Dynamic scheduling method, device, equipment and storage medium for on-the-way vehicles

Abstract

The present invention discloses a method, device, equipment, and storage medium for dynamically scheduling on-the-go vehicles. The method comprises: based on a pre-trained neural network prediction model and the real-time status data of each on-the-go vehicle to be scheduled, predicting the status data of each on-the-go vehicle to be scheduled while en route, and generating the predicted status data of each on-the-go vehicle to be scheduled while en route; dynamically matching the transport task with the predicted status data of each on-the-go vehicle to be scheduled while en route according to a preset matching rule, and obtaining a first candidate vehicle that successfully matches the transport task; performing multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting a conflict, dynamically re-matching the transport task with the predicted status data of each on-the-go vehicle to be scheduled while en route, and determining a target dispatch vehicle that does not conflict with the transport task. The present invention effectively improves the accuracy of matching transport tasks with on-the-go vehicles to be scheduled.

Description

Technical Field

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

[0002] In the logistics and transportation sector, especially in distribution, intercity, and interprovincial trunk transport scenarios, the effective scheduling and resource utilization of transport vehicles have always been a major challenge facing the industry. Currently, most transport vehicle scheduling methods still use a one-way matching model of "transportation task-dispatching vehicle", which leads to a generally high rate of empty returns for transport vehicles. In addition, when temporary transport tasks or regional transportation capacity shortages arise, conventional solutions mainly rely on outsourced vehicle leasing, which not only adds additional costs but also faces problems such as long vehicle scheduling response times and difficulty in ensuring transportation timeliness.

[0003] To address the high rate of empty transport vehicle returns, the industry has attempted to improve this through methods such as pre-booked ridesharing or fixed-route sharing. However, traditional ridesharing models rely heavily on manual scheduling, resulting in low vehicle dispatch response efficiency. Furthermore, fixed-route sharing lacks flexibility and struggles to cope with dynamically changing transport tasks, leading to low accuracy in matching transport tasks with on-the-go vehicles.

[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 dynamic dispatching method, device, equipment and storage medium for 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:

[0007] Obtain the transport task and the corresponding real-time status data of multiple vehicles to be dispatched;

[0008] 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 to 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;

[0009] 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, and the first candidate vehicle that successfully matches the transport task is obtained;

[0010] 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.

[0011] 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:

[0012] The real-time status data of each on-the-way vehicle to be dispatched is input in parallel into 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;

[0013] 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;

[0014] 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 road section on the way, and the predicted status data of each on-the-way vehicle to be dispatched is obtained.

[0015] Optionally, 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 includes:

[0016] Calculating the path overlap between the transport task path 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;

[0017] Calculating the absolute time difference between the predicted arrival time of each to-be-scheduled vehicle in the first candidate vehicle set at the starting location of the transport task and the actual start time of the transport task, and selecting a second candidate vehicle set whose absolute time difference is less than a preset absolute time difference threshold;

[0018] Calculating the transportation cost savings of each to-be-dispatched vehicle in the second candidate vehicle set when performing the transport task, and screening out the target candidate vehicle set whose transportation cost savings exceeds a preset transportation cost savings threshold;

[0019] Performing weighted processing on the path overlap, absolute time difference, and transportation cost savings corresponding to each vehicle to be dispatched in the target candidate vehicle set and the transport task, and calculating the matching value between each vehicle to be dispatched and the transport task in the target candidate vehicle set based on the weighted processing result;

[0020] The matching degree values ​​of each to-be-scheduled vehicle and the transport task in the target candidate vehicle set 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.

[0021] Optionally, performing multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting a 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, includes:

[0022] Input the transport tasks and the predicted status data of each on-the-way vehicle to be dispatched into the decision tree model for training to generate a trained conflict detection model;

[0023] 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 status data of each on-the-way vehicle to be dispatched.

[0024] 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:

[0025] 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;

[0026] 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.

[0027] Optionally, after determining the target dispatch vehicle that does not conflict with the transport task, the method further includes:

[0028] The driving path of the target dispatch vehicle is planned and dynamically adjusted by minimizing the multi-objective algorithm.

[0029] 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:

[0030] Obtain the starting and ending positions of the transport mission, as well as the starting and ending positions of the target dispatch vehicle, and generate an initial driving path for the target dispatch vehicle passing through the starting and ending positions of the transport mission;

[0031] Based on the travel time, transportation cost and energy consumption of the target dispatch vehicle, a multi-objective function for minimizing the target dispatch vehicle's travel path is constructed, and the target dispatch vehicle's mission time window and vehicle capacity are configured as constraints for minimizing the multi-objective function;

[0032] A parameter combination that minimizes a multi-objective function is searched for according to a preset search algorithm, 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.

