Dynamic scheduling method, device and equipment for vehicles on road and storage medium

Abstract

The invention discloses a dynamic scheduling method, device and equipment for vehicles on the way and a storage medium. The method comprises the following steps: on the basis of a pre-trained neural network prediction model and real-time state data of each on-the-way vehicle to be scheduled, predicting state data of each on-the-way vehicle to be scheduled on the way, and generating predicted state data of each on-the-way vehicle to be scheduled on the way; according to a preset matching rule, dynamically matching the carrying task with the predicted state data of each on-the-way vehicle to be scheduled on the way to obtain a first candidate vehicle successfully matched with the carrying task; and carrying out multi-dimensional conflict detection on the first candidate vehicle successfully matched with the carrying task, dynamically matching the carrying task with the predicted state data of each on-the-way vehicle to be scheduled on the way again after a conflict is detected, and determining a target scheduling vehicle which does not conflict with the carrying task. According to the invention, the matching accuracy of the transportation task and the on-the-road vehicle to be scheduled is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle travel technology, and in particular to a method, device, equipment and storage medium for dynamically dispatching on-the-way vehicles. Background Art

[0002] In the field of logistics and transportation, especially in distribution, inter-city and inter-provincial trunk transportation scenarios, the effective scheduling and resource utilization of transportation vehicles have always been important challenges faced by the industry. At present, most transportation vehicle scheduling methods still adopt the one-way matching mode of "transportation task-scheduling vehicle", which leads to a generally high empty return rate of transportation vehicles. In addition, when temporary transportation tasks or regional transportation capacity shortages occur, conventional solutions mainly rely on outsourced vehicle leasing, which not only increases additional costs, but also faces problems such as long vehicle scheduling response time and difficulty in ensuring transportation timeliness.

[0003] In order to deal with the high empty return rate of transport vehicles mentioned above, the industry has tried to improve it through appointment-based carpooling or fixed route sharing. However, the traditional carpooling model relies heavily on manual scheduling, resulting in low efficiency in vehicle scheduling response. In addition, fixed route sharing lacks flexibility and is difficult to cope with dynamically changing transport tasks, resulting in low accuracy in matching transport tasks with on-the-way vehicles to be scheduled.

[0004] Therefore, how to improve the accuracy of matching transportation tasks with on-the-way vehicles to be dispatched is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a method, device, equipment and storage medium for dynamically dispatching on-the-way vehicles, which are used to solve the technical problem of low accuracy in matching existing transportation tasks with on-the-way vehicles to be dispatched.

[0006] In order to solve the above technical problems, in a first aspect, the present invention provides a dynamic scheduling method for on-the-way vehicles, the method comprising: Obtain the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched; Based on the pre-trained neural network prediction model and the real-time status data of each on-the-way vehicle to be dispatched, the status data of each on-the-way vehicle to be dispatched is predicted, and the predicted status data of each on-the-way vehicle to be dispatched is generated, wherein the predicted status data of each on-the-way vehicle to be dispatched includes at least the predicted path, predicted arrival time, predicted energy consumption and predicted remaining cargo capacity of each on-the-way vehicle to be dispatched; According to the preset matching rules, the transport task is dynamically matched with the predicted status data of each on-the-way vehicle to be dispatched, so as to obtain the first candidate vehicle that successfully matches the transport task; A multi-dimensional conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched to determine the target dispatch vehicle that does not conflict with the transport task.

[0007] Optionally, the state data of each on-the-way vehicle to be dispatched is predicted based on the pre-trained neural network prediction model and the real-time state data of each on-the-way vehicle to be dispatched, and the predicted state data of each on-the-way vehicle to be dispatched is generated, including: The real-time status data of each on-the-way vehicle to be dispatched is input in parallel to the convolutional neural network layer and the long short-term memory network layer of the pre-trained neural network prediction model for spatial feature extraction and temporal feature extraction, respectively, to obtain the spatial feature vector and temporal feature vector of the real-time status data of each on-the-way vehicle to be dispatched; The spatial feature vector and the temporal feature vector of the real-time status data of each on-the-way vehicle to be dispatched are fused to obtain a fused feature vector of the real-time status data of each on-the-way vehicle to be dispatched; The fused feature vector of the real-time status data of each on-the-way vehicle to be dispatched is input into the fully connected layer of the pre-trained neural network prediction model to predict the status data of each section on the way, and the predicted status data of each on-the-way vehicle to be dispatched is obtained.

