A logistics truck transportation monitoring data processing method and system

By calculating the fitness function and cross-mutation operations, the logistics truck transportation path is optimized, and the problem of inaccurate and efficient transportation in traditional methods is solved, and more efficient logistics truck transportation is achieved.

CN118171986BActive Publication Date: 2024-11-22LUFENG BIG DATA TECH (SHANDONG) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410330445.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-22
Publication Date
2024-11-22
Estimated Expiration
2044-03-22

AI Technical Summary

Technical Problem

The traditional logistics truck transportation path determination method cannot fully consider complex real-time changes and the optimization of multiple goals, resulting in the generated transportation path inaccurate and efficient enough.

Method used

By obtaining the transportation monitoring data of the logistics truck, calculating the fitness function, selecting the transportation path with high fitness as the parent, performing cross and mutating operations, generating candidate transportation paths, and finally selecting the path with the largest fitness value as the target transportation path.

Benefits of technology

It improves the accuracy and efficiency of transportation paths, enhances the diversity of transportation paths and the quality of optimization results, and improves the efficiency and effectiveness of logistics truck transportation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118171986B_ABST
    Figure CN118171986B_ABST
Patent Text Reader

Abstract

The embodiment of the present application provides a method and system for processing logistics truck transportation monitoring data. Acquire multiple transportation paths; determine the fitness function according to preset indicators, and calculate the fitness value of each of the transportation paths; calculate the probability of selection of each of the transportation paths, and select a preset number of transportation paths from the multiple transportation paths as parent transportation paths; intersect at least two parent transportation paths at the intersection to generate child transportation paths; perform mutation operations on the child transportation paths that meet the mutation conditions; merge the child transportation paths after the mutation operation and the parent transportation paths to generate multiple candidate transportation paths, and select the candidate transportation path with the largest fitness value from the multiple candidate transportation paths as the target transportation path. The technical solution provided by the embodiment of the present application can optimize the generation of target transportation paths with higher fitness, and improve the efficiency and effect of logistics truck transportation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of logistics management technology, and in particular, to a method and system for processing logistics truck transportation monitoring data. Background Art

[0002] The method for processing logistics truck transportation monitoring data refers to a method of optimizing and determining the transportation route by using the real-time monitoring data of logistics trucks through the application of information technology and algorithms. By acquiring, processing and analyzing the transportation monitoring data of logistics trucks, the goals of real-time tracking of goods, route optimization, and transportation efficiency improvement can be achieved.

[0003] Traditional methods for determining target transportation routes are usually based on manual experience and rule-making, or use simple heuristic algorithms. In these methods, the determination of transportation routes is usually based on the principles of graph theory and network analysis, and factors such as distance, time, traffic conditions, and waypoints are considered.

[0004] However, these methods often fail to fully consider complex real-time changing factors and the optimization of multiple objectives, resulting in the generated target transportation paths being inaccurate and inefficient. Summary of the invention

[0005] The embodiments of the present application provide a method and system for processing logistics truck transportation monitoring data, which are used to solve the problem that the target transportation path generated in the prior art is not accurate and efficient enough.

[0006] In a first aspect, an embodiment of the present application provides a method for processing logistics truck transportation monitoring data, comprising:

[0007] Acquire transportation monitoring data of a logistics truck, wherein the transportation monitoring data includes a plurality of transportation routes, and each of the transportation routes includes a plurality of waypoints;

[0008] Determine a fitness function according to a preset indicator, and calculate the fitness value of each of the transport paths according to the fitness function, wherein the fitness function is used to evaluate the adaptability of the transport path in the problem domain;

[0009] Based on the fitness values ​​of the plurality of transport paths, the selection probability of each transport path is calculated, and based on the selection probability of each transport path, a preset number of transport paths are selected from the plurality of transport paths as parent transport paths;

[0010] Randomly select an intersection point, and intersect at least two parent transport paths at the intersection point to generate a child transport path;

[0011] Determine whether the child transport path meets a mutation condition, wherein the mutation condition includes whether the random number corresponding to the child transport path is less than a set mutation rate, and if so, perform a mutation operation on the child transport path, wherein the mutation operation at least includes: exchanging the waypoint positions in the child transport path;

[0012] The child transport path after the mutation operation and the parent transport path are merged to generate multiple candidate transport paths, and the candidate transport path with the largest fitness value is selected from the multiple candidate transport paths as the target transport path.

[0013] Optionally, the preset indicators include at least total distance, total cost, and total time, wherein the total distance refers to the cumulative distance of all waypoints passed by the truck during the transportation process, the total cost refers to the total cost incurred by the truck during the transportation process, and the total time refers to the total time spent by the truck during the transportation process;

[0014] Determining the fitness function according to the preset index includes:

[0015] The fitness function is calculated by the formula: Determine the fitness function;

[0016] Among them, total distance (i) represents the total distance of transport path i, w d Expressed as the weight of the total distance, total time (i) represents the total time of transportation path i, w t Expressed as the weight of the total time, total cost (i) represents the total cost of transport path i, w c Expressed as a weight to the total cost.

[0017] Optionally, calculating the fitness value of each of the transport paths according to the fitness function includes:

[0018] For each of the transport paths, a distance matrix between a plurality of waypoints included in the transport path is calculated, and according to the waypoint sequence of the plurality of waypoints included in the transport path, a corresponding waypoint is searched from the distance matrix to calculate the distance between two waypoints, so as to accumulate and obtain a total distance of the transport path;

[0019] Obtaining the average speed and travel time between waypoints of the transport path, and calculating the total time of the transport path by using the total distance of the transport path and the average speed and travel time between waypoints in the transport path;

[0020] Obtaining the unit distance cost and the unit time cost between the waypoints of the transport path, and calculating the total cost of the transport path by the total distance of the transport path and the unit distance cost and the unit time cost between the waypoints of the transport path;

[0021] The total distance of the transport path, the total time of the transport path and the total cost of the transport path are brought into the fitness function calculation formula to calculate the fitness value of each of the transport paths.

[0022] Optionally, the transport monitoring data of the logistics truck is obtained, the transport monitoring data includes a plurality of transport routes, each of the transport routes includes a plurality of waypoints, including:

[0023] Obtaining the starting point and the end point of the logistics truck from the transportation monitoring data of the logistics truck to determine the starting point and the end point of each transportation path;

[0024] Determining the waypoints of each of the transportation routes according to logistics requirements and truck loading capacity;

[0025] Starting from the starting point, select the waypoints one by one to generate multiple transportation routes.

[0026] Optionally, the calculating the selection probability of each of the transport paths based on the fitness values ​​of the plurality of transport paths comprises:

[0027] Based on the fitness values ​​of the plurality of transport paths, the sum of the fitness values ​​of all the transport paths is calculated; based on the sum of the fitness values ​​of all the transport paths, the calculation formula of the probability of being selected is: Calculating the probability of each transport path being selected;

[0028] Among them, selection probability (i) represents the probability of transport path i being selected, fitness(i) represents the fitness value of transport path i, creative factor (i) represents the creative factor of transport path i, which can be determined by the path difference of transport path i. factor (i) = diversity(i) / sum diversity , diversity(i) represents the path diversity of transport path i, sum diversity It is expressed as the sum of the path differences of all transportation paths, sum fitness It is expressed as the sum of the fitness values ​​of all transport paths (creative factor ) represents the sum of the creative factors of all transport paths;

[0029] The path differences include at least: the total distance difference between transport path i and other transport paths, the total time difference between transport path i and other transport paths, and the total cost difference between transport path i and other transport paths.

