A method and apparatus for determining a driving route of a transport vehicle

Abstract

The application provides a transportation vehicle driving route determination method and device, relates to the big data technical field, and can also be used in the financial field.The method comprises the following steps: determining a driving route initial matrix according to the number of vehicles and the number of to-be-distributed network points; iteratively optimizing the driving route initial matrix according to a pre-constructed distribution time cost analysis model to obtain a driving route optimization matrix; and performing graphical display on the driving route optimization matrix to obtain a vehicle driving route.The application can plan and display the driving route of the transportation vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, and can be used in the financial field, in particular to a transport vehicle driving route determination method and device. BACKGROUND

[0002] With the development of economy, social material exchanges are increasingly close, and the coverage of financial services is increasingly expanding. In a certain scenario, there is a demand for cash delivery between financial service outlets, and the cash transport vehicle emerges as the times require. How to improve the transportation efficiency of the cash transport vehicle and ensure the transportation safety of the cash transport vehicle has become a problem that needs to be considered by the financial service outlet. In order to achieve the above purpose, it is necessary to reasonably plan the driving path of the cash transport vehicle.

[0003] The so-called reasonable driving path planning refers to that when multiple different goods transportation demands exist at the same time, a vehicle is assigned by a goods transportation dispatching center to provide goods transportation service, and a reasonable driving path is determined through algorithm analysis, so that each demand is satisfied under certain constraints, and the shortest transportation path, the lowest cost and the shortest time are achieved.

[0004] With the rise of machine learning (ML) algorithm, neural network models are used in various fields to solve business scenario problems. For example, the prior art adopts a pointer network to solve the driving path planning problem. However, this neural network model-based analysis algorithm often needs to have a certain amount of historical data to train a better usable model. This leads to certain difficulties in actual application deployment, because in real business scenarios, there are often problems such as incomplete historical business data records and very few historical business data, making it difficult to establish a high-quality neural network model.

[0005] Further, the real cash transport vehicle driving path planning scenario often changes due to the morning and evening peak periods of urban traffic, resulting in changes in the delivery time of the cash transport vehicle between financial service outlets. For this time-varying factor, even if a high-quality neural network model is established, it is difficult to handle the impact it brings. Therefore, it is of great significance and value to propose a cash transport vehicle driving path planning scheme that does not need to be based on long-term historical data and can eliminate the influence of time-varying factors. SUMMARY

[0006] In view of the problems in the prior art, the present application provides a transport vehicle driving route determination method and device, which can plan and display the driving route of the transport vehicle.

[0007] To solve the above technical problems, the present application provides the following technical solutions:

[0008] In a first aspect, the application provides a method for determining a driving route of a delivery vehicle, comprising:

[0009] determining an initial matrix of the driving route according to the number of vehicles and the number of delivery points;

[0010] iteratively optimizing the initial matrix of the driving route according to a pre-constructed delivery time cost analysis model to obtain an optimized matrix of the driving route;

[0011] graphically displaying the optimized matrix of the driving route to obtain the driving route of the vehicle.

[0012] Further, the step of constructing the delivery time cost analysis model comprises:

[0013] determining a congestion time cost of each vehicle according to a preset driving route of each vehicle, geographical positions of each delivery point, and historical congestion data of road sections corresponding to the geographical positions;

[0014] determining an early arrival time cost of each vehicle according to a preset earliest delivery time and actual arrival times of each vehicle at the delivery points;

[0015] determining a late arrival time cost of each vehicle according to a preset latest delivery time and the actual arrival times;

[0016] determining a driving time cost consumed by each vehicle when delivering according to a preset driving route according to historical driving data of the preset driving route;

[0017] determining a delivery time cost of each vehicle according to the congestion time cost, the early arrival time cost, the late arrival time cost, and the driving time cost to obtain the delivery time cost analysis model.

[0018] Further, the initial matrix of the driving route comprises a random initial matrix; and the step of determining the initial matrix of the driving route according to the number of vehicles and the number of delivery points comprises:

[0019] randomly clustering the delivery points according to the number of delivery points;

[0020] determining the random initial matrix according to the random clustering result and the number of vehicles.

[0021] Further, the step of iteratively optimizing the initial matrix of the driving route according to the pre-constructed delivery time cost analysis model to obtain an optimized matrix of the driving route comprises:

[0022] iteratively operating the random initial matrix until an iteration operation result meets a first preset stopping condition to stop iteration, and obtaining a first process matrix; the first preset stopping condition is set according to the delivery time cost analysis model.

[0023] determining whether the first process matrix meets a second preset stopping condition;

[0024] If yes, the first process matrix is determined as the driving route optimization matrix.

[0025] Further, the driving route initial matrix includes a geographical initial matrix; and the driving route initial matrix is determined according to the number of vehicles and the number of to-be-delivered network points, including:

[0026] The to-be-delivered network points are clustered according to the number of vehicles, the number of to-be-delivered network points and the geographical positions, to obtain a network point cluster set corresponding to each cluster;

[0027] The network points in the network point cluster set are sorted according to a preset detour strategy, to obtain a driving route corresponding to each cluster;

[0028] The geographical initial matrix is generated according to the driving route and the number of vehicles.

[0029] Further, the driving route initial matrix is iteratively optimized according to a pre-constructed delivery time cost analysis model, to obtain a driving route optimization matrix, including:

[0030] The geographical initial matrix is iteratively operated until the first preset stopping condition is met, and the iteration is stopped, to obtain a second process matrix;

[0031] It is determined whether the second process matrix meets the second preset stopping condition;

[0032] If yes, the second process matrix is determined as the driving route optimization matrix.

[0033] Further, the method for determining a driving route of a transport vehicle further includes:

[0034] The first process matrix and the second process matrix are compared according to the delivery time cost analysis model, and a lower delivery time cost is selected as the driving route optimization matrix.

[0035] Further, after the driving route optimization matrix is obtained, the method further includes:

[0036] The driving route optimization matrix is adjusted by using an insertion operator and a deletion operator in a heuristic algorithm.

[0037] Further, the driving route optimization matrix is adjusted by using an insertion operator and a deletion operator in a heuristic algorithm, including:

[0038] According to the deletion operator and the first execution weight thereof, a deletion operation is performed on a to-be-delivered network point with a relatively far geographical position.

[0039] According to the insertion operator and the second execution weight thereof, an insertion operation is performed on a to-be-delivered network point with a relatively close geographical position, to obtain an adjusted driving route optimization matrix.

[0040] Further, the driving route determination method of the transport vehicle further comprises:

[0041] According to the delivery time cost analysis model, a delivery time cost of the adjusted driving route optimization matrix is calculated.

[0042] If the delivery time cost of the adjusted driving route optimization matrix is lower than that of the driving route optimization matrix before adjustment, the first execution weight and the second execution weight are adjusted.

