Engineering vehicle scheduling method and device, processor and machine readable storage medium

Abstract

The invention discloses an engineering vehicle scheduling method and device, a processor and a machine readable storage medium, and relates to the technical field of intelligent logistics. The method comprises the steps of extracting scheduling features based on acquired historical operation data, wherein the historical operation data comprises historical transportation data, historical task data and historical working condition data; and the scheduling features are respectively input into the first random forest model and the second random forest model to obtain the prediction task demand and the scheduling strategy, so that the scene adaptability of the prediction task demand and the scheduling strategy is improved. Determining an objective function and a constraint condition of a mixed integer programming model based on the prediction task demand, the scheduling strategy and the resource limitation condition of the engineering vehicle; optimizing a target function of the mixed integer programming model based on constraint conditions; and the accuracy of the mixed integer programming model is improved. And outputting an engineering vehicle scheduling scheme corresponding to the optimized target function based on the mixed integer programming model, thereby improving the effectiveness and robustness of engineering vehicle scheduling.

Description

Technical Field

[0001] The present application relates to the field of intelligent logistics technology, and specifically to an engineering vehicle scheduling method, device, processor and machine-readable storage medium. Background Art

[0002] In modern construction, the dispatching and management of concrete mixer trucks is one of the key links to ensure the progress and quality of the project. Traditional dispatching plans are usually determined by dispatchers based on current needs and professional knowledge. Such plans often rely on the dispatcher's personal experience and intuition, and are difficult to cover complex application conditions, which can easily lead to decision-making errors. Especially when faced with large-scale and changing dispatching needs, traditional manual scheduling methods rely on the dispatcher's experience and judgment, which makes it difficult to accurately predict demand fluctuations, and can easily lead to problems such as empty vehicle driving, long waiting times, and waste of resources. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the purpose of the embodiments of the present application is to provide an engineering vehicle scheduling method, device, processor and machine-readable storage medium.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a construction vehicle dispatching method, comprising:

[0005] Extract scheduling features based on the acquired historical operation data, where the historical operation data includes historical transportation data, historical task data, and historical working condition data;

[0006] The scheduling features are input into the first random forest model and the second random forest model respectively to obtain the predicted task demand and scheduling strategy;

[0007] Determine the objective function and constraints of the mixed integer programming model based on the predicted mission requirements, scheduling strategy, and resource constraints of engineering vehicles;

[0008] Optimize the objective function of the mixed integer programming model based on constraints;

[0009] The engineering vehicle scheduling plan corresponding to the optimized objective function is output based on the mixed integer programming model.

[0010] In the embodiment of the present application, the constraints include task allocation constraints, vehicle capacity constraints and time window constraints. The objective function and constraints of the mixed integer programming model are determined based on the predicted task requirements, scheduling strategies and resource constraints of engineering vehicles, including:

[0011] Determine a time window constraint based on the predicted task requirements, wherein the time window constraint is used to limit the start and end of the task to be executed within a preset time range;

[0012] Determine the task allocation constraint and vehicle capacity constraint based on the resource constraint, wherein the task allocation constraint is used to limit the engineering vehicle to only perform one task to be performed in each time unit, and the vehicle capacity constraint is used to limit the number of engineering vehicles and the operating time of each engineering vehicle;

[0013] An objective function is determined based on the scheduling strategy, wherein the objective function is used to minimize the total operating cost of the engineering vehicle scheduling solution.

[0014] In the embodiment of the present application, determining the time window constraint based on the prediction task requirement includes:

[0015] Determine a preset number of tasks to be performed and a time limit for completing the tasks based on preset task requirements, wherein the tasks to be performed include a fixed number of cargo transportation requirements;

[0016] The time window constraint of each task to be executed is determined based on the task completion deadline corresponding to each task to be executed.

[0017] In the embodiment of the present application, the engineering vehicle scheduling scheme corresponding to the optimized objective function outputted based on the mixed integer programming model includes:

[0018] Determine target values ​​of a first decision variable and a second decision variable in a mixed integer programming model based on the optimized objective function, wherein the first decision variable represents a decision variable that an engineering vehicle is assigned to a task to be performed in a preset time unit, and the second decision variable represents a decision variable that a task to be performed is started in a preset time unit;

[0019] A construction vehicle scheduling solution is generated based on the target values ​​of the first decision variable and the second decision variable.