[0033] In a second aspect, the present invention provides a dynamic scheduling device for on-the-way vehicles, comprising an acquisition module, a prediction module, a matching module, and a detection module:

[0034] The acquisition module is used to obtain the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched;

[0035] 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;

[0036] 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 to obtain a first candidate vehicle that successfully matches the transport task;

[0037] 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.

[0038] In a third aspect, the present invention provides a dynamic dispatching device for on-the-way vehicles, comprising a memory and a processor, wherein:

[0039] The memory is used to store computer programs;

[0040] 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.

[0041] 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 on-the-way vehicles as provided in the first aspect above.

[0042] 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:

[0043] 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

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only part of the embodiments of the present invention, rather than all the embodiments. For ordinary technicians in this field, without paying any creative work, other drawings obtained based on these drawings are all within the scope of protection of this application.

[0045] Figure 1 This is a flow chart of a dynamic scheduling method for on-the-way vehicles provided by an embodiment of the present invention.

[0046] Figure 2 This 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.

[0047] Figure 3 This is a flowchart of a multi-dimensional conflict detection provided by an embodiment of the present invention.

[0048] Figure 4 The present invention provides a flowchart for dynamically adjusting the driving path of a target dispatch vehicle.

[0049] Figure 5 The invention provides a dynamic dispatching device for vehicles on the same route.

[0050] Figure 6 It is a structural diagram of a dynamic dispatching device for on-the-way vehicles provided by an embodiment of the present invention.

[0051] Figure 7 It is a structural diagram of a computer-readable storage medium provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to 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 intended to limit the present invention.

[0053] In order to make the description of the present disclosure more detailed and complete, the following is an illustrative description of the implementation methods and specific examples of the present invention; however, this is not the only form of implementing or using the specific embodiments of the present invention. The implementation methods cover 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.

[0054] It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present invention described herein can be practiced in an order other than that illustrated or described herein.

[0055] 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 there can be three relationships, 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 can be combined with each other unless there is a conflict.

[0056] Example 1

[0057] like Figure 1The flowchart of a dynamic scheduling method for on-the-way vehicles provided in an embodiment of the present invention includes the following steps.

[0058] Step S101: Acquire the transport task and the corresponding real-time status data of multiple on-the-way vehicles to be dispatched.

[0059] The present embodiment first requires obtaining the current transport task and the real-time status data of the corresponding on-the-go vehicles. The transport task includes key information such as the starting location, destination, cargo information, and time requirements. The real-time status data of the corresponding on-the-go vehicles includes key information such as the current location, speed, vehicle condition, traffic conditions, and estimated arrival time of each on-the-go vehicle.

[0060] 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, 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.

[0061] In step S101, after acquiring 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 en route status data of each on-the-way vehicle to be dispatched. The real-time status data of each on-the-way vehicle to be dispatched is input into a pre-trained neural network prediction model. By learning from historical data, the prediction model can effectively capture the potential patterns and regularities in the real-time status data of the on-the-way vehicles to be dispatched and predict the future status of the on-the-way vehicles to be dispatched. The prediction model can predict information such as the route changes, arrival time, energy consumption status, and remaining cargo capacity of the on-the-way vehicles to be dispatched.

[0062] Step S103 , 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, and obtaining a first candidate vehicle that successfully matches the transport task.

[0063] In step S102, the embodiment of the present invention generates the predicted status data of each en route vehicle to be scheduled. Then, the transport task can be dynamically matched with the predicted status data of each en route vehicle to be scheduled 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 made according to the latest data, thereby improving the flexibility and efficiency of en route vehicle scheduling.

[0064] In step S104, a multi-dimensional conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after a 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.

[0065] In step S103, after obtaining the first candidate vehicle that successfully matches the transport task, this embodiment of the present invention further requires multi-dimensional conflict detection between the transport task and the first candidate vehicle to identify conflicts in the predicted state data of the transport task and the first candidate vehicle. The transport task is then dynamically re-matched and conflict-checked with the predicted state data of each on-the-way vehicle to be dispatched, ensuring that the selected target dispatch vehicle does not conflict and can successfully complete the transport task. This embodiment of the present invention ensures efficient and reliable vehicle dispatch through multi-dimensional conflict detection, enabling timely identification and adjustment when problems arise, effectively avoiding transportation delays caused by conflicts.

