A vehicle dispatching method, device, electronic equipment and computer program product

Abstract

The application discloses a kind of vehicle scheduling method, device, electronic equipment and computer program product, by obtaining the real-time state information of multiple vehicles, when detecting vehicle transportation request, according to the transportation task information in vehicle transportation request and the real-time state information of vehicle, determine the simulation transportation result of each vehicle, simulation transportation result includes the transportation mileage information of vehicle, according to each simulation transportation result, determine target vehicle, and generate vehicle scheduling instruction for target vehicle, target vehicle is the vehicle with minimum simulation mileage information, and vehicle scheduling instruction is used to indicate target vehicle to execute transportation task, so as to be able to simulate transportation to all vehicles, obtain the simulation transportation result of each vehicle, to indicate target vehicle to execute transportation task, reduce the situation that the transportation mileage of part of vehicles is much more than the transportation mileage of other vehicles, and reduce the problem that transport capacity resource allocation is uneven.

Description

Technical Field

[0001] This invention relates to the field of vehicle dispatching technology, and in particular to a vehicle dispatching method, apparatus, electronic device, and computer program product. Background Technology

[0002] Vehicle dispatching is the process of coordinating and allocating vehicle routes and transportation capacity to optimize transportation resources and improve vehicle transportation efficiency. It is widely used in logistics transportation, public transportation planning, and other scenarios.

[0003] Currently, vehicle dispatching is typically done manually, with dispatchers assigning vehicles to perform transport tasks based on transportation demand and the location of each vehicle. However, this manual dispatching method results in situations where some vehicles travel significantly longer distances than others, leading to an uneven distribution of transportation resources. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method, apparatus, electronic device and computer program product for vehicle dispatching.

[0005] In a first aspect, embodiments of the present invention provide a vehicle dispatching method, the method comprising:

[0006] Obtain real-time status information for multiple vehicles;

[0007] When a vehicle transport request is detected, the simulated transport result for each vehicle is determined based on the transport task information in the vehicle transport request and the real-time status information of the vehicle; wherein, the vehicle transport request is generated for a transport task, and the simulated transport result includes transport mileage information simulating the vehicle performing the transport task.

[0008] Based on each of the simulated transportation results, a target vehicle is determined, and a vehicle dispatch instruction is generated for the target vehicle; wherein, the target vehicle is the vehicle with the smallest transportation mileage information, and the vehicle dispatch instruction is used to instruct the target vehicle to perform the transportation task.

[0009] In one possible implementation of the first aspect above, when a vehicle transport request is detected, determining the simulated transport result for each vehicle based on the transport task information of the transport task in the vehicle transport request and the real-time status information of the vehicle includes:

[0010] When a vehicle transport request is detected, the transport mileage information of the vehicle is determined based on the transport task information of the transport task in the vehicle transport request and the real-time status information of the vehicle.

[0011] Based on the transportation mileage information and the real-time status information, the simulated average mileage of each vehicle is determined;

[0012] Based on the simulated average mileage and the preset scheduling algorithm, the simulated transportation result for each vehicle is determined; wherein, the scheduling algorithm is used to quantify the simulated average mileage to obtain the simulated transportation result.

[0013] In one possible implementation of the first aspect above, the transportation task information includes the destination location information of the transportation task, the real-time status information includes the location information of the vehicle, and the transportation mileage information is the distance the vehicle travels from its location information to the destination location information when carrying out the transportation task. Different vehicles correspond to different transportation mileage information.

[0014] In one possible implementation of the first aspect above, determining the simulated transportation result for each vehicle based on the simulated average mileage and a preset scheduling algorithm includes:

[0015] The simulated mileage variance of the vehicle is determined based on the simulated average mileage.

[0016] Based on the simulated average mileage, the simulated mileage variance, and the scheduling algorithm, the simulated transportation result for each vehicle is determined; wherein, the scheduling algorithm includes components corresponding to the simulated average mileage.

[0017] The scheduling algorithm calculates the simulated average mileage and the simulated mileage variance by weighting the first weight and the second weight, respectively, to obtain the simulated transportation result of the vehicle.

[0018] In one possible implementation of the first aspect above, the real-time status information includes the average empty mileage and the average cargo mileage, the transportation mileage information includes the empty mileage information and the cargo mileage information, and the simulated average mileage includes the simulated empty average mileage and the simulated cargo average mileage.

[0019] In one possible implementation of the first aspect above, before determining the simulated transportation result for each vehicle based on the simulated average mileage and a preset scheduling algorithm, the method further includes:

[0020] A random greedy algorithm is used to generate a set of scheduling samples; wherein, the set of samples includes multiple scheduling samples, and each scheduling sample includes a sample scheduling instruction and the expected simulation result corresponding to the sample scheduling instruction;

[0021] An initial scheduling algorithm is constructed, and the initial scheduling algorithm is trained using the scheduling sample set to obtain a target scheduling algorithm. The target scheduling algorithm is then used to execute the step of determining the simulated transportation result of each vehicle based on the simulated average mileage and the preset scheduling algorithm.

[0022] In one possible implementation of the first aspect above, training the initial scheduling algorithm using the scheduling sample set to obtain the target scheduling algorithm includes:

[0023] The sample scheduling instructions in the scheduling sample set are input into the initial scheduling algorithm to obtain the actual simulation results corresponding to the sample scheduling instructions;

[0024] Determine the loss value between the expected simulation result and the actual simulation result, and adjust the coefficients of the initial scheduling algorithm based on the loss value to obtain the target scheduling algorithm.

[0025] Secondly, embodiments of the present invention provide a vehicle dispatching apparatus, the apparatus comprising:

[0026] The acquisition module is used to acquire real-time status information of multiple vehicles;

[0027] The simulation module is used to determine the simulated transportation result for each vehicle when a vehicle transportation request is detected, based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle; wherein the vehicle transportation request is generated for a transportation task, and the simulated transportation result includes transportation mileage information simulating the vehicle performing the transportation task;

[0028] The generation module is used to determine the target vehicle based on each of the simulated transportation results, and generate a vehicle dispatch instruction for the target vehicle; wherein the target vehicle is the vehicle with the smallest transportation mileage information, and the vehicle dispatch instruction is used to instruct the target vehicle to perform the transportation task.

[0029] Thirdly, embodiments of the present invention provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the vehicle scheduling method described above.

[0030] Fourthly, embodiments of the present invention provide a computer program product, the computer program product storing a computer program, which, when executed by a processor, implements the vehicle scheduling method described above.