[0043] In a second aspect, the application provides a driving route determination device of a transport vehicle, comprising:

[0044] An initial matrix generation unit is configured to determine a driving route initial matrix according to the number of vehicles and the number of to-be-delivered network points.

[0045] An optimization matrix generation unit is configured to perform iterative optimization on the driving route initial matrix according to a pre-constructed delivery time cost analysis model, to obtain a driving route optimization matrix.

[0046] A driving route display unit is configured to perform graphical display on the driving route optimization matrix, to obtain a vehicle driving route.

[0047] Further, the driving route determination device of the transport vehicle further comprises:

[0048] A congestion time cost determination unit is configured to determine a congestion time cost of each vehicle according to a preset driving route of each vehicle, geographical positions of each to-be-delivered network point, and historical congestion data of a road section corresponding to the geographical positions.

[0049] An early arrival time cost determination unit is configured to determine an early arrival time cost of each vehicle according to a preset earliest delivery time and an actual time of each vehicle to arrive at each to-be-delivered network point.

[0050] A late arrival time cost determination unit is configured to determine a late arrival time cost of each vehicle according to a preset latest delivery time and the actual time.

[0051] A driving time cost determination unit is configured to determine a driving time cost consumed by each vehicle when performing delivery according to a preset driving route, according to historical driving data of the preset driving route.

[0052] The cost analysis model generating unit is configured to determine a delivery time cost of each vehicle according to the congestion time cost, the early arrival time cost, the late arrival time cost and the driving time cost, so as to obtain the delivery time cost analysis model.

[0053] Further, the driving route initial matrix includes a random initial matrix, and the initial matrix generating unit includes:

[0054] The random clustering module is configured to perform random clustering on the to-be-delivered network points according to the number of to-be-delivered network points.

[0055] The random initial matrix generating module is configured to determine the random initial matrix according to the random clustering result and the number of vehicles.

[0056] Further, the optimization matrix generating unit includes:

[0057] The first process matrix generating module is configured to perform iterative operation on the random initial matrix until the iterative operation result meets a first preset stop condition, so as to stop iteration and obtain a first process matrix; the first preset stop condition is set according to the delivery time cost analysis model.

[0058] The first stop judging module is configured to determine whether the first process matrix meets a second preset stop condition.

[0059] The first optimization matrix generating module is configured to determine the first process matrix as the driving route optimization matrix.

[0060] Further, the driving route initial matrix includes a geographic initial matrix, and the initial matrix generating unit includes:

[0061] The network point clustering module is configured to cluster the to-be-delivered network points according to the number of vehicles, the number of to-be-delivered network points and the geographic position, so as to obtain a network point clustering set corresponding to each cluster.

[0062] The driving route setting module is configured to sort network points in the network point clustering set according to a preset detour strategy, so as to obtain a driving route corresponding to each cluster.

[0063] The geographic initial matrix generating module is configured to generate the geographic initial matrix according to the driving route and the number of vehicles.

[0064] Further, the optimization matrix generating unit includes:

[0065] The second process matrix generating module is configured to perform iterative operation on the geographic initial matrix until the first preset stop condition is met, so as to stop iteration and obtain a second process matrix.

[0066] The second stop judgment module is configured to determine whether the second process matrix satisfies the second preset stop condition.

[0067] The second optimization matrix generation module is configured to determine the second process matrix as the driving route optimization matrix.

[0068] Further, the driving route determination device for the transport vehicle further comprises:

[0069] The process matrix selection unit is configured to select, according to the delivery time cost analysis model, the first process matrix and the second process matrix, and select the one with lower delivery time cost as the driving route optimization matrix.

[0070] Further, the driving route determination device for the transport vehicle further comprises:

[0071] The operator adjustment unit is configured to adjust the driving route optimization matrix by using the insertion operator and the deletion operator in the heuristic algorithm.

[0072] Further, the driving route determination device for the transport vehicle, the operator adjustment unit comprises:

[0073] The deletion module is configured to perform a deletion operation on the to-be-delivered network points with a relatively far geographical position according to the deletion operator and the first execution weight thereof;

[0074] The insertion module is configured to perform an insertion operation on the to-be-delivered network points with a relatively close geographical position according to the insertion operator and the second execution weight thereof, to obtain an adjusted driving route optimization matrix.

[0075] Further, the driving route determination device for the transport vehicle further comprises:

[0076] The time cost redefinition unit is configured to calculate the delivery time cost of the adjusted driving route optimization matrix according to the delivery time cost analysis model;

[0077] The execution weight adjustment unit is configured to adjust the first execution weight and the second execution weight if the delivery time cost of the adjusted driving route optimization matrix is lower than the delivery time cost of the driving route optimization matrix before adjustment.

[0078] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the driving route determination method for the transport vehicle.

[0079] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executable on a processor to implement the steps of the driving route determination method for the transport vehicle.

[0080] In a fifth aspect, the present application provides a computer program product comprising computer programs / instructions which, when executed by a processor, implement the steps of the method for determining a driving route of a transport vehicle.

[0081] To solve the problems in the prior art, the method and device for determining a driving route of a transport vehicle provided by the present application establish a mathematical model by improving a heuristic algorithm, and solve the problem of insufficient consideration of time-varying factors and unsatisfactory planning effect in neural network models and traditional heuristic algorithms by adding a time penalty cost to the mathematical model, thereby achieving planning of a route of a transport vehicle in the absence of historical data and improving the transport efficiency of the transport vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0083] Figure 1 FIG. 1 is a flowchart of a method for determining a driving route of a transport vehicle according to an embodiment of the present application;

[0084] Figure 2 FIG. 2 is a flowchart of a step of constructing a delivery time cost analysis model according to an embodiment of the present application;

[0085] Figure 3 FIG. 3 is a flowchart of a step of determining an initial matrix of a driving route according to an embodiment of the present application;

[0086] Figure 4 FIG. 4 is a flowchart of a step of generating an optimized matrix of a driving route according to an embodiment of the present application;

[0087] Figure 5 FIG. 5 is a flowchart of a step of determining an initial matrix of a driving route according to an embodiment of the present application;

[0088] Figure 6 FIG. 6 is a flowchart of a step of generating an optimized matrix of a driving route according to an embodiment of the present application;

[0089] Figure 7 FIG. 7 is a flowchart of a step of adjusting an optimized matrix of a driving route according to an embodiment of the present application;

[0090] Figure 8 FIG. 8 is a flowchart of a method for determining a driving route of a transport vehicle according to an embodiment of the present application;

[0091] Figure 9Figure 1 is a structural diagram of a vehicle driving route determination device according to an embodiment of the present application;

[0092] Figure 10 Figure 2 is a structural diagram of a vehicle driving route determination device according to another embodiment of the present application;

[0093] Figure 11 Figure 3 is a structural diagram of an initial matrix generation unit according to an embodiment of the present application;