[0008] Optionally, dynamically matching the transport task with the predicted state data of each on-the-way vehicle to be dispatched according to a preset matching rule to obtain a first candidate vehicle that successfully matches the transport task includes: Calculating the path overlap between the path of the transport task and the predicted path of each on-the-way vehicle to be dispatched, and selecting a first candidate vehicle set whose path overlap exceeds a preset path overlap threshold; Calculate the absolute time difference between the predicted arrival time of each to-be-dispatched vehicle in the first candidate vehicle set and the actual start time of the transport task, and select the second candidate vehicle set whose absolute time difference is less than a preset absolute time difference threshold; Calculate the transportation cost savings of each to-be-dispatched vehicle in the second candidate vehicle set when performing the transport task, and select the target candidate vehicle set whose transportation cost savings exceeds a preset transportation cost savings threshold; Performing weighted processing on the path overlap, absolute time difference and transportation saving cost corresponding to each vehicle to be dispatched and the transport task in the target candidate vehicle set, and calculating the matching value between each vehicle to be dispatched and the transport task in the target candidate vehicle set according to the result of the weighted processing; The matching degree values ​​of each to-be-scheduled vehicle in the target candidate vehicle set and the transport task are sorted, and the on-the-way vehicle with the highest matching value is determined as the first candidate vehicle that successfully matches the transport task.

[0009] Optionally, the multi-dimensional conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched to determine the target dispatch vehicle that does not conflict with the transport task, including: Input the predicted status data of the transport tasks and the vehicles to be dispatched on the way into the decision tree model for training, and generate a trained conflict detection model; Based on the trained conflict detection model, a conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched.

[0010] Optionally, the conflict detection is performed on the first candidate vehicle that successfully matches the transport task based on the trained conflict detection model, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched, including: Based on the trained conflict detection model, a time conflict detection, an energy consumption conflict detection and a remaining cargo capacity conflict detection are performed on the first candidate vehicle that successfully matches the transport task; If a conflict is detected, the transport task is re-matched with the predicted status data of each on-the-way vehicle to be dispatched. If no conflict is detected, the target dispatch vehicle that does not conflict with the transport task is determined.

[0011] Optionally, after determining the target dispatch vehicle that does not conflict with the transport task, the method further includes: The driving path of the target dispatching vehicle is planned, and the driving path of the target dispatching vehicle is dynamically adjusted by minimizing the multi-objective algorithm.

[0012] Optionally, planning the driving path of the target dispatch vehicle and dynamically adjusting the driving path of the target dispatch vehicle by minimizing a multi-objective algorithm includes: Obtain the starting position and the end position of the transport task, as well as the starting position and the end position of the target dispatch vehicle, and generate an initial driving path of the target dispatch vehicle passing through the starting position and the end position of the transport task; Based on the travel time, transportation cost and energy consumption of the target dispatched vehicle, a multi-objective function for minimizing the travel path of the target dispatched vehicle is constructed, and the task time window and vehicle capacity of the target dispatched vehicle are configured as constraints for minimizing the multi-objective function; According to a preset search algorithm, a parameter combination that minimizes a multi-objective function is searched, and the initial driving path is dynamically adjusted according to the searched parameter combination that minimizes the multi-objective function to obtain a driving path of a target dispatch vehicle after dynamic adjustment, wherein the parameter combination that minimizes the multi-objective function includes at least the driving time, transportation cost and energy consumption of the target dispatch vehicle.

[0013] In a second aspect, the present invention provides a dynamic dispatching device for on-the-way vehicles, comprising an acquisition module, a prediction module, a matching module and a detection module: The acquisition module is used to acquire the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched; The prediction module is used to predict the state data of each on-the-way vehicle to be dispatched on the way based on the pre-trained neural network prediction model and the real-time state data of each on-the-way vehicle to be dispatched, and generate the predicted state data of each on-the-way vehicle to be dispatched on the way, wherein the predicted state data of each on-the-way vehicle to be dispatched on the way at least includes the predicted path, predicted arrival time, predicted energy consumption and predicted remaining cargo capacity of each on-the-way vehicle to be dispatched on the way; The matching module is used to dynamically match the transport task with the predicted state data of each on-the-way vehicle to be dispatched according to a preset matching rule, so as to obtain a first candidate vehicle that successfully matches the transport task; The detection module is used to perform multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting the conflict, dynamically re-match the transport task with the predicted state data of each on-the-way vehicle to be dispatched to determine the target dispatch vehicle that does not conflict with the transport task.

[0014] In a third aspect, the present invention provides a dynamic dispatching device for on-the-way vehicles, comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor is used to read the program in the memory and execute the steps of a dynamic scheduling method for on-the-way vehicles provided in the first aspect above.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a readable computer program stored thereon, which, when executed by a processor, implements the steps of a method for dynamically scheduling en-route vehicles as provided in the first aspect above.