[0030] Optionally, the selecting a preset number of transport paths as parent transport paths from the plurality of transport paths based on the probability of selection of each transport path includes:

[0031] Normalizing the selection probability of each of the transport paths, and dividing the selection probability of each of the transport paths by the sum of the selection probabilities to obtain a normalized selection probability;

[0032] Sorting the normalized selection probabilities of the plurality of transport routes in order of magnitude to generate a cumulative probability sequence;

[0033] Generate a random number between 0 and 1, find the first transportation distance corresponding to the probability value greater than the random number from the cumulative probability sequence, and determine the transportation path as the parent transportation path.

[0034] Optionally, the randomly selecting an intersection point and intersecting at least two parent transport paths at the intersection point to generate a child transport path comprises:

[0035] Determine the length n of the parent transport path and generate a random number i between 1 and n-1 as the index of the intersection;

[0036] Select at least two of the parent transport paths, and use the intersection i as a boundary to divide the at least two parent transport paths into two parts, thereby obtaining a first part and a second part;

[0037] The first part is copied from the first parent transport path to the child transport path, and the waypoints in the second part are found in the second parent transport path, and the waypoints in the second part are inserted into the position after the intersection i of the child transport path according to the order of the waypoints to generate the child transport path.

[0038] In a second aspect, an embodiment of the present application provides a logistics truck transportation monitoring data processing system, including:

[0039] An acquisition module, used to acquire transportation monitoring data of a logistics truck, wherein the transportation monitoring data includes a plurality of transportation routes, and each of the transportation routes includes a plurality of waypoints;

[0040] A calculation module, used to determine a fitness function according to a preset index, and calculate the fitness value of each of the transport paths according to the fitness function, wherein the fitness function is used to evaluate the fitness of the transport path in the problem domain; based on the fitness values ​​of the plurality of transport paths, calculate the selection probability of each of the transport paths, and based on the selection probability of each of the transport paths, select a preset number of transport paths from the plurality of transport paths as parent transport paths;

[0041] A generation module, configured to randomly select an intersection point and intersect at least two parent transport paths at the intersection point to generate a child transport path;

[0042] The determination module is used to determine whether the offspring transport path meets the mutation condition, and the mutation condition includes whether the random number corresponding to the offspring transport path is less than the set mutation rate. If so, the offspring transport path is mutated, and the mutation operation at least includes: exchanging the waypoint positions in the offspring transport path; merging the offspring transport path after the mutation operation and the parent transport path to generate a candidate transport path, and selecting the candidate transport path with the largest fitness value from the candidate transport paths as the target transport path.

[0043] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the logistics truck transportation monitoring data processing method as described in the first aspect above.

[0044] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, the logistics truck transportation monitoring data processing method as described in the first aspect above is implemented.

[0045] In an embodiment of the present application, transportation monitoring data of a logistics truck is obtained, wherein the transportation monitoring data includes a plurality of transportation paths, and each of the transportation paths includes a plurality of waypoints; a fitness function is determined according to a preset index, and a fitness value of each of the transportation paths is calculated according to the fitness function, wherein the fitness function is used to evaluate the fitness of the transportation path in the problem domain; based on the fitness values ​​of the plurality of transportation paths, a selection probability of each of the transportation paths is calculated, and based on the selection probability of each of the transportation paths, a preset number of transportation paths are selected from the plurality of transportation paths as parent transportation paths; an intersection is randomly selected, and at least two parent transportation paths are intersected at the intersection to generate a child transportation path; it is determined whether the child transportation path meets a mutation condition, wherein the mutation condition includes whether a random number corresponding to the child transportation path is less than a set mutation rate, and if so, a mutation operation is performed on the child transportation path, wherein the mutation operation at least includes: exchanging the waypoint positions in the child transportation path; merging the child transportation path after the mutation operation and the parent transportation path to generate a plurality of candidate transportation paths, and selecting a candidate transportation path with the largest fitness value from the plurality of candidate transportation paths as a target transportation path.

[0046] The beneficial effects of the technical solution of this application include:

[0047] Improved data acquisition and processing efficiency: By acquiring and processing the transportation monitoring data of logistics trucks, effective management and analysis of multiple transportation routes and waypoints can be achieved, improving the efficiency of data processing.

[0048] Fitness function evaluates the adaptability of the transportation path: By setting the fitness function, the adaptability of each transportation path in the problem domain can be evaluated, so as to better understand and compare the advantages and disadvantages of different transportation paths.

[0049] Select transport paths with high fitness as parents: Based on the fitness value of the transport path, calculate the selection probability of each transport path, and select a preset number of transport paths as parents, so that transport paths with high fitness can be retained and used for subsequent optimization and evolution.

[0050] Crossover and mutation operations increase diversity: By randomly selecting crossover points and performing crossover operations on at least two parent transport paths, child transport paths can be generated, thereby increasing the diversity of transport paths. At the same time, mutation operations can be performed on child transport paths according to mutation conditions to further increase diversity and explore new solution spaces.

[0051] Improved accuracy of target transport path selection: By merging the child transport path and the parent transport path after the mutation operation, multiple candidate transport paths are generated, and the candidate transport path with the largest fitness value is selected as the target transport path, thereby improving the accuracy of the target transport path and the quality of the optimization results.

[0052] In summary, the method of the present application can effectively process logistics truck transportation monitoring data, and through operations such as crossover, mutation and selection, optimize and generate target transportation paths with higher fitness, thereby improving the efficiency and effectiveness of logistics truck transportation.

[0053] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A flow chart of a method for processing logistics truck transportation monitoring data provided by an embodiment of the present application;

[0056] Figure 2 A flowchart of a method for calculating the fitness value of a transport path provided in an embodiment of the present application;

[0057] Figure 3 A structural diagram of a logistics truck transportation monitoring data processing system provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0060] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0061] The technical solution of the embodiment of the present application is mainly applied to the logistics truck transportation monitoring data processing scenario. This technical solution can be used to monitor and manage the real-time location, transportation status and cargo information of logistics trucks to achieve the goals of real-time tracking of goods, route optimization, and transportation efficiency improvement. It can be applied to logistics transportation companies, warehousing and logistics companies, e-commerce platforms and other fields involving cargo transportation and distribution.

[0062] The embodiments of this application are mainly aimed at achieving the scenario of optimizing the path of goods. The inventors have found that the traditional target transportation path determination method is usually based on manual experience and rule formulation, or uses a simple heuristic algorithm. In these methods, the determination of the transportation path is usually based on the principles of graph theory and network analysis, and factors such as distance, time, traffic conditions, waypoints, etc. are considered. However, these methods often fail to fully consider complex real-time changing factors and the optimization of multiple goals, resulting in the generated transportation path being inaccurate and inefficient.

[0063] Therefore, a new logistics truck transportation monitoring data processing method and system is needed, which can make full use of real-time monitoring data, have multi-objective optimization capabilities, and provide intelligent decision support to improve the accuracy, efficiency and cost-effectiveness of transportation routes.

[0064] In view of this, an embodiment of the present application provides a method for processing transportation monitoring data of a logistics truck, the method comprising: obtaining transportation monitoring data of a logistics truck, the transportation monitoring data comprising a plurality of transportation paths, each of the transportation paths comprising a plurality of waypoints; determining a fitness function according to a preset index, and calculating a fitness value of each of the transportation paths according to the fitness function, the fitness function being used to evaluate the fitness of the transportation path in the problem domain; calculating a probability of being selected for each of the transportation paths based on the fitness values ​​of the plurality of transportation paths, and selecting a preset number of transportation paths from the plurality of transportation paths based on the probability of being selected for each of the transportation paths. The method comprises the following steps: selecting a path as a parent transport path; randomly selecting an intersection point, and intersecting at least two parent transport paths at the intersection point to generate a child transport path; determining whether the child transport path satisfies a mutation condition, wherein the mutation condition includes whether the random number corresponding to the child transport path is less than a set mutation rate, and if so, performing a mutation operation on the child transport path, wherein the mutation operation at least includes: exchanging the waypoint positions in the child transport path; merging the child transport path after the mutation operation and the parent transport path to generate multiple candidate transport paths, and selecting the candidate transport path with the largest fitness value from the multiple candidate transport paths as the target transport path.

