Vehicle dispatching method and device, storage medium and electronic device

Abstract

The present invention provides a vehicle scheduling method and device, a storage medium and an electronic device, the method comprising: when receiving a trigger instruction for scheduling each vehicle, determining each flight to which the vehicle needs to be assigned; determining a scheduling information set, the scheduling information set including the vehicle information of each vehicle and the flight information of each flight; based on the scheduling information set, determining a priority parameter set corresponding to each vehicle; according to the priority parameter set corresponding to each vehicle and a preset taboo search algorithm, determining each transport flight corresponding to each vehicle in each flight to schedule each vehicle. By applying the method of the present invention, the information of all vehicles and all flights can be combined to obtain an optimal scheduling scheme, without the need for manual scheduling, avoiding the limitations of manual scheduling, and achieving a better overall scheduling effect.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a vehicle dispatching method and device, a storage medium and an electronic device. Background Art

[0002] As people's living standards continue to improve, airplanes have become a common means of transportation in people's lives. In order to meet people's travel needs, the number of flights carried by airports has also increased. However, the airport's close parking positions are limited, and some flights need to stay at the airport's remote parking positions. Passengers cannot board the plane from the terminal through the airport bridge, or get off the plane and enter the terminal directly. The airport needs to deploy shuttle buses to pick up passengers to and from the terminal.

[0003] At present, the dispatch of shuttle buses is usually done manually by staff according to dispatch rules and flight plans. However, in the actual operation of the airport, the real-time arrival and departure of flights is not completely carried out according to the plan. There are often flight delays or other abnormal situations, which lead to changes in the dispatch requirements of vehicles.

[0004] However, with manual vehicle dispatch, when the vehicle dispatch demand changes, it is usually difficult for the staff to consider the overall vehicle allocation situation in time for vehicle dispatch. The overall dispatch effect is poor, which may cause passengers on some flights to be unable to board the shuttle bus in time. Especially when the number of flights is large, it is very easy for vehicle transportation tasks to be delayed, which will have an adverse impact on the airport ground support work, bring safety hazards, and reduce the service experience of passengers. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a vehicle dispatching method to solve the problem that manual dispatching of vehicles is difficult to consider the overall situation, the overall dispatching effect is poor, and vehicle transportation tasks are prone to delays.

[0006] The embodiment of the present invention also provides a vehicle dispatching device to ensure the practical implementation and application of the above method.

[0007] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0008] A first aspect of the present invention discloses a vehicle dispatching method, comprising:

[0009] When a trigger instruction for scheduling each vehicle is received, each flight to which the vehicle needs to be allocated is determined;

[0010] Determine a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights;

[0011] Based on the scheduling information set, determining a priority parameter set corresponding to each of the vehicles, wherein the priority parameter set corresponding to each of the vehicles includes a plurality of priority parameters, and the plurality of priority parameters correspond to each of the flights one by one;

[0012] According to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, in each of the flights, each transport flight corresponding to each of the vehicles is determined to schedule each of the vehicles.

[0013] A second aspect of the present invention discloses a vehicle dispatching device, comprising:

[0014] A first determining unit is used to determine each flight to which vehicles need to be allocated when receiving a trigger instruction for scheduling each vehicle;

[0015] A second determining unit, configured to determine a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights;

[0016] A third determining unit is used to determine a priority parameter set corresponding to each of the vehicles based on the scheduling information set, wherein the priority parameter set corresponding to each of the vehicles includes a plurality of priority parameters, and the plurality of priority parameters correspond to each of the flights one by one;

[0017] The fourth determining unit is used to determine each transport flight corresponding to each of the vehicles in each of the flights according to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, so as to schedule each of the vehicles.

[0018] A third aspect of the present invention discloses a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the vehicle dispatching method as described above.

[0019] A fourth aspect of the present invention discloses an electronic device, comprising a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to perform the above-mentioned vehicle dispatching method.

