Logistics driver scheduling method, device and equipment and storage medium

Abstract

The invention discloses a logistics driver scheduling method, apparatus and device, and a storage medium. The method comprises the steps of obtaining a historical waybill of a point; performing task allocation calculation on historical waybills by adopting a simulated annealing algorithm, and in each iterative calculation, performing acceptance evaluation on a current solution according to a target function constructed by point driver cost, external driver cost and overtime waybill cost; determining the number of point drivers according to a final task allocation scheme until an iteration ending condition is met, and obtaining a scheduling scheme; the construction of the iterative calculation initial solution is as follows: according to an inter-waybill distance calculation formula constructed by a time distance and a space distance, historical waybills are subjected to condensation clustering processing to obtain waybills, and then task allocation is performed on point drivers and outside drivers. By using the method disclosed by the invention, the scheduling scheme can be obtained more quickly and better, the cost is reduced, and the scheduling efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics scheduling, and in particular to a logistics driver scheduling method, device, equipment and storage medium. Background Art

[0002] Freight driver scheduling is a crucial part of logistics and transportation. In logistics and transportation, a large number of waybills arrive at various points and customers every day. Each point will assign these waybills to each driver and require the driver to pick up or deliver the goods to the customer at the specified time. If there are too few drivers and too many goods, the logistics throughput of the point will be too low, which will affect the number of external tasks and the timeliness of tasks. If there are too many drivers, it will increase the logistics cost of the company. How to reasonably arrange the scheduling time of freight drivers to meet the timeliness requirements of customers and the cost requirements of the company, and improve logistics efficiency and customer satisfaction has always been a challenge faced by logistics companies. Traditional scheduling methods are usually manually operated based on the experience of salesmen. The optimal scheduling time of the point is determined by reviewing historical waybills, which makes the traditional scheduling method have the following defects: First, the scheduling efficiency is low, and a large amount of manpower costs are consumed to maintain and review. According to the professional level of each salesman, the results are subjective and uncertain; second, the computing power of the human brain is limited, and the computing power advantage of the computer is not fully utilized, and the optimal driver task allocation plan cannot be obtained. Summary of the invention

[0003] The present invention provides a logistics driver scheduling method, device, equipment and storage medium, which are used to solve the technical problems in the prior art of low scheduling efficiency, subjectivity, uncertainty and inability to obtain an optimal driver task allocation plan.

[0004] In order to solve the above technical problems, in a first aspect, the present invention provides a logistics driver scheduling method, the method comprising:

[0005] Obtain the historical waybills of the point department, which include on-time waybills of the point department drivers, on-time waybills of external drivers, and overtime waybills;

[0006] The simulated annealing algorithm is used to calculate the task allocation of the historical waybills. In each iterative calculation, the acceptability of the current solution is evaluated based on the objective function constructed according to the cost of the point driver, the cost of the external driver, and the cost of the overtime waybill. The final task allocation plan is used to determine the number of point drivers and obtain the shift scheduling plan until the iteration end condition is met.

[0007] The construction of the initial solution of iterative calculation is to obtain the waybill after agglomerative clustering processing of the historical waybill according to the distance calculation formula between waybills constructed by time distance and space distance, and then assign tasks to the point drivers and outsourced drivers.

[0008] Optionally, the method of performing agglomerative clustering on the historical waybills to obtain waybills and then allocating tasks to the point drivers and the outsourced drivers includes:

[0009] Merge the two historical waybills with the smallest distance into a new waybill, and repeat the process until all the merged waybills cannot be merged any further; during the merging process, the historical waybills with time conflicts cannot be merged together;

[0010] The merged waybills that include a preset number of historical waybills will be assigned tasks to the point drivers, and the remaining merged waybills will be assigned tasks to external drivers.

[0011] Optionally, the distance calculation formula between waybills constructed by time distance and space distance includes:

[0012] d=d S *w1+d T *w2*V

[0013] Where d is the distance between two waybills, d S is the difference in longitude and latitude between the two waybills, w1 is the weight of the distance, d T is the difference in task start time between the two waybills, w2 is the time weight, and V is the truck running speed.

