A vehicle dispatching method and device, electronic equipment and computer readable medium

Abstract

The application discloses a vehicle scheduling method and device, electronic equipment and computer readable medium, and relates to the technical field of logistics transportation. The method comprises the following steps: determining vehicles to which a current wave has allocated work tasks and the number of waiting vehicles of each platform; obtaining vehicle attributes and remaining buffer performance time for each vehicle; performing hierarchical filtering and resource conflict filtering on the platform based on a target performance rate, a preset matching constraint condition, the work tasks allocated to the vehicles, the number of waiting vehicles, the vehicle attributes and the remaining buffer performance time, so as to obtain an initial feasible solution set, wherein the initial feasible solution comprises a vehicle and a platform; evaluating the initial feasible solution set based on multiple target dimensions through an evaluation model, and screening a target solution comprising a vehicle and a target platform; and scheduling the vehicle to the target platform when the target platform is idle. The method can guarantee service timeliness and a high performance rate, and can maintain high feasibility, low operation cost and reasonable operation resource scheduling.

Description

Technical Field

[0001] This application relates to the field of logistics and transportation technology, and in particular to a vehicle dispatching method, apparatus, electronic device, and computer-readable medium. Background Technology

[0002] Currently, during peak operating periods, logistics parks often cannot guarantee high fulfillment rates due to limited transportation capacity. However, simply increasing transportation capacity would lead to waste of resources and excessively high operating costs. Therefore, existing vehicle dispatching methods cannot simultaneously ensure service timeliness and high fulfillment rates while maintaining high feasibility, low operating costs, and reasonable transportation capacity allocation. Summary of the Invention

[0003] In view of this, embodiments of this application provide a vehicle dispatching method, apparatus, electronic device, and computer-readable medium, which can solve the problem that existing vehicle dispatching methods cannot maintain high feasibility, low operating costs, and reasonable scheduling of transportation resources while ensuring service timeliness and high fulfillment rate.

[0004] To achieve the above objectives, according to one aspect of the embodiments of this application, a vehicle dispatching method is provided, comprising: In response to a vehicle dispatch request, determine the vehicles assigned to tasks in the current wave and the number of waiting vehicles at each platform. For each vehicle, obtain the corresponding vehicle attributes and remaining buffer fulfillment time; Based on the target fulfillment rate, preset matching constraints, work tasks assigned to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, the platforms are subjected to hierarchical filtering and resource conflict filtering to obtain an initial feasible solution set. The initial feasible solution set includes multiple initial feasible solutions corresponding to the work tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform. The initial feasible solution set is evaluated by an evaluation model based on multiple objective dimensions. The target solution is obtained by screening based on the evaluation results. The multiple objective dimensions include timeliness, cost, resources and scheduling. The target solution includes vehicles and target platforms. When the target platform is available, dispatch the vehicle to the target platform.

[0005] Optionally, based on the target fulfillment rate, preset matching constraints, assigned tasks to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, the platform is subjected to hierarchical filtering and resource conflict filtering to obtain an initial feasible solution set, including: The urgency level of fulfillment is determined based on the remaining buffer time. Determine the transport conditions of the goods involved in the work tasks assigned to the vehicles, and determine the platform type based on the transport conditions and the urgency level of the contract. Candidate platforms are determined based on the number of waiting vehicles and the platform type; The vehicle attributes are matched with the preset matching constraints corresponding to the candidate platforms. The candidate platforms are then filtered based on the matching results and the target fulfillment rate. Based on the filtering results and the vehicles, an initial feasible solution set is obtained.

[0006] Optionally, the urgency level of fulfillment can be determined based on the remaining buffer fulfillment time, including: If the remaining buffer fulfillment time is less than the first time threshold, the fulfillment urgency level is determined to be urgent. In response to the remaining buffer fulfillment time being between the first time threshold and the second time threshold, the fulfillment urgency level is determined to be general; If the remaining buffer fulfillment time exceeds the second time threshold, the fulfillment urgency level is determined to be non-urgent. The first duration threshold is less than the second duration threshold.

[0007] Optionally, the platform type may be determined based on transport conditions and the level of urgency, including: Based on whether the transport conditions are air transport or cold chain transport, determine the corresponding proportion for each transport condition; If the proportion is greater than the preset proportion threshold and the urgency level of the fulfillment is urgent, the platform type is determined to be automated. If the proportion is less than or equal to the preset proportion threshold and the urgency level of the contract is normal, the platform type is determined to be manual. If the proportion is less than or equal to the preset proportion threshold and the urgency level of the fulfillment is not urgent, the platform type is determined to be standby.

[0008] Optionally, candidate platforms are determined based on the number of waiting vehicles and platform type, including: In response to the number of waiting vehicles exceeding a preset threshold and the platform type being standby, the candidate platform is determined as a standby platform. In response to a waiting number of vehicles being less than or equal to a preset threshold and the platform type being automated, the candidate platform is determined to be an automated platform. If the number of waiting vehicles is less than or equal to a preset threshold and the platform type is manual, the candidate platform is determined to be a manual platform.

[0009] Optionally, before performing hierarchical filtering and resource conflict filtering on the platform based on the target fulfillment rate, preset matching constraints, assigned tasks to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time to obtain an initial feasible solution set, the vehicle scheduling method further includes: In response to determining the vehicle's fulfillment urgency level as urgent based on the remaining buffer fulfillment time, the current fulfillment penalty cost and available transportation capacity of the vehicle are obtained. The fulfillment penalty cost is calculated based on the weighted average of the costs of multiple fulfillment failures and dynamic cost weights. Calculate the estimated probability of default for the vehicle based on performance penalty costs and transportation capacity resources; If the estimated probability of default is greater than a preset probability threshold, the vehicle will be postponed to the next wave of operation, and the vehicles already assigned to the vehicles will be reassigned to the current wave of operations.

[0010] Optionally, the initial feasible solution set is evaluated using an evaluation model based on multiple objective dimensions, and the objective solution is obtained by filtering based on the evaluation results, including: The evaluation model calculates the comprehensive benefits for each vehicle and platform corresponding to each initial feasible solution in the initial feasible solution set based on timeliness, cost, resource, and scheduling dimensions. The vehicles and platforms corresponding to the initial feasible solution that maximizes overall benefits are identified as the vehicles and target platforms of the objective solution.