[0065] The method of the present application can effectively process logistics truck transportation monitoring data, and through operations such as crossover, mutation and selection, optimize and generate target transportation routes with higher fitness, thereby improving the efficiency and effectiveness of logistics truck transportation.

[0066] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0067] Figure 1 A flow chart of a method for processing logistics truck transportation monitoring data provided by an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0068] 101. Acquire transportation monitoring data of a logistics truck, wherein the transportation monitoring data includes a plurality of transportation routes, and each of the transportation routes includes a plurality of waypoints;

[0069] In this step, the monitoring equipment or sensors installed on the logistics truck can be used to obtain the transportation monitoring data of the logistics truck during the transportation process, such as real-time location, speed, mileage, transportation status, temperature and humidity, transportation path and other information. Among them, the transportation path refers to the road route that the logistics truck passes through during the transportation process, which is usually composed of a starting point, an end point and an intermediate point in the route (i.e., a waypoint), which is used to determine the vehicle's driving route. The waypoint in the transportation path refers to the intermediate point in the transportation path except the starting point and the end point, which usually indicates a specific location that the logistics truck needs to pass through, such as a warehouse, a distribution point or an important traffic node.

[0070] In the embodiment of the present application, for example, a truck of a logistics transportation company needs to start from warehouse A, pass through waypoints B and C, and finally arrive at the end point D. During the entire transportation process, the transportation monitoring data obtained by the monitoring equipment includes the real-time location, speed, cargo temperature and other information of the vehicle, and also includes the transportation path information along the way of the logistics truck, that is, A->B->C->D. Among them, A is the starting point, D is the end point, and B and C are waypoints. These data can be used to monitor the transportation status of the truck in real time, and perform operations such as path optimization and transportation efficiency improvement.

[0071] 102. Determine a fitness function according to a preset indicator, and calculate the fitness value of each of the transportation paths according to the fitness function;

[0072] In this step, the preset index refers to the index set in advance to measure the quality of the transportation path in the processing of the logistics truck loading and transportation monitoring data, which can be multiple indexes or a combination of multiple indexes. For example, the preset index may include total distance, total cost, and total time, wherein the total distance refers to the cumulative distance of all the waypoints passed by the truck during the transportation process, the total cost refers to the total cost incurred by the truck during the transportation process, and the total time refers to the total time spent by the truck during the transportation process.

[0073] The fitness function is a function that maps a transport path to a fitness value based on preset indicators. The fitness function is used to evaluate the adaptability of the transport path in the problem domain. The higher the fitness value, the better the path. The problem domain refers to the scope and constraints that define the problem in a specific problem or field. It includes the entities, variables, relationships, rules, etc. involved in the problem, as well as the goals and constraints of the problem. In the data processing of logistics truck loading and transportation monitoring, the problem domain can include the transportation path of the logistics truck, etc.

[0074] Optionally, in the embodiment of the present application, taking the preset indicators as an example, which include at least total distance, total cost, and total time, as a possible implementation scheme, determining the fitness function according to the preset indicators includes:

[0075] The fitness function is calculated by the formula: Determine the fitness function;

[0076] Among them, total distance (i) represents the total distance of transport path i, w d Expressed as the weight of the total distance, total time (i) represents the total time of transportation path i, w t Expressed as the weight of the total time, total cost (i) represents the total cost of transport path i, w c Expressed as a weight to the total cost.

[0077] Optionally, in the embodiment of the present application, Figure 2 A flow chart of a method for calculating the fitness value of a transport path is provided. The method is based on the fitness function calculation formula mentioned above. The process of "calculating the fitness value of each transport path according to the fitness function" in step 102 may include:

[0078] 1021. For each of the transport paths, calculate a distance matrix between a plurality of waypoints included in the transport path, and search for a corresponding waypoint from the distance matrix according to the waypoint sequence of the plurality of waypoints included in the transport path, so as to calculate a distance between two waypoints, so as to accumulate and obtain a total distance of the transport path;

[0079] In step 1021, for each transport path, it is necessary to calculate the distance matrix between the multiple waypoints contained in the transport path, and according to the order of the waypoints in the transport path, find the corresponding waypoints from the distance matrix to calculate the distance between every two waypoints, and finally accumulate the total distance of the transport path.

[0080] The specific steps are as follows:

[0081] Assume that there is a transportation route consisting of n waypoints, where the first waypoint is the starting point and the last waypoint is the end point.

[0082] Create a distance matrix of size nxn to store the distances between waypoints.

[0083] Fill the distance matrix based on the distance information between the waypoints. According to the order of the waypoints, the distance between two waypoints can be found by looking up the corresponding rows and columns of the distance matrix and filling it into the corresponding position of the matrix.

[0084] Traverse each row of the distance matrix and accumulate the distance between each waypoint to get the total distance of the transportation path.

[0085] In the embodiment of the present application, it is assumed that a transport route includes 4 waypoints (A, B, C, D), and the order of the waypoints is A->B->C->D. The distance matrix between the known waypoints is shown in Table 1 below:

[0086] Table 1

[0087] A B C D A 0 5 8 10 B 5 0 3 6 C 8 3 0 4 D 10 6 4 0

[0088] According to the order of the waypoints, the distances between the corresponding waypoints can be found from the distance matrix in Table 1 above:

[0089] The distance between A->B is 5;

[0090] The distance between B->C is 3;

[0091] The distance between C->D is 4;

[0092] Finally, add up these distances to get the total distance of the transport path: 5+3+4=12.

[0093] Through the above embodiment, it can be seen that when calculating the total distance of the transport path, it is necessary to find the corresponding distance from the distance matrix according to the order between the waypoints and perform a cumulative operation, so as to obtain the total distance information of the transport path.

[0094] 1022. Obtain an average speed and travel time between waypoints of the transport path, and calculate a total time of the transport path by using a total distance of the transport path and the average speed and travel time between waypoints in the transport path;

[0095] In step 1022, it is necessary to obtain the average speed and travel time between the waypoints of the transportation path, and calculate the total time of the transportation path based on the total distance of the transportation path and the average speed and travel time between the waypoints.

[0096] The specific steps are as follows:

[0097] The average speed between each waypoint can be measured or estimated according to the actual situation. The average speed represents the average speed of the vehicle during the driving process between the waypoints. For example, assume that the average speed between waypoints A and B is 30 km / h.

[0098] Based on the average speed and distance between waypoints, the travel time between waypoints can be calculated. The travel time is equal to the distance divided by the average speed. For example, assuming the distance between waypoints A and B is 10km and the average speed is 30km / h, the travel time is: 10km / 30km / h = 0.33 hours.

[0099] Traverse the travel time between each waypoint in the transport path and accumulate them to get the total time of the transport path. For example, for a transport path containing 4 waypoints (A, B, C, D), the order of the waypoints is A->B->C->D, the travel time between A->B, B->C, C->D can be calculated and accumulated to get the total time of the transport path.

[0100] In the embodiment of the present application, it is assumed that a transport route includes 4 waypoints (A, B, C, D), and the order of the waypoints is A->B->C->D. The average speed and travel time between the known waypoints are shown in Table 2 below:

[0101] Table 2

[0102]

[0103] According to the order of the waypoints, the travel time between the corresponding waypoints can be found from the travel time matrix in Table 2 above:

[0104] The travel time between A->B is 0.2 hours;

[0105] The travel time between B->C is 0.1 hours;

[0106] The travel time between C->D is 0.15 hours;

[0107] Finally, these driving times are added up to get the total time for the transport route: 0.2+0.1+0.15=0.45 hours.