[0014] Optionally, during iterative calculation, the current solution is disturbed by using a perturbation operator, and one waybill in the current solution is selected to be assigned to the new driver, thereby generating a new solution for the task assignment.

[0015] Optionally, the objective function constructed based on the cost of the driver at the point, the cost of the external driver and the cost of the overtime waybill includes:

[0016] The objective function formula is:

[0017]

[0018] Among them, f(t) is the total cost of the point, N is the preset number of days for historical waybill statistics, K is the number of drivers at the point, c1 is the cost of the drivers at the point, and e i is the number of tasks assigned to the external driver on the i-th day, c2 is the cost of the external driver, o i is the number of overtime tasks of the point department on the i-th day, and c3 is the overtime task loss of the point department.

[0019] Optionally, when performing task allocation calculation, any of the following constraints must be met:

[0020] The volume of the cargo on the waybill of each task is smaller than the volume of the driver's vehicle;

[0021] The customer's required arrival time for each waybill included in each task is earlier than the driver's arrival time at the customer's destination;

[0022] The weight of the waybill contained in each task is less than the remaining load of the driver's vehicle.

[0023] Optionally, the performing acceptability evaluation on the current solution includes:

[0024] If the objective function value of the current solution is less than or equal to the objective function value of the last accepted new solution, the current solution is accepted as the new solution; otherwise, the current solution is accepted as the new solution with a certain probability.

[0025] In a second aspect, the present invention provides a logistics driver scheduling device, including a historical waybill acquisition module, a scheduling module, and an initial solution construction module;

[0026] The historical waybill acquisition module is used to acquire the historical waybill of the point department, and the historical waybill includes the on-time waybill of the point department driver, the on-time waybill of the external driver and the overtime waybill;

[0027] The scheduling module is used to perform task allocation calculation on the historical waybills using a simulated annealing algorithm. In each iterative calculation, the current solution is evaluated for acceptability based on the objective function constructed according to the cost of the driver at the point, the cost of the external driver, and the cost of the overtime waybill. The final task allocation plan is used to determine the number of drivers at the point and obtain a scheduling plan until the iteration end condition is met.

[0028] The initial solution construction module is used to iteratively calculate the initial solution by performing agglomerative clustering processing on the historical waybills according to the distance calculation formula between waybills constructed by time distance and space distance to obtain waybills, and then allocating tasks to point drivers and outsourced drivers.

[0029] In a third aspect, the present invention provides a logistics driver scheduling device, including a memory and a processor, wherein:

[0030] The memory is used to store computer programs;

[0031] The processor is used to read the program in the memory and execute the steps of the logistics driver scheduling method provided in the first aspect above.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having a readable computer program stored thereon, which, when executed by a processor, implements the steps of the logistics driver scheduling method provided in the first aspect above.

[0033] Compared with the prior art, the logistics driver scheduling method, device, equipment and storage medium provided by the present invention have the following beneficial effects:

[0034] The historical waybills of the point department are obtained, and the historical waybills include on-time waybills of the point department drivers, on-time waybills of external drivers, and overtime waybills; the simulated annealing algorithm is used to calculate the task allocation of the historical waybills. In each iterative calculation, the current solution is evaluated for acceptability according to the objective function constructed based on the cost of the point department drivers, the cost of external drivers, and the cost of overtime waybills; until the iteration end condition is met, the number of drivers of the point department is determined by the final task allocation plan, and the scheduling plan is obtained; the initial solution of the iterative calculation is constructed by agglomerative clustering of the historical waybills according to the distance calculation formula between waybills constructed by time distance and space distance to obtain the waybills, and then the tasks are allocated to the point department drivers and external drivers; the method uses the simulated annealing algorithm to calculate the task allocation of the historical waybills of the point department, and at the same time, agglomerative clustering of the historical waybills is performed according to the waybill distance to construct the initial solution, so that the scheduling plan can be obtained faster and better, thereby reducing the cost of manual scheduling, improving the efficiency and objectivity of scheduling, and the obtained driver scheduling plan is also better. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only part of the embodiments of the present invention, rather than all of the embodiments. For ordinary technicians in this field, without paying creative work, other drawings obtained based on these drawings all fall within the scope of protection of this application.