[0011] In addition, this application also provides a vehicle dispatching device, including: The request response unit is configured to respond to a vehicle dispatch request by determining the vehicles assigned to work tasks in the current wave and the number of waiting vehicles at each platform. The acquisition unit is configured to acquire the corresponding vehicle attributes and remaining buffer fulfillment time for each vehicle; The platform filtering unit is configured to perform hierarchical filtering and resource conflict filtering on the platform based on the target fulfillment rate, preset matching constraints, work tasks assigned to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, to obtain an initial feasible solution set. The initial feasible solution set includes multiple initial feasible solutions corresponding to the work tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform. The evaluation unit is configured to evaluate the initial feasible solution set based on multiple objective dimensions using an evaluation model, and to select the target solution based on the evaluation results. The multiple objective dimensions include timeliness, cost, resources and scheduling. The target solution includes vehicles and target platforms. The vehicle dispatching unit is configured to dispatch vehicles to the target platform when the target platform is available.

[0012] Optionally, the platform filtering unit is further configured to: The urgency level of fulfillment is determined based on the remaining buffer time. Determine the transport conditions of the goods involved in the work tasks assigned to the vehicles, and determine the platform type based on the transport conditions and the urgency level of the contract. Candidate platforms are determined based on the number of waiting vehicles and the platform type; The vehicle attributes are matched with the preset matching constraints corresponding to the candidate platforms. The candidate platforms are then filtered based on the matching results and the target fulfillment rate. Based on the filtering results and the vehicles, an initial feasible solution set is obtained.

[0013] Optionally, the platform filtering unit is further configured to: If the remaining buffer fulfillment time is less than the first time threshold, the fulfillment urgency level is determined to be urgent. In response to the remaining buffer fulfillment time being between the first time threshold and the second time threshold, the fulfillment urgency level is determined to be general; If the remaining buffer fulfillment time exceeds the second time threshold, the fulfillment urgency level is determined to be non-urgent. The first duration threshold is less than the second duration threshold.

[0014] Optionally, the platform filtering unit is further configured to: Based on whether the transport conditions are air transport or cold chain transport, determine the corresponding proportion for each transport condition; If the proportion is greater than the preset proportion threshold and the urgency level of the fulfillment is urgent, the platform type is determined to be automated. If the proportion is less than or equal to the preset proportion threshold and the urgency level of the contract is normal, the platform type is determined to be manual. If the proportion is less than or equal to the preset proportion threshold and the urgency level of the fulfillment is not urgent, the platform type is determined to be standby.

[0015] Optionally, the platform filtering unit is further configured to: In response to the number of waiting vehicles exceeding a preset threshold and the platform type being standby, the candidate platform is determined as a standby platform. In response to a waiting number of vehicles being less than or equal to a preset threshold and the platform type being automated, the candidate platform is determined to be an automated platform. If the number of waiting vehicles is less than or equal to a preset threshold and the platform type is manual, the candidate platform is determined to be a manual platform.

[0016] Optionally, the vehicle dispatching device also includes a performance circuit breaker unit, configured to: In response to determining the vehicle's fulfillment urgency level as urgent based on the remaining buffer fulfillment time, the current fulfillment penalty cost and available transportation capacity of the vehicle are obtained. The fulfillment penalty cost is calculated based on the weighted average of the costs of multiple fulfillment failures and dynamic cost weights. Calculate the estimated probability of default for the vehicle based on performance penalty costs and transportation capacity resources; If the estimated probability of default is greater than a preset probability threshold, the vehicle will be postponed to the next wave of operation, and the vehicles already assigned to the vehicles will be reassigned to the current wave of operations.

[0017] Optionally, the evaluation unit is further configured to: The evaluation model calculates the comprehensive benefits for each vehicle and platform corresponding to each initial feasible solution in the initial feasible solution set based on timeliness, cost, resource, and scheduling dimensions. The vehicles and platforms corresponding to the initial feasible solution that maximizes overall benefits are identified as the vehicles and target platforms of the objective solution.

[0018] In addition, this application also provides a vehicle dispatching electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, enable the one or more processors to implement the vehicle dispatching method as described above.

[0019] In addition, this application also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle scheduling method as described above.

[0020] To achieve the above objectives, according to another aspect of the embodiments of this application, a computer program product is provided.

[0021] A computer program product according to an embodiment of this application includes a computer program that, when executed by a processor, implements the vehicle scheduling method provided in an embodiment of this application.

[0022] One embodiment of the above invention has the following advantages or beneficial effects: In response to a vehicle dispatching request, this application determines the vehicles assigned to tasks in the current wave and the number of waiting vehicles at each platform; for each vehicle, it obtains the corresponding vehicle attributes and remaining buffer fulfillment time; based on the target fulfillment rate, preset matching constraints, tasks assigned to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, it performs hierarchical filtering and resource conflict filtering on platforms to obtain an initial feasible solution set. This initial feasible solution set includes multiple initial feasible solutions corresponding to tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform; an evaluation model is used to evaluate the initial feasible solution set based on multiple target dimensions, and a target solution is obtained based on the evaluation results. These multiple target dimensions include timeliness, cost, resource, and dispatching dimensions, and the target solution includes a vehicle and a target platform; when the target platform is idle, the vehicle is dispatched to the target platform. This achieves high feasibility, low operating costs, and reasonable capacity resource scheduling while ensuring service timeliness and a high fulfillment rate.

[0023] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0024] The accompanying drawings are provided to better understand this application and do not constitute an undue limitation thereof. Wherein: Figure 1 This is a schematic diagram of the main flow of a vehicle dispatching method according to an embodiment of this application; Figure 2 This is a schematic diagram of the main flow of a vehicle dispatching method according to an embodiment of this application; Figure 3 This is a schematic flowchart of a vehicle dispatching method according to an embodiment of this application; Figure 4 This is a schematic diagram of the main units of a vehicle dispatching device according to an embodiment of this application; Figure 5 This is an exemplary system architecture diagram to which embodiments of this application can be applied; Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers in the embodiments of this application. Detailed Implementation

[0025] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These embodiments should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solutions of this application comply with relevant national laws and regulations. It should also be noted that certain software, components, models, and other existing industry solutions may be mentioned in the embodiments of this application. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions. The collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solutions of this application all comply with relevant laws and regulations, are used for legal and reasonable purposes, do not violate public order and good morals, are not shared, disclosed, or sold outside of these legal uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken to prevent unauthorized access to user personal information, safeguard user personal information security, cybersecurity, and national security, and ensure that those authorized to access personal information comply with relevant laws and regulations. Once this user personal information is no longer needed, risks should be minimized by restricting or even prohibiting data collection and / or deleting the data.

[0026] When used, including in certain relevant applications, data is deidentified to protect user privacy, for example by removing specific identifiers, controlling the amount or specificity of stored data, controlling how data is stored, and / or other methods.

[0027] Figure 1 This is a schematic diagram of the main flow of a vehicle dispatching method according to an embodiment of this application, as shown below. Figure 1 As shown, the vehicle dispatching method mainly includes the following steps S101-S105.