[0066] As an optional implementation, step S102 predicts the en route state data of each en route vehicle to be dispatched based on a pre-trained neural network prediction model and the real-time state data of each en route vehicle to be dispatched, generating the predicted en route state data of each en route vehicle to be dispatched, including:

[0067] In step S1021, the real-time status data of each on-the-way vehicle to be dispatched is input in parallel into the convolutional neural network layer and the long-short-term memory network layer of the pre-trained neural network prediction model, where spatial and temporal feature extraction is performed, respectively. This results in a spatial feature vector and a temporal feature vector for the real-time status data of each on-the-way vehicle to be dispatched. Specifically, in this embodiment of the present invention, the convolutional neural network layer can effectively capture features related to spatial distribution, such as spatial feature information such as the vehicle's location, current traffic flow, and road conditions. By extracting this spatial feature information, the vehicle's location at a given moment and the surrounding traffic environment can be determined. The long-short-term memory network layer can extract temporal features from continuous time data and learn temporal information about the vehicle's travel process, such as changes in vehicle speed, fluctuations in traffic flow, and route selection. By extracting the spatial and temporal features of the real-time status data of each on-the-way vehicle to be dispatched, different types of data patterns can be more efficiently captured, resulting in more accurate predicted status data for each on-the-way vehicle to be dispatched.

[0068] Step S1022 fuses the spatial feature vectors and temporal feature vectors of the real-time status data of each on-the-way vehicle to be dispatched to obtain a fused feature vector of the real-time status data of each on-the-way vehicle to be dispatched. In this embodiment of the present invention, feature fusion can be achieved through vector weighted summation and concatenation. The fused feature vector contains the necessary information of each on-the-way vehicle 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.

[0069] In step S1023, 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 road section along the way, thereby obtaining 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 vehicles to be dispatched into the fully connected layer of the pre-trained neural network prediction model, the status data of each road section along the travel path of each on-the-way vehicle to be dispatched can be predicted based on the fused feature vector.

[0070] As an optional implementation, Figure 2 The flowchart of the embodiment of the present invention provides a flow chart for dynamically matching a transport task with each on-the-way vehicle to be dispatched. 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:

[0071] Step S1031: Calculate the degree of path overlap between the transport task's path and the predicted paths of each on-the-way vehicle to be dispatched, and select a first candidate vehicle set whose path overlap exceeds a preset path overlap threshold. For example, the threshold for path overlap between the transport task's path and the predicted paths of each on-the-way vehicle to be dispatched can be preset to 60%. If the calculated path overlap is 30%, it indicates that the transport task and the on-the-way vehicle to be dispatched are not well matched. If the calculated path overlap is 80%, it indicates that the transport task and the on-the-way vehicle to be dispatched are well matched, and the on-the-way vehicle to be dispatched can be determined as a vehicle in the first candidate vehicle set.

[0072] Step S1032: Calculate the absolute time difference between the predicted arrival time of each to-be-scheduled vehicle in the first candidate vehicle set at the starting point of the transport task and the actual start time of the transport task, and select a second candidate vehicle set whose absolute time difference is less than a 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 at the starting point 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 at the starting point of the transport task is 15:40, then a time conflict has occurred between the to-be-scheduled vehicle and the transport task. If the predicted arrival time of the to-be-scheduled vehicle at the starting point of the transport task is 15:05, then a high degree of match between the transport task and the on-the-way vehicle to be dispatched is achieved, and the to-be-scheduled vehicle can be determined as a vehicle in the second candidate vehicle set.

[0073] 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 exceed a preset transportation cost savings threshold. In this embodiment of the present invention, for example, the transportation cost savings threshold for 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.

[0074] Step S1034: perform weighted processing on the path overlap, absolute time difference, and transportation cost savings corresponding to each vehicle to be dispatched in the target candidate vehicle set and the transport task, and calculate 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 an embodiment of the present invention, the calculated path overlap, time difference, and transportation cost savings 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 larger; if cost savings are more important, the weight of the transportation cost savings is larger. 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.

[0075] Step S1035: The target candidate vehicles are ranked based on their matching scores with the transport task. The on-route vehicle with the highest matching score is then determined as the first candidate vehicle that successfully matches the transport task. In this embodiment of the present invention, by comprehensively considering multiple factors such as path overlap, arrival time, and transportation cost, candidate vehicles are gradually screened and optimized, ultimately selecting the target dispatch vehicle most suitable for the transport task. This ensures the smooth execution of the transport task, improves the efficiency of on-route vehicle scheduling, and achieves a balance between cost and time.