[0036] Figure 1 This is a first flow chart of a logistics driver scheduling method provided by an embodiment of the present invention;

[0037] Figure 2 This is a second flow chart of a logistics driver scheduling method provided by an embodiment of the present invention;

[0038] Figure 3 It is a structural schematic diagram of a logistics driver scheduling device provided by an embodiment of the present invention;

[0039] Figure 4 It is a structural schematic diagram of a logistics driver scheduling device provided by an embodiment of the present invention;

[0040] Figure 5 It is a structural schematic diagram of a computer-readable storage medium provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0042] In order to make the description of the disclosed content more detailed and complete, the following is an illustrative description of the implementation mode and specific examples of the present invention; however, this is not the only form of implementing or applying the specific embodiments of the present invention. The implementation mode covers the features of multiple specific embodiments and the method steps and their sequence for constructing and operating these specific embodiments. However, other specific embodiments can also be used to achieve the same or equal functions and step sequences. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0043] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0044] In the description of the embodiments of the present invention, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two, and other quantifiers are similar. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention, and the embodiments of the present application and the features in the embodiments may be combined with each other without conflict.

[0045] Example 1

[0046] like Figure 1 As shown, it is a first flow chart of a logistics driver scheduling method provided by an embodiment of the present invention, and the logistics driver scheduling method includes the following steps.

[0047] Step S101, obtaining the historical waybills of the point department, wherein the historical waybills include on-time waybills of the point department drivers, on-time waybills of external drivers, and overtime waybills;

[0048] In some embodiments, historical waybills are obtained, such as the network-wide waybills for the past two weeks. The historical waybills may include the freight waybill number, quantity, weight, arrival time, destination, the latest allowed time to arrive at the customer, etc. The historical waybills are classified by site, and each site is processed separately to obtain the historical waybills of the site. Subsequently, the simulated annealing algorithm is used to perform task allocation operations on the historical waybills of each site to obtain the scheduling plan for the site.

[0049] In the logistics industry, when waybills arrive at various points and customers, each point will assign these waybills to various drivers, requiring the drivers to pick up the goods or deliver them to the customers at the specified time. Such waybills are counted as waybills of point drivers. If the tasks cannot be assigned, some vehicles will be hired to pick up and deliver the goods. Such waybills are counted as waybills of hired drivers. For the historical waybills obtained, overdue waybills are counted from the waybills of point drivers and the waybills of hired drivers, that is, waybills that have not completed the pickup or delivery within the required time, and such waybills are marked as overdue waybills. The remaining waybills of point drivers are marked as on-time waybills of point drivers; the remaining waybills of hired drivers are marked as on-time waybills of hired drivers. The three types of waybills, namely on-time waybills of point drivers, on-time waybills of hired drivers, and overdue waybills, are used as inputs for task allocation calculation of the simulated annealing algorithm.

[0050] Step S102, using a simulated annealing algorithm to perform task allocation calculation on the historical waybills, in each iterative calculation, the acceptability of the current solution is evaluated based on the objective function constructed according to the cost of the driver at the point, the cost of the external driver, and the cost of the overtime waybill; until the iteration end condition is met, the number of drivers at the point is determined by the final task allocation plan, and a scheduling plan is obtained;

[0051] In some embodiments, historical waybills are simulated based on each route, and the historical waybills are assigned to each driver at the point. Statistics are collected on time from drivers at the point, on time from external drivers, and overtime waybills to serve as input for task allocation at the point.

[0052] As an optional implementation, when performing task allocation calculation, any of the following constraints must be met:

[0053] The volume of the cargo on the waybill of each task is smaller than the volume of the driver's vehicle;

[0054] The customer's required arrival time for each waybill included in each task is earlier than the driver's arrival time at the customer's destination;

[0055] The weight of the waybill contained in each task is less than the remaining load of the driver's vehicle.

[0056] In some embodiments, for each waybill contained in a task, the vehicle model constraint of the driver needs to be satisfied, that is,

[0057] W v <d v

[0058] Among them, W v is the length, width, height and volume of the waybill, d v The volume of the driver's vehicle. The volume of the cargo on the waybill needs to be smaller than the volume of the driver's vehicle.