[0016] Compared with the prior art, the method, device, equipment and storage medium for dynamically scheduling on-the-way vehicles provided by the present invention have the following beneficial effects: The embodiment of the present invention dynamically matches the transport task with the predicted status data of each on-the-way vehicle to be dispatched through preset matching rules, efficiently screens out the first candidate vehicle that meets the requirements of the transport task, and performs conflict detection on the first candidate vehicle through a multi-dimensional conflict detection mechanism, thereby avoiding task execution failure caused by the conflict between the transport task and the first candidate vehicle, and effectively improving the accuracy of matching the transport task with the on-the-way vehicle to be dispatched. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only part of the embodiments of the present invention, rather than all of the embodiments. For ordinary technicians in this field, without paying creative work, other drawings obtained based on these drawings all fall within the scope of protection of this application.

[0018] Figure 1 It is a flow chart of a method for dynamically scheduling en-route vehicles provided in an embodiment of the present invention.

[0019] Figure 2 It is a flow chart for dynamically matching a transport task with each on-the-way vehicle to be dispatched, provided by an embodiment of the present invention.

[0020] Figure 3 This is a flowchart of a multi-dimensional conflict detection provided by an embodiment of the present invention.

[0021] Figure 4 The present invention provides a flowchart for dynamically adjusting the driving path of a target dispatch vehicle.

[0022] Figure 5 A dynamic dispatching device for on-the-way vehicles is provided in an embodiment of the present invention.

[0023] Figure 6 It is a structural schematic diagram of a dynamic dispatching device for on-the-way vehicles provided in an embodiment of the present invention.

[0024] Figure 7 It is a structural schematic diagram of a computer-readable storage medium provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0026] In order to make the description of the disclosed content more detailed and complete, the following is an illustrative description of the implementation mode and specific examples of the present invention; however, this is not the only form of implementing or applying the specific embodiments of the present invention. The implementation mode covers the features of multiple specific embodiments and the method steps and their sequence for constructing and operating these specific embodiments. However, other specific embodiments can also be used to achieve the same or equal functions and step sequences. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0028] In the description of the embodiments of the present invention, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two, and other quantifiers are similar. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention, and the embodiments of the present application and the features in the embodiments may be combined with each other without conflict.

[0029] Example 1 like Figure 1 The flowchart of a method for dynamically scheduling en-route vehicles provided in an embodiment of the present invention includes the following steps.

[0030] Step S101, obtaining the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched.

[0031] The embodiment of the present invention first needs to obtain the current transportation task and the real-time status data of the on-the-way vehicles to be dispatched corresponding to the transportation task. Among them, the transportation task includes key information such as the starting position, destination, cargo information, and time requirements of the transportation. The real-time status data of the on-the-way vehicles to be dispatched corresponding to the transportation task includes key information such as the current position, speed, vehicle condition, traffic conditions, and estimated arrival time of each on-the-way vehicle to be dispatched.

[0032] Step S102, based on the pre-trained neural network prediction model and the real-time status data of each on-the-way vehicle to be dispatched, predict the status data of each on-the-way vehicle to be dispatched, and generate the predicted status data of each on-the-way vehicle to be dispatched, wherein the predicted status data of each on-the-way vehicle to be dispatched includes at least the predicted path, predicted arrival time, predicted energy consumption and predicted remaining cargo capacity of each on-the-way vehicle to be dispatched.

[0033] In step S101, after obtaining the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched, the embodiment of the present invention can predict the status data of each on-the-way vehicle to be dispatched, and input the real-time status data of each on-the-way vehicle to be dispatched into the pre-trained neural network prediction model. The prediction model can effectively capture the potential patterns and laws of the real-time status data of the on-the-way vehicles to be dispatched by learning historical data, and predict the future status of the on-the-way vehicles to be dispatched. Information such as the path change, arrival time, energy consumption status, and remaining cargo capacity of the vehicles to be dispatched can be predicted.

[0034] Step S103, dynamically matching the transport task with the predicted status data of each on-the-way vehicle to be dispatched according to a preset matching rule, to obtain a first candidate vehicle that successfully matches the transport task.

[0035] In step S102, after generating the predicted status data of each en route vehicle to be dispatched, the embodiment of the present invention can dynamically match the transport task with the predicted status data of each en route vehicle to be dispatched according to a preset matching rule. The dynamic matching can respond to changes in the transport task in a timely manner without relying on a static scheduling mode, so that each task scheduling can be selected based on the latest data, thereby improving the flexibility and efficiency of en route vehicle scheduling.

[0036] Step S104, performing multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting the conflict, dynamically re-matching the transport task with the predicted state data of each on-the-way vehicle to be dispatched, to determine a target dispatch vehicle that does not conflict with the transport task.