[0028] Step S101: In response to the vehicle dispatch request, determine the vehicles assigned to work tasks in the current wave and the number of waiting vehicles at each platform.

[0029] In this embodiment, after receiving a vehicle scheduling request, the executing entity of the vehicle scheduling method (e.g., a server) can determine the number of vehicles (e.g., vehicle 1, vehicle 2, ..., vehicle n) that have been assigned tasks in the current wave and the number of waiting vehicles at each platform (e.g., platform 1, platform 2, ..., platform n).

[0030] Step S102: For each vehicle, obtain the corresponding vehicle attributes and remaining buffer fulfillment time.

[0031] Taking vehicle k as an example, where 1≤k≤n, and n is the total number of vehicles assigned tasks in the current wave. Obtain the vehicle attributes of vehicle k (e.g., vehicle business type, vehicle length, total weight of vehicle cargo, total volume of vehicle cargo, and type of vehicle cargo) and the remaining buffer fulfillment time.

[0032] Step S103: Based on the target fulfillment rate, preset matching constraints, work tasks assigned to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, the platforms are subjected to hierarchical filtering and resource conflict filtering to obtain an initial feasible solution set. The initial feasible solution set includes multiple initial feasible solutions corresponding to the work tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform.

[0033] Specifically, before performing hierarchical filtering and resource conflict filtering on the platform based on the target fulfillment rate, preset matching constraints, assigned tasks to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time to obtain an initial feasible solution set, the vehicle scheduling method further includes: in response to determining the vehicle's fulfillment urgency level as urgent based on the remaining buffer fulfillment time (e.g., <1 hour), obtaining the vehicle's current fulfillment penalty cost and available transport capacity resources, wherein the fulfillment penalty cost is calculated based on the cost of multiple fulfillment failures and a dynamic cost weight, wherein the dynamic cost weight can be dynamically adjusted based on the number of fulfillment failures of the vehicle to achieve accurate calculation of the vehicle's fulfillment penalty cost; and calculating the vehicle's estimated default probability based on the fulfillment penalty cost and transport capacity resources. For example, the fulfillment penalty cost and transport capacity resources can be input into a pre-trained default probability prediction model, wherein the default prediction model characterizes the correspondence between the fulfillment penalty cost, transport capacity resources, and the estimated default probability, and the default probability prediction model quickly outputs the corresponding estimated default probability. In response to an estimated default probability greater than a preset probability threshold (e.g., 5%), the vehicle (e.g., vehicle i) is postponed to the next wave of operations, and the tasks already assigned to the vehicle are reassigned to vehicles available in the current wave (e.g., vehicle k) to avoid downstream operations continuing to wait and increasing the amount of unfulfilled goods, thus ensuring a high fulfillment rate while preventing some vehicles from being unable to operate for extended periods.

[0034] After identifying the vehicles available for operation (e.g., vehicle k), the platform is subjected to hierarchical filtering (e.g., filtering based on platform capacity matching, urgency level, special business rules, secondary handling rules, large-volume vehicle non-adjacent rules, and maximum number of vehicles bound to the platform) and resource conflict filtering (e.g., filtering based on platform overload circuit breaker, performance circuit breaker, and secondary handling triggering rules) based on the target fulfillment rate, preset matching constraints, the operation tasks assigned to the vehicle (e.g., vehicle k), the number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time. This accurately yields an initial feasible solution set, including multiple initial feasible solutions (e.g., including vehicle k and one platform) corresponding to the operation tasks assigned to the vehicle (e.g., vehicle k).

[0035] Step S104: The initial feasible solution set is evaluated by the evaluation model based on multiple target dimensions. The target solution is obtained by screening based on the evaluation results. The multiple target dimensions include timeliness, cost, resources and scheduling. The target solution includes vehicles and target platforms.

[0036] Specifically, the initial feasible solution set is evaluated using an evaluation model based on multiple objective dimensions. Target solutions are then selected based on the evaluation results. This includes: calculating the comprehensive benefits for each vehicle and platform corresponding to each initial feasible solution in the initial feasible solution set based on timeliness, cost, resource, and scheduling dimensions. Specifically, for each vehicle and platform corresponding to each initial feasible solution in the initial feasible solution set, the scheduling response rate (i.e., the proportion of vehicles meeting performance requirements) and performance deviation (i.e., the average absolute deviation between actual operating time and promised time) are calculated in the timeliness dimension. In the cost dimension, the unit cargo volume scheduling cost (i.e., the scheduling cost averaged per order) and resource scheduling cost (i.e., platform start-up and stop costs, secondary handling costs, etc.) are calculated. The system calculates the platform utilization rate (i.e., the proportion of platform idle time during startup) in the resource dimension, and the scheduling response rate (i.e., the proportion of vehicles allocated to platforms within 30 minutes) and the circuit breaker trigger frequency (i.e., the number of times the performance circuit breaker rule is activated per unit time) in the scheduling dimension. Finally, based on the calculated scores and their corresponding weights for scheduling response rate, performance deviation, unit cargo scheduling cost, resource scheduling cost, platform utilization rate, scheduling response rate, and circuit breaker trigger frequency, a weighted calculation is performed to obtain a comprehensive score, i.e., comprehensive benefit. The vehicle (e.g., vehicle k) and platform (e.g., platform 1) corresponding to the initial feasible solution with the highest comprehensive benefit are accurately determined as the vehicle and target platform of the target solution.

[0037] Step S105: When the target platform is idle, dispatch the vehicle to the target platform.

[0038] When a target platform is detected to be available, a vehicle number is automatically called (e.g., vehicle k is called), and the corresponding vehicle (e.g., vehicle k) is dispatched to the target platform (e.g., platform 1). This achieves high feasibility, low operating costs, and reasonable scheduling of transportation resources while ensuring service timeliness and high fulfillment rate.

[0039] This embodiment, in response to vehicle dispatching requests, determines the vehicles assigned to tasks in the current wave and the number of waiting vehicles at each platform. For each vehicle, it obtains the corresponding vehicle attributes and remaining buffer fulfillment time. Based on the target fulfillment rate, preset matching constraints, tasks assigned to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, it performs hierarchical filtering and resource conflict filtering on platforms to obtain an initial feasible solution set. This initial feasible solution set includes multiple initial feasible solutions corresponding to tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform. An evaluation model is used to evaluate the initial feasible solution set based on multiple target dimensions. The target solution is obtained by filtering based on the evaluation results. These target dimensions include timeliness, cost, resources, and dispatching. The target solution includes a vehicle and a target platform. When the target platform is idle, the vehicle is dispatched to the target platform. This achieves high feasibility, low operating costs, and reasonable capacity resource scheduling while ensuring service timeliness and a high fulfillment rate.

