

It should be understood by those skilled in the art that although in the above embodiment the assembling of the cargo transportation tasks into at least one transportation group PGP at block 106 is obtained by performing density-based assembling and distance-based assembling, the present invention is not limited thereto. In other embodiments of the present invention, the grouping of cargo delivery tasks into at least one delivery group PGP may be achieved by performing any other suitable operation.

It will be appreciated by those skilled in the art that although in the above embodiment the method 100 comprises the block 104 to merge multiple cargo conveyance tasks having the same pick-up and drop-off locations, pick-up time windows having an intersection, drop-off time windows having an intersection and not requiring separate conveyance into a single cargo conveyance task, this can reduce the computational load of vehicle path optimization, however, the invention is not so limited. In other embodiments of the present invention, the method 100 may not include the block 104.

FIG. 2 shows a flow diagram of a method for vehicle path optimization according to one embodiment of the invention. The method 200 shown in fig. 2 may be implemented, for example, by any suitable computing unit having computing capabilities.

As shown in fig. 2, the method 200 may include, at block 202, assembling the cargo transferring tasks to be completed into at least one transferring group, each transferring group including at least one cargo transferring task that can be transferred together in a truck, and a distance between a discharging location of a specific cargo transferring task and discharging locations of other respective cargo transferring tasks among the at least one cargo transferring task is less than a distance threshold.

The method 200 may further include, at block 204, clustering cargo carrying tasks included in any of the at least one carrying groups into at least one task set of the any carrying group based on a first optimization objective, wherein a total cargo amount of each of the at least one task set of the any carrying group is not greater than a maximum cargo amount of a largest available vehicle, and the first optimization objective has a minimum value when the at least one cargo carrying task of the any carrying group is completed in a manner that each of the at least one task set of the any carrying group is completed by one vehicle.

The method 200 may further include, at block 206, adjusting the cargo shipment task between the plurality of task sets of any of the one or more shipment groups based on the constraint information and based on a second optimization objective if there are one or more of the at least one shipment group each having a plurality of task sets.

The method 200 may further include, at block 208, after making the adjustment, determining at least the specific vehicles and the travel route of each specific vehicle required to complete the cargo-handling task included in each of the at least one delivery group based on the task set each of the at least one delivery group has.

In a first aspect, block 206 includes: in each iteration of the multiple iterations, selecting at least one cargo conveying task from each of the plurality of task sets of the arbitrary conveying group adjusted in the last iteration to obtain a plurality of selected cargo conveying tasks; calculating a plurality of evaluation value-observation value pairs for each of the selected cargo-carrying tasks, wherein an evaluation value in any one of the evaluation value-observation value pairs for any one of the selected cargo-carrying tasks is equal to one of the plurality of task sets assumed to place the any one of the selected cargo-carrying tasks in the arbitrary carrying group after the last iterative adjustment, a value of the second optimization objective for completing a specific travel route of the plurality of possible travel routes of the cargo-carrying task included in the one of the task sets assumed to have placed the any one of the selected cargo-carrying tasks, and an evaluation value in the any one of the evaluation value-observation value pairs is equal to a value of the second optimization objective required for completing the plurality of task sets of the arbitrary carrying group after the last iterative adjustment in such a manner that one task set is completed by one vehicle and a value of the second optimization objective required for assuming to place the any one of the selected cargo-carrying tasks in the previous iterative adjustment Iteratively adjusting the difference between the values of the second optimization objectives required for completing the task sets of the arbitrary transportation group according to the manner that one task set is completed by one vehicle after the one of the task sets of the arbitrary transportation group is iteratively adjusted, wherein the specific driving route is the driving route of which the value of the second optimization objective is the smallest among the feasible driving routes, and the calculation of the value of the second optimization objective of the feasible driving routes takes the constraint information into account; calculating respective regret values for the plurality of selected cargo-delivery tasks of the arbitrary delivery group, wherein the regret value for each selected cargo-delivery task is equal to a difference between a next-smallest evaluation value and a smallest evaluation value of the plurality of evaluation-observation value pairs for the selected cargo-delivery task; calculating respective comprehensive values of the plurality of selected cargo-carrying tasks, wherein the comprehensive value of each selected cargo-carrying task is equal to the weighted sum of the regret value of the selected cargo-carrying task and each observation value in the plurality of evaluation value-observation value pairs of the selected cargo-carrying task; and putting the cargo transportation task with the maximum comprehensive value in the selected cargo transportation tasks into a first task set corresponding to the minimum evaluation value of the cargo transportation task with the maximum comprehensive value in the task sets of the arbitrary transportation group after the last iterative adjustment to obtain a plurality of task sets of the arbitrary transportation group after the iterative adjustment, wherein the minimum evaluation value of the cargo transportation task with the maximum comprehensive value is calculated by assuming that the cargo transportation task with the maximum comprehensive value is put into the first task set.