[0020] Compared with the prior art, the present invention has the following advantages:

[0021] The present invention provides a vehicle scheduling method and device, a storage medium and an electronic device, the method comprising: when receiving a trigger instruction for scheduling each vehicle, determining each flight to which the vehicle needs to be assigned; determining a scheduling information set, the scheduling information set including the vehicle information of each vehicle and the flight information of each flight; based on the scheduling information set, determining a priority parameter set corresponding to each vehicle, the priority parameter set corresponding to each vehicle including multiple priority parameters, the multiple priority parameters corresponding to each flight one by one; according to the priority parameter set corresponding to each vehicle and a preset taboo search algorithm, determining each transport flight corresponding to each vehicle in each flight, so as to schedule each vehicle. Based on the scheme provided by the present invention, when it is necessary to schedule each vehicle, the global information of all vehicles and all flights can be combined to obtain a relatively good scheduling scheme, without manual scheduling, avoiding the limitations of manual scheduling, and even in the case of a large number of flights, the vehicle scheduling can be completed quickly, the overall scheduling effect is good, which is conducive to ensuring that each vehicle performs the passenger carrying task in time, so as to ensure the normal boarding or disembarking of flight passengers, ensure passenger safety and improve passenger service experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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 embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0023] Figure 1 A method flow chart of a vehicle dispatching method provided by an embodiment of the present invention;

[0024] Figure 2 Another method flow chart of a vehicle dispatching method provided by an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the structure of a neural network model provided by an embodiment of the present invention;

[0026] Figure 4 Another method flow chart of a vehicle dispatching method provided by an embodiment of the present invention;

[0027] Figure 5 A schematic diagram of the structure of a vehicle dispatching device provided by an embodiment of the present invention;

[0028] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] As can be seen from the background technology, the scheduling of airport shuttle buses is usually done manually, and manual scheduling usually has certain limitations. It is usually difficult for staff to quickly combine global information to give a better scheduling plan. The overall scheduling effect is poor, and it is easy for vehicles to fail to perform passenger transportation tasks in time. Passengers need to wait for shuttle buses for a long time, which makes the service experience of passengers poor. In addition, if passengers who get off the plane cannot be picked up in time, they will stay in the apron area for a long time, which will bring certain safety hazards and have an adverse impact on the airport ground support work.

[0034] Therefore, an embodiment of the present invention provides a vehicle dispatching method, which can be applied to a vehicle dispatching system for an airport shuttle bus. The execution subject of the method can be a processor running on a computer. The method flow chart of the vehicle dispatching method is as follows: Figure 1 As shown, including:

[0035] S101: When a trigger instruction for scheduling each vehicle is received, each flight to which a vehicle needs to be allocated is determined;

[0036] In the method provided by the embodiment of the present invention, when it is necessary to dispatch each shuttle bus at the airport, the staff can send a trigger instruction for dispatching each vehicle through the front end of the vehicle dispatching system.

[0037] When the system processor receives the corresponding trigger instruction, it can obtain the flights that need to be assigned vehicles from the airport's flight plan. The airport's flight plan can be pre-imported into the vehicle dispatch system, or obtained from a system that stores this information. If the vehicle dispatch plan for the day is required, the flights that need to be assigned vehicles are the flights that are scheduled to take off or land at the airport's remote parking positions on the day.

[0038] It should be noted that in actual application scenarios, the airport's vehicle dispatch can be dispatched by region, that is, each vehicle currently being dispatched can be a vehicle responsible for a certain area of ​​the airport's transportation mission, and each flight that needs to be assigned a vehicle can be a flight scheduled to take off and land in that area. The airport's vehicle dispatch can also be dispatched in a unified manner, and each vehicle can be all vehicles that can currently perform transportation missions at the airport, and each flight includes all take-off and landing flights that need to be assigned a vehicle.

[0039] S102: Determine a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights;

[0040] In the method provided by the embodiment of the present invention, the vehicle information of each vehicle and the flight information of each flight can be obtained to obtain a scheduling information set. The vehicle information of a vehicle may include the location of the vehicle, the number of passengers that can be carried, the driver driving the vehicle, the driver's working hours, and other information. The flight information of a flight may include the flight number, the parking position, the expected boarding time / expected landing time, the number of passengers, and other information.

[0041] S103: Determine a priority parameter set corresponding to each of the vehicles based on the scheduling information set, wherein the priority parameter set corresponding to each of the vehicles includes a plurality of priority parameters, and the plurality of priority parameters correspond to each of the flights one by one;

[0042] In the method provided in an embodiment of the present invention, the priority parameters corresponding to each vehicle and each flight, that is, the priority level of each vehicle assigned to each flight, can be determined according to the predicted scheduling strategy based on the vehicle information of each vehicle and the flight information of each flight.

[0043] It should be noted that the scheduling strategy provided in the embodiment of the present invention is provided with a conflict management mechanism, that is, for the same vehicle, for each flight that transports passengers at a similar time, there is usually at most only one priority parameter representing a higher priority, so as to ensure that the vehicle will not be assigned tasks twice at the same time.

[0044] S104: According to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, in each of the flights, each transport flight corresponding to each of the vehicles is determined to schedule each of the vehicles.