[0037] In step S103, after obtaining the first candidate vehicle that successfully matches the transport task, the embodiment of the present invention also needs to perform multi-dimensional conflict detection on the transport task and the first candidate vehicle, identify the conflict between the state prediction data of the transport task and the first candidate vehicle, and dynamically match and conflict-detect the transport task with the predicted state data of each on-the-way vehicle to be dispatched, to ensure that the selected target dispatch vehicle does not conflict and can successfully complete the transport task. The embodiment of the present invention ensures the efficiency and reliability of vehicle dispatch through multi-dimensional conflict detection, can timely identify and adjust when problems occur, and effectively avoids transportation delays caused by conflicts.

[0038] As an optional implementation, step S102 predicts the state data of each on-the-way vehicle to be dispatched based on the pre-trained neural network prediction model and the real-time state data of each on-the-way vehicle to be dispatched, and generates the predicted state data of each on-the-way vehicle to be dispatched, including: Step S1021, the real-time status data of each on-the-way vehicle to be dispatched are input in parallel to the convolutional neural network layer and the long short-term memory network layer of the pre-trained neural network prediction model for spatial feature extraction and temporal feature extraction, respectively, to obtain the spatial feature vector and temporal feature vector of the real-time status data of each on-the-way vehicle to be dispatched. Specifically, in the embodiment of the present invention, the convolutional neural network layer can effectively capture the features related to the spatial distribution, for example, the spatial feature information such as the location of the vehicle, the current traffic flow, and the road conditions. By extracting the spatial feature information, the location of the vehicle at a certain moment and the surrounding traffic environment can be determined; the long short-term memory network layer can extract the temporal features from the continuous time data and learn the time series information during the vehicle driving process, such as the vehicle's driving speed change, the fluctuation of the traffic flow, the route selection, etc. By extracting the spatial features and temporal features of the real-time status data of each on-the-way vehicle to be dispatched, different types of data rules can be captured more efficiently, so that the generated predicted status data of each on-the-way vehicle to be dispatched is more accurate.

[0039] Step S1022, the spatial feature vector and the temporal feature vector of the real-time status data of each on-the-way vehicle to be dispatched are fused to obtain a fused feature vector of the real-time status data of each on-the-way vehicle to be dispatched. In the embodiment of the present invention, feature fusion can be achieved by vector weighted summation and splicing, and the fused feature vector contains the necessary information of each on-the-way vehicle to be dispatched at the current moment, such as the position, speed, time information, road conditions and other key information of each on-the-way vehicle to be dispatched.

[0040] Step S1023, input the fused feature vector of the real-time status data of each on-the-way vehicle to be dispatched into the fully connected layer of the pre-trained neural network prediction model to predict the status data of each road section on the way, and obtain the predicted status data of each on-the-way vehicle to be dispatched. In this embodiment of the present invention, by inputting the fused feature vector of the real-time status data of the on-the-way vehicle to be dispatched into the fully connected layer of the pre-trained neural network prediction model, the status data of each road section in the driving path of each on-the-way vehicle to be dispatched can be predicted based on the fused feature vector.

[0041] As an optional implementation, Figure 2 The above is a flowchart of dynamically matching a transport task with each on-the-way vehicle to be dispatched provided by an embodiment of the present invention. In step S103, according to a preset matching rule, the transport task is dynamically matched with the predicted state data of each on-the-way vehicle to be dispatched to obtain a first candidate vehicle that successfully matches the transport task, including: Step S1031, calculate the path overlap between the path of the transport task and the predicted path of each on-the-way vehicle to be dispatched, and select the first candidate vehicle set whose path overlap exceeds the preset path overlap threshold. For example, the path overlap threshold between the path of the transport task and the predicted path of each on-the-way vehicle to be dispatched can be preset as 60%. If the calculated path overlap is 30%, it indicates that the matching degree between the transport task and the on-the-way vehicle to be dispatched is not high. If the calculated path overlap is 80%, it indicates that the matching degree between the transport task and the on-the-way vehicle to be dispatched is high, and the on-the-way vehicle to be dispatched can be determined as a vehicle in the first candidate vehicle set.

[0042] Step S1032, calculate the absolute time difference between the predicted arrival time of each to-be-scheduled vehicle in the first candidate vehicle set when it travels to the starting position of the transport task and the actual start time of the transport task, and select the second candidate vehicle set whose absolute time difference is less than the preset absolute time difference threshold. For example, the absolute time difference between the predicted arrival time of each to-be-scheduled vehicle in the first candidate vehicle set when it travels to the starting position of the transport task and the actual start time of the transport task is preset to be 10 minutes. For example, if the actual start time of the transport task is 15:00, and the predicted arrival time of the to-be-scheduled vehicle when it travels to the starting position of the transport task is 15:40, it indicates that there is a time conflict between the to-be-scheduled vehicle and the transport task. If the predicted arrival time of the to-be-scheduled vehicle when it travels to the starting position of the transport task is 15:05, it indicates that the transport task and the on-the-way vehicle to be dispatched have a high degree of matching, and the to-be-scheduled vehicle can be determined as a vehicle in the second candidate vehicle set.