In a second aspect, the plurality of selected cargo carrying tasks include cargo carrying tasks exceeding a time limit, cargo carrying tasks exceeding a capacity limit, cargo carrying tasks where a detour phenomenon occurs, and/or cargo carrying tasks with a small task relevance in each of the plurality of task sets of the arbitrary carrying group after the last iterative adjustment.

In a third aspect, the first optimization objective is a total cost, a total elapsed time, or a total trip, and the second optimization objective is a total cost, a total elapsed time, or a total trip.

In a fourth aspect, the constraint information includes a demand for goods, a delivery amount, a delivery time window, a vehicle capacity limit, a mileage limit, and a travel time limit.

In a fifth aspect, block 202 includes: counting the number of tasks of each cargo transferring task in the cargo transferring tasks to be completed, wherein the number of the cargo transferring tasks to be completed represents the number of the cargo transferring tasks which can be carried by loading together with the cargo transferring task and the distance between the unloading place of the cargo transferring task and the unloading place of the cargo transferring task is less than a first distance threshold value; and if at least one cargo conveying task with the task number larger than the number threshold exists in the cargo conveying tasks to be completed, for any cargo conveying task in the at least one cargo conveying task, integrating those cargo conveying tasks and any cargo conveying task, which can be carried on a truck together with any cargo conveying task and have the unloading position of which is less than the first distance threshold from the unloading position of any cargo conveying task, into a conveying group.

In the sixth aspect, block 202 further comprises: if there are still at least two cargo transferring tasks that are not grouped together into a transferring group among the cargo transferring tasks to be completed, performing at least one collage such that the at least two cargo delivery tasks are both collaged into delivery groups, wherein in each of the at least one collage, for a still unassembled cargo transferring task of the at least two cargo transferring tasks, a seed cargo transferring task and those of the still unassembled cargo transferring tasks which are transportable on-board with the seed cargo transferring task and whose discharging location is at a distance from the discharging location of the seed cargo transferring task which is smaller than a second distance threshold are grouped together into one transferring group, the seed cargo conveyance task is the cargo conveyance task whose discharge site is farthest from its pickup site among the cargo conveyance tasks that have not been assembled yet.

In the seventh aspect, the method 200 further comprises: the travel route of each specific vehicle is further optimized to reduce the travel distance of each specific vehicle.

In the eighth aspect, the method 200 further comprises: and combining two or more cargo conveying tasks which have the same cargo lifting location and unloading location, cargo lifting time windows have intersection, and unloading time windows have intersection and do not require independent conveying into a single cargo conveying task to obtain a plurality of combined cargo conveying tasks, wherein the total cargo quantity of the single cargo conveying tasks obtained by combination is not more than the maximum cargo loading quantity of the available maximum vehicle, and the at least one conveying group is obtained by assembling the plurality of combined cargo conveying tasks.

Fig. 3 shows a schematic view of an arrangement for vehicle path optimization according to an embodiment of the invention. The apparatus 300 shown in fig. 3 can be implemented by software, hardware or a combination of software and hardware. The apparatus 300 may be installed in any suitable computing unit having computing capabilities, for example.