[0076] As an optional implementation, Figure 3 The flowchart of a multi-dimensional conflict detection provided by an embodiment of the present invention includes the following steps: in step S104, multi-dimensional conflict detection is performed on the first candidate vehicle that successfully matches the transport task, and after a 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.

[0077] In step S1041, the transport tasks and the predicted status data for each on-the-way vehicle to be dispatched are input into a decision tree model for training, generating a trained conflict detection model. This embodiment of the present invention utilizes a machine learning algorithm for conflict detection, improving the automation of conflict detection and reducing errors due to human judgment. Furthermore, the trained conflict detection model can quickly identify conflicts, improving the efficiency of on-the-way vehicle dispatching.

[0078] Step S1042, based on the trained conflict detection model, performs conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting the conflict, dynamically re-matches the transport task with the predicted state data of each on-the-way vehicle to be dispatched. If a conflict is detected in this 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, re-screen candidate vehicles that meet path matching, time matching, and resource availability, and after conflict detection, determine the target dispatch vehicle that does not conflict with the transport task. This embodiment of the present invention avoids task execution failures caused by conflicts between the transport task and the target dispatch vehicle through multi-dimensional conflict detection, and improves the reliability of the target dispatch vehicle in executing the transportation task.

[0079] As an optional implementation, in step S1042, the first candidate vehicle that successfully matches the transport task is subjected to conflict detection based on the trained conflict detection model, and after a 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:

[0080] In step S10421, based on the trained conflict detection model, the first candidate vehicle that successfully matches the transport mission is tested for time conflicts, energy consumption conflicts, and remaining cargo capacity conflicts. In this embodiment of the present invention, it is first necessary to confirm whether the first candidate vehicle can arrive at the starting point of the transport mission on time and whether any time conflicts will occur during mission execution; secondly, it is necessary to confirm whether the energy consumption of the first candidate vehicle when performing the transport mission is within an acceptable range; and finally, it is necessary to confirm whether the first candidate vehicle has sufficient remaining cargo capacity to undertake the transport mission. Through multi-dimensional conflict detection, a more comprehensive assessment of the first candidate vehicle's suitability for the current transport mission can be achieved, effectively reducing the risk of mission failure.

[0081] In 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, a target dispatch vehicle that does not conflict with the transport task is determined. In an 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 successfully perform the transport task. If no conflict is detected 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.

[0082] 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 an 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 vehicles to be dispatched.

[0083] As an optional implementation, Figure 4 The flowchart of dynamically adjusting the driving path of a target dispatch vehicle provided by an embodiment of the present invention includes: in step S105, 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, including:

[0084] S1051. Obtain the starting and ending positions of the transport mission, as well as the starting and ending positions of the target dispatch vehicle, and generate an initial driving path for the target dispatch vehicle passing through the starting and ending positions of the transport mission. In an embodiment of the present invention, the initial driving path is generated based on the starting and ending positions of the transport mission using map data and a path planning algorithm to ensure that the path covers the starting and ending points of the transport mission and selects the shortest or fastest route as much as possible. The path planning algorithm may use a Dijkstra algorithm or an A* algorithm. In the generated initial driving path, the starting and ending points of the transport mission need to be marked as waypoints to ensure that the path meets the transportation requirements.

[0085] S1052. Based on the travel time, transportation cost and energy consumption of the target dispatch vehicle, a multi-objective function for minimizing the travel path of the target dispatch vehicle is constructed, and the mission time window and vehicle capacity of the target dispatch 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 dispatch vehicle are used as multiple objectives, and the time window and vehicle capacity configuration of the transport mission are used as constraints to ensure that the target dispatch vehicle can complete the mission within the specified time. Among them, minimizing the multi-objective function The expression of is as described in formula (1):

[0086] (1)

[0087] in, represents the travel time of the target dispatch vehicle, represents the transportation cost of the target dispatch vehicle, Represents the energy consumption of the target dispatch vehicle.

[0088] 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 dynamically adjusted driving path of the target dispatch vehicle, 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. In an embodiment of the present invention, a 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 based on the current parameter combination to adjust the initial driving path. For example, it is possible to choose 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.

[0089] 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.

[0090] Example 2

[0091] Based on the above-mentioned dynamic scheduling method for on-the-way vehicles, an embodiment of the present invention provides a dynamic scheduling device for on-the-way vehicles, such as Figure 5 As shown, its structural 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:

[0092] 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;

[0093] 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;

[0094] The matching module 53 is used to dynamically match 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;

[0095] 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.