[0043] Step S1033, calculate the transportation cost savings of each to-be-dispatched vehicle in the second candidate vehicle set when performing the transport task, and select the target candidate vehicle set whose transportation cost savings exceeds the preset transportation cost savings threshold. In the embodiment of the present invention, for example, the transportation cost savings threshold of each to-be-dispatched vehicle in the second candidate vehicle set when performing the transport task can be preset as 100 yuan. If the transportation cost savings of each to-be-dispatched vehicle in the second candidate vehicle set when performing the transport task is 200 yuan, the to-be-dispatched vehicle can be determined as a vehicle in the target candidate vehicle set.

[0044] Step S1034, weighting the path overlap, absolute time difference and transportation cost saving corresponding to each vehicle to be dispatched in the target candidate vehicle set and the transport task, and calculating the matching value of each vehicle to be dispatched in the target candidate vehicle set and the transport task based on the result of the weighted processing. In the embodiment of the present invention, the calculated path overlap, time difference and transportation cost saving are weighted, and different factors are assigned different weights according to the priority and importance of the transport task. For example, if the time requirement is high, the weight of the time difference may be large; if cost saving is more important, the weight of the transportation cost saving is large, and the weighted result is used as a comprehensive matching value, which represents the matching degree between each vehicle to be dispatched in the target candidate vehicle set and the current transport task. The higher the matching degree, the more suitable the vehicle is for the current transport task.

[0045] Step S1035, sort the matching values ​​of the vehicles to be dispatched and the transport task in the target candidate vehicle set, and determine the vehicle on the way with the highest matching value as the first candidate vehicle that successfully matches the transport task. In the embodiment of the present invention, by comprehensively considering multiple factors such as path overlap, arrival time, and transportation cost, the candidate vehicles are gradually screened and optimized, and finally the target dispatch vehicle that is most suitable for performing the transport task can be selected, ensuring the smooth execution of the transport task, not only improving the efficiency of dispatching vehicles on the way, but also achieving a balance in terms of cost and time.

[0046] As an optional implementation, Figure 3 The flowchart of a multi-dimensional conflict detection provided by an embodiment of the present invention, in step S104, the multi-dimensional conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched, and the target dispatch vehicle that does not conflict with the transport task is determined, including: Step S1041, input the predicted state data of the transport task and each on-the-way vehicle to be dispatched into the decision tree model for training, and generate a trained conflict detection model. The embodiment of the present invention performs conflict detection through a machine learning algorithm, which can improve the automation of conflict detection, reduce the error of human judgment, and can quickly identify conflict situations through the trained conflict detection model, thereby improving the efficiency of on-the-way vehicle dispatch.

[0047] Step S1042, based on the trained conflict detection model, the first candidate vehicle that successfully matches the transport task is subjected to conflict detection, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched. If a conflict is detected in the embodiment of the present invention, it is necessary to dynamically re-match the transport task with the predicted state data of each on-the-way vehicle to be dispatched, and re-screen the candidate vehicles that meet the path matching, time matching, and resource availability. After the conflict detection, the target dispatch vehicle that does not conflict with the transport task is determined. The embodiment of the present invention avoids the failure of task execution due to the conflict between the transport task and the target dispatch vehicle through multi-dimensional conflict detection, and improves the reliability of the target dispatch vehicle in performing the transportation task.

[0048] As an optional implementation, in step S1042, the conflict detection is performed on the first candidate vehicle that successfully matches the transport task based on the trained conflict detection model, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched, including: Step S10421, based on the trained conflict detection model, the first candidate vehicle that successfully matches the transport task is subjected to time conflict detection, energy consumption conflict detection, and remaining cargo capacity conflict detection. In the embodiment of the present invention, first, it is necessary to confirm whether the first candidate vehicle can arrive at the starting point of the transport task on time, and whether there will be a time conflict during the task execution; second, it is necessary to confirm whether the energy consumption of the first candidate vehicle when performing the transport task is within an acceptable range; finally, it is necessary to confirm whether the first candidate vehicle has sufficient remaining cargo capacity to undertake the transport task. Through multi-dimensional conflict detection, it is possible to more comprehensively evaluate whether the first candidate vehicle is suitable for performing the current transport task, effectively reducing the risk of task execution failure.

[0049] Step S10422, if a conflict is detected, the transport task is re-matched with the predicted state data of each on-the-way vehicle to be dispatched. If no conflict is detected, the target dispatch vehicle that does not conflict with the transport task is determined. In the embodiment of the present invention, if a conflict is detected between the transport task and the first candidate vehicle, the transport task is re-matched with the predicted state data of each on-the-way vehicle to be dispatched to ensure that the selected vehicle to be dispatched can smoothly perform the transport task. If it is detected that there is no conflict between the transport task and the first candidate vehicle, the first candidate vehicle can be directly determined as the target dispatch vehicle. Through multi-dimensional conflict detection and preset matching rules, the utilization rate and transportation efficiency of the vehicles to be dispatched can be effectively improved, thereby reducing logistics costs.