[0020] In the embodiment of the present application, the scheduling features are extracted based on the acquired historical job data, including:

[0021] Get historical job data;

[0022] Preprocess historical operation data, including data denoising, missing value processing, and data standardization;

[0023] Extract scheduling features based on preprocessed historical job data.

[0024] In the embodiment of the present application, the engineering vehicle dispatching method further includes:

[0025] Obtain input task execution feedback information, and adjust constraint conditions based on the task execution feedback information;

[0026] Optimize the objective function of the mixed integer programming model based on the adjusted constraints.

[0027] In the embodiment of the present application, the engineering vehicle dispatching method further includes:

[0028] Determine the personnel to be executed and the tasks to be executed corresponding to the personnel to be executed based on the engineering vehicle dispatch plan and the preset shift schedule;

[0029] The tasks to be executed are sent to the mobile terminal associated with the person to be executed.

[0030] A second aspect of the present application provides an engineering vehicle dispatching device, comprising:

[0031] A feature extraction module is used to extract scheduling features based on the acquired historical operation data, where the historical operation data includes historical transportation data, historical task data, and historical working condition data;

[0032] A model prediction module, used to input the scheduling features into the first random forest model and the second random forest model respectively to obtain predicted task requirements and scheduling strategies;

[0033] A function determination module is used to determine the objective function and constraints of the mixed integer programming model based on the predicted task requirements, scheduling strategies, and resource constraints of the engineering vehicle;

[0034] Model optimization module, used to optimize the objective function of the mixed integer programming model based on constraints;

[0035] The scheme determination module is used to output the engineering vehicle scheduling scheme corresponding to the optimized objective function based on the mixed integer programming model.

[0036] A third aspect of the present application provides a processor configured to execute the engineering vehicle scheduling method as described in the above embodiment.

[0037] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the engineering vehicle scheduling method as described in the above-mentioned embodiment.

[0038] Through the above technical solution, the scheduling features are extracted based on the historical operation data obtained, and the historical operation data includes historical transportation data, historical task data and historical working condition data; the scheduling features are respectively input into the first random forest model and the second random forest model to obtain the predicted task requirements and scheduling strategies, thereby improving the scenario adaptability of the predicted task requirements and scheduling strategies. The objective function and constraints of the mixed integer programming model are determined based on the predicted task requirements, scheduling strategies and resource constraints of engineering vehicles; the objective function of the mixed integer programming model is optimized based on the constraints; and the accuracy of the mixed integer programming model is improved. Based on the output of the mixed integer programming model, the engineering vehicle scheduling scheme corresponding to the optimized objective function is improved, thereby improving the effectiveness and robustness of engineering vehicle scheduling.

[0039] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0041] Figure 1 A schematic diagram of a process flow of a method for dispatching engineering vehicles according to an embodiment of the present application is schematically shown;

[0042] Figure 2 The structural diagram of an engineering vehicle dispatching device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0044] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0045] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0046] Figure 1 The following schematically shows a flow chart of a method for dispatching engineering vehicles according to an embodiment of the present application. Figure 1As shown, the embodiment of the present application provides a method for dispatching engineering vehicles, which may include the following steps:

[0047] Step 100, extracting scheduling features based on the acquired historical operation data, where the historical operation data includes historical transportation data, historical task data, and historical operating condition data;

[0048] In this embodiment, it should be noted that historical operation data refers to the relevant data of the engineering vehicle performing operations within the past preset time. Based on the historical operation data, the scheduling of engineering vehicles in multiple time periods can be obtained, so that the scheduling needs of engineering vehicles in the future preset time can be predicted based on the historical operation data, thereby improving the effectiveness of engineering vehicle scheduling. Historical operation data includes historical transportation data, historical task data and historical working condition data. Among them, historical transportation data includes the waybill records of engineering vehicles within the past preset time, for example, the start production time, end production time, departure time, arrival time at the construction site, unloading time, return time to the base, single mileage and single fuel consumption data for each operation. Historical task data includes the operation demand for engineering vehicles in different time periods and different areas within the past preset time. Historical working condition data includes the vehicle position, driving speed and operation status of engineering vehicles within the past preset time. Scheduling features refer to the features in the historical operation data that have a direct impact on the scheduling of engineering vehicles, which can be defined based on actual application scenarios, for example, historical order volume, vehicle idle time, average completion time, etc.

