Vehicle scheduling method and device, electronic equipment and storage medium
By introducing OptaPlanner and a heuristic local search algorithm to optimize underground vehicle scheduling, the problems of resource waste and inefficiency in underground vehicle scheduling were solved, and safe and efficient vehicle scheduling and resource utilization were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-09
- Publication Date
- 2026-03-27
AI Technical Summary
Underground vehicle dispatching suffers from resource waste, low dispatching efficiency, and insufficient flexibility. Traditional methods struggle to coordinate multiple constraints in real time, such as vehicle location, load status, driver shifts, and route conflicts, leading to vehicle idleness, task delays, and safety hazards.
The OptaPlanner AI solver is used in conjunction with downhole environmental constraints. Heuristic and local search algorithms are employed to optimize vehicle scheduling, construct optimal routes, and respond to dynamic demands in real time, taking into account the constraints of drivers, vehicles, and scheduling requests.
It has improved the efficiency and safety of underground vehicle dispatching, reduced the risk of human error, and achieved efficient resource utilization and safe and efficient transportation.
Smart Images
Figure CN121745787A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application belongs to the technical field of data processing, and particularly relates to a vehicle scheduling method and device, an electronic device and a storage medium. BACKGROUND
[0002] As a key link of mine production and transportation, underground vehicle scheduling faces a highly complex and special working environment. The underground space usually presents the characteristics of intersecting roadways, narrow cross-section, limited lighting, relatively weak communication conditions, and is strictly restricted by safety factors such as ventilation, gas and dust. In this environment, there are various types of vehicles, and the transportation tasks have the requirements of suddenness, multi-source and high timeliness. Traditional scheduling methods mostly rely on manual experience or simple rule algorithms, such as first-come-first-served (FIFO) algorithm, that is, preferentially assigning orders to users who submit the use of vehicle application first; shortest path priority (SPP) algorithm, that is, preferentially meeting the scheduling order of short transportation distance. These methods are difficult to comprehensively and timely coordinate multiple constraints such as vehicle position, load state, driver shift, path conflict, and are prone to cause vehicle idling, task delay and path congestion, which not only affects the efficiency, but also lays the safety hidden danger.
[0003] The existing scheduling methods mainly have three defects: first, resource waste, unable to efficiently match vehicles and dynamic demand, leading to empty running or waiting; second, poor flexibility, responding to continuous changes of underground operation with lag; third, low safety, lacking comprehensive consideration of vehicle state, personnel safety and environmental factors. SUMMARY
[0004] In view of the problems of uneven resource allocation, low scheduling efficiency and insufficient flexibility in underground vehicle scheduling, the present application aims to provide a solution to improve the intelligent level and safety of mine vehicle scheduling.
[0005] In a first aspect, the present application provides a vehicle scheduling method, comprising: obtaining a vehicle scheduling application, extracting scheduling information from the vehicle scheduling application, and determining a scheduling optimization mode; According to the constraint conditions in the scheduling optimization mode, the scheduling information is distributed and optimized to obtain a vehicle scheduling scheme; According to the vehicle scheduling scheme, the target vehicle is scheduled.
[0006] Further, the vehicle scheduling application includes one or more of the following data: use time, location, number of people, material type and volume.
[0007] Further, after obtaining the vehicle scheduling application, data cleaning will be performed on the vehicle scheduling application, including: performing data type conversion on the data in the vehicle scheduling application; removing invalid and duplicate data in the vehicle scheduling application; Filling in missing data in the vehicle dispatch application.
[0008] Further, extracting dispatch information from the vehicle dispatch application, including: Writing the vehicle dispatch application into a database, determining the mapping relationship between each column and field in the vehicle dispatch application, and obtaining the dispatch information.
[0009] Further, determining a dispatch optimization mode, including: Constructing entity classes corresponding to each data in the vehicle dispatch application; Based on the existence of each entity class, determining the variable type to be allocated to each entity in the entity class; Based on the variable type, determining the constraint condition to obtain the dispatch optimization mode.