As shown in fig. 3, the apparatus 300 may include a set-spelling module 302, a clustering module 304, an adjustment module 306, and a determination module 308. The assembling module 302 is configured to assemble the cargo transferring tasks to be completed into at least one transferring group, each transferring group includes at least one cargo transferring task that can be transferred together by loading, and a distance between a discharging location of a specific cargo transferring task and discharging locations of other cargo transferring tasks in the at least one cargo transferring task is smaller than a distance threshold. The clustering module 304 is configured to cluster the cargo-carrying tasks included in any one of the at least one transport group into at least one task set of the any one transport group based on a first optimization objective, wherein a total cargo amount of each of the at least one task set of the any one transport group is not greater than a maximum cargo capacity of an available maximum vehicle, and a value of the first optimization objective is minimized when the at least one cargo-carrying task of the any one transport group is completed in a manner that each of the at least one task set of the any one transport group is completed by one vehicle. The adjustment module 306 is configured to adjust the cargo delivery task between the plurality of task sets of any of the one or more delivery groups based on the second optimization objective and according to the constraint information if there are one or more delivery groups of the at least one delivery group each having a plurality of task sets. The determining module 308 is configured to determine at least a specific vehicle and a driving route of each specific vehicle required for completing the cargo transferring task included in each of the at least one transportation group based on the task set included in each of the at least one transportation group after the adjustment.

In a first aspect, the adjustment module 306 includes: means for selecting at least one cargo shipment task from each of the plurality of task sets of the arbitrary shipment group adjusted for the previous iteration to obtain a plurality of selected cargo shipment tasks in each of a plurality of iterations; a module for calculating a plurality of evaluation value-observation value pairs for each of the selected cargo-moving tasks, wherein an evaluation value in any one of the evaluation value-observation value pairs for any one of the selected cargo-moving tasks is equal to one of the plurality of task sets assumed to place the any one of the selected cargo-moving tasks in the arbitrary moving group after the last iterative adjustment, a value for completing the second optimization objective for a specific moving route among the possible moving routes of the cargo-moving task included in the one of the task sets assumed to have placed the any one of the selected cargo-moving tasks, and wherein the evaluation value in any one of the evaluation value-observation value pairs is equal to a value of the second optimization objective required for completing the plurality of task sets of the arbitrary moving group after the last iterative adjustment in such a manner that one task set is completed by one vehicle and a value of the observation objective for any one of the selected cargo-moving tasks assumed to be used A difference value of values of the second optimization objectives required to complete the plurality of task sets of the arbitrary transportation group in such a manner that one task set is completed by one vehicle after putting the one of the plurality of task sets of the arbitrary transportation group after the last iterative adjustment, wherein the specific travel route is one of the respective feasible travel routes for which the value of the second optimization objective is the smallest, and the calculation of the value of the second optimization objective of the respective feasible travel routes takes into account the constraint information; means for calculating respective regresses of said plurality of selected cargo-delivery tasks of said arbitrary delivery group, wherein the regret of each selected cargo-delivery task is equal to the difference between the next-smallest and smallest of said plurality of evaluation-observation pairs of the selected cargo-delivery task; means for calculating respective composite values for the plurality of selected cargo-handling tasks, wherein the composite value for each selected cargo-handling task is equal to a weighted sum of a regret value for the selected cargo-handling task and each of a plurality of evaluation-observation value pairs for the selected cargo-handling task; and a module for placing the cargo transporting task with the maximum comprehensive value in the selected cargo transporting tasks into a first task set corresponding to the minimum evaluation value of the cargo transporting task with the maximum comprehensive value in the task sets of the arbitrary transporting group after the last iterative adjustment, so as to obtain a plurality of task sets of the arbitrary transporting group after the iterative adjustment, wherein the minimum evaluation value of the cargo transporting task with the maximum comprehensive value is calculated on the assumption that the cargo transporting task with the maximum comprehensive value is placed in the first task set.