[0049] Specifically, in one embodiment, extracting scheduling features based on the acquired historical job data includes:

[0050] Get historical job data;

[0051] Preprocess historical operation data, including data denoising, missing value processing, and data standardization;

[0052] Extract scheduling features based on preprocessed historical job data.

[0053] It should be noted that the acquisition of historical operation data may be based on the collection of multiple data sources, and there may be some data noise or some data missing in each historical operation data. In order to improve the effectiveness of the acquisition of scheduling features. In this embodiment, before extracting scheduling features based on historical operation data, the historical operation data is preprocessed, and then the scheduling features are extracted based on the preprocessed historical operation data. Preprocessing includes data denoising, missing value processing and data standardization. Among them, data denoising includes identifying and eliminating outliers, such as abnormal driving speed records (speeding or stagnation), unreasonable operation time, etc.; missing value processing includes using interpolation to process missing data to ensure data continuity and integrity; data standardization includes unified standardization of data from different sources and scales.

[0054] In this embodiment, the historical operation data is preprocessed to improve the validity and accuracy of the historical operation data and improve the accuracy of the extraction of scheduling features.

[0055] Step 200, inputting the scheduling features into the first random forest model and the second random forest model respectively to obtain predicted task requirements and scheduling strategies;

[0056] Step 300, determining the objective function and constraints of the mixed integer programming model based on the predicted task requirements, scheduling strategy and resource constraints of the engineering vehicle;

[0057] It should be noted that random forest is an integrated learning method, which is particularly suitable for classification, regression and other machine learning tasks. Random forest is an extension based on the decision tree algorithm, which improves the accuracy and robustness of the overall prediction by constructing multiple decision trees and aggregating the predictions of the multiple decision trees. In this embodiment, the first random forest model is used to generate the prediction task demand, and the first random forest model is used to generate the scheduling strategy. Specifically, the scheduling features are respectively input into the first random forest model and the second random forest model to obtain the prediction task demand and the scheduling strategy. Among them, the prediction task demand includes the execution time limit corresponding to the task to be performed by the engineering vehicle, for example, the start time and end time of the task to be performed, the total execution time of the task to be performed, etc. The scheduling strategy is used to limit the relevant impacts of engineering vehicle scheduling, such as the operating cost of engineering vehicle scheduling, the vehicle utilization rate of engineering vehicle scheduling, the completion rate of the task to be performed, etc. It can be understood that different random forest models with different functions can be generated by setting different random forest objective functions and model parameters during training, thereby meeting the generation requirements of setting different prediction task requirements and different scheduling strategies.

[0058] It should be noted that the mixed integer programming model is an important branch of operations research and optimization theory. It is a special mathematical programming problem in which some decision variables are restricted to integer values, while other decision variables can take real values. This problem combines the characteristics of integer programming and linear programming, allowing the model to simulate decision problems in the real world more flexibly. The mixed integer programming model abstracts the actual problem into a mathematical model, defining decision variables, objective functions and constraints. In this embodiment, the decision variables of the mixed integer programming model are determined based on the job planning of engineering vehicle scheduling. For example, the decision variables include a first decision variable and a second decision variable, wherein the first decision variable represents the decision variable that the engineering vehicle is assigned to the task to be executed in a preset time unit, and the second decision variable represents the decision variable that the task to be executed is started in a preset time unit.