[0050] As an optional implementation, after determining the target dispatch vehicle that does not conflict with the transport task, the method further includes: step S105, planning the driving path of the target dispatch vehicle, and dynamically adjusting the driving path of the target dispatch vehicle by minimizing the multi-objective algorithm. In the embodiment of the present invention, in step S104, after determining the target dispatch vehicle that does not conflict with the transport task, the driving path of the target dispatch vehicle can also be planned to ensure that the target dispatch vehicle can effectively and quickly complete the transport task. After planning the driving path of the target dispatch vehicle, the driving path of the target dispatch vehicle can also be dynamically adjusted by minimizing the multi-objective algorithm to achieve multi-objective optimization of the on-the-way vehicles to be dispatched.

[0051] As an optional implementation, Figure 4 The above is a flowchart of dynamically adjusting the driving path of a target dispatch vehicle provided by an embodiment of the present invention. In step S105, the driving path of the target dispatch vehicle is planned, and the driving path of the target dispatch vehicle is dynamically adjusted by minimizing a multi-objective algorithm, including: S1051. Obtain the starting point and end point of the transport task, as well as the starting point and end point of the target dispatch vehicle, and generate an initial driving path for the target dispatch vehicle passing through the starting point and end point of the transport task. The embodiment of the present invention generates an initial driving path based on the starting point and end point of the transport task using map data and a path planning algorithm to ensure that the path covers the starting point and end point of the transport task, and tries to select the shortest or fastest route, wherein the path planning algorithm may use a Dijkstra algorithm or an A* algorithm. In the generated initial driving path, the starting point and end point of the transport task need to be marked as waypoints to ensure that the path meets the transportation requirements.

[0052] S1052: Based on the travel time, transportation cost and energy consumption of the target dispatched vehicle, a multi-objective function for minimizing the travel path of the target dispatched vehicle is constructed, and the task time window and vehicle capacity of the target dispatched vehicle are configured as constraints for minimizing the multi-objective function. In the embodiment of the present invention, the travel time, transportation cost and energy consumption of the target dispatched vehicle are used as multiple objectives, and the time window and vehicle capacity configuration of the transport task are used as constraints to ensure that the target dispatched vehicle can complete the task within the specified time. Among them, the minimization of the multi-objective function The expression of is as described in formula (1): (1) in, represents the travel time of the target dispatched vehicle, represents the transportation cost of the target dispatch vehicle, Represents the energy consumption of the target dispatch vehicle.

[0053] S1053. Search for a parameter combination that minimizes the multi-objective function according to a preset search algorithm, and dynamically adjust the initial driving path according to the searched parameter combination that minimizes the multi-objective function to obtain the driving path of the target dispatch vehicle after dynamic adjustment, wherein the parameter combination that minimizes the multi-objective function at least includes the driving time, transportation cost, and energy consumption of the target dispatch vehicle. In an embodiment of the present invention, the preset search algorithm can be used to search for the best possible parameter combination in the parameter space that minimizes the multi-objective function, and the driving time, transportation cost, and energy consumption of the target dispatch vehicle can be calculated according to the current parameter combination, and the initial driving path can be adjusted. For example, it is possible to replace part of the path, change the driving order, or use different roads to reduce the driving time and energy consumption of the target dispatch vehicle.

[0054] The embodiment of the present invention dynamically matches the transport task with the predicted status data of each on-the-way vehicle to be dispatched through preset matching rules, efficiently screens out the first candidate vehicle that meets the requirements of the transport task, and performs conflict detection on the first candidate vehicle through a multi-dimensional conflict detection mechanism, thereby avoiding task execution failure caused by the conflict between the transport task and the first candidate vehicle, and effectively improving the accuracy of matching the transport task with the on-the-way vehicle to be dispatched.

[0055] Example 2 Based on the above-mentioned dynamic dispatching method for on-the-way vehicles, an embodiment of the present invention provides a dynamic dispatching device for on-the-way vehicles, such as Figure 5 As shown, its structural schematic diagram is shown in Figure 5. The dynamic scheduling device for on-the-way vehicles includes an acquisition module 51, a prediction module 52, a matching module 53 and a detection module 54: The acquisition module 51 is used to acquire the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched; The prediction module 52 is used to predict the state data of each on-the-way vehicle to be dispatched based on the pre-trained neural network prediction model and the real-time state data of each on-the-way vehicle to be dispatched, and generate the predicted state data of each on-the-way vehicle to be dispatched, wherein the predicted state data of each on-the-way vehicle to be dispatched includes at least the predicted path, predicted arrival time, predicted energy consumption and predicted remaining cargo capacity of each on-the-way vehicle to be dispatched; The matching module 53 is used to dynamically match the transport task with the predicted state data of each on-the-way vehicle to be dispatched according to a preset matching rule, so as to obtain a first candidate vehicle that successfully matches the transport task; The detection module 54 is used to perform multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting the conflict, dynamically re-match the transport task with the predicted state data of each on-the-way vehicle to be dispatched, to determine the target dispatch vehicle that does not conflict with the transport task.