[0040] Figure 2 This is a schematic diagram of the main flow of a vehicle dispatching method according to an embodiment of this application, as follows: Figure 2 As shown, the vehicle dispatching method mainly includes the following steps S201-S208.

[0041] Step S201: In response to the vehicle dispatch request, determine the vehicles assigned to work tasks in the current wave and the number of waiting vehicles at each platform.

[0042] Upon receiving a vehicle dispatch request, it is possible to determine the number of vehicles assigned to work tasks in the current wave (e.g., vehicle 1, vehicle 2, ..., vehicle n) and the number of waiting vehicles at each platform (e.g., platform 1, platform 2, ..., platform n).

[0043] Step S202: For each vehicle, obtain the corresponding vehicle attributes and remaining buffer fulfillment time.

[0044] Taking vehicle k as an example, where 1≤k≤n, and n is the total number of vehicles assigned tasks in the current wave. Obtain the vehicle attributes of vehicle k (e.g., vehicle business type, vehicle length, total weight of vehicle cargo, total volume of vehicle cargo, and type of vehicle cargo) and the remaining buffer fulfillment time.

[0045] Step S203: Determine the urgency level of fulfillment based on the remaining buffer fulfillment time.

[0046] Specifically, the urgency level of fulfillment is determined based on the remaining buffer fulfillment time, including: in response to the remaining buffer fulfillment time being less than a first time threshold (e.g., <1 hour), the urgency level is determined to be urgent; in response to the remaining buffer fulfillment time being between the first time threshold and a second time threshold (e.g., 1-3 hours), the urgency level is determined to be moderate; in response to the remaining buffer fulfillment time being greater than the second time threshold (>3 hours), the urgency level is determined to be non-urgent; wherein the first time threshold is less than the second time threshold.

[0047] Step S204: Determine the transportation conditions of the goods involved in the work tasks assigned to the vehicles, and determine the platform type based on the transportation conditions and the urgency level of the performance.

[0048] Specifically, the platform type is determined based on the transportation conditions and the urgency level, including: in response to the transportation conditions being air transport or cold chain transport, determining the corresponding proportion of the transportation conditions, for example, the proportion of air transport among all transportation conditions (e.g., air shipments), for example, 60%, or the proportion of cold chain transport among all transportation conditions (e.g., cold chain shipments), for example, 40%; in response to the proportion being greater than a preset proportion threshold (e.g., 50%) and the urgency level being urgent, determining the platform type as automated; in response to the proportion being less than or equal to the preset proportion threshold (e.g., 50%) and the urgency level being moderate, determining the platform type as manual; in response to the proportion being less than or equal to the preset proportion threshold (e.g., 50%) and the urgency level being non-urgent, determining the platform type as standby.

[0049] Step S205: Determine candidate platforms based on the number of waiting vehicles and platform type.

[0050] Specifically, candidate platforms are determined based on the number of waiting vehicles and the platform type. These include: If the number of waiting vehicles at each platform exceeds a preset threshold (e.g., 5 vehicles) and the platform type is "standby," a standby platform is selected as the candidate platform. Standby platforms are non-standard platforms, typically defined in a virtual space within the parking area. They generally employ a combination of forklifts and manual labor for two loading / unloading operations, resulting in the lowest loading / unloading efficiency. If the number of waiting vehicles at each platform is less than or equal to a preset threshold (e.g., 5 vehicles) and the platform type is "automated," an automated platform is selected as the candidate platform. Automated platforms are standard platforms that meet vehicle parking requirements and are equipped with automated loading / unloading equipment, resulting in high loading / unloading efficiency. If the number of waiting vehicles at each platform is less than or equal to a preset threshold (e.g., 5 vehicles) and the platform type is "manual," a manual platform is selected as the candidate platform. Manual platforms are standard platforms that meet vehicle parking requirements but are not equipped with automated loading / unloading equipment, resulting in moderate loading / unloading efficiency.

[0051] Step S206: Match the vehicle attributes with the preset matching constraints corresponding to the candidate platforms. Filter the candidate platforms based on the matching results and the target fulfillment rate. Obtain an initial feasible solution set based on the filtering results and the vehicles. The initial feasible solution set includes multiple initial feasible solutions corresponding to the work tasks assigned to the vehicles. Each initial feasible solution includes a vehicle and a platform.

[0052] For example, the preset matching constraints for candidate platforms include: vehicle service type must belong to the platform's allowed type set, vehicle length ≤ platform strength, vehicle length ≤ equipment length + buffer value, total cargo weight ≤ platform load-bearing limit, total cargo volume ≤ platform temporary storage area capacity, and vehicle cargo type must match the platform operation type. Vehicle attributes (e.g., vehicle service type, vehicle length, total vehicle cargo weight, total vehicle cargo volume, and vehicle cargo type) are matched against the preset matching constraints for the candidate platforms to obtain a matching result (e.g., match or no match). Candidate platforms are then filtered based on the matching result and the target fulfillment rate. Based on the filtering result and the vehicles, an initial feasible solution set is obtained. For example, if the matching result is a match, candidate platforms are further filtered using the target fulfillment rate to obtain a filtering result (this filtering result refers to the platforms that can form an initial feasible solution; the number can be one or more). Each platform in the filtering result is combined with the currently targeted vehicle (e.g., vehicle k) to form an initial feasible solution. An initial feasible solution set is obtained from these initial feasible solutions.

[0053] Step S207: The initial feasible solution set is evaluated by the evaluation model based on multiple target dimensions. The target solution is obtained by screening based on the evaluation results. The multiple target dimensions include timeliness, cost, resources and scheduling. The target solution includes vehicles and target platforms.

[0054] For each vehicle and platform corresponding to an initial feasible solution in the initial feasible solution set, the evaluation model calculates the scheduling response rate (i.e., the proportion of vehicles meeting the fulfillment requirements) and fulfillment deviation (i.e., the average absolute deviation between the actual operation time and the promised time) in the timeliness dimension; the unit cargo volume scheduling cost (i.e., the scheduling cost averaged per order) and resource scheduling cost (i.e., the proportion of platform start-up and stop costs and secondary handling costs in the total cost) in the cost dimension; the platform utilization rate (i.e., the proportion of platform idle time during startup) in the resource dimension; and the scheduling response rate (i.e., the proportion of platform idle time during startup) in the scheduling dimension. The comprehensive score, or comprehensive benefit, is calculated by weighting the scores and weights of the dispatch response rate, performance deviation, unit cargo dispatch cost, resource dispatch cost, platform utilization rate, dispatch response rate, and circuit breaker trigger frequency within 30 minutes. The vehicles (e.g., vehicle k) and platforms (e.g., platform 1) corresponding to the initial feasible solution with the highest comprehensive benefit are accurately determined as the target vehicles and target platforms.