[0096] 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.

[0097] Example 3

[0098] Based on the above dynamic scheduling method for on-the-way vehicles, Figure 6FIG. 1 is a schematic diagram of a structure of a dynamic dispatching device for on-the-way vehicles provided in an embodiment of the present invention. The device includes a processor 61 and a memory 62 coupled to the processor 61. The memory 62 stores a computer program. 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.

[0099] 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.

[0100] 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 Processor), 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.

[0101] Example 4

[0102] 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, wherein a readable computer program 71 is stored on the storage medium; wherein the computer program 71 can be stored in the above-mentioned storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a 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: 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), and other media that can store program code, or a terminal device such as a computer, server, mobile phone, or tablet.

[0103] In the several embodiments provided in this 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 merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, 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.

[0104] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of the present embodiment according to actual needs.

[0105] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may be stored in a computer-readable storage medium.

[0106] 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.

[0107] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present application are fully or partially generated. 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. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that can be stored by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, hard disk, or tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0108] The above is a detailed introduction to the technical solution provided by the present application. Specific examples are used in the present application to illustrate the principles and implementation methods of 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 ideas 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.

[0109] 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 take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0110] 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 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0113] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is 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 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 to 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; 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, and the first candidate vehicle that successfully matches the transport task is obtained; Performing multi-dimensional conflict detection on the first candidate vehicle that successfully matches the transport task, and after detecting a 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; Plan the target dispatch vehicle's driving path and dynamically adjust the target dispatch vehicle's driving path by minimizing the multi-objective algorithm, including: Obtain the starting and ending positions of the transport mission, as well as the starting and ending positions of the target dispatch vehicle, and generate an initial driving path for the target dispatch vehicle passing through the starting and ending positions of the transport mission; Based on the travel time, transportation cost and energy consumption of the target dispatch vehicle, a multi-objective function for minimizing the target dispatch vehicle's travel path is constructed, and the target dispatch vehicle's mission time window and vehicle capacity are configured as constraints for minimizing the multi-objective function; Constructed minimization multi-objective function The expression is as follows: in, represents the travel time of the target dispatch vehicle, represents the transportation cost of the target dispatch vehicle, represents the energy consumption of the target dispatch vehicle; A parameter combination that minimizes a multi-objective function is searched for according to a preset search algorithm, 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.

2. The dynamic dispatching method for on-the-way vehicles according to claim 1, characterized in that: The method of predicting 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 generating the predicted state data of each on-the-way vehicle to be dispatched on the way, includes: The real-time status data of each on-the-way vehicle to be dispatched is input in parallel into 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 road section on the way, and the predicted status data of each on-the-way vehicle to be dispatched is obtained.

3. The dynamic dispatching method for on-the-way vehicles according to claim 1, characterized in that: The method of 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 includes: Calculating the path overlap between the transport task path 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; Calculating the absolute time difference between the predicted arrival time of each to-be-scheduled vehicle in the first candidate vehicle set at the starting location of the transport task and the actual start time of the transport task, and selecting a second candidate vehicle set whose absolute time difference is less than a preset absolute time difference threshold; Calculating the transportation cost savings of each to-be-dispatched vehicle in the second candidate vehicle set when performing the transport task, and screening out 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 cost savings corresponding to each vehicle to be dispatched in the target candidate vehicle set and the transport task, and calculating the matching value between each vehicle to be dispatched and the transport task in the target candidate vehicle set based on the weighted processing result; The matching degree values ​​of each to-be-scheduled vehicle and the transport task in the target candidate vehicle set 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 dynamic dispatching method for 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 a conflict is detected, to determine a target dispatch vehicle that does not conflict with the transport task, includes: Input the transport tasks and the predicted status data of each on-the-way vehicle to be dispatched into the decision tree model for training to generate a trained conflict detection model; 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 status data of each on-the-way vehicle to be dispatched.

5. The dynamic dispatching method for 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, 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; 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. A dynamic dispatching device for vehicles on the same route, characterized in that: The device is used to implement the dynamic scheduling method for on-the-way vehicles according to any one of claims 1 to 5, comprising an acquisition module, a prediction module, a matching module, and a detection module: The acquisition module is used to obtain 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 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.

7. A dynamic dispatching device for vehicles on the way, characterized in that: comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor is configured to read the computer program in the memory and execute the steps of the method for dynamically scheduling on-the-way vehicles according to any one of claims 1 to 5.

8. 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 5 are implemented.

Images