[0031] This invention is achieved through the following technical solution:

[0032] This invention discloses a vehicle scheduling method. By acquiring real-time status information of multiple vehicles, when a vehicle transportation request is detected, the method determines the simulated transportation result for each vehicle based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle. The vehicle transportation request is generated for a transportation task, and the simulated transportation result includes the transportation mileage information of the simulated vehicle performing the transportation task. Based on each simulated transportation result, a target vehicle is determined, and a vehicle scheduling instruction is generated for the target vehicle. The target vehicle is the vehicle with the smallest transportation mileage information. The vehicle scheduling instruction is used to instruct the target vehicle to perform the transportation task. This allows for simulated transportation of all vehicles, obtaining the simulated transportation result for each vehicle, and selecting the vehicle with the smallest transportation mileage information from all the simulated transportation results as the target vehicle to instruct the target vehicle to perform the transportation task. This reduces the situation where the transportation mileage of some vehicles is much greater than that of other vehicles, and also reduces the problem of uneven distribution of transportation resources. Attached Figure Description

[0033] Figure 1 This is a flowchart illustrating the steps of a vehicle dispatching method according to an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram illustrating an application scenario of a scheduling agent provided in an embodiment of the present invention;

[0035] Figure 3 This is a schematic diagram of a transportation route provided in an embodiment of the present invention;

[0036] Figure 4 This is a flowchart of another vehicle dispatching method provided in an embodiment of the present invention;

[0037] Figure 5 This is a schematic diagram of the structure of a vehicle dispatching device according to an embodiment of the present invention;

[0038] Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0039] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0040] It should be noted that when a component is referred to as being "fixed to" or "set on" another component, it can be directly on or indirectly on that other component. When a component is referred to as being "connected to" another component, it can be directly connected to or indirectly connected to that other component.

[0041] It should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention.

[0042] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, "a plurality of sets" means two or more sets, "a plurality of pieces" means two or more pieces, and "a number" means one or more, unless otherwise explicitly specified.

[0043] Vehicle dispatching is the process of coordinating and allocating vehicle routes and transportation capacity to optimize transportation resources and improve vehicle transportation efficiency. It is widely used in logistics transportation, public transportation planning, and other scenarios.

[0044] Currently, vehicle dispatching is usually done manually, with dispatchers assigning vehicles to perform transportation tasks based on transportation needs and the location of each vehicle.

[0045] Specifically, the manual dispatching method involves dispatchers communicating with the drivers of each vehicle via walkie-talkies or other communication tools to determine the status and location of each vehicle, thereby selecting the vehicle with the best status and / or location to perform the transportation task. However, the manual dispatching method has the problem that some vehicles travel significantly more mileage than others, meaning that the same vehicle performs transportation tasks far more often than other vehicles, resulting in an uneven distribution of transportation resources.

[0046] Furthermore, each dispatch requires dispatchers to communicate with the drivers of each vehicle in turn, which takes a lot of time and results in low dispatch efficiency.

[0047] Based on this, the present invention discloses a vehicle scheduling method. By acquiring real-time status information of multiple vehicles, when a vehicle transportation request is detected, the method determines the simulated transportation result of each vehicle based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle. The vehicle transportation request is generated for the transportation task, and the simulated transportation result includes the transportation mileage information of the simulated vehicle performing the transportation task. Based on each simulated transportation result, a target vehicle is determined, and a vehicle scheduling instruction is generated for the target vehicle. The target vehicle is the vehicle with the smallest transportation mileage information. The vehicle scheduling instruction is used to instruct the target vehicle to perform the transportation task, thereby enabling simulated transportation for all vehicles, obtaining the simulated transportation result of each vehicle, and selecting the vehicle with the smallest transportation mileage information from all the simulated transportation results as the target vehicle to instruct the target vehicle to perform the transportation task. This reduces the situation where the transportation mileage of some vehicles is much greater than that of other vehicles, and also reduces the problem of uneven distribution of transportation resources.

[0048] See Figure 1 , Figure 1 The diagram illustrates a flowchart of a vehicle dispatching method according to an embodiment of the present invention, which may specifically include the following steps:

[0049] S101, obtain real-time status information of multiple vehicles.

[0050] Among them, the vehicle can be a transportation tool capable of performing transportation tasks, such as electric freight vehicles, trailers, trucks, tank trucks, etc. The real-time status information can be information describing the vehicle status, which can specifically include the vehicle model, operating status, location information, remaining mileage, total mileage, etc. The operating status can include the vehicle being in transportation, the vehicle waiting for transportation, and the vehicle being under maintenance.

[0051] When vehicle dispatching and management are required, it can detect in real time whether there are vehicle transportation requests and obtain real-time status information of each vehicle that can perform transportation tasks.

[0052] Specifically, a vehicle transport request can be generated in response to a transport task, which can be a task to transport any object to a destination. A vehicle transport request can be a request to any vehicle to transport any item to a destination.

[0053] In practical applications, when it is necessary to manage vehicle scheduling, a scheduling agent can be built and communicated with each vehicle to obtain the real-time status information of the vehicle.

[0054] Specifically, the scheduling agent can be used to generate instructions for scheduling vehicles.

[0055] join Figure 2, Figure 2 The diagram illustrates an application scenario of a scheduling agent according to an embodiment of the present invention, such as... Figure 2 As shown, the environment module can collect real-time status information of each vehicle and detect the existence of vehicle transportation requests in real time. When a vehicle transportation request is detected, the real-time status information of each vehicle is transmitted to the scheduling agent. The scheduling agent can then generate instructions to dispatch vehicles based on the received real-time status information and vehicle transportation requests, and transmit the generated instructions to the environment module so that the environment module can distribute the generated instructions to all vehicles.

[0056] S102, when a vehicle transportation request is detected, the simulated transportation result for each vehicle is determined based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle.

[0057] The transportation task information includes details about transporting goods to their destination. This information may include the object to be transported, the starting location of the transportation task, and the destination location. The object to be transported can be any object that needs to be transported, such as goods or passengers. The starting location is the current location of the object, and the destination is the location the object needs to reach. The simulated transportation result includes the result of each vehicle performing the transportation task. This result may include the mileage information of the simulated vehicles after performing the task. The mileage information is the distance traveled by the vehicle from its current location to its destination, specifically the sum of the distance from its current location to the starting location and the distance from the starting location to the destination. Different vehicles correspond to different mileage information.

[0058] When vehicle dispatching and management are required, the system can detect the existence of vehicle transport requests in real time. Upon detection of a vehicle transport request, the system can determine the transport task information in the vehicle transport request, identify the object to be transported, and determine the starting and destination location information of the object to be transported.