[0094] Figure 12 Figure 4 is a structural diagram of an optimized matrix generation unit according to an embodiment of the present application;

[0095] Figure 13 Figure 5 is a structural diagram of an initial matrix generation unit according to another embodiment of the present application;

[0096] Figure 14 Figure 6 is a structural diagram of an optimized matrix generation unit according to another embodiment of the present application;

[0097] Figure 15 Figure 7 is a structural diagram of an operator adjustment unit according to an embodiment of the present application;

[0098] Figure 16 Figure 8 is a structural diagram of a vehicle driving route determination device according to another embodiment of the present application;

[0099] Figure 17 Figure 9 is a structural diagram of an electronic device according to an embodiment of the present application;

[0100] Figure 18 Figure 10 is a graphical display of a driving route optimization matrix according to an embodiment of the present application. DETAILED DESCRIPTION

[0101] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0102] It should be noted that the vehicle driving route determination method and device provided by the present application can be used in the financial field, and can also be used in any field other than the financial field. The application field of the vehicle driving route determination method and device provided by the present application is not limited.

[0103] With economic development, there is a demand for cash transportation between financial service outlets. In order to safely deliver cash to the financial service outlets as soon as possible, the driving path of the cash transport vehicle needs to be reasonably planned. The method for planning the driving path of the cash transport vehicle in the prior art often has problems such as lack of historical business data, which makes it difficult to establish a neural network model for planning the driving path. Even if the model is established, various time-varying factors in the actual business scenario will greatly reduce the prediction effect of the model. In order to solve the problems existing in the prior art, the application provides a method and device for determining the driving route of a transport vehicle.

[0104] In an embodiment, referring to Figure 1 In order to be able to plan and display the driving route of the transport vehicle, the application provides a method for determining the driving route of a transport vehicle, which includes the following steps:

[0105] S101: determining a driving route initial matrix according to the number of vehicles and the number of to-be-distributed outlets;

[0106] S102: iteratively optimizing the driving route initial matrix according to a pre-constructed distribution time cost analysis model to obtain a driving route optimization matrix;

[0107] S103: graphically displaying the driving route optimization matrix to obtain the driving route of the vehicle.

[0108] It can be understood that the method for determining the driving route of a transport vehicle provided by the application can be applied to various transport vehicles in various industries, and the following will only be described and explained by taking the cash transport vehicle in the financial field as an example, but the application is not limited thereto.

[0109] In the driving route planning scenario of the cash transport vehicle, the method provided by the application can establish a distribution time cost analysis model according to the number of cash transport vehicles, the number, geographical location and distribution demand of the financial service outlets (also referred to as to-be-distributed outlets). Then, the initial driving route of each cash transport vehicle is optimized by using the model. The initial driving route of each cash transport vehicle is stored in the driving route initial matrix. The driving route initial matrix can be iteratively optimized to obtain a driving route optimization matrix. The driving route optimization matrix is used to store the driving route of the optimized cash transport vehicle. Finally, the driving route optimization matrix of each cash transport vehicle is graphically displayed to visualize the driving route of the cash transport vehicle.

[0110] When establishing the distribution time cost analysis model, the method provided by the application fully considers various factors such as time penalty cost and service substandard penalty cost, thereby solving the problem that the existing neural network model and traditional heuristic algorithm have insufficient consideration of time-varying factors and the calculation effect is not ideal when calculating the driving route.

[0111] In an embodiment, referring to Figure 2The steps of constructing the delivery time cost analysis model include:

[0112] S201: determining congestion time costs of each vehicle according to preset driving routes of each vehicle, geographical positions of each to-be-delivered network point, and historical congestion data of the geographical positions corresponding to road sections;

[0113] S202: determining early arrival time costs of each vehicle according to preset earliest delivery time and actual times of each vehicle arriving at each to-be-delivered network point;

[0114] S203: determining late arrival time costs of each vehicle according to preset latest delivery time and actual times;

[0115] S204: determining driving time costs consumed by each vehicle when delivery is performed according to preset driving routes according to historical driving data of the preset driving routes;

[0116] S205: determining delivery time costs of each vehicle according to the congestion time costs, the early arrival time costs, the late arrival time costs, and the driving time costs, to obtain a delivery time cost analysis model.

[0117] Specifically, the delivery time cost analysis model in the embodiment of the application is as follows:

[0118] Delivery time cost = vehicle driving time cost (corresponding to step S204) + early arrival time cost (corresponding to step S202) + late arrival time cost (corresponding to step S203) + congestion penalty cost (corresponding to step S201).

[0119] The mathematical language is expressed as:

[0120]

[0121] Wherein, α, β and δ are weight coefficients;

[0122] V represents a set of all to-be-delivered network points;

[0123] K represents a set of all transport vehicles;

[0124] x ijk = 1 indicates that the kth vehicle is from the ith network point to the jth network point;

[0125] x ijk = 0 indicates that the kth vehicle is not from the ith network point to the jth network point;

[0126] Q i , P i respectively represent an upper limit (also referred to as earliest arrival time) and a lower limit (also referred to as latest arrival time) of a service time window of the ith network point;

[0127] t kiis the true time of the kth vehicle arriving at the i-th node;

[0128] C k is the congestion penalty cost of the kth vehicle;

[0129] d ij (t) represents the running distance (time) between the i-th and j-th nodes, the value of which is related to the time at which the vehicle runs between the i-th and j-th nodes, and the specific configuration method is to determine according to the position of the i-th and j-th nodes in the departure sequence (or the departure time of the i-->j route).

[0130] Example 1:

[0131]

[0132] d ij (t) can be the above function. In the 0th to 120th minute time period, the traffic is relatively congested. The vehicle travel time in the 0th to 30th minute time period is 1.5 times that in the 120th to 180th minute time period, the vehicle travel time in the 30th to 90th minute time period is 2 times that in the 120th to 180th minute time period, and the vehicle travel time in the 90th to 120th minute time period is 1.5 times that in the 120th to 180th minute time period.

[0133] Example 2:

[0134]

[0135] d ij (t) can be the above function. The vehicle travel time in the 0th to 30th minute time period is W ij , the vehicle travel time in the 30th to 90th minute time period is X ij , the vehicle travel time in the 90th to 120th minute time period is Y ij , and the vehicle travel time in the 120th to 180th minute time period is Z ij .

[0136] It should be noted that the congestion time cost of each vehicle is closely related to the preset driving route of each vehicle, the geographical position of each to-be-delivered network point, and the road section corresponding to the geographical position; wherein, the preset driving route can be stored in the driving route initial matrix and / or the driving route optimization matrix, and each row (also referred to as a row vector) in the matrix represents a to-be-delivered network point to be successively arrived at by a cash transport vehicle. Therefore, according to each row vector of the driving route initial matrix and / or the driving route optimization matrix, the to-be-delivered network point responsible for by the cash transport vehicle corresponding to the row vector can be determined; these to-be-delivered network points correspond to the preset driving route. On this basis, in combination with the digital map, the geographical position of the to-be-delivered network point and the road section corresponding to the geographical position can be determined, and then the congestion time cost of the cash transport vehicle is determined through historical congestion data (such as obtained by using Big Data technology).