[0108] From this example, we can see that when calculating the total time of a transportation route, we need to calculate the travel time between each waypoint based on the average speed and travel time between waypoints, and perform cumulative operations. In this way, we can obtain the total time information of the transportation route.

[0109] 1023. Obtain the unit distance cost and the unit time cost between the waypoints of the transportation path, and calculate the total cost of the transportation path by the total distance of the transportation path and the unit distance cost and the unit time cost between the waypoints of the transportation path;

[0110] In step 1023, it is necessary to obtain the unit distance cost and unit time cost between the waypoints of the transportation path, and calculate the total cost of the transportation path based on the total distance of the transportation path and the unit distance cost and unit time cost between the waypoints.

[0111] The specific steps are as follows:

[0112] The unit distance cost and unit time cost between each waypoint can be calculated or estimated based on the actual situation. The unit distance cost indicates the cost per unit distance between waypoints, such as the cost per kilometer. The unit time cost indicates the cost per unit time between waypoints, such as the cost per hour.

[0113] The distance cost between waypoints can be calculated based on the unit distance cost and distance between waypoints. The distance cost is equal to the distance multiplied by the unit distance cost. For example, assuming the distance between waypoints A and B is 10km and the unit distance cost is 2 yuan / km, the distance cost is: 10km*2 yuan / km=20 yuan.

[0114] The time cost between waypoints can be calculated based on the unit time cost and driving time between waypoints. The time cost is equal to the driving time multiplied by the unit time cost. For example, assuming that the driving time between waypoints A and B is 0.33 hours and the unit time cost is 10 yuan / hour, the time cost is: 0.33 hours * 10 yuan / hour = 3.3 yuan.

[0115] Traverse the distance cost and time cost between each waypoint in the transport path, and add them up to get the total cost of the transport path. For example, for a transport path containing 4 waypoints (A, B, C, D), the order of the waypoints is A->B->C->D, the distance cost and time cost between A->B, B->C, C->D can be calculated, and they can be added up to get the total cost of the transport path.

[0116] In the embodiment of the present application, it is assumed that a transport route includes 4 waypoints (A, B, C, D), and the order of the waypoints is A->B->C->D. The unit distance cost and unit time cost between the known waypoints are shown in Table 3 below:

[0117] Table 3

[0118] A B C D A 0 2 3 4 B 2 0 1 2 C 3 1 0 1.5 D 4 2 1.5 0

[0119] According to the order of the waypoints, the unit distance cost and unit time cost between the corresponding waypoints can be found from the cost matrix in Table 3 above:

[0120] The unit distance cost between A->B is 2 yuan / km, and the unit time cost is 10 yuan / hour;

[0121] The unit distance cost between B->C is 1 yuan / km, and the unit time cost is 5 yuan / hour;

[0122] The unit distance cost between C->D is 1.5 yuan / km, and the unit time cost is 8 yuan / hour;

[0123] According to the distance cost and time cost between the waypoints, the distance cost and time cost can be calculated:

[0124] The distance cost between A->B is 10km*2yuan / km=20yuan, and the time cost is 0.33hours*10yuan / hour=3.3yuan.

[0125] The distance cost between B->C is 10km*1 yuan / km=10 yuan, and the time cost is 0.1 hour*5 yuan / hour=0.5 yuan.

[0126] The distance cost between C->D is 10km*1.5 yuan / km=15 yuan, and the time cost is 0.15 hours*8 yuan / hour=1.2 yuan.

[0127] Finally, add up these distance costs and time costs to get the total cost of the transportation route: 20+3.3+10+0.5+15+1.2=50 yuan.

[0128] From this example, we can see that when calculating the total cost of a transportation route, we need to calculate the distance cost and time cost between each waypoint based on the unit distance cost and unit time cost between waypoints, and perform cumulative operations. In this way, we can obtain the total cost information of the transportation route.

[0129] 1024. Substitute the total distance of the transport path, the total time of the transport path, and the total cost of the transport path into the fitness function calculation formula to calculate the fitness value of each of the transport paths.

[0130] In step 1024, the total distance, total time and total cost of the transportation path calculated in steps 1021 to 1023 are substituted into the fitness function calculation formula to calculate the fitness value of each transportation path.

[0131] Among them, the fitness function calculation formula is: Determine the fitness function;

[0132] Among them, total distance (i) represents the total distance of transport path i, w d Expressed as the weight of the total distance, total time (i) represents the total time of transportation path i, w t Expressed as the weight of the total time, total cost (i) represents the total cost of transport path i, w c Expressed as a weight to the total cost.

[0133] The specific steps are as follows:

[0134] The total distance, total time and total cost of the i-th transport path are substituted into the fitness function calculation formula to calculate the fitness value of the i-th transport path according to the formula.

[0135] In the present embodiment, it is assumed that there is a transportation route with a total distance of 100 km, a total time of 2 hours, and a total cost of 200 yuan. d is 0.5, w t is 0.3, w c is 0.2. Substitute these values ​​into the fitness function calculation formula:

[0136] Through this example, we can see that according to the fitness function calculation formula, the total distance, total time and total cost of the transportation path can be entered to calculate the fitness value of each transportation path. The fitness value can be used to evaluate the quality of the transportation path, so as to optimize and select the path.

[0137] 103. Calculate the selection probability of each of the transport paths based on the fitness values ​​of the plurality of transport paths, and select a preset number of transport paths from the plurality of transport paths as parent transport paths based on the selection probability of each of the transport paths;

[0138] In this step, based on the fitness values ​​of the multiple transportation paths, the selection probability of each transportation path is calculated, and a preset number of transportation paths are selected from the multiple transportation paths as parent transportation paths according to the selection probability.

[0139] The specific steps are as follows:

[0140] According to the fitness value of each transport path, the probability of selection of each transport path is calculated. The selection probability can be normalized according to the fitness value so that the sum of all selection probabilities is equal to 1. A common normalization method is to use the roulette algorithm, that is, the probability of selection of each transport path is equal to its fitness value divided by the sum of all fitness values.

[0141] According to the selection probability and the preset number of each transport path, a corresponding number of transport paths are selected from the multiple transport paths as parent transport paths. The selection method can be random selection, sampling according to the selection probability of each transport path, and then selecting the transport path with high probability as the parent transport path.

[0142] In the embodiment of the present application, it is assumed that there are 5 transport paths, and their fitness values ​​and selection probabilities are shown in Table 4 below:

[0143] Table 4

[0144] Transport route Fitness value Probability of being selected Transport route 1 0.2 0.1 Transport route 2 0.5 0.25 Transport route 3 0.3 0.15 Transport route 4 0.4 0.2 Transport route 5 0.6 0.3

[0145] Assume that the number of transportation paths selected by default is 2. According to the probability of being selected, sampling can be performed to select the transportation paths with high selection probability as the parent transportation paths. Assuming that the sampling results are transportation path 2 and transportation path 5, transportation path 2 and transportation path 5 will be selected as the parent transportation paths.

[0146] Through this example, it can be seen that in step 103, the selection probability is calculated according to the fitness value of each transport path, and a preset number of transport paths are selected from multiple transport paths as parent transport paths according to the selection probability. In this way, transport paths with high fitness values ​​can be retained and provide seeds for the next generation of transport path selection.

[0147] 104. Randomly select an intersection point, and intersect at least two parent transport paths at the intersection point to generate a child transport path;

[0148] In this step, a crossover point is randomly selected, and at least two parent transport paths are crossed at the crossover point to generate a child transport path.

[0149] The specific steps are as follows:

[0150] Randomly select an intersection. The intersection can be a location in the transportation path, such as a node or a distribution point. The intersection can be selected randomly or according to certain rules.