[0010] Further, according to the constraint condition in the dispatch optimization mode, the dispatch information is optimized, including: Obtaining the constraint condition in the dispatch optimization mode; According to the constraint condition, the variable is allocated to each entity by using a heuristic algorithm.
[0011] Further, according to the vehicle dispatch scheme, the target vehicle is dispatched, including: According to the vehicle dispatch scheme, determining the optimal path of the target vehicle; According to the optimal path, the target vehicle is dispatched.
[0012] In a second aspect, the present application provides a vehicle dispatch device, including: An information extraction module is configured to obtain a vehicle dispatch application, extract dispatch information from the vehicle dispatch application, and determine a dispatch optimization mode; An allocation optimization module is configured to optimize the allocation of the dispatch information according to the constraint condition in the dispatch optimization mode, and obtain a vehicle dispatch scheme; A dispatch instruction module is configured to dispatch a target vehicle according to the vehicle dispatch scheme.
[0013] In a third aspect, the present application provides an electronic device, including: a processor; and a memory storing a program, wherein the program includes instructions that, when executed by the processor, cause the processor to perform the vehicle dispatch method as described above.
[0014] In a fourth aspect, the present application provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the vehicle dispatch method as described above.
[0015] The beneficial effects of the present application are as follows: The application solves by introducing an AI solver OptaPlanner, considering the complexity and unique constraints of the underground scene, and comprehensively considering the driver, vehicle and vehicle scheduling application for solving. In the solving process, the heuristic algorithm is responsible for quickly constructing a feasible solution, and the local search algorithm is responsible for optimizing the solution. The combination of the two not only guarantees the speed of solving by considering the comprehensive satisfaction of hard and soft constraints, but also ensures the quality of the solution. The vehicle scheduling method of the application can improve the scheduling efficiency while reducing the risk of human operation errors. BRIEF DESCRIPTION OF DRAWINGS
[0016] Figure 1 An application scenario of vehicle scheduling in the application.
[0017] Figure 2 A flowchart of the vehicle scheduling method in the application.
[0018] Figure 3 An E-R table containing scheduling information in the application.
[0019] Figure 4 A UML class diagram of the OrderAssignment class in the application.
[0020] Figure 5 A schematic diagram of the vehicle scheduling device in the application. DETAILED DESCRIPTION
[0021] The application will be further described in detail below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the application, and not to limit the application. In addition, it should be noted that, in order to facilitate description, only the parts related to the application are shown in the drawings, not all structures.
[0022] In the related art, underground vehicle scheduling is a key link of mine production and transportation, and its working environment has high complexity and particularity. The underground space usually presents the characteristics of intersecting roadways, narrow cross section, limited lighting, relatively weak communication conditions, and is strictly restricted by safety factors such as ventilation, gas and dust. In this environment, the types of vehicles are various, the transportation tasks often have the requirements of suddenness, multi-source and high timeliness, and the safe and efficient transportation of personnel and materials needs to be considered. In view of this, the application proposes a vehicle scheduling method, device, electronic equipment and storage medium.
[0023] The specific embodiment of the application illustrates an application scenario of a vehicle scheduling method, such as Figure 1As shown, the application scenario includes a processing terminal 102, the processing terminal 102 collects vehicle scheduling applications from one or more users 101, the processing terminal 102 optimally allocates the contents in the vehicle scheduling application, and delivers the result of the optimal allocation to the corresponding driver 103, and the driver 103 performs the corresponding vehicle carrying task according to the result of the optimal allocation. The processing terminal 102 can be a server, which can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms.
[0024] The vehicle scheduling method provided by the embodiment of the application can be executed by the vehicle scheduling device provided by the embodiment of the application or a computer device integrated with the vehicle scheduling method, and the vehicle scheduling device can be realized in the form of hardware or software. The computer device can be the processing terminal 102 shown in Figure 1
[0025] The first aspect of the application provides a vehicle scheduling method, the flow is as shown in Figure 2 S201, obtaining a vehicle scheduling application, extracting scheduling information from the vehicle scheduling application, and determining a scheduling optimization mode; S202, according to the constraint condition in the scheduling optimization mode, the scheduling information is allocated and optimized, and the vehicle scheduling scheme is obtained; S203, scheduling the target vehicle according to the vehicle scheduling scheme.