[0059] The customer's required arrival time for each waybill contained in the task must be earlier than the time when the driver arrives at the customer's destination, that is,

[0060] W t >d t

[0061] Among them, W t The time it takes for the waybill to reach the customer, d t The time when the driver arrives at the customer's destination. The driver needs to arrive in advance. The required arrival time of the waybill refers to the time required to deliver or pick up the goods at the customer's place.

[0062] The weight of the waybill contained in each task must be less than the remaining load of the driver's vehicle, that is,

[0063] W w <d w

[0064] Among them, W w is the weight of the waybill, d w The remaining load of the driver's vehicle. The weight of the waybill needs to be less than the remaining load of the driver's vehicle.

[0065] In the embodiment of the present invention, when the simulated annealing algorithm is used to perform task allocation calculation, the model and load constraints of the driver's freight vehicle and the time constraints are performed on the assigned task waybill, which can improve the loading rate and the timeliness of the waybill in the logistics transportation process, avoid the ineffective allocation of tasks, and improve the rationality of the driver's task allocation.

[0066] As an optional implementation, the objective function constructed based on the cost of the driver at the point, the cost of the external driver and the cost of the overtime waybill includes:

[0067] The objective function formula is:

[0068]

[0069] Among them, f(t) is the total cost of the point, N is the preset number of days for historical waybill statistics, K is the number of drivers at the point, c1 is the cost of the drivers at the point, and e i is the number of tasks assigned to the external driver on the i-th day, c2 is the cost of the external driver, o i is the number of overtime tasks of the point department on the i-th day, and c3 is the overtime task loss of the point department.

[0070] In some embodiments, N may be less than or equal to 14, and the current solution is evaluated for acceptability based on the objective function constructed according to the point driver cost, the outsourced driver cost, and the overtime waybill cost. The more saturated the point driver's working hours, the fewer the outsourced drivers, and the fewer the overtime tasks, the lower the total cost of the point and the more reasonable the driver scheduling plan of the point.

[0071] The embodiment of the present invention performs an acceptability evaluation on the current solution in the iterative calculation by constructing an objective function based on the cost of drivers at the point, the cost of hiring drivers, and the cost of overtime waybills, thereby providing an objective standard for the rationality of the scheduling plan, so that the scheduling plan finally obtained by the iterative calculation is in line with reality.

[0072] As an optional implementation, during iterative calculation, the current solution is disturbed by using a perturbation operator, and one waybill in the current solution is selected to be assigned to the new driver, thereby generating a new solution for task assignment.

[0073] In some embodiments, during iterative calculation, the random_removal operator and the worst_removal operator are used to perturb the current solution, and a waybill in the current solution is selected to be assigned to the new driver, thereby generating a new solution for task assignment. At this time, the new solution is the current solution of the current iteration.

[0074] Use the above objective function to evaluate the acceptability of the current solution and obtain the total cost of the point corresponding to the new solution, that is, the objective function value f(t"),

[0075]

[0076] Among them, d" is the number of drivers at the point corresponding to the current solution, e i "is the number of tasks assigned to external drivers on the i-th day corresponding to the current solution, o i " is the number of overtime tasks on the i-th day corresponding to the current solution.

[0077] As an optional implementation manner, the acceptability evaluation of the current solution includes:

[0078] If the objective function value of the current solution is less than or equal to the objective function value of the last accepted new solution, the current solution is accepted as the new solution; otherwise, the current solution is accepted as the new solution with a certain probability.