[0059] In practice, vehicle transportation requests can be triggered by users or based on production needs. For example, the object to be transported can be steel slag in a blast furnace. When any blast furnace needs to clean steel slag, production staff can trigger a vehicle transportation request through terminal devices, mobile devices, or other means and send the request to a device capable of dispatching vehicles. Alternatively, monitoring equipment can monitor the thickness of the steel slag in the blast furnace in real time, and when the thickness exceeds a preset thickness, a vehicle transportation request can be automatically generated and sent to a device capable of dispatching vehicles.

[0060] After determining the transportation task information in the vehicle transportation request, the simulated transportation result for each vehicle can be determined based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle.

[0061] In practical applications, the result of each vehicle performing its transportation task can be determined based on the starting and destination location information of the object to be transported. This yields the simulated transportation result for each vehicle, meaning that for each vehicle, the mileage information after performing its transportation task can be simulated to obtain the transportation mileage information for each vehicle.

[0062] As an example, after obtaining the simulated transportation results for each vehicle, the vehicle that travels the shortest distance to perform the transportation task can be identified as the target vehicle.

[0063] In one embodiment of the present invention, S102 may include S1021 to S1023:

[0064] S1021, When a vehicle transport request is detected, the transport mileage information of the vehicle is determined based on the transport task information of the transport task in the vehicle transport request and the real-time status information of the vehicle.

[0065] After determining the transportation task information in the vehicle transportation request, for each vehicle, the mileage from the vehicle's location to the location of the object to be transported, as well as the mileage from the location of the object to the location the object needs to reach, can be calculated based on the vehicle's location information, the starting location information of the object to be transported, and the destination location information. Then, the mileage of the vehicle performing the transportation task can be calculated based on the above mileage, thus obtaining the transportation mileage information of the vehicle performing the transportation task, thereby obtaining the transportation mileage information of each vehicle.

[0066] In practical applications, the vehicle needs to travel to the location of the object to be transported to pick it up, transport the object to its destination, and unload it at the destination to complete the transport of the object.

[0067] S1022, based on transportation mileage information and real-time status information, determines the simulated average mileage of each vehicle.

[0068] The real-time status information of the vehicle may also include the number of times the vehicle has performed transportation tasks in the past period, and the simulated average mileage can be the average mileage of the vehicle after simulating the performance of transportation tasks.

[0069] After obtaining the transportation mileage information for each vehicle, the simulated average mileage for each vehicle can be determined based on the transportation mileage information and real-time status information.

[0070] In practical applications, for each vehicle, the sum of the vehicle's total mileage and the transportation mileage information can be calculated to obtain the simulated total mileage after the vehicle simulates the transportation task. Then, the number of times the vehicle has performed transportation tasks in the past period is incremented by one to obtain the simulated total number of times the vehicle has performed transportation tasks. Finally, the simulated total mileage of the vehicle can be divided by the simulated total number of times the vehicle has performed transportation tasks to obtain the simulated average mileage of the vehicle. Thus, the simulated average mileage of each vehicle can be obtained.

[0071] join Figure 3 , Figure 3 A schematic diagram of a transportation route provided by an embodiment of the present invention is shown, as follows. Figure 3 As shown, each object to be transported can be transported to a different region, and there is only one fixed transport path between any object to be transported and any region.

[0072] As an example, the object to be transported can be steel slag in a blast furnace. When any blast furnace needs to clean up the steel slag, a vehicle transport request will be generated to transport the steel slag in the blast furnace to any area that can handle the steel slag. There are fixed transport routes between different blast furnaces and different areas that handle steel slag.

[0073] S1023, Based on the simulated average mileage and the preset scheduling algorithm, determine the simulated transportation result for each vehicle.

[0074] The scheduling algorithm is used to quantify the simulated average mileage in order to obtain the simulated transportation results.

[0075] After obtaining the simulated average mileage, the simulated transportation result for each vehicle can be determined based on the simulated average mileage and the preset scheduling algorithm.

[0076] In practical applications, scheduling algorithms can be used to quantify the simulated average mileage of each vehicle to obtain the simulated transportation result of each vehicle. Specifically, the reciprocal of the simulated average mileage of each vehicle can be calculated by the scheduling algorithm, and the reciprocal of the simulated average mileage of each vehicle can be normalized to obtain the normalized result of the simulated average mileage of each vehicle, which is the simulated transportation result of each vehicle.

[0077] In one embodiment of the present invention, S1023 may include the following steps:

[0078] Based on the simulated average mileage, the simulated mileage variance of the vehicles is determined. Based on the simulated average mileage, simulated mileage variance, and scheduling algorithm, the simulated transportation result for each vehicle is determined.

[0079] The simulated mileage variance can be the variance between the simulated average mileage and the vehicle average mileage, where the vehicle average mileage can be the average mileage of all vehicles. The scheduling algorithm can include a first weight corresponding to the simulated average mileage and a second weight corresponding to the simulated mileage variance. The scheduling algorithm can perform a weighted calculation on the simulated average mileage and the simulated mileage variance based on the first weight and the second weight to obtain the simulated transportation results of the vehicles.

[0080] After obtaining the simulated average mileage of each vehicle, we can determine the number of times each vehicle performed transportation tasks in the past period, as well as the total mileage of each vehicle in the past period. Then, based on the number of times each vehicle performed transportation tasks and the total mileage of the transportation tasks, we can determine the average mileage of all vehicles and obtain the vehicle average mileage.

[0081] After obtaining the simulated average mileage and vehicle average mileage for each vehicle, the variance between each vehicle and the vehicle average mileage can be determined based on the simulated average mileage and vehicle average mileage, thus obtaining the simulated mileage variance for each vehicle.

[0082] After obtaining the simulated mileage variance for each vehicle, a scheduling algorithm can be used to calculate the simulated average mileage and simulated mileage variance based on the first weight and the second weight, so as to obtain the simulated transportation results for each vehicle.

[0083] It's important to understand that selecting the vehicle with the shortest mileage solely based on the transportation task corresponding to the vehicle's transportation request can lead to situations where the same vehicle performs several consecutive transportation tasks, meaning some vehicles still end up with significantly longer mileages than others. However, by determining the simulated average mileage and variance of each vehicle, and using these metrics to determine the simulated transportation results for each vehicle, we can select the target vehicle that satisfies both a smaller simulated average mileage and a smaller difference from the other vehicles. The simulated mileage variance represents the difference between the simulated average mileage of this vehicle and the simulated average mileage of the others. This ensures that after performing the current transportation task, the difference in mileage between each vehicle is minimized, reducing the likelihood of some vehicles exceeding the mileage of others and mitigating the problem of uneven distribution of transportation resources.