[0137] For example, the driving route initial matrix / driving route optimization matrix is as follows:

[0138] In the cash transport vehicle route planning of N cash transport vehicles and M to-be-delivered network points, the cash transport vehicle route is represented as an N*M matrix. Taking 4 cash transport vehicles and 50 to-be-delivered network points as an example, the matrix is specifically as follows:

[0139] cars_list=[

[0140] [1,3,5,7,8,9,13,16,18,23,29,47,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1],

[0141] [2,4,6,10,14,15,19,40,41,42,45,46,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1],

[0142] [11,12,17,20,21,25,30,31,32,34,35,36,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1],

[0143] [22,24,26,27,28,33,37,38,39,43,44,48,49,50,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1] ]

[0145] Each row (also called a row vector) corresponds to the route of an armored truck. The truck needs to travel along this route from left to right, delivering cash to the various distribution points along the route. Let the number of the cash center be 0, and the other numbers represent the distribution points.

[0146] For example:

[0147] The location numbers corresponding to the driving route [1,3,5,7,8,9,13,16,18,23,29,47,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1] are:

[0148] 0->1->3->5->7->8->9->13->16->18->23->29->49->0

[0149] The -1 added at the end is to ensure that the number of elements in each row is the same.

[0150] Similarly, when delivering goods according to a preset route, the driving time cost of each vehicle is also closely related to the preset route; similarly, the driving time cost of each vehicle can be determined by historical driving data (such as by using Big Data technology).

[0151] As can be seen from the above description, the method for determining the driving route of transport vehicles provided in this application can establish a mathematical model by improving the heuristic algorithm, and solve the problem that the neural network model and the traditional heuristic algorithm do not consider time-varying factors enough and the planning effect is not ideal by adding time penalty cost to the mathematical model. Thus, it can plan the route of transport vehicles in the absence of historical data and improve the transportation efficiency of transport vehicles.

[0152] In one embodiment, see Figure 3The initial route matrix includes: a random initial matrix; and an initial route matrix determined according to the number of vehicles and the number of to-be-delivered sites, including:

[0153] S301: randomly clustering the to-be-delivered sites according to the number of to-be-delivered sites;

[0154] S302: determining a random initial matrix according to the random clustering result and the number of vehicles.

[0155] It can be understood that, in this embodiment, the initial route matrix is a random initial matrix, that is, the to-be-delivered sites are randomly clustered, and the specific allocation method can use a random clustering algorithm, including but not limited to a partition-based clustering method, a density-based clustering method, and a hierarchical clustering method.

[0156] For example, in an actual business scenario, the demand time of cash delivery can be clustered according to the number of to-be-delivered sites, but the present application is not limited thereto. Assuming that the transportation task is undertaken by R cash transport vehicles, the to-be-delivered sites are then clustered into R classes, and then each cash transport vehicle is randomly allocated a class (corresponding to a driving route).

[0157] From the above description, it can be seen that the method for determining a driving route of a transportation vehicle provided by the present application can determine an initial route matrix of a driving route according to the number of vehicles and the number of to-be-delivered sites.

[0158] In an embodiment, referring to Figure 4 The initial route matrix is iteratively optimized according to a pre-constructed delivery time cost analysis model to obtain an optimized route matrix, including:

[0159] S401: iteratively operating the random initial matrix until the iteration operation result meets a first preset stop condition to stop iteration, and obtaining a first process matrix; the first preset stop condition is set according to the delivery time cost analysis model;

[0160] S402: determining whether the first process matrix meets a second preset stop condition;

[0161] S403: if yes, determining the first process matrix as the optimized route matrix.

[0162] It can be understood that the purpose of the iteration operation method in the embodiment of the present application is to optimize the initial route matrix. The iteration operation method can be implemented by using a simulated annealing algorithm, and the steps are as follows:

[0163] Step 1: select an initial solution (also called initial matrix of driving route) cars_list_0; let current solution cars_list_i = cars_list_0; current iteration step k = 0; current temperature t k = t max .

[0164] Step 2: if the temperature reaches the inner loop stop condition, go to Step 3; otherwise, randomly select a neighbor cars_list_j from the neighborhood N(cars_list_i), calculate Δf = f(cars_list_i) - f(cars_list_j), if Δf < 0, then cars_list_i = cars_list_j, otherwise, if exp(-Δf / t k ) > random(0,1), then cars_list_i = cars_list_j, repeat Step 2.

[0165] Step 3: k = k + 1, t k+i = d(t k ) (indicates the function of temperature drop), if the termination condition is met, go to Step 4; otherwise, go to Step 2.

[0166] Step 4: output the calculation result and stop.

[0167] In the above simulated annealing algorithm, there is an inner loop and an outer loop. The inner loop is Step 2, which represents random search within some states at the same temperature t. The outer loop mainly includes the temperature drop change t k+i = d(t k ) in Step 3, the increase of iteration step k = k + 1 and the stop condition, etc.

[0168] Where Δf = f(cars_list_i) - f(cars_list_j) is the "first preset stop condition" in Step S401, also called "inner loop stop condition". The f function is the distribution time cost analysis model, see Steps S201 to S205. Inputting the cars_list_i matrix into the distribution time cost analysis model can get f(cars_list_i); inputting the cars_list_j matrix into the distribution time cost analysis model can get f(cars_list_j).

[0169] In addition, how to select neighbors and how to iterate can refer to existing simulated annealing algorithms.

[0170] The driving route optimization matrix can be obtained by the above method.

[0171] From the above description, the transportation vehicle driving route determination method provided by the application can iteratively optimize the driving route initial matrix according to the pre-constructed distribution time cost analysis model to obtain the driving route optimization matrix.

[0172] In an embodiment, referring to Figure 5 The driving route initial matrix includes a geographical initial matrix; the driving route initial matrix is determined according to the number of vehicles and the number of to-be-distributed network points, and includes:

[0173] S501: clustering the to-be-distributed network points according to the number of vehicles, the number of to-be-distributed network points and geographical positions to obtain a network point clustering set corresponding to each cluster;

[0174] S502: sorting the network points in the network point clustering set according to a preset detour strategy to obtain a driving route corresponding to each cluster;

[0175] S503: generating the geographical initial matrix according to the driving route and the number of vehicles.