[0079] In some embodiments, if the objective function value of the current solution is f(f"), and the objective function value of the last accepted new solution is f(t), if the objective function value of the current solution is less than or equal to the objective function value of the last accepted new solution, the current solution is accepted as the new solution. If the objective function value of the current solution is greater than the objective function value of the last accepted new solution, then there is a certain probability that the current solution is accepted as the new solution. Specifically, if the probability value p is greater than the random number r, the current solution is accepted as the new solution. If the probability value p is not greater than the random number r, the current solution is not accepted as the new solution. The probability value T0 is the current temperature parameter of the simulated annealing algorithm, 0 <r<1。

[0080] In some embodiments, in each iterative calculation, the acceptability of the current solution is evaluated based on the objective function constructed according to the cost of the driver at the point, the cost of the external driver, and the cost of the overtime waybill. After the current iteration is completed, the current iteration number is reduced by 1, and the next iteration is performed until the current iteration number is 0 or the number of times the current solution has no improvement reaches a preset number, and the current iteration is terminated. Specifically, it can be expressed by the following expression:

[0081] Iter=Iter-1

[0082] Iter≥0

[0083] num≤L

[0084] Among them, Iter is the current iteration number, which needs to be greater than 0. If not, the current iteration will be skipped. num is the current number of no improvements, and L is the preset number of no improvements. If the current temperature has no improvement times reaching L, the current iteration will end and the cooling operation will be performed. In the next iteration, the expression of the cooling operation is as follows:

[0085] T0=T0*a

[0086] Iter=M

[0087] count=count+1

[0088] count <n

[0089] Among them, T0 is the current temperature parameter, a is the current cooling coefficient, M is the maximum number of iterations of the current temperature, count is the current number of cooling times, and n is the threshold of the number of cooling times. After each round of iteration, the current temperature parameter is multiplied by the relevant coefficient to reduce the temperature, and then the current temperature iteration number Iter is reset. At the same time, the number of cooling times count is accumulated and added by 1, and the next round of iteration is performed until count ≥ n, that is, the iteration end condition is met, and the number of drivers at the point is determined by the final task allocation plan to obtain the scheduling plan.

[0090] In the embodiment of the present invention, a simulated annealing algorithm is used to calculate the task allocation for the historical waybills of the point department, and the number of drivers of the point department is determined to optimize the cost according to the final task allocation, so as to obtain the final logistics scheduling plan, thereby improving the scheduling efficiency and making the scheduling plan better.

[0091] Step S103, the construction of the iterative calculation initial solution is to obtain the waybill after agglomerative clustering processing of the historical waybill according to the distance calculation formula between waybills constructed by time distance and space distance, and then assign tasks to the point drivers and outsourced drivers.

[0092] When using the simulated annealing algorithm to calculate the allocation of historical waybills, the initial solution is not generated randomly, but is obtained by agglomerating and clustering the historical waybills according to the distance between the waybills, and then allocating tasks to the point drivers and external drivers. Among them, the distance between waybills is calculated based on the time distance and space distance.

[0093] In some embodiments, it is assumed that there are 4 historical waybills, namely A, B, C, and D, and the distance from A to B is 2, and the distance from B to C is 1. When constructing the initial solution, the traditional simulated annealing algorithm generally adopts a greedy algorithm. When searching all historical waybills, the greedy algorithm only considers the optimal match of historical waybills A when traversing to historical waybills A, and does not consider the optimal match of historical waybills B, so that the historical original waybills A and historical waybills B are combined into one task for allocation, but in fact, it is optimal to combine historical waybills B and historical waybills C into one task for allocation. When constructing the initial solution, the embodiment of the present invention uses agglomerative clustering to process the historical waybills, and can find the optimal match from the global perspective, that is, the historical waybills with the shortest global distance are matched in pairs, so historical waybills B and historical waybills C are processed first, and historical waybills B and historical waybills C are combined together, and then historical waybills A and historical waybills D are processed. The initial solution constructed in this way is better, and based on the better initial solution, the subsequent simulated annealing algorithm searches for the global optimum faster and obtains a better solution.

[0094] As an optional implementation manner, the distance calculation formula between waybills constructed by time distance and space distance includes:

[0095] d=d S *w1+d T *w2*V

[0096] Where d is the distance between two waybills, d S is the difference in longitude and latitude between the two waybills, w1 is the weight of the distance, d T is the difference between the task start times of the two waybills, w2 is the time weight, and V is the running speed of the truck. For example, the running speed of the truck can be 30 km / h.