[0084] In one embodiment of the present invention, the real-time status information may further include actual empty mileage and actual loaded mileage. Actual empty mileage can be the mileage traveled by the vehicle in an empty state at any given time within a past period. Actual loaded mileage can be the mileage traveled by the vehicle in a loaded state at any given time within a past period. An empty state refers to a state where the vehicle is not transporting goods, persons, or other objects; a loaded state refers to a state where the vehicle is transporting goods, persons, or other objects. The real-time status information may also include the number of empty trips and the number of loaded trips. The number of empty trips can be the number of times the vehicle traveled in an empty state within a past period. The number of loaded trips can be the number of times the vehicle traveled in a loaded state within a past period. The transportation mileage information may also include empty mileage information and loaded mileage information. Empty mileage information can be the mileage traveled by the vehicle in an empty state when performing a transportation task, i.e., the mileage from the vehicle's location information to the starting location information of the transportation task. Loaded mileage information can be the mileage traveled by the vehicle in a loaded state when performing a transportation task, i.e., the mileage from the starting location information of the transportation task to the destination location information of the transportation task. The simulated average mileage includes the simulated empty average mileage and the simulated loaded average mileage. Specifically, it is the sum of the simulated empty average mileage and the simulated loaded average mileage. The simulated empty average mileage can be the average empty mileage of the vehicle after simulating the transportation task, and the simulated loaded average mileage can be the average loaded mileage of the vehicle after simulating the transportation task.

[0085] In practical applications, when a vehicle transportation request is detected, the actual empty mileage and actual cargo mileage in the real-time status information can be determined. Then, based on the transportation task information in the vehicle transportation request, each vehicle can be simulated to perform the transportation task corresponding to the vehicle transportation request, and the transportation mileage information of each vehicle can be obtained. That is, the mileage traveled by the vehicle in an empty state when simulating the transportation task can be determined, and the mileage traveled by the vehicle in a cargo state when simulating the transportation task can be determined. The empty mileage information and cargo mileage information of each vehicle can be obtained. Based on the actual empty mileage, the number of empty trips, and the empty mileage information of each vehicle, the simulated average empty mileage of the vehicle can be determined. Based on the actual cargo mileage, the number of cargo trips, and the cargo mileage information of each vehicle, the simulated average cargo mileage of the vehicle can be determined.

[0086] Specifically, the simulated average mileage for cargo transport can be determined using the following formula:

[0087]

[0088] in, It can be used to calculate the number of trips made for cargo. It can be the mileage of the i-th trip in a loaded state, including the mileage of any trip in a loaded state within a past period and the loaded mileage information corresponding to the current vehicle transport request.

[0089] The simulated average mileage under no-load conditions can be determined using the following formula:

[0090]

[0091] in, It can be the number of times the vehicle travels without a load. It can be the mileage of the j-th trip in an empty state, including the mileage of any trip in an empty state within a past period and the empty mileage information corresponding to the current vehicle transport request.

[0092] After obtaining the simulated average mileage for each vehicle, the simulated mileage variance for each vehicle can be determined based on the real-time status information and the average mileage of each vehicle. Specifically, the variance between the simulated average mileage and the average mileage of each vehicle can be determined to obtain the simulated mileage variance.

[0093] Specifically, simulated mileage variance can also include simulated empty-load mileage variance and simulated loaded mileage variance, which are the sum of simulated empty-load mileage variance and simulated loaded mileage variance. Vehicle average mileage can include average empty-load mileage and average loaded mileage. Simulated empty-load mileage variance can be the variance between the mileage traveled in an empty state at any given time within a past period and the empty-load mileage information corresponding to the current vehicle transport request, and the average empty-load mileage. Simulated loaded mileage variance can be the variance between the mileage traveled in a loaded state at any given time within a past period and the loaded mileage information corresponding to the current vehicle transport request, and the average loaded mileage. Average empty-load mileage can be the average of the empty-load mileage of all vehicles, i.e., the total empty-load mileage of all vehicles divided by the number of times all vehicles traveled in an empty state. Average loaded mileage can be the average of the loaded mileage of all vehicles, i.e., the total loaded mileage of all vehicles divided by the number of times all vehicles traveled in a loaded state.

[0094] In practical applications, the variance of simulated empty mileage can be determined based on the actual empty mileage, number of empty trips, empty mileage information, and average empty mileage of each vehicle. Similarly, the variance of simulated cargo mileage can be determined based on the actual cargo mileage, number of cargo trips, cargo mileage information, and average cargo mileage of each vehicle.

[0095] Specifically, the variance of the simulated cargo mileage can be determined using the following formula:

[0096]

[0097] in, It can be used to calculate the number of trips made for cargo. This can be the mileage of the i-th trip in a loaded state, including the mileage of any trip in a loaded state within a past period and the loaded mileage information corresponding to the current vehicle transport request. It can be used to calculate the average cargo mileage of a vehicle.

[0098] The variance of the simulated no-load mileage can be determined using the following formula:

[0099]

[0100] in, It can be the number of times the vehicle travels without a load. This can be the mileage of the j-th trip when the vehicle is in an empty state, including the mileage of any trip in an empty state within a past period and the empty mileage information corresponding to the current vehicle transport request. It can be used to calculate the average unloaded mileage of a vehicle.

[0101] After obtaining the simulated average mileage with cargo, the simulated average mileage without cargo, the variance of the simulated mileage without cargo, and the variance of the simulated mileage with cargo, a scheduling algorithm can be used to calculate the simulated average mileage and the variance of the simulated mileage based on the first weight and the second weight to obtain the simulated transportation results for each vehicle.

[0102] Specifically, the simulated transportation results for each vehicle can be determined using the following formula:

[0103]

[0104] in, It can be the reciprocal of the simulated average mileage. It can be the reciprocal of the variance of the simulated mileage. as well as It can be a scaling factor, and α+β=1, with α and β both taking values ​​in the range of (0,1).

[0105] In practical implementation, after obtaining the simulated average mileage for loaded and unloaded cargo, the sum of the simulated average mileage for loaded and unloaded cargo can be calculated to obtain the simulated average mileage. Then, the reciprocal of the simulated average mileage can be calculated, and the reciprocal of the simulated average mileage can be normalized, resulting in... Similarly, after obtaining the variances of simulated empty-load mileage and simulated loaded-load mileage, we can calculate the sum of these variances to obtain the simulated mileage variance. Then, we can calculate the reciprocal of the simulated mileage variance and normalize it, resulting in: .

[0106] In one embodiment of the present invention, when the vehicle is a tanker truck or other vehicle that needs to be equipped with a corresponding container for transportation, it is also necessary to determine the mileage of the vehicle to the area where the container is installed each time from the real-time status information, and to determine the mileage from the destination of the transportation task to the area where the container is installed after each completion of the transportation task.