[0176] It can be understood that in this embodiment, the driving route initial matrix is the geographical initial matrix, that is, the driving path of each armored car needs to be allocated according to the geographical position of each to-be-distributed network point, and the to-be-distributed network points in the same geographical position are arranged in the same armored car as much as possible to save transportation costs. As described above, the application does not limit the specific clustering method. For example, in an embodiment, the k-means clustering algorithm can be selected to cluster the to-be-distributed network points according to their geographical positions.

[0177] After clustering, the detour order between network points of the same type also needs to be considered. In this embodiment, the network points in the same cluster (also referred to as the same network point clustering set) can be sorted according to a preset detour strategy to obtain a driving route corresponding to each cluster. For example, the detour strategy can be a from-far-to-near ring strategy.

[0178] Finally, for a transportation vehicle fleet consisting of R armored cars, the to-be-distributed network points need to be clustered into R clusters, and then each armored car is allocated a cluster (corresponding to a driving route).

[0179] The main difference between this embodiment and the "random initial matrix" embodiment is the principle of clustering. The "random initial matrix" is randomly clustered, and this embodiment is clustered according to geographical positions.

[0180] From the above description, the transportation vehicle driving route determination method provided by the application can iteratively optimize the driving route initial matrix according to the pre-constructed distribution time cost analysis model to obtain the driving route optimization matrix.

[0181] In an embodiment, referring to Figure 6According to the pre-constructed distribution time cost analysis model, the initial matrix of the driving route is iteratively optimized to obtain an optimized matrix of the driving route, including:

[0182] S601: Iterative operation is performed on the geographical initial matrix until a first preset stopping condition is met, and the iterative operation is stopped to obtain a second process matrix;

[0183] S602: It is determined whether the second process matrix meets a second preset stopping condition;

[0184] S603: If yes, the second process matrix is determined as the optimized matrix of the driving route.

[0185] It can be understood that the iterative operation method is named as the SA-Adapt algorithm in the embodiment. It is considered that starting from the cash center, the service of each to-be-distributed point has a certain service time, in order to fully utilize the traffic off-peak period and avoid the traffic peak period, the driving route of the embodiment first skips several points close to the cash center, takes the point with a moderate distance (not close nor far) from the cash center as the first distribution point, and then according to the classic strategy of surrounding from near to far, starts from the farthest point to fold back, and finally visits the point close to the cash center.

[0186] In order to achieve the above effect, the initial matrix of the driving route used in the embodiment is a geographical initial matrix. The iterative operation method is the same as the method of steps S401 to S403, and the only difference is that the initial solution cars_list_0 in the first step is the geographical initial matrix. The subsequent steps are not described again.

[0187] As can be known from the above description, the method for determining the driving route of the transport vehicle can iteratively optimize the initial matrix of the driving route according to the pre-constructed distribution time cost analysis model to obtain an optimized matrix of the driving route.

[0188] In an embodiment, the method for determining the driving route of the transport vehicle further includes:

[0189] According to the distribution time cost analysis model, the first process matrix and the second process matrix are compared, and the one with lower distribution time cost is selected as the optimized matrix of the driving route.

[0190] In an embodiment, after obtaining the optimized matrix of the driving route, the method further includes:

[0191] The optimized matrix of the driving route is adjusted by using the insertion operator and the deletion operator in the heuristic algorithm.

[0192] In an embodiment, referring to Figure 7, the insertion operator and the deletion operator in the heuristic algorithm are used to adjust the driving route optimization matrix, including:

[0193] S701: According to the deletion operator and the first execution weight thereof, a deletion operation is performed on the to-be-delivered network points with a relatively far geographical position;

[0194] S702: According to the insertion operator and the second execution weight thereof, an insertion operation is performed on the to-be-delivered network points with a relatively close geographical position, to obtain an adjusted driving route optimization matrix.

[0195] It can be understood that the embodiment is realized by improving the ALNS algorithm. In the embodiment, there are two types of operators, namely, destroy operators and repair operators, which are “node deletion operators” and “node insertion operators” in the driving route planning scenario. The node deletion operators include two types of operators, namely, a geographical position deletion operator and a general deletion operator. The node insertion operators include two types of operators, namely, a geographical position insertion operator and a general insertion operator. The geographical position operator will consider the latitude and longitude distance or driving distance between the delivery points.

[0196] For example:

[0197] In an embodiment, the node deletion operators are three, namely, D 普通 , D 经纬度距离 , and D 行车距离 . D 普通 corresponds to unlimited node deletion, D 经纬度距离 corresponds to node deletion with a limited latitude and longitude distance less than a threshold Y 经纬度距离 , and D 行车距离 corresponds to node deletion with a limited driving distance less than a threshold Y 行车距离 . The function of the node deletion operator is to randomly select a route or a delivery point and delete it.

[0198] Similarly, the node insertion operators are also three, namely, I 普通 , I 经纬度距离 , and I 行车距离 . I 普通 corresponds to unlimited node insertion, I 经纬度距离 corresponds to node insertion with a limited latitude and longitude distance less than a threshold Y 经纬度距离 , and I 行车距离 corresponds to node insertion with a limited driving distance less than a threshold Y 行车距离 . The function of the node insertion operator is to randomly select a route and insert the delivery point deleted by the “node deletion operator” at a random point sequence position.

[0199] Algorithm running steps:

[0200] 1. Provide a initialization plan car_list, and initialize the weight p. Where the weight p can be seen as two categories, respectively, the weight p of the node deletion operator D (contains p D普通 , p D经纬度距离 , p D行车距离 ) and the weight p of the node insertion operator I . All p will be initialized to 1.

[0201] 2. Improved ALNS algorithm loop

[0202] a) According to the weight p D , select the node deletion operator, and according to the weight p i , select the node insertion operator. Specifically, a random number X between [0, 1] is randomly selected.

[0203] · When X is less than or equal to , select D 普通 ,

[0204] · When X does not meet the above condition and is less than or equal to , select D 经纬 degree distance

[0205] · When X does not meet the above condition and is less than or equal to , select D 行车距离

[0206] b) Execute the node deletion operator and the node insertion operator to get a new plan new_car_list.

[0207] c) Step C is consistent with the method of evaluating the plan in the second step of the SA-Adapt algorithm. If new_car_list is better than car_list, then car_list = new_car_list, otherwise a random number X between [0, 1] is randomly selected, and X is higher than the threshold value, then car_list = new_car_list.

[0208] d) Repeat the above a, b, c steps until a certain stopping condition is reached (specifically, the number of iterations can reach 1000 rounds or car_list is not optimized in 20 iterations).

[0209] The transport vehicle driving route determination method provided by the application can adjust the driving route optimization matrix by using the insertion operator and the deletion operator in the heuristic algorithm.

[0210] In an embodiment, referring to Figure 8 , the transport vehicle driving route determination method further comprises:

[0211] S801: Calculate the delivery time cost of the adjusted driving route optimization matrix according to the delivery time cost analysis model;

[0212] S802: If the delivery time cost of the adjusted driving route optimization matrix is lower than the delivery time cost of the unadjusted driving route optimization matrix, adjust the first execution weight and the second execution weight.