[0059] It should be noted that in conventional technology, the objective function and constraints of the mixed integer programming model are determined based on the scheduling requirements input by the user. The objective function and constraints determined based on subjective experience usually have certain adaptability limitations in practical applications, especially for scenarios with large fluctuations in scheduling requirements, which are not friendly to the optimization of the mixed integer programming model. To overcome the above problems, in this embodiment, the first random forest model and the second random forest model are used to generate predicted task requirements and scheduling strategies, and the objective function and constraints of the mixed integer programming model are determined based on the predicted task requirements, scheduling strategies and resource constraints of engineering vehicles. The first random forest model and the second random forest model generate predicted task requirements and scheduling strategies based on the scheduling features extracted from historical operation data, which improves the applicability of the predicted task requirements and scheduling strategies, removes the adaptability limitations of the mixed integer programming model to the application scenarios, and thus improves the accuracy of the mixed integer programming model.

[0060] Step 400, optimizing the objective function of the mixed integer programming model based on the constraint conditions;

[0061] Step 500: Outputting an engineering vehicle scheduling solution corresponding to the optimized objective function based on the mixed integer programming model.

[0062] It should be noted that the objective function of the mixed integer programming model is continuously iteratively optimized based on the constraints, so that the engineering vehicle scheduling plan corresponding to the objective function of the mixed integer programming model satisfies the constraints, thereby improving the effectiveness of the engineering vehicle scheduling plan. It should be noted that for the iterative optimization of the objective function, the iteration termination condition can be restricted based on a preset number of iterations, or the iteration termination condition can be restricted based on the degree of convergence of the function. After the objective function is iteratively optimized, the mixed integer programming model outputs the engineering vehicle scheduling plan corresponding to the optimized objective function.

[0063] Specifically, in one embodiment, the engineering vehicle scheduling solution corresponding to the optimized objective function is output based on the mixed integer programming model, including:

[0064] Determine target values ​​of a first decision variable and a second decision variable in a mixed integer programming model based on the optimized objective function, wherein the first decision variable represents a decision variable that an engineering vehicle is assigned to a task to be performed in a preset time unit, and the second decision variable represents a decision variable that a task to be performed is started in a preset time unit;

[0065] A construction vehicle scheduling solution is generated based on the target values ​​of the first decision variable and the second decision variable.

[0066] It should be noted that the first decision variable represents the decision variable that the engineering vehicle is assigned to the task to be executed in the preset time unit, and the second decision variable represents the decision variable that the task to be executed is started in the preset time unit; in one embodiment, the first decision variable is x ijt , x ijt represents the decision variable for the i-th engineering vehicle to be assigned to the j-th task at time t, x ijt ∈{0, 1}, is an integer variable. The second decision variable is y jt ,y jt represents the decision variable for the jth task to be started at time t, y jt ∈{0, 1}, is an integer variable. The objective function is determined based on the operating cost of the engineering vehicle. Assume that the objective function is z t , z t represents the total operating cost of dispatching engineering vehicles in the tth period and is a continuous variable. In one embodiment, the objective function z t It can be expressed as:

[0067]

[0068] Among them, C ij represents the cost of the i-th engineering vehicle to perform task j; W j Represents the unit time cost of executing the jth task at time t; other cost items can be determined or deleted based on the actual application scenario.

[0069] In this embodiment, the objective is to minimize the objective function, and the objective function is optimized based on the constraint conditions, and then the target values ​​of the first decision variable and the second decision variable in the mixed integer programming model can be determined based on the optimized objective function.

[0070] In this embodiment, the target values ​​of the first decision variable and the second decision variable in the mixed integer programming model are determined based on the optimized objective function, the data accuracy of the first decision variable and the second decision variable is improved, and then the effectiveness of the engineering vehicle scheduling plan is improved, the waste of resources caused by inaccurate demand estimation is reduced, and the utilization rate of engineering vehicles is improved.

[0071] In one embodiment, the engineering vehicle scheduling method further includes:

[0072] Obtain input task execution feedback information, and adjust constraint conditions based on the task execution feedback information;

[0073] Optimize the objective function of the mixed integer programming model based on the adjusted constraints.