[0056] For other details about how the modules in the above-mentioned dynamic scheduling device for on-the-way vehicles implement the above-mentioned technical solution, please refer to the description of the dynamic scheduling method for on-the-way vehicles provided in the above-mentioned invention embodiment, which will not be repeated here.

[0057] Example 3 Based on the above dynamic dispatching method for on-the-way vehicles, Figure 6 As shown, a schematic diagram of the structure of a dynamic dispatching device for on-the-way vehicles provided in an embodiment of the present invention, the identification device includes a processor 61 and a memory 62 coupled to the processor 61. The memory 62 stores a computer program, and when the computer program is executed by the processor 61, the processor 61 executes the steps of the dynamic dispatching method for on-the-way vehicles in the above embodiment.

[0058] For other details about how the processor 61 in the above-mentioned dynamic scheduling device for on-the-way vehicles implements the above-mentioned technical solution, please refer to the description of the dynamic scheduling method for on-the-way vehicles provided in the above-mentioned embodiment of the invention, which will not be repeated here.

[0059] Among them, the processor 61 can also be called a CPU (Central Processing Unit), and the processor 61 may be an integrated circuit chip with signal processing capabilities; the processor 61 can also be a general-purpose processor, DSP (Digital Signal Process), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, among which the general-purpose processor can be a microprocessor or the processor 61 can also be any conventional processor, etc.

[0060] Example 4 like Figure 7 As shown, a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present invention, on which a readable computer program 71 is stored; wherein the computer program 71 can be stored in the above storage medium in the form of a software product, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0061] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0062] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0063] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0064] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0065] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0066] The technical solution provided by the present application is introduced in detail above. The principles and implementation methods of the present application are explained by using specific examples in the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0067] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0068] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A dynamic dispatching method for on-the-way vehicles, characterized in that: include: Obtain the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched; Based on the pre-trained neural network prediction model and the real-time status data of each on-the-way vehicle to be dispatched, the status data of each on-the-way vehicle to be dispatched is predicted, and the predicted status data of each on-the-way vehicle to be dispatched is generated, wherein the predicted status data of each on-the-way vehicle to be dispatched includes at least the predicted path, predicted arrival time, predicted energy consumption and predicted remaining cargo capacity of each on-the-way vehicle to be dispatched; According to the preset matching rules, the transport task is dynamically matched with the predicted status data of each on-the-way vehicle to be dispatched, so as to obtain the first candidate vehicle that successfully matches the transport task; A multi-dimensional conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched to determine a target dispatch vehicle that does not conflict with the transport task.

2. The method for dynamically dispatching on-the-way vehicles according to claim 1, characterized in that: The method predicts the state data of each on-the-way vehicle to be dispatched based on the pre-trained neural network prediction model and the real-time state data of each on-the-way vehicle to be dispatched, and generates the predicted state data of each on-the-way vehicle to be dispatched, including: The real-time status data of each on-the-way vehicle to be dispatched is input in parallel to the convolutional neural network layer and the long short-term memory network layer of the pre-trained neural network prediction model for spatial feature extraction and temporal feature extraction, respectively, to obtain the spatial feature vector and temporal feature vector of the real-time status data of each on-the-way vehicle to be dispatched; The spatial feature vector and the temporal feature vector of the real-time status data of each on-the-way vehicle to be dispatched are fused to obtain a fused feature vector of the real-time status data of each on-the-way vehicle to be dispatched; The fused feature vector of the real-time status data of each on-the-way vehicle to be dispatched is input into the fully connected layer of the pre-trained neural network prediction model to predict the status data of each section on the way, and the predicted status data of each on-the-way vehicle to be dispatched is obtained.