In a fifth aspect, the assembly module 302 includes: means for counting a number of tasks for each of the cargo transferring tasks to be completed, which represents a number of those cargo transferring tasks of the cargo transferring tasks to be completed that can be shipped on-board with the cargo transferring task and whose location of discharge is less than a first distance threshold from the location of discharge of the cargo transferring task; and a module for, if there is at least one cargo transferring task among the cargo transferring tasks to be completed, whose number of tasks is greater than a number threshold, for any one of the at least one cargo transferring tasks, integrating those cargo transferring tasks and any one cargo transferring task, which can be shipped on board with the any one cargo transferring task and whose location of discharge is less than the first distance threshold from the location of discharge of the any one cargo transferring task, into one transferring group.

In a sixth aspect, the assembly module 302 further comprises: for if there are still at least two cargo transferring tasks that are not grouped together into a transferring group among the cargo transferring tasks to be completed, performing at least one collage such that the at least two cargo delivery tasks are both collaged to modules in a delivery group, wherein in each of the at least one collage, for a still unassembled cargo transferring task of the at least two cargo transferring tasks, a seed cargo transferring task and those of the still unassembled cargo transferring tasks which are transportable on-board with the seed cargo transferring task and whose discharging location is at a distance from the discharging location of the seed cargo transferring task which is smaller than a second distance threshold are grouped together into one transferring group, the seed cargo conveyance task is the cargo conveyance task whose discharge site is farthest from its pickup site among the cargo conveyance tasks that have not yet been merged.

In a seventh aspect, the apparatus 300 further comprises: and the module is used for further optimizing the driving route of each specific vehicle so as to reduce the driving distance of each specific vehicle.

In the eighth aspect, the apparatus 300 further comprises: a merging module, configured to merge two or more cargo transportation tasks of the cargo transportation tasks to be completed, which have the same pickup location and discharge location, have an intersection in pickup time windows, and have an intersection in discharge time windows, and do not require separate transportation, into a single cargo transportation task, so as to obtain a plurality of merged cargo transportation tasks, where a total cargo capacity of the single cargo transportation tasks obtained by merging is not greater than a maximum cargo capacity of an available maximum vehicle, and where the assembly module 302 is further configured to assemble the plurality of merged cargo transportation tasks into the at least one transportation group.

FIG. 4 shows a schematic diagram of a computing unit, according to an embodiment of the invention. As shown in fig. 4, the control unit 400 may include a processor 402 and a memory 404. The memory 404 has stored thereon executable instructions that, when executed, cause the processor 402 to perform the method 100 of fig. 1A or the method 200 of fig. 2.

There is also provided, in accordance with an embodiment of the present invention, a machine-readable storage medium having stored thereon executable instructions, wherein the executable instructions, when executed, cause a machine to perform the method 100 of fig. 1A or the method 200 of fig. 2.

The detailed description set forth above in connection with the appended drawings describes exemplary embodiments but does not represent all embodiments that may be practiced or fall within the scope of the claims. The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous" over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for vehicle path optimization, comprising:

assembling the cargo transferring tasks to be completed into at least one transferring group, wherein each transferring group comprises at least one cargo transferring task which can be transferred together by loading, and the distance between the unloading place of a specific cargo transferring task and the unloading places of other cargo transferring tasks in the at least one cargo transferring task is smaller than a distance threshold value;

clustering cargo carrying tasks included in any one of the at least one carrying groups into at least one task set of the any one carrying group based on a first optimization objective, wherein a total cargo amount of each task set of the at least one task set of the any one carrying group is not larger than a maximum cargo capacity of an available maximum vehicle, and a value of the first optimization objective is minimum when the at least one cargo carrying task of the any one carrying group is completed in a manner that each task set of the at least one task set of the any one carrying group is completed by one vehicle;

adjusting the cargo shipment task among the plurality of task sets of any of the one or more shipment groups based on the second optimization objective and in accordance with the constraint information if there are one or more shipment groups in the at least one shipment group each having a plurality of task sets; and

after the adjustment, at least the specific vehicles and the travel routes of each specific vehicle required to complete the cargo transferring task included in each of the at least one transfer group are determined based on the task set each of the at least one transfer group has.