[0026] S201, obtaining a vehicle scheduling application, extracting scheduling information from the vehicle scheduling application, and determining a scheduling optimization mode.
[0027] Vehicle scheduling refers to arranging and deploying vehicle resources according to task requirements to ensure the completion of the carrying task. Vehicle scheduling application refers to a user or department applying for calling vehicle resources according to task requirements to expect to complete the carrying task of the user or department.
[0028] In this embodiment, the user or department submits a vehicle scheduling application through a vehicle scheduling platform, which can be the processing terminal 102 in Figure 1 The contents of the vehicle scheduling application include the use time, place, number of people, material type and volume. After submitting the vehicle scheduling application, the dispatching room approves the vehicle scheduling application on the vehicle scheduling platform, and extracts the scheduling information from the vehicle scheduling application after the approval.
[0029] The present application considers that the vehicle scheduling applications submitted by different users or departments may be inconsistent in format due to differences in working environment and different scheduling single templates. Therefore, data cleaning is performed on the vehicle scheduling application before extracting the scheduling information therefrom, so as to ensure the standardization and accuracy of the vehicle scheduling application. In some embodiments, EasyExcel is used to read the information in the vehicle scheduling application, data type conversion is performed on the data in the vehicle scheduling application, invalid and duplicate data is removed, and missing data is supplemented.
[0030] The vehicle scheduling application after data cleaning, driver data and vehicle data are written into a database, the @ExcelProperty annotation is used to specify the mapping relationship between columns and fields, and the E-R table containing scheduling information is extracted, as shown in Figure 3 .
[0031] It is easy to understand that the E-R table containing scheduling information does not necessarily contain the optimal vehicle scheduling scheme, therefore, the present application proposes a scheduling optimization mode, which can optimize the scheduling information in the E-R table and obtain the optimal vehicle scheduling scheme as much as possible. The scheduling optimization mode proposed by the present application abstracts the vehicle scheduling problem as a structure optimization problem, solves the vehicle scheduling problem through constraint conditions containing hard constraints and soft constraints, evaluates the pros and cons of each solution through the violation of the constraint conditions, and finally optimizes the quality of the solution through heuristic search until the optimal solution is found.
[0032] The scheduling optimization mode proposed by the present application constructs the entity class corresponding to each data in the scheduling information according to the scheduling information in the E-R table, and further determines the variable types that can be allocated to each entity in the entity class. Exemplarily, for the two types of entities of “driver” and “vehicle”, three types of variables of “working time”, “working route” and “task” can be allocated.
[0033] S202 performs allocation optimization on the scheduling information according to the constraint conditions in the scheduling optimization mode, and obtains a vehicle scheduling scheme.
[0034] In the present embodiment, the characteristic constraint conditions are constructed according to the characteristics and requirements of the underground vehicle scheduling scenario. The constraint conditions include hard constraints and soft constraints, and the specific constraint conditions include: (1) the vehicle belongs to the same team as the vehicle scheduling application; (2) the number of personnel requested by the vehicle scheduling application matches the maximum number of people that the vehicle can carry; (3) the driver and the vehicle are idle and available at the current time period; (4) the vehicle scheduling application can be one-to-many with the driver and the vehicle, and the driver and the vehicle are one-to-one; (5) the order transportation material type matches the vehicle transportable material type; (6) The volume / weight of the order to be transported matches the carrying capacity of the vehicle; (7) The vehicle scheduling application is assigned in priority; (8) The time of use of the vehicle scheduling application is as close as possible to the assigned time; (9) The current driver's location is as close as possible to the location of the use of the vehicle.
[0035] Among them, (1)-(6) are hard constraints, and (7)-(9) are soft constraints.
[0036] In this step, the E-R table in the database is read, and the content in the E-R table is input into the OptaPlanner solver for scheduling solution. The OrderAssignment class in the OptaPlanner solver is responsible for recording the results of each solution as an entity class, and the UML class diagram of the OrderAssignment class is as shown in Figure 4
[0037] The OptaPlanner solver uses a constructive heuristic algorithm to quickly generate a preliminary schedule, which assigns a task that best meets the constraints to each driver in turn. The specific steps are as follows: (A1) Select a driver from all unassigned drivers.