[0107] In practical applications, when a vehicle equipped with a corresponding container needs to perform a transportation task, it will travel from its current location to the area where the container is installed to install it. After installation, it will travel from the container installation area to the location of the object to be transported to store the object in the installed container. After obtaining the object, it will travel from the object's location to its destination and unload the object from the vehicle to complete the transportation task. After completing the transportation task, it will travel from the destination to the container installation area to disassemble the container installed in the vehicle.

[0108] Specifically, for vehicles that need to be equipped with corresponding containers for transportation, the mileage from the vehicle's current location to the area where the container is installed can be defined as the empty vehicle mileage information, the sum of the mileage from the area where the container is installed to the location of the object to be transported and the mileage from the destination of the object to the area where the container is installed is the empty load mileage information, and the mileage from the location of the object to the destination of the object to be transported is the loaded mileage information.

[0109] Similarly, when a vehicle transport request is detected, the simulated transport result for each vehicle can be determined based on the transport task information in the vehicle transport request and the real-time status information of the vehicle.

[0110] Specifically, the simulated average empty mileage and simulated empty mileage variance for each vehicle can be determined based on the empty mileage information in the transportation task information and the actual empty mileage, number of empty trips, and average empty mileage of the vehicle in the real-time status information. Similarly, the simulated average cargo mileage and simulated cargo mileage variance for each vehicle can be determined based on the cargo mileage information in the transportation task information and the actual cargo mileage, number of cargo trips, and average cargo mileage of the vehicle in the real-time status information. Furthermore, the simulated average empty mileage and simulated empty mileage variance for each vehicle can be determined based on the empty vehicle mileage information in the transportation task information and the actual empty vehicle mileage, number of empty vehicle trips, and average empty vehicle mileage of the vehicle in the real-time status information.

[0111] The average empty mileage can be the average of the empty mileage of all vehicles, calculated by dividing the total empty mileage of all vehicles by the number of times each vehicle traveled in an empty state. The simulated empty mileage variance can be the variance between the mileage traveled in an empty state at any given time in the past, the empty mileage corresponding to the current vehicle transport request, and the average empty mileage. The simulated average mileage can be the sum of the simulated empty average mileage, the simulated empty load average mileage, and the simulated loaded average mileage. The simulated mileage variance can be the sum of the simulated empty load mileage variance, the simulated loaded mileage variance, and the simulated empty mileage variance.

[0112] After obtaining the simulated average empty vehicle mileage, simulated average empty load mileage, and simulated average loaded mileage, the sum of these three values ​​can be determined to obtain the simulated average mileage. After obtaining the variances of the simulated empty load mileage, simulated loaded mileage, and simulated empty vehicle mileage, the sum of these three variances can be determined to be the simulated mileage variance.

[0113] Specifically, the simulated average mileage determined based on the simulated empty vehicle average mileage can be calculated using the following formula:

[0114]

[0115] in, This can be represented as the distance traveled in the kth trip with the vehicle empty. This can be expressed as the number of times the vehicle travels without passengers.

[0116] Specifically, the variance of the simulated mileage determined based on the average mileage of the simulated empty vehicles can be calculated using the following formula:

[0117]

[0118] in, It can be used to calculate the average empty mileage of a vehicle.

[0119] After obtaining the simulated average mileage and simulated mileage variance, a scheduling algorithm can be used to weight the simulated average mileage and simulated mileage variance with a first weight and a second weight to obtain the simulated transportation results for each vehicle.

[0120] S103: Based on each simulated transportation result, determine the target vehicle and generate a vehicle dispatch instruction for the target vehicle.

[0121] The target vehicle can be the optimal vehicle determined based on the simulated transportation results, such as the vehicle with the smallest transportation mileage, the vehicle with the smallest simulated average mileage, or the vehicle with the smallest simulated mileage variance. Vehicle dispatch instructions can be used to instruct the target vehicle to perform transportation tasks.

[0122] Specifically, when the simulated transportation result is determined by the scheduling algorithm based on the first weight and the second weight, the target vehicle can be the vehicle with the smallest simulated transportation result among all vehicles.

[0123] After obtaining the simulated transportation results for each vehicle, the optimal vehicle can be determined as the target vehicle from the simulated transportation results for each vehicle.

[0124] Once the target vehicle is identified, a vehicle dispatch instruction can be generated to instruct the target vehicle to perform the transportation task. This vehicle dispatch instruction is then sent to the target vehicle, which is instructed to perform the transportation task according to the vehicle dispatch instruction.

[0125] Specifically, vehicle dispatch instructions may include the starting location information of the object to be transported, the destination location information, and the transportation route used to instruct the target vehicle to travel. As an example, for vehicles that require the use of appropriate containers for transportation, the vehicle dispatch instructions may also include the location information of the area where the containers are installed.

[0126] In this embodiment of the invention, by acquiring real-time status information of multiple vehicles, when a vehicle transportation request is detected, the simulated transportation result of each vehicle is determined based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle. The vehicle transportation request is generated for the transportation task, and the simulated transportation result includes the transportation mileage information of the simulated vehicle performing the transportation task. Based on each simulated transportation result, a target vehicle is determined, and a vehicle dispatch instruction is generated for the target vehicle. The target vehicle is the vehicle with the smallest transportation mileage information. The vehicle dispatch instruction is used to instruct the target vehicle to perform the transportation task, thereby enabling simulated transportation for all vehicles, obtaining the simulated transportation result of each vehicle, and selecting the vehicle with the smallest transportation mileage information from all the simulated transportation results as the target vehicle to instruct the target vehicle to perform the transportation task. This reduces the situation where the transportation mileage of some vehicles is much greater than that of other vehicles, and also reduces the problem of uneven distribution of transportation resources.

[0127] See Figure 4 , Figure 4 The following is a flowchart illustrating another vehicle dispatching method according to an embodiment of the present invention, which may specifically include the following steps:

[0128] S401 obtains real-time status information for multiple vehicles.

[0129] S402, when a vehicle transport request is detected, the transport mileage information of the vehicle is determined based on the transport task information in the vehicle transport request and the real-time status information of the vehicle.

[0130] S403 determines the simulated average mileage for each vehicle based on transport mileage information and real-time status information.

[0131] For explanations of steps S401 to S403, please refer to steps S101 to S102, which will not be repeated here.

[0132] S404 uses a random greedy algorithm to generate a set of scheduling samples.