2. The method of claim 1, wherein adjusting cargo conveyance tasks between task sets of any of the one or more conveyance groups based on constraint information and based on a second optimization objective comprises:

in each iteration of the multiple iterations, selecting at least one cargo conveying task from each of the plurality of task sets of the arbitrary conveying group adjusted in the last iteration to obtain a plurality of selected cargo conveying tasks;

calculating a plurality of evaluation value-observation value pairs for each of the selected cargo-carrying tasks, wherein an evaluation value in any one of the evaluation value-observation value pairs for any one of the selected cargo-carrying tasks is equal to a value of a second optimization objective for completing a specific travel route of each possible travel route of the cargo-carrying task included in the one of the task sets assumed to have been placed in the any one of the selected cargo-carrying tasks, among the plurality of task sets assumed to have been placed in the any one of the selected cargo-carrying tasks after the last iterative adjustment, and wherein an evaluation value in any one of the evaluation value-observation value pairs is equal to a value of a second optimization objective required for completing the plurality of task sets for the any one of the selected cargo-carrying tasks after the last iterative adjustment in such a manner that one task set is completed by one vehicle and an iterative adjustment performed after assuming that the any one of the selected cargo-carrying tasks is placed in the any one of the selected cargo-carrying tasks A difference value of values of second optimization objectives required to complete the plurality of task sets of the arbitrary transportation group in such a manner that one task set is completed by one vehicle after the one of the plurality of task sets of the arbitrary transportation group, wherein the specific travel route is a travel route of which a value of a second optimization objective is smallest among the respective feasible travel routes, and the constraint information is considered in calculating the value of the second optimization objective of the respective feasible travel routes;

calculating respective regret values for the plurality of selected cargo-delivery tasks of the arbitrary delivery group, wherein the regret value for each selected cargo-delivery task is equal to a difference between a next-smallest evaluation value and a smallest evaluation value of the plurality of evaluation-observation value pairs for the selected cargo-delivery task;

calculating respective comprehensive values of the plurality of selected cargo-carrying tasks, wherein the comprehensive value of each selected cargo-carrying task is equal to the weighted sum of the regret value of the selected cargo-carrying task and each observation value in the plurality of evaluation value-observation value pairs of the selected cargo-carrying task; and

and putting the cargo transportation task with the maximum comprehensive value in the selected cargo transportation tasks into a first task set corresponding to the minimum evaluation value of the cargo transportation task with the maximum comprehensive value in the task sets of the arbitrary transportation group after the last iterative adjustment to obtain a plurality of task sets of the arbitrary transportation group after the iterative adjustment, wherein the minimum evaluation value of the cargo transportation task with the maximum comprehensive value is calculated by supposing that the cargo transportation task with the maximum comprehensive value is put into the first task set.

3. The method of claim 2, wherein,

the plurality of selected cargo transporting tasks comprise cargo transporting tasks exceeding a time limit, cargo transporting tasks exceeding a capacity limit, cargo transporting tasks generating a detour phenomenon and/or cargo transporting tasks with smaller task relevance in each task set of the plurality of task sets of the arbitrary transporting group after last iterative adjustment.

4. The method of claim 1, wherein,

the first optimization objective is a total cost, a total elapsed time or a total distance, and

the second optimization objective is total cost, total elapsed time, or total distance.

5. The method of claim 1, wherein,

the constraint information includes a demand for goods, a delivery amount, a delivery time window, a vehicle capacity limit, a mileage limit, and a travel time limit.