[0038] (A2) Assign a task that meets the hard constraints to the driver.
[0039] (A3) Update the schedule and continue to assign shifts to the next driver until all tasks are scheduled.
[0040] At this time, the initial solution of the heuristic algorithm has been generated, which meets all the hard constraints, but may not fully meet other soft constraints. Next, a local search algorithm is used to further optimize the solution, so that the schedule not only meets the hard constraints, but also tries to meet the soft constraints. The specific steps of the local search algorithm are as follows: (B1) Randomly select a shift of a driver and try to modify it, such as swapping the driver's shift with another driver or adjusting the working hours.
[0041] (B2) If the score of the modified solution is higher, i.e. the soft constraints are better met, then accept this solution and continue to optimize from the new solution.
[0042] (B3) Avoid falling into a local optimal solution by using a simulated annealing strategy or a particle swarm optimization algorithm, and finally find a solution that is closer to the global optimal solution as the vehicle scheduling solution.
[0043] The solving process of the OptaPlanner solver in this embodiment, the heuristic algorithm is responsible for quickly constructing a feasible solution, and the local search algorithm is responsible for optimizing the solution. The combination of the two ensures that the comprehensive satisfaction of hard and soft constraints guarantees the solving speed, and ensures the quality of the solution, realizing the dual optimization of scheduling efficiency and resource utilization.
[0044] S203 dispatches the target vehicle according to the vehicle scheduling scheme.
[0045] The vehicle scheduling scheme generated in the previous step contains joint information of each driver, vehicle, and executed task. The present application further proposes a method for planning a path for executing a task in combination with the vehicle scheduling scheme, using The algorithm uses the underground road network map for global optimization, calculates the shortest path for executing a task, and comprehensively considers the constraints of underground speed limit, roadway traffic direction, and forbidden area, to establish an underground transportation model. The vehicle scheduling scheme is input into the underground transportation model to obtain a planned path adapted to the vehicle scheduling scheme. In some embodiments, the RRT or Dijkstra algorithm is used to perform global optimization using the underground road network map.
[0046] Further, the planned path is added to the vehicle scheduling scheme, and each vehicle is dispatched according to the vehicle scheduling scheme containing the planned path.
[0047] The vehicle scheduling method provided in the first aspect of the present application also monitors the running state of the driver and the vehicle and the number of tasks in a timely manner. When the processing terminal 102 receives a new vehicle scheduling application, the processing terminal 102 triggers a dynamic response mechanism, re-evaluates the existing vehicle scheduling scheme, calculates a new vehicle scheduling scheme using the OptaPlanner solver, and uses The algorithm updates the planned path to respond to the new vehicle scheduling application. This dynamic response mechanism ensures the efficiency and safety of the scheduling scheme.
[0048] The second aspect of the present application provides a vehicle scheduling device, as shown in Figure 5 The vehicle scheduling device can be integrated into an electronic device and can specifically include an information extraction module, an allocation optimization module, and a dispatching instruction module.
[0049] The information extraction module is used to obtain a vehicle scheduling application, extract scheduling information from the vehicle scheduling application, and determine a scheduling optimization mode; The allocation optimization module is used to allocate and optimize the scheduling information according to the constraint conditions in the scheduling optimization mode to obtain a vehicle scheduling scheme; The dispatching instruction module is used to dispatch a target vehicle according to the vehicle scheduling scheme.
[0050] The vehicle scheduling device provided by the embodiments of the present application comprises an information extraction module, an allocation optimization module and a scheduling instruction module, and the functions of the modules correspond to the steps of the vehicle scheduling method one by one. For the specific explanation of the vehicle scheduling device and the related refinement and optimization, refer to the specific embodiments of the vehicle scheduling method, which will not be repeated here.