[0213] Finally, referring to Figure 18 When the driving route optimization matrix is established, the driving route optimization matrix can be graphically displayed to obtain the vehicle driving route.

[0214] 1. Query the geographic location of the to-be-delivered network point. Call the map service according to the address of the to-be-delivered network point to query the latitude and longitude of each to-be-delivered network point, and draw the position of each point in the way according to the position relationship information of the to-be-delivered network point.

[0215] 2. Route planning display. Analyze the driving route optimization matrix, and draw the route sequence of each vehicle with solid lines of different colors.

[0216] The route display diagram will ignore the actual travel route between each two network points, and directly connect the routes between each two network points. Simplify the complexity of route display and improve readability.

[0217] From the above description, it can be seen that the transport vehicle driving route determination method and device provided by the application establish a mathematical model by improving the heuristic algorithm, and solve the problem of insufficient consideration of time-varying factors and unsatisfactory planning effect in the neural network model and the traditional heuristic algorithm by adding a time penalty cost in the mathematical model, thereby realizing the planning of the route of the transport vehicle in the case of lack of historical data, and improving the transport efficiency of the transport vehicle.

[0218] Based on the same inventive concept, the embodiments of the application also provide a vehicle driving route determination device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving problems of the vehicle driving route determination device is similar to that of the transport vehicle driving route determination method, the implementation of the vehicle driving route determination device can be referred to the implementation of the software performance benchmark determination method, and the repeated parts will not be described again. The term "unit" or "module" used below can be a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and is conceived.

[0219] In an embodiment, referring to Figure 9In order to be able to plan and show the driving route of the transport vehicle, the application provides a transport vehicle driving route determination device, comprising: an initial matrix generating unit 901, an optimized matrix generating unit 902 and a driving route showing unit 903.

[0220] The initial matrix generating unit 901 is used for determining a driving route initial matrix according to the number of vehicles and the number of to-be-delivered network points;

[0221] The optimized matrix generating unit 902 is used for iteratively optimizing the driving route initial matrix according to a pre-constructed delivery time cost analysis model to obtain a driving route optimized matrix;

[0222] The driving route showing unit 903 is used for graphically showing the driving route optimized matrix to obtain a vehicle driving route.

[0223] In an embodiment, referring to Figure 10 The transport vehicle driving route determination device further comprises a congestion time cost determining unit 1001, an early arrival time cost determining unit 1002, a late arrival time cost determining unit 1003, a driving time cost determining unit 1004 and a cost analysis model generating unit 1005.

[0224] The congestion time cost determining unit 1001 is used for determining the congestion time cost of each vehicle according to the preset driving route of each vehicle, the geographical position of each to-be-delivered network point and the historical congestion data of the road section corresponding to the geographical position;

[0225] The early arrival time cost determining unit 1002 is used for determining the early arrival time cost of each vehicle according to the preset earliest delivery time and the actual time of each vehicle to arrive at the to-be-delivered network points;

[0226] The late arrival time cost determining unit 1003 is used for determining the late arrival time cost of each vehicle according to the preset latest delivery time and the actual time;

[0227] The driving time cost determining unit 1004 is used for determining the driving time cost consumed by each vehicle when delivering according to the preset driving route according to the historical driving data of the preset driving route;

[0228] The cost analysis model generating unit 1005 is used for determining the delivery time cost of each vehicle according to the congestion time cost, the early arrival time cost, the late arrival time cost and the driving time cost to obtain the delivery time cost analysis model.

[0229] In an embodiment, referring to Figure 11The transport vehicle driving route determination apparatus, the driving route initial matrix comprises: a random initial matrix; the initial matrix generation unit 901 comprises: a random clustering module 1101 and a random initial matrix generation module 1102.

[0230] The random clustering module 1101 is used for randomly clustering the to-be-delivered network points according to the number of to-be-delivered network points.

[0231] The random initial matrix generation module 1102 is used for determining the random initial matrix according to the random clustering result and the number of vehicles.

[0232] In an embodiment, referring to Figure 12 The transport vehicle driving route determination apparatus, the optimization matrix generation unit 902 comprises: a first process matrix generation module 1201, a first stop judgment module 1202 and a first optimization matrix generation module 1203.

[0233] The first process matrix generation module 1201 is used for performing iterative operation on the random initial matrix until the iterative operation result meets a first preset stop condition to stop iteration, and obtaining a first process matrix; the first preset stop condition is set according to the delivery time cost analysis model.

[0234] The first stop judgment module 1202 is used for determining whether the first process matrix meets a second preset stop condition.

[0235] The first optimization matrix generation module 1203 is used for determining the first process matrix as the driving route optimization matrix.

[0236] In an embodiment, referring to Figure 13 The driving route initial matrix comprises: a geographical initial matrix; the initial matrix generation unit 901 comprises: a network point clustering module 1301, a driving route setting module 1302 and a geographical initial matrix generation module 1303.

[0237] The network point clustering module 1301 is used for clustering the to-be-delivered network points according to the number of vehicles, the number of to-be-delivered network points and the geographical positions, to obtain a network point clustering set corresponding to each cluster;

[0238] The driving route setting module 1302 is used for sorting network points in the network point clustering set according to a preset detour strategy, to obtain a driving route corresponding to each cluster.

[0239] The geographical initial matrix generation module 1303 is used for generating the geographical initial matrix according to the driving route and the number of vehicles.

[0240] In an embodiment, referring to Figure 14The optimization matrix generating unit 902 comprises a second process matrix generating module 1401, a second stop judging module 1402, and a second optimization matrix generating module 1403.

[0241] The second process matrix generating module 1401 is configured to perform iterative operation on the geographic initial matrix until the first preset stop condition is met and the iteration is stopped, so as to obtain a second process matrix.

[0242] The second stop judging module 1402 is configured to determine whether the second process matrix meets the second preset stop condition.

[0243] The second optimization matrix generating module 1403 is configured to determine the second process matrix as the driving route optimization matrix.

[0244] In an embodiment, the driving route determining device of the transport vehicle further comprises:

[0245] A process matrix selecting unit is configured to compare the first process matrix and the second process matrix according to the distribution time cost analysis model, and select the one with lower distribution time cost as the driving route optimization matrix.

[0246] In an embodiment, the driving route determining device of the transport vehicle further comprises:

[0247] An operator adjusting unit is configured to adjust the driving route optimization matrix by using an insertion operator and a deletion operator in the heuristic algorithm.

[0248] In an embodiment, referring to Figure 15 The operator adjusting unit comprises a deletion module 1501 and an insertion module 1502.

[0249] The deletion module 1501 is configured to perform a deletion operation on the distribution points with far geographic positions according to the deletion operator and the first execution weight thereof.