[0151] At least two parent transport paths are selected. The parent transport paths may be the parent transport paths determined in step 103.

[0152] Crossover is performed at the intersection. The crossover can be a single-point crossover, that is, the two parent transport paths are cut at the intersection and then the cut parts are swapped. It can also be a multi-point crossover, that is, cutting and swapping are performed at multiple locations around the intersection. The specific method of crossover depends on the characteristics of the problem and the design of the algorithm.

[0153] Generate offspring transport paths. Through the crossover operation, part of the parent transport path is swapped to generate a new offspring transport path. The offspring transport path will inherit part of the parent's genetic information and may have better characteristics.

[0154] In the embodiment of the present application, it is assumed that there are two parent transport paths, transport path 1 is ABCDE, and transport path 2 is FGHIJ. The randomly selected intersection point is C, and a single-point intersection is performed.

[0155] Crossover operation: AB is before the intersection of transport path 1, and DE is after the intersection of transport path 2. The parts before the intersection are swapped to obtain a new transport path 3 of FGB, and the parts after the intersection are swapped to obtain a new transport path 4 of ACDE.

[0156] Through this example, it can be seen that in step 104, a crossover point is randomly selected and at least two parent transport paths are crossed at the crossover point to generate a child transport path. The crossover operation can help explore new transport paths, increase the diversity of the population, and facilitate the search process of the evolutionary algorithm.

[0157] 105. Determine whether the child transport path satisfies a mutation condition, wherein the mutation condition includes whether the random number corresponding to the child transport path is less than a set mutation rate. If so, perform a mutation operation on the child transport path, wherein the mutation operation at least includes: exchanging the waypoint positions in the child transport path;

[0158] In this step, it is determined whether the offspring transport path meets the mutation condition. The mutation condition includes whether the random number corresponding to the offspring transport path is less than the set mutation rate. If the mutation condition is met, the offspring transport path is mutated. The mutation operation at least includes exchanging the waypoint position in the offspring transport path.

[0159] The specific steps are as follows:

[0160] A random number is generated according to the offspring transport path. The range of the random number is usually between [0,1], and it is determined whether the random number is less than the set mutation rate. The mutation rate is a probability value between 0 and 1, indicating the probability of mutation of the offspring transport path.

[0161] If the random number is less than the mutation rate, the offspring transport path will be mutated. Otherwise, the offspring transport path will not be mutated.

[0162] The mutation operation at least includes exchanging the position of the waypoints in the child transport path. The exchange can be to randomly select two waypoints and then exchange their positions. It can also be to select the waypoints suitable for exchange according to a certain rule and exchange their positions. The specific setting can be based on the needs.

[0163] In the embodiment of the present application, it is assumed that the offspring transport path is ABCDE, and the mutation rate is set to 0.2. The random number generated by the offspring transport path is 0.15, which is less than the mutation rate and meets the mutation condition. By performing the mutation operation, two path points, such as B and D, can be randomly selected, and their positions can be exchanged to obtain a new offspring transport path of ADCBE.

[0164] Through this example, it can be seen that in step 105, it is determined whether the offspring transport path meets the mutation condition and a mutation operation is performed. The mutation operation at least includes exchanging the waypoint positions in the offspring transport path. The mutation operation can increase the diversity of the transport path and help the search process of the evolutionary algorithm.

[0165] 106. Merge the child transport path after the mutation operation and the parent transport path to generate multiple candidate transport paths, and select a candidate transport path with the largest fitness value from the multiple candidate transport paths as the target transport path.

[0166] In this step, the child transport path and the parent transport path after the mutation operation are merged to generate multiple candidate transport paths, and the candidate transport path with the largest fitness value is selected as the target transport path.

[0167] The specific steps are as follows:

[0168] The child transport path after the mutation operation is merged with the parent transport path. The merging method can be to directly connect the two paths to form a new transport path.

[0169] Multiple candidate transport routes are generated based on the merged transport routes. Multiple slightly different candidate transport routes can be generated by randomly exchanging, deleting or inserting waypoints in the transport routes.

[0170] Calculate the fitness value of each candidate transportation path. The fitness value can be defined according to the specific requirements of the problem, usually including the total cost, total distance, total time, etc. of the transportation path.

[0171] The candidate transport path with the largest fitness value is selected from multiple candidate transport paths as the target transport path. The fitness value of each candidate transport path can be compared to select the path with the largest fitness value as the optimal solution. Other selection strategies can also be used, such as roulette selection, tournament selection, etc.

[0172] In the embodiment of the present application, through this step, the child transport path after the mutation operation can be merged with the parent transport path to generate multiple candidate transport paths, and the path with the largest fitness value is selected as the target transport path. Selecting the path with the largest fitness value can obtain a better solution, which helps to optimize the loading and transportation efficiency of logistics trucks.

[0173] Optionally, in the embodiment of the present application, as a specific implementation scheme, step 101 may specifically include:

[0174] 1011. Obtain the starting position and the ending position of the logistics truck from the transportation monitoring data of the logistics truck to determine the starting point and the ending point of each transportation path;

[0175] In step 1011, the starting point and the end point are obtained from the transportation monitoring data of the logistics truck: the coordinate information of the starting point and the end point of the truck transportation can be obtained through the monitoring data of the logistics truck. These monitoring data may include GPS positioning data, transportation order information, etc. Based on these data, the starting point and the end point of each transportation path can be determined.

[0176] For example, the starting position of a truck obtained from the monitoring data is A (longitude: x1, latitude: y1), and the end position is B (longitude: x2, latitude: y2).

[0177] 1012. Determine the waypoints of each transportation route according to logistics requirements and truck loading capacity;

[0178] In step 1012, the waypoints of each transport route are determined according to the logistics demand and the loading capacity of the truck: the waypoints that each transport route needs to pass through are determined according to the logistics demand and the loading capacity of the truck. The waypoints can be the shipping point, the receiving point, or other important locations that need to be passed through.

[0179] For example, according to logistics requirements, it is determined that the truck needs to pass through waypoints C and D. At the same time, according to the loading capacity of the truck, the order and number of the waypoints also need to be reasonably arranged.

[0180] 1013. Starting from the starting point, select the waypoints one by one to generate multiple transportation routes.

[0181] In step 1013, starting from the starting point, waypoints are selected one by one to generate multiple transportation paths: starting from the starting point of the truck, waypoints are selected one by one to generate multiple transportation paths. The paths can be generated by using a depth-first search, a backtracking algorithm, or the like.

[0182] For example, starting from the starting point A, select the waypoint C, and generate path 1: AC. Then continue to select the waypoint D from the waypoint C to generate path 2: ACD. More transportation paths can be generated according to needs.

[0183] Through this step, we can determine the starting and ending locations based on the transportation monitoring data of the logistics truck, determine the waypoints based on the logistics demand and the truck loading capacity, and then select the waypoints one by one from the starting point to generate multiple transportation paths. These transportation paths can be used as inputs for subsequent optimization algorithms to improve the efficiency of logistics truck loading and transportation.

[0184] Optionally, in the embodiment of the present application, as a specific implementation scheme, the "calculating the probability of selection of each transport path based on the fitness values ​​of the plurality of transport paths" in step 103 may specifically include: calculating the sum of the fitness values ​​of all transport paths based on the fitness values ​​of the plurality of transport paths; calculating the sum of the fitness values ​​of all transport paths and the calculation formula of the probability of selection based on the following formula: Calculating the probability of each transport path being selected;

[0185] Among them, selection probability (i) represents the probability of transport path i being selected, fitness(i) represents the fitness value of transport path i, creative factor (i) represents the creative factor of transport path i, which can be determined by the path difference of transport path i. factor (i) = diversity(i) / sum diversity , diversity(i) represents the path diversity of transport path i, sum diversity It is expressed as the sum of the path differences of all transportation paths, sum fitness It is expressed as the sum of the fitness values ​​of all transport paths (creative factor ) represents the sum of the creative factors of all transport paths;

[0186] The path differences include at least: the total distance difference between transport path i and other transport paths, the total time difference between transport path i and other transport paths, and the total cost difference between transport path i and other transport paths.