[0097] In an embodiment of the present invention, the distance between waybills is calculated by combining the time distance and the space distance. While considering the spatial distance of the waybills, the timeliness of the waybills is also considered, so that historical waybills are processed according to agglomerative clustering and the waybills with the shortest distance are merged more reasonably and accurately, thereby making the constructed initial solution better.

[0098] As an optional implementation manner, the method of obtaining a waybill after agglomerative clustering processing is performed on the historical waybill, and then allocating tasks to the point drivers and the external drivers includes:

[0099] Merge the two historical waybills with the smallest distance into a new waybill, and repeat the process until all the merged waybills cannot be merged any further; during the merging process, the historical waybills with time conflicts cannot be merged together;

[0100] The merged waybills that include a preset number of historical waybills will be assigned tasks to the point drivers, and the remaining merged waybills will be assigned tasks to external drivers.

[0101] In some embodiments, the two historical waybills with the smallest distance are merged into a new waybill, and the new waybill is merged with other waybills into a new waybill, and the process is repeated until all the merged waybills can no longer be merged. During the merging process, the historical waybills with time conflicts cannot be merged together. Time conflicts include the inability to process different waybills at the same time. For example, there is a conflict between waybills for two pickup tasks at different locations at the same time. The waybills that include a preset number of historical waybills after merging are assigned tasks to the point drivers, and the remaining merged waybills are assigned tasks to external drivers. The waybills that include a large number of historical waybills after merging are assigned to the point drivers, so that the number of waybills processed by the point drivers to perform tasks is large, and the number of waybills processed by the corresponding tasks assigned to external drivers is small, thereby reducing the point costs. After the allocation is completed, the assigned task plan is the initial solution.

[0102] In some embodiments, a second flow chart of a logistics driver scheduling method is as follows: Figure 2 As shown, the logistics driver scheduling method may include the following process: obtaining historical waybills within a preset period, classifying the historical waybills by point, and obtaining the historical waybills of the target point; performing agglomerative clustering on the historical waybills and assigning tasks as the initial solution, and obtaining the objective function score f(w) of the initial solution; using the perturbation operator to perturb the current solution, assigning a waybill in the current solution to the new driver, generating a new solution w′ for task assignment, calculating the objective function score f(w′) of the new solution, and defining f=f(w′)-f(w); judging whether f≤0 holds, if so, accepting the new solution w=w ′, so that the objective function score of the current solution is the objective function score of the new solution, that is, f(w) = f(w′), otherwise, the new solution is accepted with a certain probability; determine whether this round of iterative calculation has reached the number of iterations, if not, continue with the next iterative calculation and perform the above perturbation strategy, if so, end this round of iterative calculation, and further determine whether the iteration end condition is met; if the iteration end condition is not met, reduce the temperature parameter, reset the number of iterations, continue with the next round of iterative calculation, and perform the above perturbation strategy; if the iteration end condition is met, end the iteration and obtain the final task allocation plan.

[0103] In an embodiment of the present invention, when performing agglomerative clustering processing on historical waybills, historical waybills with time conflicts are not merged, thereby improving the rationality of historical waybills classified as one task. At the same time, merged waybills containing as many historical waybills as possible are assigned to point drivers, reducing the number of waybills processed by tasks assigned to external drivers, thereby reducing costs and making the initial solution better.

[0104] The logistics driver scheduling method provided by the embodiment of the present invention obtains the historical waybills of the point department, and the historical waybills include on-time waybills of the drivers of the point department, on-time waybills of the external drivers, and overtime waybills; a simulated annealing algorithm is used to perform task allocation calculation on the historical waybills, and in each iterative calculation, the current solution is evaluated for acceptability according to the objective function constructed based on the cost of the drivers of the point department, the cost of the external drivers, and the cost of the overtime waybills; until the iteration end condition is met, the number of drivers of the point department is determined by the final task allocation plan, and a scheduling plan is obtained; the initial solution of the iterative calculation is constructed by performing agglomerative clustering processing on the historical waybills according to the distance calculation formula between waybills constructed by time distance and space distance to obtain the waybills, and then tasks are assigned to the drivers of the point department and the external drivers; the method uses a simulated annealing algorithm to perform task allocation calculation on the historical waybills of the point department, and at the same time combines the agglomerative clustering processing based on the waybill distance to construct the initial solution, so that the scheduling plan can be obtained faster and better, the cost of manual scheduling is reduced, the efficiency and objectivity of scheduling are improved, and the obtained driver scheduling plan is also better.