[0133] Here, a greedy algorithm can be used to select the currently locally optimal solution, while a stochastic greedy algorithm can be used to introduce random solutions when selecting the currently locally optimal solution. The scheduling sample set can include multiple scheduling samples, each of which can include a sample scheduling instruction and the expected simulation result corresponding to the sample scheduling instruction. The sample scheduling instruction can be an instruction to schedule vehicles, and the expected simulation result can include the transportation results after scheduling vehicles according to the sample scheduling instruction, including the average mileage of each vehicle after scheduling according to the sample scheduling instruction and the mileage variance. The mileage variance can be the variance between the average mileage of each vehicle after scheduling according to the sample scheduling instruction and the average mileage of all vehicles.

[0134] In practical applications, a random greedy algorithm can be used to randomly generate multiple sample scheduling instructions and determine the expected simulation result corresponding to each sample scheduling instruction, thereby obtaining a set of scheduling samples including multiple sample scheduling instructions.

[0135] In practical implementation, a randomized greedy algorithm can be used to randomly generate multiple different sample transportation requests. These sample transportation requests can be vehicle transportation requests used only for training purposes. Different sample transportation requests correspond to different objects to be transported, and these objects may include different starting and destination locations. This allows for the generation of sample scheduling instructions for dispatching vehicles to transport the objects corresponding to the sample transportation requests. Simultaneously, the optimal vehicle for each sample transportation request can be determined. This involves identifying the optimal vehicle for transporting the object corresponding to that sample transportation request based on its starting and destination locations, and determining the transportation path of this optimal vehicle. Then, through manual calculations or other methods, the average mileage and mileage variance of each vehicle after dispatching the optimal vehicle are calculated, yielding the expected simulation results corresponding to the sample scheduling instructions.

[0136] S405, Construct an initial scheduling algorithm and train it using a set of scheduling samples to obtain the target scheduling algorithm.

[0137] The initial scheduling algorithm can be an untrained scheduling algorithm used to quantify the simulated average mileage, while the target scheduling algorithm can be a trained scheduling algorithm used to quantify the simulated average mileage, i.e., a scheduling algorithm trained on the initial scheduling algorithm.

[0138] After obtaining the scheduling sample set, an initial scheduling algorithm can be constructed to quantify the simulated average mileage. The initial scheduling algorithm can then be trained using the scheduling sample set to obtain the target scheduling algorithm.

[0139] Specifically, the initial scheduling algorithm can be a convolutional neural network that includes multiple transformation layers and hidden layers.

[0140] In one embodiment of the present invention, S405 may include S4051 to S4052:

[0141] S4051, input the sample scheduling instructions from the scheduling sample set into the initial scheduling algorithm to obtain the actual simulation results corresponding to the sample scheduling instructions.

[0142] The actual simulation results can be the average mileage and mileage variance of each vehicle after scheduling the vehicles using the initial scheduling algorithm.

[0143] In practical applications, sample scheduling instructions from the scheduling sample set can be input into the initial scheduling algorithm. The initial scheduling algorithm can then determine the starting and destination positions of the sample transportation requests based on the sample scheduling instructions for transporting the objects to be transported corresponding to the sample transportation requests. Based on the starting and destination positions of the sample transportation requests, it can determine the optimal vehicle for transporting the objects to be transported corresponding to the sample transportation requests, thus obtaining the optimal vehicle determined by the initial scheduling algorithm. The initial scheduling algorithm can then calculate the average mileage and mileage variance of each vehicle after scheduling the optimal vehicles determined by the initial scheduling algorithm, thus obtaining the actual simulation results corresponding to the sample scheduling instructions.

[0144] In practical implementation, after obtaining the optimal vehicle determined by the initial scheduling algorithm, the average mileage and mileage variance of each vehicle after the optimal vehicle determined by the initial scheduling algorithm transports the object to be transported corresponding to the sample transportation request can be determined, thus obtaining the actual simulation results corresponding to the sample scheduling instruction.

[0145] S4052, determine the loss value between the expected simulation result and the actual simulation result, and adjust the coefficients of the initial scheduling algorithm based on the loss value to obtain the target scheduling algorithm.

[0146] After obtaining the actual simulation results, the loss value between the expected simulation result and the actual simulation result can be determined.

[0147] It is important to understand that the optimal vehicle in the expected simulation results corresponds to the sample transportation request. That is, after the sample transportation request is generated, the optimal vehicle corresponding to the sample transportation request will be determined by means of manual determination or other methods. However, the optimal vehicle in the actual simulation results is determined by the initial scheduling algorithm.

[0148] In practical applications, for each vehicle, the difference between the average mileage of the vehicle in the expected simulation result and the average mileage of the vehicle in the actual simulation result can be obtained to get the difference in the average mileage of the vehicle. The difference between the mileage variance of the vehicle in the expected simulation result and the mileage variance of the vehicle in the actual simulation result can be obtained to get the difference in the mileage variance of the vehicle. Thus, the difference in the average mileage and the difference in the mileage variance of all vehicles can be obtained. Therefore, the loss value between the expected simulation result and the actual simulation result can be determined based on the difference in the average mileage and the difference in the mileage variance of all vehicles.

[0149] In practice, the largest difference among the differences in average mileage of all vehicles can be determined as the loss value of average mileage between the expected simulation result and the actual simulation result. Alternatively, the average of the differences in average mileage of all vehicles can be determined as the loss value of average mileage between the expected simulation result and the actual simulation result. Similarly, the largest mileage variance among all vehicles can be determined as the loss value of mileage variance between the expected simulation result and the actual simulation result. Alternatively, the average of the mileage variances of all vehicles can be determined as the loss value of mileage variance between the expected simulation result and the actual simulation result.

[0150] After determining the loss value between the expected simulation result and the actual simulation result, the coefficients of the initial scheduling algorithm can be adjusted based on the loss value to obtain the target scheduling algorithm.

[0151] In practical applications, after obtaining the loss value between the expected simulation result and the actual simulation result obtained by the initial scheduling algorithm for any sample transportation request, the obtained loss value can be compared with a preset loss threshold. If the loss value is greater than the loss threshold, the coefficients of the initial scheduling algorithm are adjusted based on the loss value. The adjusted initial scheduling algorithm is then used to repeatedly execute the step of determining the loss value between the expected simulation result and the actual simulation result for any sample transportation request, until the loss value between the expected simulation result and the actual simulation result for any sample transportation request determined by the adjusted initial scheduling algorithm is less than the loss threshold. This is the target scheduling algorithm.

[0152] Specifically, the preset loss threshold can be a user-defined value or a value obtained based on experience.

[0153] S406 determines the simulated transportation result for each vehicle based on the simulated average mileage and the target scheduling algorithm.

[0154] After obtaining the target scheduling algorithm, the simulated average mileage of each vehicle can be quantified using the target scheduling algorithm to obtain the simulated transportation results of each vehicle.

[0155] S407 determines the target vehicle based on each simulated transport result and generates a vehicle dispatch instruction for the target vehicle.