[0187] In the embodiment of the present application, the probability of each transport path being selected is calculated based on the fitness values ​​of multiple transport paths. Specifically, the following steps are included:

[0188] Calculate the sum of the fitness values ​​of all transport paths: Add the fitness values ​​of all transport paths to get the sum of the fitness values. The fitness value can be an evaluation indicator determined based on factors such as logistics demand and truck loading capacity, such as total transportation distance, total time, total cost, etc.

[0189] Calculate the sum of the creative factors: Calculate the creative factor according to the path differences of each transportation path. The path differences may include the total distance difference, total time difference, total cost difference, etc. between the transportation path and other transportation paths.

[0190] Calculate the probability of each transport path being selected: According to the calculation formula of the probability of being selected: Calculate the probability of each transportation route being selected.

[0191] For example, suppose there are three transport routes: route 1, route 2, and route 3. Their fitness values ​​are fitness(1), fitness(2), and fitness(3), and their creative factors are creative. factor (1)creative factor (2) and creative factor (3).

[0192] Calculate the sum of fitness values: sum fitness =fitness(1)+fitness(2)+fitness(3).

[0193] Calculate the sum of creative factors: sum(creative factor )=creative factor (1) +creative factor (2) +creative factor (3).

[0194] Calculate the probability of transport path 1 being selected:

[0195] Similarly, the selection probabilities of path 2 and path 3 can be calculated.

[0196] Through this step, the selection probability of each transport path can be calculated according to the fitness value and creativity factor of each transport path. These selection probabilities can be used in subsequent selection operations to determine the optimal transport path.

[0197] Optionally, in the embodiment of the present application, as a specific implementation scheme, the step 103 of “selecting a preset number of transport paths from the plurality of transport paths as parent transport paths based on the probability of selection of each transport path” may specifically include:

[0198] 1031. Normalize the selection probability of each of the transport paths, and divide the selection probability of each of the transport paths by the sum of the selection probabilities to obtain a normalized selection probability;

[0199] In step 1031, the selection probability of each transport path is normalized: the selection probability of each transport path is divided by the sum of the selection probabilities to perform normalization. The normalized selection probability represents the relative probability of each transport path being selected.

[0200] 1032. Sort the normalized selection probabilities of the plurality of transport paths by size to generate a cumulative probability sequence;

[0201] In step 1032, the normalized selection probabilities are sorted by size: the normalized selection probabilities of the multiple transport paths are sorted in descending order. In this way, the transport paths with higher probabilities are arranged in front. The sorted normalized probabilities are added in sequence to generate a cumulative probability sequence. The cumulative probability sequence represents the cumulative probability of each transport path being selected.

[0202] 1033. Generate a random number between 0 and 1, find the first transportation distance corresponding to the probability value greater than the random number from the cumulative probability sequence, and determine the transportation path as the parent transportation path.

[0203] In step 1033, a random number between 0 and 1 is generated, and the parent transport path is selected according to the cumulative probability sequence: a random number between 0 and 1 is generated, and then the first transport path corresponding to the probability value greater than the random number is found from the cumulative probability sequence. This transport path is determined as the parent transport path.

[0204] For example, suppose there are three transport routes: transport route 1, transport route 2, and transport route 3. Their normalized selection probabilities are probability (1) Normalized probability (2) Normalized probability (3), where normalized probability (i) is the normalized probability of selection probability (i).

[0205] Sort the normalized probabilities: Arrange the normalized probabilities in descending order to obtain a sorted probability sequence.

[0206] Generate a cumulative probability sequence: Add the sorted probabilities in sequence to obtain a cumulative probability sequence.

[0207] Generate random number: Generate a random number between 0 and 1, for example 0.6.

[0208] Select the parent transport path according to the cumulative probability sequence: find the first transport path corresponding to the probability value greater than the random number 0.6 from the cumulative probability sequence, such as transport path 2. Transport path 2 is determined as the parent transport path.

[0209] Through this step, a preset number of transport paths can be selected as parent transport paths according to the selection probability of each transport path. These parent transport paths will be used in subsequent crossover and mutation operations to generate the next generation of transport paths.

[0210] Optionally, in the embodiment of the present application, as a specific implementation scheme, the "randomly selecting an intersection point and intersecting at least two parent transport paths at the intersection point to generate a child transport path" in step 104 may specifically include:

[0211] 1041. Determine the length n of the parent transport path and generate a random number i between 1 and n-1 as the index of the intersection;

[0212] In step 1041, the length n of the parent transport path is determined, and a random number i between 1 and n-1 is generated as the index of the intersection: the length n of the parent transport path involved in the intersection is determined, and a random number i between 1 and n-1 is generated as the index of the intersection. This random number i determines the position of the intersection on the parent transport path.

[0213] 1042. Select at least two of the parent transport paths, and use the intersection i as a boundary to divide the at least two parent transport paths into two parts, thereby obtaining a first part and a second part.

[0214] In step 1042, at least two parent transport paths are selected, and the parent transport paths are divided into two parts with the intersection i as the boundary: at least two parent transport paths that participate in the intersection are selected from the parent transport paths, and the parent transport paths are divided into two parts with the intersection i as the boundary. The first part is the part before the intersection, and the second part is the part after the intersection.

[0215] 1043. Copy the first part from the first parent transport path to the child transport path, search for waypoints in the second part in the second parent transport path, and insert the waypoints in the second part into the position after the intersection i of the child transport path in the order of waypoints to generate a child transport path.

[0216] In step 1043, the first portion is copied from the first parent transport path to the child transport path: The first portion in the first parent transport path is copied to the child transport path.

[0217] Search the waypoints in the second part of the second parent transport path, and insert the waypoints in order after the intersection i of the child transport path: Search the waypoints in the second part of the second parent transport path in order, and insert the waypoints in order after the intersection i of the child transport path. In this way, the generated child transport path contains the first part from the first parent transport path, the second part from the second parent transport path, and the waypoints are inserted in order.

[0218] Through this step, we can randomly select a crossover point and cross at least two parent transport paths at the crossover point to generate child transport paths. These child transport paths will be evolved as the next generation of transport paths.

[0219] Figure 3 A structural diagram of a logistics truck transportation monitoring data processing system provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the system includes:

[0220] An acquisition module 31 is used to acquire transportation monitoring data of a logistics truck, wherein the transportation monitoring data includes a plurality of transportation routes, and each of the transportation routes includes a plurality of waypoints;

[0221] The calculation module 32 is used to determine a fitness function according to a preset index, and calculate the fitness value of each of the transport paths according to the fitness function, wherein the fitness function is used to evaluate the fitness of the transport path in the problem domain; calculate the selection probability of each of the transport paths based on the fitness values ​​of the plurality of transport paths, and select a preset number of transport paths from the plurality of transport paths as parent transport paths based on the selection probability of each of the transport paths;

[0222] A generation module 33, configured to randomly select an intersection point and intersect at least two parent transport paths at the intersection point to generate a child transport path;

[0223] The determination module 34 is used to determine whether the offspring transport path meets the mutation condition, and the mutation condition includes whether the random number corresponding to the offspring transport path is less than the set mutation rate. If so, the offspring transport path is mutated, and the mutation operation at least includes: exchanging the waypoint positions in the offspring transport path; merging the offspring transport path after the mutation operation and the parent transport path to generate a candidate transport path, and selecting the candidate transport path with the largest fitness value from the candidate transport paths as the target transport path.