[0105] The logistics driver scheduling method provided by the embodiment of the present invention is based on the initial solution construction of improved agglomerative clustering. According to the different weights of time distance and space distance, the distance between two waybills is calculated, and then the constrained agglomerative clustering is used to cluster and construct the initial solution of each waybill. Based on the initial solution, the task allocation operation is performed, and a satisfactory solution can be obtained more quickly, thereby reducing the cost of manual scheduling, improving the efficiency and objectivity of scheduling, and obtaining a better driver scheduling plan.

[0106] Example 2

[0107] Based on the above logistics driver scheduling method, an embodiment of the present invention provides a logistics driver scheduling device, and its structural diagram is as follows: Figure 3 As shown, the logistics driver scheduling device 30 includes a historical waybill acquisition module 31, a scheduling module 32 and an initial solution construction module 33;

[0108] The historical waybill acquisition module 31 is used to acquire the historical waybill of the point department, and the historical waybill includes the on-time waybill of the point department driver, the on-time waybill of the external driver and the overtime waybill;

[0109] The scheduling module 32 is used to perform task allocation calculation on the historical waybills using a simulated annealing algorithm. In each iterative calculation, the acceptability of the current solution is evaluated based on the objective function constructed according to the cost of the driver at the point, the cost of the external driver, and the cost of the overtime waybill. Until the iteration end condition is met, the number of drivers at the point is determined by the final task allocation plan to obtain a scheduling plan.

[0110] The initial solution construction module 33 is used to iteratively calculate the initial solution by performing agglomerative clustering processing on the historical waybills according to the distance calculation formula between waybills constructed by time distance and space distance to obtain waybills, and then allocating tasks to the point drivers and outsourced drivers.

[0111] For other details about how the modules in the logistics driver scheduling device implement the above technical solution, please refer to the description of the logistics driver scheduling method provided in the above invention embodiment, which will not be repeated here.

[0112] Example 3

[0113] Based on the above logistics driver scheduling method, the embodiment of the present invention also provides a logistics driver scheduling device, and its structural diagram is as follows: Figure 4 As shown, the logistics driver scheduling device 40 includes a processor 41 and a memory 42 coupled to the processor 41. The memory 42 stores a computer program, and when the computer program is executed by the processor 41, the processor 41 executes the steps of the logistics driver scheduling method in the above embodiment.

[0114] For other details about how the processor 41 in the logistics driver scheduling device 40 implements the above technical solution, please refer to the description of the logistics driver scheduling method provided in the above invention embodiment, which will not be repeated here.

[0115] Among them, the processor 41 can also be called a CPU (Central Processing Unit), and the processor 41 may be an integrated circuit chip with signal processing capabilities; the processor 41 can also be a general-purpose processor, DSP (Digital Signal Process), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, among which the general-purpose processor can be a microprocessor or the processor 41 can also be any conventional processor, etc.

[0116] Example 4

[0117] The embodiment of the present invention further provides a computer-readable storage medium, a schematic diagram of which is shown in FIG. Figure 5 As shown, a readable computer program 51 is stored on the storage medium 50; wherein, the computer program 51 can be stored in the above storage medium 50 in the form of a software product, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium 50 includes: U disk, mobile hard disk, magnetic disk or optical disk, ROM (Read-Only Memory), RAM (Random Access Memory) and other media that can store program codes, or terminal devices such as computers, servers, mobile phones, and tablets.