[0250] The insertion module 1502 is configured to perform an insertion operation on the distribution points with close geographic positions according to the insertion operator and the second execution weight thereof, so as to obtain an adjusted driving route optimization matrix.

[0251] In an embodiment, referring to Figure 16 The driving route determining device of the transport vehicle further comprises a time cost resetting unit 1601 and an execution weight adjusting unit 1602.

[0252] The time cost resetting unit 1601 is configured to calculate the distribution time cost of the adjusted driving route optimization matrix according to the distribution time cost analysis model.

[0253] The execution weight adjusting unit 1602 is configured to adjust the first execution weight and the second execution weight if the delivery time cost of the adjusted route optimization matrix is lower than the delivery time cost of the route optimization matrix before adjustment.

[0254] From the hardware level, in order to be able to plan and display the driving route of the transport vehicle, the present application provides an embodiment of an electronic device for implementing all or part of the contents of the transport vehicle driving route determination method, which specifically includes the following contents:

[0255] A processor (Processor), a memory (Memory), a communications interface (Communications Interface) and a bus; wherein the processor, the memory, the communications interface complete the communication among each other through the bus; the communications interface is used to realize the information transmission between the vehicle driving route determination device and the core business system, the user terminal and the related database and other related devices; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., and the embodiment is not limited thereto. In the embodiment, the logic controller can be implemented with reference to the embodiments of the transport vehicle driving route determination method and the embodiments of the vehicle driving route determination device, the contents of which are incorporated herein, and the repeated parts will not be described again.

[0256] It can be understood that the user terminal can include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. The smart wearable device can include smart glasses, a smart watch, a smart bracelet, etc.

[0257] In actual application, part of the transport vehicle driving route determination method can be executed on the electronic device as described above, or all operations can be completed in the client device. Specifically, the selection can be made according to the processing capacity of the client device and the limitation of the user's use scenario, etc. The present application does not limit this. If all operations are completed in the client device, the client device can further include a processor.

[0258] The above-mentioned client device can have a communication module (i.e. a communication unit) and can be communicatively connected with a remote server to realize the data transmission with the server. The server can include a server of the task scheduling center side, and the server of the intermediate platform side can also be included in other implementation scenarios, such as the server of the third-party server platform communicatively connected with the server of the task scheduling center. The server can include a single computer device, or a server cluster composed of multiple servers, or a server structure of a distributed device.

[0259] Figure 17 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that the configuration shown in Figure 17 is exemplary; other types of configurations can also be used to supplement or replace the configuration to implement telecommunication functions or other functions. Figure 17

[0260] In an embodiment, the vehicle driving route determination method function can be integrated into the central processor 9100. The central processor 9100 can be configured to control as follows:

[0261] S101: determining a driving route initial matrix according to the number of vehicles and the number of to-be-delivered network points;

[0262] S102: iteratively optimizing the driving route initial matrix according to a pre-constructed delivery time cost analysis model to obtain a driving route optimization matrix;

[0263] S103: graphically displaying the driving route optimization matrix to obtain a vehicle driving route.

[0264] From the above description, it can be seen that the vehicle driving route determination method and device provided by the present application solves the problem of insufficient consideration of time-varying factors and unsatisfactory planning effect in neural network models and traditional heuristic algorithms by improving the heuristic algorithm to establish a mathematical model and adding a time penalty cost in the mathematical model, thereby realizing planning of the route of the transport vehicle in the absence of historical data and improving the transport efficiency of the transport vehicle.

[0265] In another embodiment, the vehicle driving route determination device can be configured separately from the central processor 9100, for example, the data composite transmission device vehicle driving route determination device can be configured as a chip connected to the central processor 9100 to realize the function of the transport vehicle driving route determination method through the control of the central processor.

[0266] As shown in Figure 17 , the electronic device 9600 can further include a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily include all the components shown in Figure 17 ; in addition, the electronic device 9600 can also include components not shown in Figure 17 , which can be referred to the prior art.

[0267] As shown in Figure 17 ​As shown, the central processing unit 9100, which is sometimes also referred to as a controller or operation control, can include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of the various components of the electronic device 9600.

[0268] The memory 9140, for example, can be one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. Information relating to failures can be stored, and in addition, programs for executing the information can be stored. The central processing unit 9100 can execute the programs stored in the memory 9140 to achieve information storage or processing, etc.

[0269] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and text. The display can be, for example, an LCD display, but is not limited thereto.

[0270] The memory 9140 can be a solid state memory such as a read only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROM, etc. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 can include an application / function storage section 9142 for storing application programs and function programs or for storing a flow for executing the operation of the electronic device 9600 by the central processing unit 9100.

[0271] The memory 9140 can also include a data storage section 9143 for storing data such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. A driver program storage section 9144 of the memory 9140 can include various driver programs of the electronic device for communication functions and / or for performing other functions of the electronic device (e.g., a messaging application, an address book application, etc.).

[0272] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0273] Based on different communication technologies, multiple communication modules 9110, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, can be provided in the same electronic device. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and to receive audio input from the microphone 9132, thereby enabling typical telecommunication functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers, etc. In addition, the audio processor 9130 is coupled to the central processor 9100, thereby enabling recording on-board via the microphone 9132 and playing stored sounds on-board via the speaker 9131.

[0274] Embodiments of the present application also provide a computer readable storage medium capable of implementing all steps of the transport vehicle driving route determination method in the above embodiments, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement all steps of the transport vehicle driving route determination method in the above embodiments, for example, the processor executes the computer program to implement the following steps:

[0275] S101: determining a driving route initial matrix according to the number of vehicles and the number of to-be-delivered sites;

[0276] S102: iteratively optimizing the driving route initial matrix according to a pre-constructed delivery time cost analysis model to obtain a driving route optimization matrix;

[0277] S103: graphically displaying the driving route optimization matrix to obtain a vehicle driving route.

[0278] As can be seen from the above description, the transport vehicle driving route determination method and device provided by the present application solve the problems of insufficient consideration of time-varying factors and unsatisfactory planning effect in neural network models and traditional heuristic algorithms by improving the heuristic algorithm to establish a mathematical model and adding a time penalty cost in the mathematical model, thereby realizing planning of the route of the transport vehicle in the case of lack of historical data and improving the transport efficiency of the transport vehicle.

[0279] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0280] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0281] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0282] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 Figure 1 The steps of the function specified in one or more boxes.