[0224] Optionally, in the embodiment of the present application, the preset indicators include at least total distance, total cost, and total time, wherein the total distance refers to the cumulative distance of all waypoints passed by the truck during the transportation process, the total cost refers to the total cost incurred by the truck during the transportation process, and the total time refers to the total time spent by the truck during the transportation process;

[0225] The calculation module 32 is also used to calculate the fitness function formula: Determine the fitness function;

[0226] Among them, total distance (i) represents the total distance of transport path i, wd Expressed as the weight of the total distance, total time (i) represents the total time of transportation path i, w t Expressed as the weight of the total time, total cost (i) represents the total cost of transport path i, w c Expressed as a weight to the total cost.

[0227] Optionally, in an embodiment of the present application, the calculation module 32 is also used to calculate, for each of the transport paths, a distance matrix between multiple waypoints included in the transport path, and search for corresponding waypoints from the distance matrix according to the waypoint order of the multiple waypoints included in the transport path to calculate the distance between two waypoints, so as to accumulate and obtain the total distance of the transport path; obtain the average speed and travel time between the waypoints of the transport path, and calculate the total time of the transport path through the total distance of the transport path and the average speed and travel time between the waypoints in the transport path; obtain the unit distance cost and unit time cost between the waypoints of the transport path, and calculate the total cost of the transport path through the total distance of the transport path and the unit distance cost and unit time cost between the waypoints of the transport path; and bring the total distance of the transport path, the total time of the transport path and the total cost of the transport path into the fitness function calculation formula to calculate the fitness value of each of the transport paths.

[0228] Optionally, in an embodiment of the present application, the acquisition module 31 is specifically used to obtain the starting point and end point of the logistics truck from the transportation monitoring data of the logistics truck to determine the starting point and end point of each transportation path; determine the waypoints of each transportation path according to logistics demand and truck loading capacity; starting from the starting point, select the waypoints one by one to generate multiple transportation paths.

[0229] Optionally, in the embodiment of the present application, the calculation module 32 is further used to calculate the sum of the fitness values ​​of all the transport paths based on the fitness values ​​of the multiple transport paths; based on the sum of the fitness values ​​of all the transport paths, and the calculation formula of the probability of being selected: Calculating the probability of each transport path being selected;

[0230] Among them, selection probability (i) represents the probability of transport path i being selected, fitness(i) represents the fitness value of transport path i, creative factor (i) represents the creative factor of transport path i, which can be determined by the path difference of transport path i. factor(i) = diversity(i) / sum diversity , diversity(i) represents the path diversity of transport path i, sum diversity It is expressed as the sum of the path differences of all transportation paths, sum fitness It is expressed as the sum of the fitness values ​​of all transport paths (creative factor ) represents the sum of the creative factors of all transport paths;

[0231] The path differences include at least: the total distance difference between transport path i and other transport paths, the total time difference between transport path i and other transport paths, and the total cost difference between transport path i and other transport paths.

[0232] Optionally, in an embodiment of the present application, the calculation module 32 is also used to normalize the selection probability of each of the transport paths, and divide the selection probability of each of the transport paths by the sum of the selection probabilities to obtain a normalized selection probability; sort the normalized selection probabilities of multiple transport paths according to size to generate a cumulative probability sequence; generate a random number between 0 and 1, and find the first transport distance corresponding to a probability value greater than the random number from the cumulative probability sequence, and determine the transport path as the parent transport path.

[0233] Optionally, in an embodiment of the present application, the generation module 33 is specifically used to determine the length n of the parent transport path, and generate a random number i between 1 and n-1 as the index of the intersection; select at least two of the parent transport paths, and use the intersection i as the boundary to divide the at least two parent transport paths into two parts to obtain a first part and a second part; copy the first part from the first parent transport path to the child transport path, and search for the waypoints in the second part in the second parent transport path, and insert the waypoints in the second part into the position after the intersection i of the child transport path in the order of the waypoints to generate a child transport path.

[0234] Figure 3 The logistics truck transportation monitoring data processing system can execute Figure 1 The implementation principle and technical effect of the logistics truck transportation monitoring data processing method described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the logistics truck transportation monitoring data processing system in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0235] In one possible design, Figure 3The logistics truck transportation monitoring data processing system of the illustrated embodiment can be implemented as a computing device, such as Figure 4 As shown, the computing device may include a storage component 401 and a processing component 402;

[0236] The storage component 401 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 402 .

[0237] The processing component 402 is used to: obtain the transportation monitoring data of the logistics truck, the transportation monitoring data includes a plurality of transportation paths, each of the transportation paths includes a plurality of waypoints; determine the fitness function according to the preset index, and calculate the fitness value of each of the transportation paths according to the fitness function, the fitness function is used to evaluate the fitness of the transportation path in the problem domain; calculate the selection probability of each of the transportation paths based on the fitness values ​​of the plurality of transportation paths, and select a preset number of transportation paths from the plurality of transportation paths as parent transportation paths based on the selection probability of each of the transportation paths; and The machine selects an intersection point and intersects at least two parent transport paths at the intersection point to generate a child transport path; determines whether the child transport path meets a mutation condition, the mutation condition includes whether the random number corresponding to the child transport path is less than a set mutation rate, and if so, performs a mutation operation on the child transport path, the mutation operation at least includes: exchanging the waypoint positions in the child transport path; merging the child transport path after the mutation operation and the parent transport path to generate multiple candidate transport paths, and selecting the candidate transport path with the largest fitness value from the multiple candidate transport paths as the target transport path.

[0238] The processing component 402 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0239] The storage component 401 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0240] The display component 403 may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.

[0241] Of course, a computing device may also include other components, such as input / output interfaces, communication components, etc.

[0242] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0243] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0244] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0245] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The logistics truck transportation monitoring data processing method of the embodiment shown.