[0051] In some embodiments, the present application also provides an electronic device, which can be a mobile phone, a computer or a tablet computer, etc., comprising a memory and a processor, and the memory stores a computer program, and the computer program is executed by the processor to implement the vehicle scheduling method in the above embodiments.
[0052] The processor is configured to execute all or part of the steps of the vehicle scheduling method in the above embodiments. The memory is configured to store various types of data, which may, for example, include instructions of any application program or method in the electronic device, and application program related data.
[0053] The processor can be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor or other electronic elements, which is configured to execute the steps of the vehicle scheduling method in the above embodiments.
[0054] The memory can be implemented by any type of volatile or non-volatile storage devices or a combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read Only Memory (EEPROM), an Erasable Programmable Read Only Memory (EPROM), a Programmable Read Only Memory (PROM), a Read Only Memory (ROM), a programmable flash memory, or a register. Only Memory, and the like. Only Memory, ROM), magnetic storage, flash memory, disk or optical disk.
[0055] In some embodiments, the present application also provides a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read only memory (ROM), an electrically erasable programmable read only memory (EEPROM), a programmable read only memory (PROM), a magnetic storage, a disk, an optical disk, a server, an App application store, etc., which stores a computer program, and the computer program is executed by a processor to implement the above method steps. The specific embodiment process can be referred to the above embodiment, and the embodiment will not be repeated here.
[0056] It should be understood that although each step in the flowchart of each embodiment of the present application is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps has no strict order limitation, and these steps can be executed in other order. Moreover, at least part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.
[0057] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.
[0058] The above is only a preferred embodiment of the present application, and does not limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims
1. A vehicle dispatching method, characterized in that, include: Obtain a vehicle dispatch request, extract dispatch information from the vehicle dispatch request, and determine the dispatch optimization mode; Based on the constraints in the scheduling optimization mode, the scheduling information is allocated and optimized to obtain a vehicle scheduling scheme; The target vehicles are dispatched according to the vehicle dispatching scheme.
2. The method according to claim 1, characterized in that, The vehicle dispatch request includes one or more of the following data: vehicle usage time, location, number of people, material type, and volume.
3. The method according to claim 2, characterized in that, After obtaining the vehicle dispatch request, the data will be cleaned, including: Perform data type conversion on the data in the vehicle dispatch request; Remove invalid and duplicate data from the vehicle dispatch request; The missing data in the vehicle dispatch request was supplemented.
4. The method according to claim 1, characterized in that, Extracting dispatch information from the vehicle dispatch request includes: The vehicle dispatch request is written into the database, and the mapping relationship between each column and field in the vehicle dispatch request is determined to obtain the dispatch information.
5. The method according to claim 4, characterized in that, Determine the scheduling optimization mode, including: Construct entity classes corresponding to each piece of data in the vehicle dispatch request; Based on the existence of each entity class, determine the types of variables to be assigned to each entity in the entity class; Based on the types of variables, the constraints are determined, and the scheduling optimization mode is obtained.
6. The method according to claim 5, characterized in that, Based on the constraints in the scheduling optimization mode, the scheduling information is allocated and optimized, including: Obtain the constraints in the scheduling optimization mode; Based on the constraints, a heuristic algorithm is used to assign the variables to each of the entities.
7. The method according to claim 6, characterized in that, Dispatching target vehicles according to the vehicle dispatching scheme includes: Based on the vehicle scheduling scheme, determine the optimal route for the target vehicle; The target vehicle is scheduled according to the optimal path.
8. A vehicle dispatching device, characterized in that, include: The information extraction module is used to obtain vehicle dispatch requests, extract dispatch information from the vehicle dispatch requests, and determine the dispatch optimization mode; The allocation optimization module is used to optimize the allocation of the scheduling information according to the constraints in the scheduling optimization mode to obtain a vehicle scheduling scheme. The dispatch instruction module is used to dispatch target vehicles according to the vehicle dispatch scheme.
9. An electronic device, characterized in that, include: processor; And a memory storing a program, wherein the program includes instructions that, when executed by the processor, cause the processor to perform the method as described in any one of claims 1-7.
10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method as described in any one of claims 1-7.