[0074] In this embodiment, it should be noted that after executing the engineering vehicle scheduling operation for the engineering vehicle based on the engineering vehicle scheduling plan, the relevant personnel who perform the engineering vehicle scheduling operation can provide feedback based on the execution status of the engineering vehicle scheduling operation. Specifically, the task execution feedback information can be input to adjust the constraints of the mixed integer programming model based on the task execution feedback information, and further optimize the objective function of the mixed integer programming model based on the adjusted constraints to enhance the adaptability of the mixed integer programming model to actual application scenarios.

[0075] In one embodiment, the engineering vehicle scheduling method further includes:

[0076] Determine the personnel to be executed and the tasks to be executed corresponding to the personnel to be executed based on the engineering vehicle dispatch plan and the preset shift schedule;

[0077] The tasks to be executed are sent to the mobile terminal associated with the person to be executed.

[0078] In this embodiment, after the engineering vehicle scheduling plan is generated, the personnel to be executed and the tasks to be executed corresponding to the personnel to be executed for performing the engineering vehicle scheduling operation can be determined based on the engineering vehicle scheduling plan and the preset shift schedule, and the tasks to be executed can be sent to the mobile terminal associated with the personnel to be executed, so that the personnel to be executed can directly receive the tasks to be executed, thereby improving the execution efficiency of the engineering vehicle scheduling operation.

[0079] In this embodiment, the scheduling features are extracted based on the acquired historical operation data, which includes historical transportation data, historical task data, and historical working condition data; the scheduling features are respectively input into the first random forest model and the second random forest model to obtain the predicted task requirements and scheduling strategies, thereby improving the scenario adaptability of the predicted task requirements and scheduling strategies. The objective function and constraints of the mixed integer programming model are determined based on the predicted task requirements, scheduling strategies, and resource constraints of engineering vehicles; the objective function of the mixed integer programming model is optimized based on the constraints; and the accuracy of the mixed integer programming model is improved. Based on the output of the mixed integer programming model, an engineering vehicle scheduling solution corresponding to the optimized objective function is output, thereby improving the effectiveness and robustness of engineering vehicle scheduling.

[0080] In one embodiment, the constraints include task allocation constraints, vehicle capacity constraints, and time window constraints. The objective function and constraints of the mixed integer programming model are determined based on the predicted task requirements, scheduling strategies, and resource constraints of the engineering vehicle, including:

[0081] Determine a time window constraint based on the predicted task requirements, wherein the time window constraint is used to limit the start and end of the task to be executed within a preset time range;

[0082] Determine the task allocation constraint and vehicle capacity constraint based on the resource constraint, wherein the task allocation constraint is used to limit the engineering vehicle to only perform one task to be performed in each time unit, and the vehicle capacity constraint is used to limit the number of engineering vehicles and the operating time of each engineering vehicle;

[0083] An objective function is determined based on the scheduling strategy, wherein the objective function is used to minimize the total operating cost of the engineering vehicle scheduling solution.

[0084] It should be noted that the predicted task demand includes an execution time limit corresponding to the pending task that the engineering vehicle needs to perform. In this embodiment, it is used to limit the start and end of the pending task within a preset time range. Specifically, the time window constraint in the constraint condition is determined by predicting the task demand, so as to limit the start time and end time of the pending task based on the time window constraint.

[0085] Specifically, in one embodiment, determining the time window constraint based on the predicted task demand includes:

[0086] Determine a preset number of tasks to be performed and a time limit for completing the tasks based on preset task requirements, wherein the tasks to be performed include a fixed number of cargo transportation requirements;

[0087] The time window constraint of each task to be executed is determined based on the task completion deadline corresponding to each task to be executed.

[0088] It should be noted that after determining the preset task requirements, the tasks to be performed included in the preset task requirements are obtained, and the time window constraint of each task to be performed is determined based on the task completion time limit corresponding to each task to be performed. In this embodiment, the time window constraint can be completed by limiting the start time and departure time of the engineering vehicle to perform the task to be performed. Specifically, in one embodiment, the time window constraint may include:

[0089] 1. Start time: Construction vehicles must arrive at the construction site within the specified time window:

[0090]

[0091] Among them, textEarliestTime j LatestTime represents the earliest time that the construction vehicle arrives at the construction site in the jth task; j represents the latest time that the engineering vehicle arrives at the construction site in the jth task; t ij Indicates the start time when the i-th engineering vehicle completes the j-th task.