[0055] Step S208: When the target platform is idle, dispatch the vehicle to the target platform.

[0056] This will enable us to ensure timely service and high fulfillment rates while maintaining high feasibility, low operating costs, and reasonable allocation of transportation resources.

[0057] Figure 3 This is a schematic diagram of the main flow of a vehicle dispatching method according to an embodiment of this application. Figure 3As shown, in response to a vehicle scheduling request, the system determines the number of vehicles (e.g., vehicle k) assigned to tasks in the current wave and the number of waiting vehicles at each platform (e.g., platform 1, platform 2, ..., platform n). For each vehicle (e.g., vehicle k), the system obtains the corresponding vehicle attributes and remaining buffer fulfillment time. Based on the target fulfillment rate, preset matching constraints, the tasks assigned to that vehicle (e.g., vehicle k), the number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, the system performs hierarchical filtering and resource conflict filtering on the platforms to obtain an initial feasible solution set. This initial feasible solution set includes multiple initial feasible solutions corresponding to the tasks assigned to the vehicles (e.g., initial feasible solution 1, initial feasible solution 2, initial feasible solution 3, initial feasible solution 4, initial feasible solution 5, initial feasible solution 6, initial feasible solution 7, initial feasible solution 8, initial feasible solution 9, initial feasible solution 10 ... Initial feasible solutions are defined as follows: Initial Feasible Solution 1, ..., Initial Feasible Solution n. Each initial feasible solution includes the vehicle (e.g., vehicle k) and a platform. For example, Initial Feasible Solution 1 includes vehicle k and platform 1, Initial Feasible Solution 2 includes vehicle k and platform 2, ..., Initial Feasible Solution n includes vehicle k and platform n. The initial feasible solution set is evaluated using an evaluation model based on multiple objective dimensions. Target solutions are obtained by filtering based on the evaluation results. These multiple objective dimensions include timeliness, cost, resources, and scheduling. The target solution includes the vehicle (e.g., vehicle k) and the target platform (e.g., platform 1). When the target platform (e.g., platform 1) is idle, the vehicle is scheduled to the target platform (e.g., platform 1). This achieves high feasibility, low operating costs, and reasonable capacity resource scheduling while ensuring service timeliness and high fulfillment rates.

[0058] This application, under the rigid constraint of ensuring an order fulfillment rate ≥ target fulfillment rate (e.g., 99%), achieves structural optimization of costs across four dimensions: transportation, manpower, equipment, and cargo damage, through a dynamic scheduling mechanism. This results in a significant increase in order fulfillment rate; shorter time from order call to completion; fewer open platforms, directly reducing energy and labor costs; improved platform utilization and optimized space resources; and reduced secondary handling through precise platform-warehouse matching, leading to lower cargo damage rates and quality cost control. In existing logistics parks, there are typically multiple warehouses / sorting centers with varying capabilities, each with different types of goods stored and shipping routes. Each warehouse / sorting center requires multiple platforms for vehicle loading and unloading operations. Due to limitations in physical space, loading and unloading equipment, and internal equipment, platforms have certain requirements for the vehicles they can accommodate. For example, a platform might be limited to vehicles no longer than 9.6 meters, meaning vehicles longer than 9.6 meters are not allowed to park at that platform.

[0059] A platform capacity-vehicle matching matrix has been constructed, which includes the following: Platform Attributes: Service Type Attribute description: Loading, unloading, and integrated loading and unloading; Preset matching constraints: Vehicle service type must belong to the platform's allowed type set; Platform attributes: Platform length Attribute description: Parking area length (≤19.6m); Preset matching constraint: Vehicle length ≤ Platform strength; Platform attributes: Equipment length Attribute description: Length of telescopic belt conveyor (≤17m); Preset matching constraint: Vehicle length ≤ Equipment length + Buffer value; Platform attributes: load-bearing capacity Attribute description: differentiated by material (steel platform has lower load-bearing capacity); preset matching constraint: total weight of goods ≤ platform load-bearing limit; Platform attributes: Platform space Attribute description: Based on the platform's temporary storage space, for example, the maximum temporary storage for a medium-density platform is 120m. 2 Cargo; Preset matching constraints: Total cargo volume ≤ Platform temporary storage area capacity; Platform Attributes: Operation Type Attribute description: trunk line, branch line, transfer station, full cargo, less-than-cargo; Preset matching constraints: vehicle cargo type must match platform operation type.

[0060] The dynamic scheduling mechanism is based on the elastic resource allocation rules: when the number of waiting vehicles exceeds a certain number, the backup platform is activated. The number of backup platforms is affected by factors such as equipment, site space, and manpower. At the same time, activating the platform will trigger platform start-up and shutdown costs.

[0061] Specifically, loading platforms are categorized into automated platforms, manual platforms, and standby platforms. Automated platforms are standard platforms that meet vehicle parking requirements and are equipped with automated loading and unloading equipment, resulting in high efficiency. Manual platforms are also standard platforms that meet vehicle parking requirements, but they are not equipped with automated loading and unloading equipment, leading to generally lower efficiency. Standby platforms are non-standard platforms, typically located in designated virtual spaces within the parking area. They generally employ a combination of forklifts and manual labor for two loading and unloading operations, resulting in the lowest efficiency. Automated and manual platforms are fixed assets and cannot be adjusted in the short term, while standby platforms, limited by site space and safety requirements, can be dynamically adjusted in a certain number.

[0062] The dynamic scheduling mechanism is based on inter-warehouse transfer rules: when warehouse platform resources are scarce and spare platforms are insufficient, cross-warehouse coordinated scheduling, i.e., secondary handling, is permitted. Secondary handling incurs corresponding costs and damage risks depending on the handling method, and is also limited by the equipment and human resources available. Secondary handling typically takes two forms: manual forklift handling and automated equipment handling. Manual forklift handling costs are calculated per pallet; goods are stacked on pallets, and handling costs are calculated based on the number of pallets. Damage costs are calculated based on the company's average handling damage cost, and time is calculated by multiplying the forklift operation's secondary handling time by the total number of pallets. Resources are limited by the total number of forklifts. Automated equipment, generally belt conveyors, calculates handling costs per item, i.e., the cost per item, with the standard referenced to the company's single-item inter-warehouse handling cost. Automated equipment handling does not consider damage costs, and time is referenced to the standard equipment transportation time. Resources are limited by the maximum number of items the equipment can transport per unit time.