[0156] In this embodiment of the invention, by acquiring real-time status information of multiple vehicles, when a vehicle transportation request is detected, the transportation mileage information of the vehicle is determined based on the transportation task information and the real-time status information of the vehicle in the transportation request. Based on the transportation mileage information and the real-time status information, the simulated average mileage of each vehicle is determined. A random greedy algorithm is used to generate a scheduling sample set, an initial scheduling algorithm is constructed, and the initial scheduling algorithm is trained using the scheduling sample set to obtain a target scheduling algorithm. Based on the simulated average mileage and the target scheduling algorithm, the simulated transportation result of each vehicle is determined. Based on each simulated transportation result, a target vehicle is determined, and a vehicle scheduling instruction for the target vehicle is generated. The vehicle scheduling instruction is used to instruct the target vehicle to perform the transportation task, thereby enabling simulated transportation for all vehicles, obtaining the simulated transportation result of each vehicle, and selecting the vehicle with the smallest transportation mileage information from all the simulated transportation results as the target vehicle to instruct the target vehicle to perform the transportation task. This reduces the situation where the transportation mileage of some vehicles is much greater than that of other vehicles, and also reduces the problem of uneven distribution of transportation resources.

[0157] See Figure 5 , Figure 5 The diagram shows a structural schematic of a vehicle dispatching device according to an embodiment of this application. The device may specifically include the following modules:

[0158] The acquisition module 501 is used to acquire real-time status information of multiple vehicles;

[0159] The simulation module 502 is used to determine the simulated transportation result of each vehicle when a vehicle transportation request is detected, based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle; wherein the vehicle transportation request is generated for a transportation task, and the simulated transportation result includes transportation mileage information simulating the vehicle performing the transportation task.

[0160] The generation module 503 is used to determine the target vehicle based on each of the simulated transportation results, and generate a vehicle dispatching instruction for the target vehicle; wherein the target vehicle is the vehicle with the smallest transportation mileage information, and the vehicle dispatching instruction is used to instruct the target vehicle to perform the transportation task.

[0161] In one implementation, the simulation module 502 described above can also be used for:

[0162] When a vehicle transport request is detected, the transport mileage information of the vehicle is determined based on the transport task information in the vehicle transport request and the real-time status information of the vehicle.

[0163] Based on transportation mileage information and real-time status information, determine the simulated average mileage for each vehicle;

[0164] Based on the simulated average mileage and the preset scheduling algorithm, the simulated transportation result for each vehicle is determined; wherein, the scheduling algorithm is used to quantify the simulated average mileage to obtain the simulated transportation result.

[0165] In one implementation, the transportation task information includes the destination location information of the transportation task, the real-time status information includes the vehicle's location information, and the transportation mileage information is the distance the vehicle travels from its location information to the destination location information. Different vehicles correspond to different transportation mileage information.

[0166] In one implementation, the simulation module 502 described above can also be used for:

[0167] The simulated mileage variance of the vehicle is determined based on the simulated average mileage.

[0168] Based on the simulated average mileage, simulated mileage variance, and scheduling algorithm, the simulated transportation result for each vehicle is determined. The scheduling algorithm includes a first weight corresponding to the simulated average mileage and a second weight corresponding to the simulated mileage variance. The scheduling algorithm performs a weighted calculation on the simulated average mileage and simulated mileage variance based on the first weight and the second weight to obtain the simulated transportation result for the vehicle.

[0169] In one implementation, the real-time status information includes the average empty mileage and the average cargo mileage, the transportation mileage information includes the empty mileage information and the cargo mileage information, and the simulated average mileage includes the simulated empty average mileage and the simulated cargo average mileage.

[0170] In one implementation, the device further includes the following modules:

[0171] The training module is used to generate a set of scheduling samples using a random greedy algorithm before determining the simulated transportation result for each vehicle based on the simulated average mileage and the preset scheduling algorithm. The set of samples includes multiple scheduling samples, and each scheduling sample includes a sample scheduling instruction and the expected simulation result corresponding to the sample scheduling instruction.

[0172] An initial scheduling algorithm is constructed and trained using a set of scheduling samples to obtain a target scheduling algorithm. The target scheduling algorithm is then used to execute the steps of determining the simulated transportation results for each vehicle based on the simulated average mileage and the preset scheduling algorithm.

[0173] In one implementation, the above training module can also be used for:

[0174] Input the sample scheduling instructions from the scheduling sample set into the initial scheduling algorithm to obtain the actual simulation results corresponding to the sample scheduling instructions;

[0175] Determine the loss value between the expected simulation result and the actual simulation result, and adjust the coefficients of the initial scheduling algorithm based on the loss value to obtain the target scheduling algorithm.

[0176] In this embodiment of the invention, by acquiring real-time status information of multiple vehicles, when a vehicle transportation request is detected, the simulated transportation result of each vehicle is determined based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle. The vehicle transportation request is generated for the transportation task, and the simulated transportation result includes the transportation mileage information of the simulated vehicle performing the transportation task. Based on each simulated transportation result, a target vehicle is determined, and a vehicle dispatch instruction is generated for the target vehicle. The target vehicle is the vehicle with the smallest transportation mileage information. The vehicle dispatch instruction is used to instruct the target vehicle to perform the transportation task, thereby enabling simulated transportation for all vehicles, obtaining the simulated transportation result of each vehicle, and selecting the vehicle with the smallest transportation mileage information from all the simulated transportation results as the target vehicle to instruct the target vehicle to perform the transportation task. This reduces the situation where the transportation mileage of some vehicles is much greater than that of other vehicles, and also reduces the problem of uneven distribution of transportation resources.

[0177] It should be noted that the information interaction and execution process between the above-mentioned devices are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0178] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0179] See Figure 6 , Figure 6 This application provides a structural block diagram of an electronic device according to an embodiment of the present application, as shown below. Figure 6 As shown, this embodiment provides an electronic device 61, which includes at least one processor 611, a memory 612, and a computer program 6121 stored in the memory 612 and executable on at least one processor 611. When the processor 611 executes the computer program 6121, it implements the steps in any of the above-described method embodiments.

[0180] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in any of the above method embodiments.

[0181] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the various method embodiments.

[0182] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium.

[0183] The above detailed description is a specific description of feasible embodiments of the present invention. These embodiments are not intended to limit the patent scope of the present invention. All equivalent implementations or modifications that do not depart from the present invention should be included in the patent scope of this case.