[0092] 2. Leaving time: Taking into account the operation time, construction vehicles must leave the construction site before the specified time:

[0093]

[0094] Among them, LatestDepartureTime j Indicates the latest time when the construction vehicle leaves the construction site; t ij represents the start time of the i-th engineering vehicle completing the j-th task; s ij The operating time required for the i-th engineering vehicle to complete the j-th task.

[0095] Determine the task allocation constraint and vehicle capacity constraint based on the resource constraint, wherein the task allocation constraint is used to limit the engineering vehicle to only perform one task to be performed in each time unit, and the vehicle capacity constraint is used to limit the number of engineering vehicles and the operating time of each engineering vehicle;

[0096] It should be noted that the resource constraint is used to limit the engineering vehicle resources that can be used for the task to be performed. Specifically, the task allocation constraint is used to limit the engineering vehicle to only perform one task to be performed in each time unit, including:

[0097] Vehicle capacity constraints are used to limit the number of engineering vehicles and the operating time of each engineering vehicle, including:

[0098] 1. Ensure that the number of engineering vehicles assigned to a task does not exceed the total number of available engineering vehicles:

[0099]

[0100] Among them, sum j represents the sum of all tasks; x ij The decision variable that indicates that the i-th engineering vehicle is assigned to perform the j-th task.

[0101] 2. Ensure that the driver's working hours for each vehicle do not exceed the prescribed upper limit:

[0102]

[0103] Among them, sum j represents the sum of all tasks; t ij represents the start time of the i-th engineering vehicle completing the j-th task; s ij The working time required for the i-th engineering vehicle to complete the j-th task; MaxWorkingHours indicates the upper limit of the vehicle's working time.

[0104] The scheduling strategy is used to limit the impact of engineering vehicle scheduling. In this embodiment, the objective function is determined based on the scheduling strategy to minimize the total operating cost of the engineering vehicle scheduling solution through the objective function. t It can be expressed as:

[0105]

[0106] Among them, C ij represents the cost of the i-th engineering vehicle to perform task j; W j Represents the unit time cost of executing the jth task at time t; other cost items can be determined or deleted based on the actual application scenario.

[0107] In this embodiment, by determining the constraint conditions, the effectiveness and accuracy of the objective function are improved, thereby improving the effectiveness of the engineering vehicle scheduling plan, reducing the waste of resources caused by inaccurate demand estimation, and improving the utilization rate of engineering vehicles.

[0108] refer to Figure 2 The embodiment of the present application further provides an engineering vehicle dispatching device 1000, comprising:

[0109] A feature extraction module 1001 is used to extract scheduling features based on the acquired historical operation data, where the historical operation data includes historical transportation data, historical task data, and historical working condition data;

[0110] Model prediction module 1002, used to input the scheduling features into the first random forest model and the second random forest model respectively to obtain predicted task requirements and scheduling strategies;

[0111] Function determination module 1003, used to determine the objective function and constraint conditions of the mixed integer programming model based on the predicted task requirements, scheduling strategy and resource constraints of the engineering vehicle;

[0112] Model optimization module 1004, used for optimizing the objective function of the mixed integer programming model based on constraint conditions;

[0113] The solution determination module 1005 is used to output an engineering vehicle scheduling solution corresponding to the optimized objective function based on the mixed integer programming model.

[0114] The engineering vehicle dispatching device provided in the embodiment of the present application can respectively realize Figure 1 The various processes of the engineering vehicle scheduling method in the method embodiment can achieve the same technical effect. To avoid repetition, they will not be described here.

[0115] An embodiment of the present application also provides a processor configured to execute the engineering vehicle scheduling method as described in the above embodiment.

[0116] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned engineering vehicle scheduling method.