6. The method of claim 1, wherein assembling the cargo shipments to be completed into at least one shipping group comprises:

counting the number of tasks of each cargo transferring task in the cargo transferring tasks to be completed, wherein the number of the cargo transferring tasks to be completed represents the number of the cargo transferring tasks which can be carried by loading together with the cargo transferring task and the distance between the unloading place of the cargo transferring task and the unloading place of the cargo transferring task is less than a first distance threshold value; and

if at least one cargo transporting task of which the number of tasks is greater than a number threshold exists in the cargo transporting tasks to be completed, for any cargo transporting task in the at least one cargo transporting task, the cargo transporting tasks which can be loaded and transported together with the any cargo transporting task and of which the distance between the unloading place and the unloading place of the any cargo transporting task is less than the first distance threshold and the any cargo transporting task are integrated into a transporting group.

7. The method of claim 6, wherein assembling the cargo shipments to be completed into at least one shipping group further comprises:

if there are still at least two cargo transferring tasks that are not yet pieced together into a transferring group among the cargo transferring tasks that need to be completed, performing at least one piecing together such that both of the at least two cargo transferring tasks are pieced together into a transferring group,

wherein, in each of the at least one collage, for a still unassembled cargo transfer task of the at least two cargo transfer tasks, a seed cargo transfer task, which is a cargo transfer task of the still unassembled cargo transfer task whose discharge location is farthest from its pickup location, and those of the still unassembled cargo transfer tasks that can be truck-transferred with the seed cargo transfer task and whose discharge location is at a distance from the discharge location of the seed cargo transfer task that is less than a second distance threshold value, are ganged together into one transfer group.

8. The method of claim 1, further comprising:

the travel route of each specific vehicle is further optimized to reduce the travel distance of each specific vehicle.

9. The method of any of claims 1-8, further comprising:

combining two or more cargo transferring tasks of the cargo transferring tasks to be completed, which have the same goods picking-up location and unloading location, the goods picking-up time windows have intersection, the unloading time windows have intersection and do not require separate transferring, into a single cargo transferring task to obtain a plurality of combined cargo transferring tasks, wherein the total cargo quantity of the single cargo transferring tasks obtained by combining is not more than the maximum cargo capacity of the available maximum vehicle,

wherein the at least one delivery group is obtained by assembling the merged multiple cargo delivery tasks.

10. An apparatus for vehicle path optimization, comprising:

the cargo conveying system comprises a gathering module, a control module and a control module, wherein the gathering module is used for gathering cargo conveying tasks to be completed into at least one conveying group, each conveying group comprises at least one cargo conveying task which can be carried by loading together, and the distance between the unloading place of a specific cargo conveying task in the at least one cargo conveying task and the unloading place of each other cargo conveying task is smaller than a distance threshold value;

a clustering module for clustering cargo carrying tasks included in any one of the at least one carrying group into at least one task set of the any one carrying group based on a first optimization objective, wherein a total cargo amount of each of the at least one task set of the any one carrying group is not more than a maximum cargo capacity of an available maximum vehicle, and a value of the first optimization objective is minimum when the at least one cargo carrying task of the any one carrying group is completed in a manner that each of the at least one task set of the any one carrying group is completed by one vehicle;

an adjustment module for adjusting the cargo conveyance task between the plurality of task sets of any of the one or more conveyance groups according to constraint information and based on a second optimization objective if there are one or more conveyance groups of the at least one conveyance group each having a plurality of task sets; and

and the determining module is used for determining at least specific vehicles and driving routes of each specific vehicle required for completing the cargo transportation task respectively included in the at least one transportation group based on the task set respectively included in the at least one transportation group after the adjustment.