[0063] The dynamic scheduling mechanism is based on a performance suspension rule: when a waiting vehicle is unable to fulfill its obligations due to resource constraints, excessive penalty costs, or other reasons, the suspension rule can be activated. This means the vehicle will not operate in the current wave and will be postponed to the next wave. The reason is that when on-site conditions cannot meet operational requirements, downstream operations should not continue to wait, thus increasing the volume of unfulfilled goods. In subsequent operations, the performance penalty costs for delayed vehicles can be weighted and calculated, increasing the cost of multiple performance failures to prevent certain vehicles from being unable to operate for extended periods.

[0064] The mixed-integer programming model upon which dynamic scheduling mechanisms are based: Decision variables: ,

[0065] Objective function: Minimize the sum of transportation costs (positively correlated with vehicle waiting time), labor and equipment costs (positively correlated with the duration of open platform operation), platform start-up and stop costs (positively correlated with the number of platform start-ups and stop-ups), handling and cargo damage costs (positively correlated with the amount of secondary handling), and non-performance penalty costs, which means minimizing operating costs.

[0066]

[0067] Where V represents the number of secondary handling operations, which can be optimized to be charged by piece, by volume, or by weight. N represents the number of goods that have not met the fulfillment requirements.

[0068] Core constraints, ensuring target fulfillment rate:

[0069] From the vehicle being called Initially, vehicles must drive from the waiting area to the designated platform. and prepare for the operation. Preparations include safety checks, removing and installing tarpaulins, and placing brake pads. After these preliminary steps are completed, platform staff will proceed with loading and unloading operations. The operation time is related to the platform's operational efficiency. If there are goods requiring secondary handling, they must be moved to the designated location using forklifts or other equipment, and the secondary handling time will be [not specified]. It depends on the number of handling operations. Depending on the type of goods (general cargo, cold chain, air freight, etc.), there are fixed fulfillment times each day. Requirements. Warehouse operations. The sorting operation time is indicated by a relatively fixed standard based on the warehouse's process requirements and operational specifications.

[0070] Vehicle attributes must meet the following conditions to be compatible with platform capabilities: Business type adaptation:

[0071] Length adaptation:

[0072] Equipment length adaptation:

[0073] Load-bearing capacity:

[0074] Platform space adaptation:

[0075] Operation type adaptation:

[0076] Time window continuity:

[0077] This application obtains the optimal vehicle scheduling scheme, i.e., the target solution, through a two-stage optimization process. Specifically, based on a two-stage solution framework that combines rule-driven feasible solution generation with intelligent optimization, it achieves real-time generation of feasible solutions and refined multi-objective cost optimization under hard performance constraints. Stage 1: Rule-driven feasible solution generation. Based on the real-time system state, an initial feasible solution set is quickly constructed using a hierarchical rule engine and a resource conflict rule engine. While ensuring that all output solutions meet the target performance rate requirements, the scope of the feasible solution set is simplified, laying the foundation for the feasible domain in subsequent optimizations. Stage 2: Intelligent optimization collaboration. Within the initial feasible solution set, a solver is used to perform global cost optimization. The multi-objective evaluation function dynamically weights transportation, manpower, cargo damage, and performance penalty costs, and adjusts the weight priorities in real time according to vehicle backlog conditions. Under the premise of ensuring feasibility, the cost-optimal vehicle scheduling scheme, i.e., the target solution (including the current vehicles and the target platform), is output.

[0078] Phase 1: The rules upon which rule-driven feasible solution generation is based can be as follows: Example of hierarchical filtering: Filtering rule: Platform capacity matching; Description: Based on the constructed platform capacity-vehicle type matching matrix, exclude allocation combinations with incompatible physical attributes; Filtering rules: urgency level classification; Description: Classified by remaining buffer time: Urgent (<1 hour), prioritize automated platforms; Normal (1-3 hours), prioritize manual platforms; Non-urgent (>3 hours), can be assigned to backup platforms or delayed scheduling; Filtering rules: Special business rules; Description: Air shipments accounting for more than 50% are treated the same as emergency delivery vehicles; Cold chain shipments accounting for more than 50% are treated the same as emergency delivery vehicles; Filtering rule: Secondary handling rule; Description: If more than 50% of the goods require secondary handling, the secondary handling rule will not be triggered; Filtering rule: Large-volume vehicles cannot be parked adjacent to each other; Description: Vehicles with cargo volume exceeding 120m³ cannot park at adjacent platforms. Filtering rule: Maximum number of vehicles bound to a platform; Description: The maximum number of vehicles bound to a single platform is no more than 5.

[0079] Example of resource conflict filtering: Filtering rule: Platform overload fuse; Description: When more than 5 vehicles are waiting on a single platform, the backup platform is activated; Filtering rule: Performance suspension; Description: For emergency vehicles, if the estimated probability of default is >5%, the delay will be extended to the next round. Filtering rule: Triggered by secondary handling; Description: If the number of goods requiring secondary handling is less than 100, secondary handling will be triggered first.

[0080] Phase 2: Intelligent optimization and collaboration, based on a cost-performance-based lean maturity assessment model for the park: quantifying the comprehensive benefits of vehicle scheduling optimization solutions, conducting four-dimensional assessments of timeliness, cost, resources, and scheduling, and further classifying the park's operational level into multiple levels based on the performance of these four-dimensional indicators.

[0081] For example, the evaluation dimensions are: timeliness stability; the indicators are: dispatch response rate (the proportion of vehicles that meet the performance requirements) and performance deviation (the average absolute deviation between the actual operation time and the promised time). Evaluation dimensions: Cost health; Indicators: Unit cargo dispatch cost: average dispatch cost per order; Resource dispatch cost: the proportion of platform start-up and shutdown costs and secondary handling costs in the total cost; Evaluation Dimension: Resource Efficiency; Indicator: Platform Utilization Rate: The percentage of platform idle time during startup; Evaluation dimensions: dynamic response capability; indicators: dispatch response rate: the percentage of vehicles allocated to the platform within 30 minutes; circuit breaker trigger frequency: the number of times the performance circuit breaker rule is activated per unit time.

[0082] A two-stage solution framework decouples the complex scheduling problem. The first stage (rule-driven) leverages domain knowledge to rapidly narrow down the solution space, ensuring the executability and performance rigidity of the solution. The second stage (model optimization) performs refined cost optimization within the feasible region. Simultaneously, the introduction of flexible resource allocation rules and dynamic cost weights enhances the system's robustness and adaptability.

[0083] Figure 4 This is a schematic diagram of the main units of a vehicle dispatching device according to an embodiment of this application. Figure 4 As shown, the vehicle dispatching device 400 includes a request response unit 401, an acquisition unit 402, a platform filtering unit 403, an evaluation unit 404, and a vehicle dispatching unit 405.

[0084] The request response unit 401 is configured to, in response to a vehicle dispatch request, determine the vehicles assigned to work tasks in the current wave and the number of waiting vehicles at each platform.