[0246] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0247] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0248] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0249] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for processing logistics truck transportation monitoring data, characterized in that: include: Acquire transportation monitoring data of a logistics truck, wherein the transportation monitoring data includes a plurality of transportation routes, and each of the transportation routes includes a plurality of waypoints; Determine a fitness function according to a preset indicator, and calculate the fitness value of each of the transport paths according to the fitness function, wherein the fitness function is used to evaluate the adaptability of the transport path in the problem domain; Based on the fitness values ​​of the plurality of transport paths, the selection probability of each transport path is calculated, and based on the selection probability of each transport path, a preset number of transport paths are selected from the plurality of transport paths as parent transport paths; Randomly select an intersection point, and intersect at least two parent transport paths at the intersection point to generate a child transport path; Determine whether the child transport path meets a mutation condition, wherein the mutation condition includes whether the random number corresponding to the child transport path is less than a set mutation rate, and if so, perform a mutation operation on the child transport path, wherein the mutation operation at least includes: exchanging the waypoint positions in the child transport path; Merging the child transport path after the mutation operation and the parent transport path to generate multiple candidate transport paths, and selecting the candidate transport path with the largest fitness value from the multiple candidate transport paths as the target transport path; The preset indicators include at least total distance, total cost, and total time, wherein the total distance refers to the cumulative distance of all waypoints passed by the truck during the transportation process, the total cost refers to the total cost incurred by the truck during the transportation process, and the total time refers to the total time spent by the truck during the transportation process; Determining the fitness function according to the preset index includes: The fitness function is calculated by the formula: , determine the fitness function; in, Indicates the transport route The total distance, Expressed as the weight of the total distance, Indicates the transport route The total time, Expressed as the weight of the total time, Indicates the transport route The total cost, Expressed as the weight of the total cost; Calculating the fitness value of each of the transport paths according to the fitness function includes: For each of the transport paths, a distance matrix between a plurality of waypoints included in the transport path is calculated, and according to the waypoint sequence of the plurality of waypoints included in the transport path, a corresponding waypoint is searched from the distance matrix to calculate the distance between two waypoints, so as to accumulate and obtain a total distance of the transport path; Obtaining the average speed and travel time between waypoints of the transport path, and calculating the total time of the transport path by using the total distance of the transport path and the average speed and travel time between waypoints in the transport path; Obtaining the unit distance cost and the unit time cost between the waypoints of the transport path, and calculating the total cost of the transport path by the total distance of the transport path and the unit distance cost and the unit time cost between the waypoints of the transport path; Substituting the total distance of the transport path, the total time of the transport path and the total cost of the transport path into the fitness function calculation formula to calculate the fitness value of each of the transport paths; The step of calculating the selection probability of each of the transport paths based on the fitness values ​​of the plurality of transport paths comprises: Based on the fitness values ​​of the plurality of transport paths, the sum of the fitness values ​​of all the transport paths is calculated; based on the sum of the fitness values ​​of all the transport paths, the calculation formula of the probability of being selected is: , calculate the probability of each transportation path being selected; in, Represented as a transport path The probability of being selected, Represented as a transport path The fitness value of Indicates the transport route The inventive factor can be transported through the transport path Determined by the path differences, , Represented as a transport path The path differences, It is expressed as the sum of the path differences of all transportation paths, Expressed as the sum of the fitness values ​​of all transport paths represents the sum of the creative factors of all transport paths; The path differences include at least: transportation path Total distance difference with other transport routes, transport routes Total time difference with other transport routes, transport routes Total cost difference with other transport routes; The step of selecting a preset number of transport paths from the plurality of transport paths as parent transport paths based on the probability of selection of each transport path comprises: Normalizing the selection probability of each of the transport paths, and dividing the selection probability of each of the transport paths by the sum of the selection probabilities to obtain a normalized selection probability; Sorting the normalized selection probabilities of the plurality of transport routes in order of magnitude to generate a cumulative probability sequence; Generate a random number between 0 and 1, and find the first transportation distance corresponding to the probability value greater than the random number from the cumulative probability sequence, and determine the transportation path as the parent transportation path; The method of randomly selecting an intersection point and crossing at least two parent transport paths at the intersection point to generate a child transport path comprises: Determine the length n of the parent transport path and generate a random number i between 1 and n-1 as the index of the intersection; Select at least two of the parent transport paths, and use the intersection i as a boundary to divide the at least two parent transport paths into two parts, thereby obtaining a first part and a second part; The first part is copied from the first parent transport path to the child transport path, and the waypoints in the second part are found in the second parent transport path, and the waypoints in the second part are inserted into the position after the intersection i of the child transport path according to the order of the waypoints to generate the child transport path.

2. The method according to claim 1, characterized in that The transport monitoring data of the logistics truck is obtained, wherein the transport monitoring data includes a plurality of transport routes, and each of the transport routes includes a plurality of waypoints, including: Obtaining the starting point and the end point of the logistics truck from the transportation monitoring data of the logistics truck to determine the starting point and the end point of each transportation path; Determining the waypoints of each of the transportation routes according to logistics requirements and truck loading capacity; Starting from the starting point, select the waypoints one by one to generate multiple transportation routes.

3. A logistics truck transportation monitoring data processing system, characterized in that: include: An acquisition module, used to acquire transportation monitoring data of a logistics truck, wherein the transportation monitoring data includes a plurality of transportation routes, and each of the transportation routes includes a plurality of waypoints; A calculation module, used to determine a fitness function according to a preset indicator, and calculate the fitness value of each of the transportation paths according to the fitness function, wherein the fitness function is used to evaluate the adaptability of the transportation path in the problem domain; Based on the fitness values ​​of the plurality of transport paths, the selection probability of each transport path is calculated, and based on the selection probability of each transport path, a preset number of transport paths are selected from the plurality of transport paths as parent transport paths; A generation module, configured to randomly select an intersection point and intersect at least two parent transport paths at the intersection point to generate a child transport path; A determination module is used to determine whether the child transport path meets a mutation condition, wherein the mutation condition includes whether the random number corresponding to the child transport path is less than a set mutation rate. If so, a mutation operation is performed on the child transport path, wherein the mutation operation at least includes: exchanging the waypoint positions in the child transport path; merging the child transport path after the mutation operation and the parent transport path to generate a candidate transport path, and selecting the candidate transport path with the largest fitness value from the candidate transport paths as the target transport path; The preset indicators include at least total distance, total cost, and total time, wherein the total distance refers to the cumulative distance of all waypoints passed by the truck during the transportation process, the total cost refers to the total cost incurred by the truck during the transportation process, and the total time refers to the total time spent by the truck during the transportation process; The calculation module is also used to calculate the fitness function formula: , determine the fitness function; in, Indicates the transport route The total distance, Expressed as the weight of the total distance, Indicates the transport route The total time, Expressed as the weight of the total time, Indicates the transport route The total cost, Expressed as the weight of the total cost; The calculation module is also used to calculate, for each of the transport paths, a distance matrix between a plurality of waypoints included in the transport path, and search for corresponding waypoints from the distance matrix according to the waypoint sequence of the plurality of waypoints included in the transport path, so as to calculate the distance between two waypoints, so as to accumulate and obtain the total distance of the transport path; obtain the average speed and travel time between the waypoints of the transport path, and calculate the total time of the transport path through the total distance of the transport path and the average speed and travel time between the waypoints in the transport path; obtain the unit distance cost and unit time cost between the waypoints of the transport path, and calculate the total cost of the transport path through the total distance of the transport path and the unit distance cost and unit time cost between the waypoints of the transport path; bring the total distance of the transport path, the total time of the transport path and the total cost of the transport path into the fitness function calculation formula, so as to calculate the fitness value of each of the transport paths; The calculation module is also used to calculate the sum of the fitness values ​​of all the transport paths based on the fitness values ​​of the multiple transport paths; the calculation formula based on the sum of the fitness values ​​of all the transport paths and the probability of being selected is: , calculate the probability of each transportation path being selected; in, Represented as a transport path The probability of being selected, Represented as a transport path The fitness value of Indicates the transport route The inventive factor can be transported through the transport path Determined by the path differences, , Represented as a transport path The path differences, It is expressed as the sum of the path differences of all transportation paths, Expressed as the sum of the fitness values ​​of all transport paths represents the sum of the creative factors of all transport paths; The path differences include at least: transportation path Total distance difference with other transport routes, transport routes Total time difference with other transport routes, transport routes Total cost difference with other transport routes; The calculation module is also used to normalize the selection probability of each of the transport paths, and divide the selection probability of each of the transport paths by the sum of the selection probabilities to obtain the normalized selection probability; sort the normalized selection probabilities of the multiple transport paths in order to generate a cumulative probability sequence; generate a random number between 0 and 1, and find the first transport distance corresponding to the probability value greater than the random number from the cumulative probability sequence, and determine the transport path as the parent transport path; The generation module is specifically used to determine the length n of the parent transport path and generate a random number i between 1 and n-1 as the index of the intersection; select at least two of the parent transport paths and divide the at least two parent transport paths into two parts with the intersection i as the boundary to obtain a first part and a second part; copy the first part from the first parent transport path to the child transport path, search for the waypoints in the second part in the second parent transport path, and insert the waypoints in the second part into the position after the intersection i of the child transport path in the order of the waypoints to generate the child transport path.

4. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the logistics truck transportation monitoring data processing method as described in claim 1 or 2.

5. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed, the logistics truck transportation monitoring data processing method as described in claim 1 or 2 is implemented.