Claims

1. A method for vehicle dispatching, characterized in that, The method includes: Obtain real-time status information for multiple vehicles; When a vehicle transport request is detected, the simulated transport result for each vehicle is determined based on the transport task information in the vehicle transport request and the real-time status information of the vehicle; wherein the vehicle transport request is generated for a transport task, and the simulated transport result includes transport mileage information simulating the vehicle performing the transport task. Based on each of the simulated transportation results, a target vehicle is determined, and a vehicle dispatch instruction is generated for the target vehicle; wherein, the target vehicle is the vehicle with the smallest transportation mileage information, and the vehicle dispatch instruction is used to instruct the target vehicle to perform the transportation task; The real-time status information includes actual empty mileage and actual cargo mileage. The actual empty mileage is the mileage traveled by the vehicle in an empty state at any time within a past period, and the actual cargo mileage is the mileage traveled by the vehicle in a cargo state at any time within a past period. The transportation mileage information includes empty mileage information and cargo mileage information. When a vehicle transport request is detected, the simulated transport result for each vehicle is determined based on the transport task information in the vehicle transport request and the real-time status information of the vehicle, including: When a vehicle transport request is detected, the transport mileage information of the vehicle is determined based on the transport task information of the transport task in the vehicle transport request and the real-time status information of the vehicle. Based on the transportation mileage information and the real-time status information, the simulated average mileage of each vehicle is determined; wherein, the simulated average mileage is the quotient of the simulated total mileage and the total number of simulations, the simulated total mileage is the sum of the total mileage of the vehicle and the transportation mileage information, and the total number of simulations is the number of times the vehicle has performed transportation tasks in the past period plus one. Based on the simulated average mileage and a preset scheduling algorithm, the simulated transportation result for each vehicle is determined; wherein, the scheduling algorithm is used to quantify the simulated average mileage to obtain the simulated transportation result. The step of determining the simulated transportation result for each vehicle based on the simulated average mileage and a preset scheduling algorithm includes: The simulated mileage variance of the vehicle is determined based on the simulated average mileage. Based on the simulated average mileage, the simulated mileage variance, and the scheduling algorithm, the simulated transportation result for each vehicle is determined; wherein, the scheduling algorithm includes a first weight corresponding to the simulated average mileage and a second weight corresponding to the simulated mileage variance, and the scheduling algorithm performs a weighted calculation on the simulated average mileage and the simulated mileage variance based on the first weight and the second weight to obtain the simulated transportation result for the vehicle; Wherein, when the simulated transportation result is determined by the scheduling algorithm based on the first weight and the second weight, the target vehicle is the vehicle with the smallest simulated transportation result among all vehicles.

2. The vehicle dispatching method as described in claim 1, characterized in that, The transportation task information includes the destination location information of the transportation task, the real-time status information includes the location information of the vehicle, and the transportation mileage information is the distance the vehicle travels from its location information to the destination location information when carrying out the transportation task. Different vehicles correspond to different transportation mileage information.

3. The vehicle dispatching method as described in claim 1, characterized in that, The simulated average mileage includes simulated empty average mileage and simulated loaded average mileage.

4. The vehicle dispatching method according to any one of claims 1 to 3, characterized in that, Before determining the simulated transport result for each vehicle based on the simulated average mileage and a preset scheduling algorithm, the method further includes: A random greedy algorithm is used to generate a set of scheduling samples; wherein, the set of samples includes multiple scheduling samples, and each scheduling sample includes a sample scheduling instruction and the expected simulation result corresponding to the sample scheduling instruction; An initial scheduling algorithm is constructed, and the initial scheduling algorithm is trained using the scheduling sample set to obtain a target scheduling algorithm. The target scheduling algorithm is then used to execute the step of determining the simulated transportation result of each vehicle based on the simulated average mileage and the preset scheduling algorithm.

5. The vehicle dispatching method as described in claim 4, characterized in that, The step of training the initial scheduling algorithm using the scheduling sample set to obtain the target scheduling algorithm includes: The sample scheduling instructions in the scheduling sample set are input into the initial scheduling algorithm to obtain the actual simulation results corresponding to the sample scheduling instructions; Determine the loss value between the expected simulation result and the actual simulation result, and adjust the coefficients of the initial scheduling algorithm based on the loss value to obtain the target scheduling algorithm.

6. A vehicle dispatching device, characterized in that, The device includes: The acquisition module is used to acquire real-time status information of multiple vehicles; The simulation module is used to determine the simulated transportation result for each vehicle when a vehicle transportation request is detected, based on the transportation task information in the vehicle transportation request and the real-time status information of the vehicle; wherein the vehicle transportation request is generated for a transportation task, and the simulated transportation result includes transportation mileage information simulating the vehicle performing the transportation task; The generation module is used to determine the target vehicle based on each of the simulated transportation results, and generate a vehicle dispatching instruction for the target vehicle; wherein the target vehicle is the vehicle with the smallest transportation mileage information, and the vehicle dispatching instruction is used to instruct the target vehicle to perform the transportation task; The real-time status information includes actual empty mileage and actual cargo mileage. The actual empty mileage is the mileage traveled by the vehicle in an empty state at any time within a past period, and the actual cargo mileage is the mileage traveled by the vehicle in a cargo state at any time within a past period. The transportation mileage information includes empty mileage information and cargo mileage information. The simulation module is also used for: When a vehicle transport request is detected, the transport mileage information of the vehicle is determined based on the transport task information of the transport task in the vehicle transport request and the real-time status information of the vehicle. Based on the transportation mileage information and the real-time status information, the simulated average mileage of each vehicle is determined; wherein, the simulated average mileage is the quotient of the simulated total mileage and the total number of simulations, the simulated total mileage is the sum of the total mileage of the vehicle and the transportation mileage information, and the total number of simulations is the number of times the vehicle has performed transportation tasks in the past period plus one. Based on the simulated average mileage and a preset scheduling algorithm, the simulated transportation result for each vehicle is determined; wherein, the scheduling algorithm is used to quantify the simulated average mileage to obtain the simulated transportation result. The simulation module is also used for: The simulated mileage variance of the vehicle is determined based on the simulated average mileage. Based on the simulated average mileage, the simulated mileage variance, and the scheduling algorithm, the simulated transportation result for each vehicle is determined; wherein, the scheduling algorithm includes a first weight corresponding to the simulated average mileage and a second weight corresponding to the simulated mileage variance, and the scheduling algorithm performs a weighted calculation on the simulated average mileage and the simulated mileage variance based on the first weight and the second weight to obtain the simulated transportation result for the vehicle; Wherein, when the simulated transportation result is determined by the scheduling algorithm based on the first weight and the second weight, the target vehicle is the vehicle with the smallest simulated transportation result among all vehicles.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the vehicle scheduling method as described in any one of claims 1 to 5.

8. A computer program product, said computer program product storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the vehicle scheduling method as described in any one of claims 1 to 5.

Images