[0085] The acquisition unit 402 is configured to acquire the corresponding vehicle attributes and remaining buffer fulfillment time for each vehicle.

[0086] Platform filtering unit 403 is configured to perform hierarchical filtering and resource conflict filtering on platforms based on target fulfillment rate, preset matching constraints, work tasks assigned to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, to obtain an initial feasible solution set. The initial feasible solution set includes multiple initial feasible solutions corresponding to the work tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform.

[0087] Evaluation unit 404 is configured to evaluate the initial feasible solution set based on multiple objective dimensions using an evaluation model, and to select the target solution based on the evaluation results. The multiple objective dimensions include timeliness, cost, resources and scheduling, and the target solution includes vehicles and target platforms.

[0088] Vehicle dispatching unit 405 is configured to dispatch vehicles to the target platform when the target platform is idle.

[0089] In some embodiments, the platform filtering unit 403 is further configured to: determine the fulfillment urgency level based on the remaining buffer fulfillment time; determine the transportation conditions of the goods involved in the work tasks assigned to vehicles; determine the platform type based on the transportation conditions and the fulfillment urgency level; determine candidate platforms based on the number of waiting vehicles and the platform type; match vehicle attributes with preset matching constraints corresponding to the candidate platforms; filter the candidate platforms based on the matching results and the target fulfillment rate; and obtain an initial feasible solution set based on the filtering results and the vehicles.

[0090] In some embodiments, the platform filtering unit 403 is further configured to: determine the fulfillment urgency level as urgent in response to the remaining buffer fulfillment time being less than a first time threshold; determine the fulfillment urgency level as normal in response to the remaining buffer fulfillment time being between the first time threshold and a second time threshold; and determine the fulfillment urgency level as non-urgent in response to the remaining buffer fulfillment time being greater than the second time threshold; wherein the first time threshold is less than the second time threshold.

[0091] In some embodiments, the platform filtering unit 403 is further configured to: determine the proportion corresponding to the transportation condition in response to the transportation condition being air transport or cold chain transport; determine the platform type as automated in response to the proportion being greater than a preset proportion threshold and the fulfillment urgency level being urgent; determine the platform type as manual in response to the proportion being less than or equal to the preset proportion threshold and the fulfillment urgency level being normal; and determine the platform type as standby in response to the proportion being less than or equal to the preset proportion threshold and the fulfillment urgency level being non-urgent.

[0092] In some embodiments, the platform filtering unit 403 is further configured to: determine a candidate platform as a standby platform in response to the number of waiting vehicles being greater than a preset number threshold and the platform type being standby; determine a candidate platform as an automated platform in response to the number of waiting vehicles being less than or equal to a preset number threshold and the platform type being automated; and determine a candidate platform as a manual platform in response to the number of waiting vehicles being less than or equal to a preset number threshold and the platform type being manual.

[0093] In some embodiments, the vehicle dispatching device also includes Figure 4 The performance suspension unit (not shown) is configured to: in response to determining that the performance urgency level of a vehicle is urgent based on the remaining buffer performance time, obtain the current performance penalty cost and available transportation resources of the vehicle, wherein the performance penalty cost is calculated based on the cost of multiple performance failures of the vehicle and dynamic cost weights; calculate the estimated default probability of the vehicle based on the performance penalty cost and transportation resources; in response to the estimated default probability being greater than a preset probability threshold, postpone the vehicle to the next wave of operation, and reallocate the operation tasks already assigned to the vehicle to vehicles that can be operated in the current wave.

[0094] In some embodiments, the evaluation unit 404 is further configured to: calculate the comprehensive benefits of the vehicles and platforms corresponding to each initial feasible solution in the initial feasible solution set based on the timeliness dimension, cost dimension, resource dimension and scheduling dimension; and determine the vehicles and platforms corresponding to the initial feasible solution with the largest comprehensive benefits as the target vehicles and target platforms.

[0095] It should be noted that the vehicle dispatching method and vehicle dispatching device in this application are related in terms of specific implementation content, so repeated content will not be described again.

[0096] Figure 5 An exemplary system architecture 500 is shown that can be applied to the vehicle scheduling method or vehicle scheduling device of the embodiments of this application.

[0097] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, and 503, a network 504, and a server 505. Network 504 serves as the medium for providing communication links between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0098] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, and 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0099] Terminal devices 501, 502, and 503 can be various electronic devices with vehicle dispatch processing screens and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0100] Server 505 can be a server providing various services, such as a backend management server supporting vehicle dispatch requests submitted by users using terminal devices 501, 502, and 503 (for example only). The backend management server can respond to vehicle dispatch requests by determining the vehicles assigned to tasks in the current wave and the number of waiting vehicles at each platform; for each vehicle, it obtains the corresponding vehicle attributes and remaining buffer fulfillment time; based on the target fulfillment rate, preset matching constraints, tasks assigned to vehicles, the number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, it performs hierarchical filtering and resource conflict filtering on platforms to obtain an initial feasible solution set. This initial feasible solution set includes multiple initial feasible solutions corresponding to tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform; the initial feasible solution set is evaluated using an evaluation model based on multiple target dimensions, and a target solution is obtained based on the evaluation results. These multiple target dimensions include timeliness, cost, resources, and scheduling; the target solution includes a vehicle and a target platform; when the target platform is idle, the vehicle is dispatched to the target platform. This allows for ensuring timely service and high fulfillment rates while maintaining high feasibility, low operating costs, and reasonable allocation of transportation resources.

[0101] It should be noted that the vehicle scheduling method provided in this application embodiment is generally executed by server 505, and correspondingly, the vehicle scheduling device is generally set in server 505.

[0102] It should be understood that Figure 5 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0103] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing a terminal device according to the embodiments of this application. Figure 6 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0104] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the computer system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0105] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0106] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this application.

[0107] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0109] The units described in the embodiments of this application can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including a request response unit, an acquisition unit, a platform filtering unit, an evaluation unit, and a vehicle scheduling unit. The names of these units do not necessarily limit the specific unit itself.

[0110] In another respect, this application also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist alone and not assembled into the device. The aforementioned computer-readable medium carries one or more programs. When these programs are executed by a device, the device responds to a vehicle dispatching request by determining the vehicles assigned to tasks in the current wave and the number of waiting vehicles at each platform. For each vehicle, it obtains the corresponding vehicle attributes and remaining buffer fulfillment time. Based on the target fulfillment rate, preset matching constraints, tasks assigned to vehicles, number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time, it performs hierarchical filtering and resource conflict filtering on platforms to obtain an initial feasible solution set. The initial feasible solution set includes multiple initial feasible solutions corresponding to tasks assigned to vehicles, and each initial feasible solution includes a vehicle and a platform. The initial feasible solution set is evaluated using an evaluation model based on multiple target dimensions. The target solution is obtained by filtering based on the evaluation results. The multiple target dimensions include timeliness, cost, resources, and scheduling. The target solution includes a vehicle and a target platform. When the target platform is idle, the vehicle is dispatched to the target platform.