[0117] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0118] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0119] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0120] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0121] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0122] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0123] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0124] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0125] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for dispatching engineering vehicles, characterized in that: include: Extracting scheduling features based on the acquired historical operation data, wherein the historical operation data includes historical transportation data, historical task data, and historical operating condition data; Inputting the scheduling features into a first random forest model and a second random forest model respectively to obtain predicted task requirements and scheduling strategies; Determining the objective function and constraint conditions of the mixed integer programming model based on the predicted task requirements, the scheduling strategy, and the resource constraints of the engineering vehicle; Optimizing the objective function of the mixed integer programming model based on the constraint conditions; An engineering vehicle scheduling plan corresponding to the optimized objective function is output based on the mixed integer programming model.

2. The engineering vehicle dispatching method according to claim 1, characterized in that: The constraints include task allocation constraints, vehicle capacity constraints and time window constraints. The objective function and constraints of the mixed integer programming model are determined based on the predicted task requirements, the scheduling strategy and the resource constraints of the engineering vehicle, including: Determining the time window constraint based on the predicted task demand, wherein the time window constraint is used to limit the start and end of the task to be executed within a preset time range; Determining the task allocation constraint and the vehicle capability constraint based on the resource constraint, wherein the task allocation constraint is used to limit the engineering vehicle to only perform one task to be performed in each time unit, and the vehicle capability constraint is used to limit the number of the engineering vehicles and the operating time of each of the engineering vehicles; The objective function is determined based on the scheduling strategy, wherein the objective function is used to minimize the total operating cost of the engineering vehicle scheduling solution.

3. The engineering vehicle dispatching method according to claim 2, characterized in that: The determining the time window constraint based on the forecast task requirement includes: Determine a preset number of tasks to be performed and a time limit for completing the tasks based on preset task requirements, wherein the tasks to be performed include a fixed number of cargo transportation requirements; The time window constraint of each of the tasks to be executed is determined based on the task completion time limit corresponding to each of the tasks to be executed.

4. The engineering vehicle dispatching method according to claim 1, characterized in that: The engineering vehicle scheduling solution based on the output of the mixed integer programming model and corresponding to the optimized objective function includes: Determining target values ​​of a first decision variable and a second decision variable in the mixed integer programming model based on the optimized objective function, wherein the first decision variable represents a decision variable that the engineering vehicle is assigned to a task to be performed in a preset time unit, and the second decision variable represents a decision variable that the task to be performed is started in the preset time unit; A construction vehicle scheduling plan is generated based on the target values ​​of the first decision variable and the second decision variable.

5. The engineering vehicle dispatching method according to claim 1, characterized in that: The extracting of scheduling features based on the acquired historical job data includes: Get historical job data; Preprocessing the historical operation data, wherein the preprocessing includes data denoising, missing value processing, and data standardization; Extract scheduling features based on preprocessed historical job data.

6. The engineering vehicle dispatching method according to claim 1, characterized in that: Also includes: Acquire input task execution feedback information, and adjust the constraint condition based on the task execution feedback information; The objective function of the mixed integer programming model is optimized based on the adjusted constraints.

7. The engineering vehicle dispatching method according to claim 1, characterized in that: Also includes: Determine the personnel to be executed and the tasks to be executed corresponding to the personnel to be executed based on the engineering vehicle dispatching plan and the preset shift personnel; The task to be executed is sent to a mobile terminal associated with the person to be executed.

8. An engineering vehicle dispatching device, characterized in that: include: A feature extraction module, used to extract scheduling features based on the acquired historical operation data, wherein the historical operation data includes historical transportation data, historical task data, and historical working condition data; A model prediction module, used to input the scheduling features into the first random forest model and the second random forest model respectively to obtain predicted task requirements and scheduling strategies; A function determination module, used to determine the objective function and constraint conditions of a mixed integer programming model based on the predicted task requirements, the scheduling strategy and the resource constraints of the engineering vehicle; A model optimization module, used for optimizing the objective function of the mixed integer programming model based on the constraint conditions; The scheme determination module is used to output an engineering vehicle scheduling scheme corresponding to the optimized objective function based on a mixed integer programming model.

9. A processor, characterized in that: The method is configured to execute the engineering vehicle dispatching method according to any one of claims 1 to 7.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling a machine to execute the engineering vehicle dispatching method according to any one of claims 1 to 7.

Images