3. The method for dynamically dispatching on-the-way vehicles according to claim 1, characterized in that: According to the preset matching rules, the transport task is dynamically matched with the predicted state data of each on-the-way vehicle to be dispatched to obtain the first candidate vehicle that successfully matches the transport task, including: Calculating the path overlap between the path of the transport task and the predicted path of each on-the-way vehicle to be dispatched, and selecting a first candidate vehicle set whose path overlap exceeds a preset path overlap threshold; Calculate the absolute time difference between the predicted arrival time of each to-be-scheduled vehicle in the first candidate vehicle set and the actual start time of the transport task, and select the second candidate vehicle set whose absolute time difference is less than a preset absolute time difference threshold; Calculate the transportation cost savings of each to-be-dispatched vehicle in the second candidate vehicle set when performing the transport task, and select the target candidate vehicle set whose transportation cost savings exceeds a preset transportation cost savings threshold; Performing weighted processing on the path overlap, absolute time difference and transportation saving cost corresponding to each vehicle to be dispatched and the transport task in the target candidate vehicle set, and calculating the matching value between each vehicle to be dispatched and the transport task in the target candidate vehicle set according to the result of the weighted processing; The matching degree values ​​of each to-be-scheduled vehicle in the target candidate vehicle set and the transport task are sorted, and the on-the-way vehicle with the highest matching value is determined as the first candidate vehicle that successfully matches the transport task.

4. The method for dynamically dispatching on-the-way vehicles according to claim 1, characterized in that: The method of performing multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and dynamically re-matching the transport task with the predicted state data of each on-the-way vehicle to be dispatched after the conflict is detected, and determining a target dispatch vehicle that does not conflict with the transport task, includes: Input the predicted status data of the transport tasks and the vehicles to be dispatched on the way into the decision tree model for training, and generate a trained conflict detection model; Based on the trained conflict detection model, a conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched.

5. The method for dynamically dispatching on-the-way vehicles according to claim 4, characterized in that: The conflict detection is performed on the first candidate vehicle that successfully matches the transport task based on the trained conflict detection model, and after the conflict is detected, the transport task is dynamically re-matched with the predicted state data of each on-the-way vehicle to be dispatched, including: Based on the trained conflict detection model, a time conflict detection, an energy consumption conflict detection and a remaining cargo capacity conflict detection are performed on the first candidate vehicle that successfully matches the transport task; If a conflict is detected, the transport task is re-matched with the predicted status data of each on-the-way vehicle to be dispatched. If no conflict is detected, the target dispatch vehicle that does not conflict with the transport task is determined.

6. The method for dynamically dispatching on-the-way vehicles according to claim 1, characterized in that: After determining the target dispatch vehicle that does not conflict with the transport task, the method further includes: The driving path of the target dispatching vehicle is planned, and the driving path of the target dispatching vehicle is dynamically adjusted by minimizing the multi-objective algorithm.

7. The method for dynamically dispatching on-the-way vehicles according to claim 6, characterized in that: The driving path of the target dispatched vehicle is planned, and the driving path of the target dispatched vehicle is dynamically adjusted by minimizing a multi-objective algorithm, including: Obtain the starting position and the end position of the transport task, as well as the starting position and the end position of the target dispatch vehicle, and generate an initial driving path of the target dispatch vehicle passing through the starting position and the end position of the transport task; Based on the travel time, transportation cost and energy consumption of the target dispatched vehicle, a multi-objective function for minimizing the travel path of the target dispatched vehicle is constructed, and the task time window and vehicle capacity of the target dispatched vehicle are configured as constraints for minimizing the multi-objective function; According to a preset search algorithm, a parameter combination that minimizes a multi-objective function is searched, and the initial driving path is dynamically adjusted according to the searched parameter combination that minimizes the multi-objective function to obtain a driving path of a target dispatch vehicle after dynamic adjustment, wherein the parameter combination that minimizes the multi-objective function includes at least the driving time, transportation cost and energy consumption of the target dispatch vehicle.

8. A dynamic dispatching device for on-the-way vehicles, characterized in that: Including acquisition module, prediction module, matching module and detection module: The acquisition module is used to acquire the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched; The prediction module is used to predict the state data of each on-the-way vehicle to be dispatched on the way based on the pre-trained neural network prediction model and the real-time state data of each on-the-way vehicle to be dispatched, and generate the predicted state data of each on-the-way vehicle to be dispatched on the way, wherein the predicted state data of each on-the-way vehicle to be dispatched on the way at least includes the predicted path, predicted arrival time, predicted energy consumption and predicted remaining cargo capacity of each on-the-way vehicle to be dispatched on the way; The matching module is used to dynamically match the transport task with the predicted state data of each on-the-way vehicle to be dispatched according to a preset matching rule, so as to obtain a first candidate vehicle that successfully matches the transport task; The detection module is used to perform multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting the conflict, dynamically re-match the transport task with the predicted state data of each on-the-way vehicle to be dispatched to determine the target dispatch vehicle that does not conflict with the transport task.

9. A dynamic dispatching device for on-the-way vehicles, characterized in that: comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor is used to read the computer program in the memory and execute the steps of the method for dynamically scheduling on-the-way vehicles as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A readable computer program is stored thereon, and when the program is executed by a processor, the steps of a dynamic scheduling method for on-the-way vehicles as described in any one of claims 1 to 7 are implemented.

Images