11. The apparatus of claim 10, wherein the adjustment module comprises:

means for selecting at least one cargo shipment task from each of the plurality of task sets of the arbitrary shipment group adjusted for the previous iteration to obtain a plurality of selected cargo shipment tasks in each of a plurality of iterations;

a module for calculating a plurality of evaluation-observation value pairs for each of the selected cargo-moving tasks, wherein an evaluation value in any one of the evaluation-observation value pairs for any one of the selected cargo-moving tasks is equal to one of the plurality of task sets assumed to place the any one of the selected cargo-moving tasks into the arbitrary moving group after the last iterative adjustment, a second optimization objective for accomplishing a specific traveling route of each feasible traveling route of the cargo-moving tasks included in the one of the task sets assumed to have placed the any one of the selected cargo-moving tasks, and wherein the evaluation value in any one of the evaluation-observation value pairs is equal to a second optimization objective required for accomplishing the plurality of task sets of the arbitrary moving group after the last iterative adjustment in such a manner that one task set is accomplished by one vehicle and a value required for assuming to place the any one of the selected cargo-moving tasks into the previous iterative adjustment After the second iteration, calculating a value of a second optimization goal of each of the feasible travel routes, wherein the value of the second optimization goal is a minimum value of the second optimization goals in the feasible travel routes, and the constraint information is considered in calculating the value of the second optimization goal of each of the feasible travel routes;

means for calculating respective regresses of said plurality of selected cargo-delivery tasks of said arbitrary delivery group, wherein the regret of each selected cargo-delivery task is equal to the difference between the next-smallest and smallest of said plurality of evaluation-observation pairs of the selected cargo-delivery task;

means for calculating respective composite values for the plurality of selected cargo-handling tasks, wherein the composite value for each selected cargo-handling task is equal to a weighted sum of a regret value for the selected cargo-handling task and each of a plurality of evaluation-observation value pairs for the selected cargo-handling task; and

a module, configured to put a cargo transportation task with a maximum integrated value in the selected cargo transportation tasks into a first task set corresponding to a minimum evaluation value of the cargo transportation task with the maximum integrated value in the task sets of the arbitrary transportation group after the last iterative adjustment, so as to obtain a plurality of task sets of the arbitrary transportation group after the iterative adjustment, where the minimum evaluation value of the cargo transportation task with the maximum integrated value is calculated assuming that the cargo transportation task with the maximum integrated value is put into the first task set.

12. The apparatus of claim 11, wherein,

13. The apparatus of claim 10, wherein,

14. The apparatus of claim 10, wherein,

15. The apparatus of claim 10, wherein the assembly module comprises:

means for counting a number of tasks for each of the cargo transferring tasks to be completed, which represents a number of cargo transferring tasks that can be carried on-board the cargo transferring task and whose unloading location is less than a first distance threshold from the unloading location of the cargo transferring task; and

and a module for, if there is at least one cargo transferring task among the cargo transferring tasks to be completed, the number of tasks being greater than a number threshold, for any one of the at least one cargo transferring tasks, grouping together a cargo transferring task and any one cargo transferring task, which can be truck-transferred together with the any one cargo transferring task and whose discharging location is at a distance from the discharging location of the any one cargo transferring task that is less than the first distance threshold, into one transferring group.

16. The apparatus of claim 15, wherein the assembly module further comprises:

means for performing at least one collage at least once if there are still at least two cargo transferring tasks in the cargo transferring tasks to be completed that are not collaged into a transferring group such that both cargo transferring tasks are collaged into a transferring group,

17. The apparatus of claim 10, further comprising:

and the module is used for further optimizing the driving route of each specific vehicle so as to reduce the driving distance of each specific vehicle.

18. The apparatus of any of claims 10-17, further comprising:

a merging module, configured to merge two or more cargo carrying tasks with the same pick-up location and drop-off location, pick-up time windows having intersection, drop-off time windows having intersection and not requiring separate carrying into a single cargo carrying task, so as to obtain a plurality of merged cargo carrying tasks, wherein the total cargo capacity of the single cargo carrying tasks obtained by merging is not greater than the maximum cargo capacity of the available maximum vehicle,

wherein the assembling module is further configured to assemble the merged cargo transporting tasks into the at least one transporting group.

19. A computing unit, comprising:

a processor; and

a memory having executable instructions stored thereon, wherein the executable instructions, when executed, cause the processor to perform the method of any of claims 1-9.

20. A machine readable storage medium having stored thereon executable instructions, wherein the executable instructions, when executed, cause a machine to perform the method of any one of claims 1-9.