[0111] The computer program product of this application includes a computer program that, when executed by a processor, implements the vehicle scheduling method in the embodiments of this application.

[0112] According to the technical solution of the embodiments of this application, it is possible to ensure service timeliness and high fulfillment rate while maintaining high feasibility, low operating costs, and reasonable scheduling of transportation resources.

[0113] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A vehicle dispatching method, characterized in that, include: In response to a vehicle dispatch request, determine the vehicles assigned to tasks in the current wave and the number of waiting vehicles at each platform. For each of the aforementioned vehicles, obtain the corresponding vehicle attributes and remaining buffer fulfillment time; Based on the target fulfillment rate, preset matching constraints, the work tasks assigned to the vehicles, the number of waiting vehicles, the vehicle attributes, and the remaining buffer fulfillment time, the platforms are subjected to hierarchical filtering and resource conflict filtering to obtain an initial feasible solution set. The initial feasible solution set includes multiple initial feasible solutions corresponding to the work tasks assigned to the vehicles, and each initial feasible solution includes the vehicle and a platform. The initial feasible solution set is evaluated by an evaluation model based on multiple objective dimensions. The target solution is obtained by filtering according to the evaluation results. The multiple objective dimensions include timeliness, cost, resource and scheduling dimensions. The target solution includes the vehicle and the target platform. When the target platform is idle, the vehicle will be dispatched to the target platform.

2. The method according to claim 1, characterized in that, The platform is subjected to hierarchical filtering and resource conflict filtering based on the target fulfillment rate, preset matching constraints, work tasks assigned to the vehicles, the number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time to obtain an initial feasible solution set, including: The urgency level of fulfillment is determined based on the remaining buffer fulfillment time. Determine the transport conditions of the goods involved in the work tasks assigned to the vehicle, and determine the platform type based on the transport conditions and the urgency level of the performance. Candidate platforms are determined based on the number of waiting vehicles and the platform type; The vehicle attributes are matched with the preset matching constraints corresponding to the candidate platforms. The candidate platforms are then filtered based on the matching results and the target fulfillment rate. An initial feasible solution set is obtained based on the filtering results and the vehicles.

3. The method according to claim 2, characterized in that, The step of determining the urgency level of fulfillment based on the remaining buffer fulfillment time includes: In response to the remaining buffer fulfillment time being less than a first time threshold, the fulfillment urgency level is determined to be urgent. In response to the remaining buffer fulfillment time being between a first time threshold and a second time threshold, the fulfillment urgency level is determined to be general; In response to the remaining buffer fulfillment time being greater than the second time threshold, the fulfillment urgency level is determined to be non-urgent; Wherein, the first duration threshold is less than the second duration threshold.

4. The method according to claim 3, characterized in that, The process of determining the platform type based on the transportation conditions and the urgency level of fulfillment includes: In response to the transport conditions being air transport or cold chain transport, determine the proportion corresponding to the transport conditions; In response to the fact that the proportion is greater than a preset proportion threshold and the fulfillment urgency level is urgent, the platform type is determined to be automated. In response to the fact that the proportion is less than or equal to a preset proportion threshold and the urgency level of the performance is normal, the platform type is determined to be manual. In response to the fact that the proportion is less than or equal to a preset proportion threshold and the urgency level of the performance is not urgent, the platform type is determined to be standby.

5. The method according to claim 2, characterized in that, The step of determining candidate platforms based on the number of waiting vehicles and the platform type includes: In response to the number of waiting vehicles exceeding a preset threshold and the platform type being standby, the candidate platform is determined as a standby platform. In response to the number of waiting vehicles being less than or equal to a preset number threshold and the platform type being automated, the candidate platform is determined to be an automated platform. In response to the number of waiting vehicles being less than or equal to a preset threshold and the platform type being manual, the candidate platform is determined to be a manual platform.

6. The method according to claim 1, characterized in that, Before performing hierarchical filtering and resource conflict filtering on the platform based on the target fulfillment rate, preset matching constraints, work tasks assigned to the vehicle, the number of waiting vehicles, vehicle attributes, and remaining buffer fulfillment time to obtain an initial feasible solution set, the method further includes: In response to determining the vehicle's fulfillment urgency level as urgent based on the remaining buffer fulfillment time, the current fulfillment penalty cost and available transportation capacity of the vehicle are obtained, wherein the fulfillment penalty cost is calculated based on the cost of multiple fulfillment failures of the vehicle and a dynamic cost weight. Calculate the estimated probability of default for the vehicle based on the performance penalty cost and the transportation capacity resources. In response to the estimated probability of default being greater than a preset probability threshold, the vehicle is postponed to the next wave of operation, and the work tasks already assigned to the vehicle are reassigned to vehicles available for operation in the current wave.

7. The method according to claim 1, characterized in that, The step of evaluating the initial feasible solution set using an evaluation model based on multiple objective dimensions, and then selecting the objective solution based on the evaluation results, includes: The evaluation model calculates the comprehensive benefits for each vehicle and platform corresponding to each initial feasible solution in the initial feasible solution set based on timeliness, cost, resource, and scheduling dimensions. The vehicles and platforms corresponding to the initial feasible solution that maximizes overall benefits are identified as the vehicles and target platforms of the objective solution.

8. A vehicle dispatching device, characterized in that, include: The request response unit is configured to respond to a vehicle dispatch request by determining the vehicles assigned to work tasks in the current wave and the number of waiting vehicles at each platform. The acquisition unit is configured to acquire, for each of the vehicles, the corresponding vehicle attributes and the remaining buffer fulfillment time; The platform filtering unit is configured to perform hierarchical filtering and resource conflict filtering on the platform based on the target fulfillment rate, preset matching constraints, the work tasks assigned to the vehicle, the number of waiting vehicles, the vehicle attributes, and the remaining buffer fulfillment time, to obtain an initial feasible solution set. The initial feasible solution set includes multiple initial feasible solutions corresponding to the work tasks assigned to the vehicle, and each initial feasible solution includes the vehicle and a platform. The evaluation unit is configured to evaluate the initial feasible solution set based on multiple target dimensions using an evaluation model, and to select a target solution based on the evaluation results. The multiple target dimensions include timeliness, cost, resource, and scheduling dimensions, and the target solution includes the vehicle and the target platform. The vehicle dispatching unit is configured to dispatch the vehicle to the target platform when the target platform is idle.

9. A vehicle dispatching electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images