[0283] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method of determining a travel route of a transportation vehicle, characterized by, The application relates to a method for determining a vehicle driving route, comprising the following steps: determining an initial matrix of the vehicle driving route according to the number of vehicles and the number of to-be-delivered network points; iteratively optimizing the initial matrix of the vehicle driving route according to a pre-constructed delivery time cost analysis model to obtain an optimized matrix of the vehicle driving route; graphically displaying the optimized matrix of the vehicle driving route to obtain a vehicle driving route; the initial matrix of the vehicle driving route comprises a geographical initial matrix; the step of determining the initial matrix of the vehicle driving route according to the number of vehicles and the number of to-be-delivered network points comprises the following steps: clustering the to-be-delivered network points according to the number of vehicles, the number of to-be-delivered network points, the delivery demand time corresponding to the number of to-be-delivered network points and the geographical position of the to-be-delivered network points to obtain a network point clustering set corresponding to each cluster; sequentially arranging the network points in the network point clustering set according to a preset detour strategy to obtain a vehicle driving route corresponding to each cluster; generating the geographical initial matrix according to the vehicle driving route and the number of vehicles; the detour strategy is a from-far-to-near ring strategy; the steps of constructing the delivery time cost analysis model comprise the following steps: determining the congestion time cost of each vehicle according to a preset vehicle driving route of each vehicle, the geographical position of each to-be-delivered network point and historical congestion data of a road section corresponding to the geographical position; determining the early arrival time cost of each vehicle according to a preset earliest delivery time and the actual time when each vehicle arrives at each to-be-delivered network point; determining the late arrival time cost of each vehicle according to a preset latest delivery time and the actual time; determining the driving time cost consumed by each vehicle when delivery is performed according to a historical driving data of the preset vehicle driving route; determining the delivery time cost of each vehicle according to the congestion time cost, the early arrival time cost, the late arrival time cost and the driving time cost to obtain the delivery time cost analysis model.

2. The transportation vehicle routing method of claim 1, wherein, the initial matrix of the vehicle driving route comprises a random initial matrix; the step of determining the initial matrix of the vehicle driving route according to the number of vehicles and the number of to-be-delivered network points comprises the following steps: randomly clustering the to-be-delivered network points according to the number of to-be-delivered network points; determining the random initial matrix according to the random clustering result and the number of vehicles.

3. The transportation vehicle routing method of claim 2, wherein, the step of iteratively optimizing the initial matrix of the vehicle driving route according to the pre-constructed delivery time cost analysis model to obtain the optimized matrix of the vehicle driving route comprises the following steps: iteratively operating the random initial matrix until the iteratively operating result meets a first preset stop condition to stop iteration and obtain a first process matrix; the first preset stop condition is set according to the delivery time cost analysis model; determining whether the first process matrix meets a second preset stop condition; if yes, the first process matrix is determined as the optimized matrix of the vehicle driving route.

4. The transportation vehicle routing method of claim 1, wherein, the step of iteratively optimizing the initial matrix of the vehicle driving route according to the pre-constructed delivery time cost analysis model to obtain the optimized matrix of the vehicle driving route comprises the following steps: iteratively operating the geographical initial matrix until the first preset stop condition is met to stop iteration and obtain a second process matrix; determining whether the second process matrix meets the second preset stop condition; if yes, the second process matrix is determined as the optimized matrix of the vehicle driving route.

5. The transportation vehicle routing method according to claim 3 or 4, characterized in that, the method further comprises the following steps: According to the delivery time cost analysis model, the first process matrix is compared with the second process matrix, and a delivery time cost lower one is selected as the driving route optimization matrix.

6. The transportation vehicle routing method of claim 1, wherein, After obtaining the driving route optimization matrix, further comprising: The driving route optimization matrix is adjusted by using the insertion operator and the deletion operator in the heuristic algorithm.

7. The transportation vehicle routing method of claim 1, wherein, The driving route optimization matrix is adjusted by using the insertion operator and the deletion operator in the heuristic algorithm, comprising: According to the deletion operator and the first execution weight thereof, a deletion operation is performed on a to-be-delivered network point with a far geographical position; According to the insertion operator and the second execution weight thereof, an insertion operation is performed on a to-be-delivered network point with a close geographical position, to obtain an adjusted driving route optimization matrix.

8. The transportation vehicle routing method of claim 7, wherein, Further comprising: According to the delivery time cost analysis model, the delivery time cost of the adjusted driving route optimization matrix is calculated; If the delivery time cost of the adjusted driving route optimization matrix is lower than that of the driving route optimization matrix before adjustment, the first execution weight and the second execution weight are adjusted.

9. A transport vehicle routing determination apparatus characterized by comprising: Comprising: An initial matrix generation unit is configured to determine a driving route initial matrix according to the number of vehicles and the number of to-be-delivered network points; An optimization matrix generation unit is configured to iteratively optimize the driving route initial matrix according to a pre-constructed delivery time cost analysis model, to obtain a driving route optimization matrix; A driving route display unit is configured to graphically display the driving route optimization matrix, to obtain a vehicle driving route; The driving route initial matrix comprises a geographical initial matrix; the initial matrix generation unit comprises a network point clustering module, a driving route setting module, and a geographical initial matrix generation module; The network point clustering module is configured to cluster the to-be-delivered network points according to the number of vehicles, the number of to-be-delivered network points, delivery demand time corresponding to the number of to-be-delivered network points, and geographical positions of the to-be-delivered network points, to obtain a network point clustering set corresponding to each cluster; The driving route setting module is configured to sort network points in the network point clustering set according to a preset detour strategy, to obtain a driving route corresponding to each cluster; The geographical initial matrix generation module is configured to generate the geographical initial matrix according to the driving route and the number of vehicles; and the detour strategy is a from-far-to-near ring strategy. The transport vehicle driving route determination device further comprises a congestion time cost determination unit, an early arrival time cost determination unit, a late arrival time cost determination unit, a driving time cost determination unit, and a cost analysis model generation unit. The congestion time cost determination unit is configured to determine a congestion time cost of each vehicle according to a preset driving route of each vehicle, geographical positions of each to-be-delivered network point, and historical congestion data of a road section corresponding to the geographical positions. The early arrival time cost determination unit is configured to determine an early arrival time cost of each vehicle according to a preset earliest delivery time and an actual time of each vehicle to arrive at each to-be-delivered network point. The late arrival time cost determination unit is configured to determine a late arrival time cost of each vehicle according to a preset latest delivery time and the actual time. The late arrival time cost determination unit is configured to determine a late arrival time cost of each vehicle according to a preset latest delivery time and the actual time. The driving time cost determination unit is configured to determine driving time costs of each vehicle consumed when the delivery is performed according to the preset driving route based on historical driving data of the preset driving route. The cost analysis model generation unit is configured to determine a delivery time cost of each vehicle based on the congestion time cost, the early arrival time cost, the late arrival time cost and the driving time cost, so as to obtain the delivery time cost analysis model.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the steps of the transport vehicle driving route determination method according to any one of claims 1 to 9 when executing the program.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the transport vehicle driving route determination method according to any one of claims 1 to 9.

12. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the steps of the transport vehicle driving route determination method according to any one of claims 1 to 9.

Images