[0118] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0119] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0121] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0122] 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 embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may 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 may be transmitted from a website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0123] The technical solution provided by the present application is introduced in detail above. The principles and implementation methods of the present application are explained by using specific examples in the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0125] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A logistics driver scheduling method, characterized in that: include: Obtain the historical waybills of the point department, which include on-time waybills of the point department drivers, on-time waybills of external drivers, and overtime waybills; The simulated annealing algorithm is used to calculate the task allocation of the historical waybills. In each iterative calculation, the acceptability of the current solution is evaluated based on the objective function constructed according to the cost of the point driver, the cost of the external driver, and the cost of the overtime waybill. The final task allocation plan is used to determine the number of point drivers and obtain the shift scheduling plan until the iteration end condition is met. The construction of the initial solution of iterative calculation is to obtain the waybill after agglomerative clustering processing of the historical waybill according to the distance calculation formula between waybills constructed by time distance and space distance, and then assign tasks to the point drivers and outsourced drivers.

2. The logistics driver scheduling method according to claim 1 is characterized in that: The method of obtaining a waybill after agglomerative clustering of the historical waybill is performed, and then allocating tasks to the point drivers and the external drivers, includes: Merge the two historical waybills with the smallest distance into a new waybill, and repeat the process until all the merged waybills cannot be merged any further; during the merging process, the historical waybills with time conflicts cannot be merged together; The merged waybills that include a preset number of historical waybills will be assigned tasks to the point drivers, and the remaining merged waybills will be assigned tasks to external drivers.

3. The logistics driver scheduling method according to claim 1 or 2, characterized in that: The distance calculation formula between waybills constructed by time distance and space distance includes: d=d S *w1+d T *w2*V Where d is the distance between two waybills, d S is the difference in longitude and latitude between the two waybills, w1 is the weight of the distance, d T is the difference in task start time between the two waybills, w2 is the time weight, and V is the truck running speed.

4. The logistics driver scheduling method according to claim 1, characterized in that: During iterative calculation, the perturbation operator is used to perturb the current solution, and one waybill in the current solution is selected to be assigned to the new driver, thus generating a new solution for task assignment.

5. The logistics driver scheduling method according to claim 1, characterized in that: The objective function constructed based on the cost of drivers at the point, the cost of external drivers and the cost of overtime waybills includes: The formula of the objective function is: Among them, f(t) is the total cost of the point, N is the preset number of days for historical waybill statistics, K is the number of drivers at the point, c1 is the cost of the drivers at the point, and e i is the number of tasks assigned to the external driver on the i-th day, c2 is the cost of the external driver, o i is the number of overtime tasks of the point department on the i-th day, and c3 is the overtime task loss of the point department.

6. The logistics driver scheduling method according to claim 1, characterized in that: When performing task allocation calculation, any of the following constraints must be met: The volume of the cargo on the waybill of each task is smaller than the volume of the driver's vehicle; The customer's required arrival time for each waybill included in each task is earlier than the driver's arrival time at the customer's destination; The weight of the waybill contained in each task is less than the remaining load of the driver's vehicle.

7. The logistics driver scheduling method according to claim 1, characterized in that: The acceptability evaluation of the current solution includes: If the objective function value of the current solution is less than or equal to the objective function value of the last accepted new solution, the current solution is accepted as the new solution; otherwise, the current solution is accepted as the new solution with a certain probability.

8. A logistics driver scheduling device, characterized in that: It includes historical waybill acquisition module, scheduling module and initial solution construction module; The historical waybill acquisition module is used to acquire the historical waybill of the point department, and the historical waybill includes the on-time waybill of the point department driver, the on-time waybill of the external driver and the overtime waybill; The scheduling module is used to perform task allocation calculation on the historical waybills using a simulated annealing algorithm. In each iterative calculation, the current solution is evaluated for acceptability based on the objective function constructed according to the cost of the driver at the point, the cost of the external driver, and the cost of the overtime waybill. The final task allocation plan is used to determine the number of drivers at the point and obtain a scheduling plan until the iteration end condition is met. The initial solution construction module is used to iteratively calculate the initial solution by performing agglomerative clustering processing on the historical waybills according to the distance calculation formula between waybills constructed by time distance and space distance to obtain waybills, and then allocating tasks to point drivers and outsourced drivers.

9. A logistics driver scheduling device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor is used to read the computer program in the memory and execute the steps of the logistics driver scheduling method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A readable computer program is stored thereon, and when the program is executed by a processor, the steps of the logistics driver scheduling method as described in any one of claims 1 to 7 are implemented.

Images