[0045] In the method provided by the embodiment of the present invention, various scheduling schemes can be obtained according to the priority parameter set corresponding to each vehicle, and each scheduling scheme includes the scheduling arrangement of each vehicle, that is, the flights assigned to each vehicle. The optimal scheduling scheme can be iteratively searched in each scheduling scheme through the taboo search algorithm to find the optimal scheduling scheme, and the transport flights corresponding to each vehicle can be determined in each flight according to the optimal scheduling scheme to complete the scheduling of each vehicle. That is, each vehicle needs to perform the transport task of each transport flight corresponding to it, and pick up and drop off the passengers of the flight to and from the terminal.

[0046] It should be noted that in actual application scenarios, multiple shuttle buses can be assigned to transport passengers for one flight, different vehicles can correspond to the same flight, and the same vehicle can also transport passengers on the same flight multiple times.

[0047] Based on the method provided by the embodiment of the present invention, when it is necessary to dispatch each vehicle, each flight to which the vehicle needs to be assigned can be determined, and the dispatch information set corresponding to each vehicle and each flight can be determined. Based on the dispatch information set, the priority parameter set corresponding to each vehicle and each flight can be determined. According to the priority parameter set corresponding to each vehicle and the preset taboo search algorithm, each transport flight corresponding to each vehicle is determined in each flight to dispatch each vehicle. By applying the method provided by the embodiment of the present invention, a relatively good dispatching scheme can be quickly obtained by combining the global information of all vehicles and all flights, without the need for manual dispatching, and avoiding the limitations of manual dispatching. The overall dispatching effect is good, which is conducive to ensuring that each vehicle can transport passengers to and from the terminal in a timely manner to ensure that passengers can board or disembark normally, which is conducive to ensuring passenger safety and improving passenger service experience. In addition, human resources for manual dispatching can also be saved, and airport operating costs can be reduced.

[0048] In order to better illustrate the method provided by the embodiment of the present invention, Figure 1 Based on the method shown, combined Figure 2 As shown in the method flow chart, the embodiment of the present invention provides another vehicle scheduling method. In the method provided by the embodiment of the present invention, the process of determining the priority parameter set corresponding to each of the vehicles based on the scheduling information set mentioned in step S103 includes:

[0049] S201: Determine a first score set corresponding to each of the vehicles according to a preset dispatch rule and the dispatch information set, wherein the first score set corresponding to each of the vehicles includes a plurality of scores, the plurality of scores correspond to the respective flights one by one, and the plurality of scores represent the allocation priority of the vehicle corresponding to the respective flights;

[0050] In the method provided in the embodiment of the present invention, a dispatching rule regarding the priority of vehicle allocation can be preset. The preset dispatching rule and the current dispatching information set can be combined to determine a first score set corresponding to each vehicle, and each score in the first score set represents the priority of the vehicle in allocating the flight corresponding to the score.

[0051] In a specific implementation process, the first score set corresponding to each vehicle can be recorded in the form of a matrix. A score matrix can be generated according to the matching of each information in the scheduling information set with the scheduling rule, the horizontal coordinate of the matrix is ​​the flight, specifically the flight number of the flight, and the vertical coordinate of the matrix is ​​the vehicle, specifically the vehicle number of the vehicle. Each element in the matrix is ​​a score, and each score is the score in the first score set of the vehicle corresponding to its position, and corresponds to the flight corresponding to its position.

[0052] Optionally, the dispatch rules mentioned in the embodiments of the present invention may specifically include multiple sub-rules. The factors involved in each sub-rule may include: the vehicle's driving path, the distance between the vehicle's current position and the aircraft position (the vehicle can only travel according to the pre-planned driving path in the apron, and the distance between the vehicle's position and the aircraft position is determined based on the available driving path, not the straight-line distance), the error time between the vehicle's arrival time and the passenger's boarding / disembarking time, the number of vehicles required for the flight, the dependent time (the time interval between the arrival time of the first shuttle bus and the arrival time of the second shuttle bus), etc. The process of determining the first score set corresponding to each vehicle is to globally assign corresponding scores based on the information of all vehicles and all flights. When multiple sub-rules are applied, the corresponding priority allocation under each sub-rule can be obtained according to each sub-rule, and the final first score set can be obtained based on the priority allocation corresponding to all sub-rules.

[0053] It should be noted that in the specific implementation process, a combination of different scheduling sub-rules can be used as a scheduling rule, or a scheduling rule with only one rule content can be used. The specific rule content used can also be different, which does not affect the function of the method provided in the embodiment of the present invention.

[0054] For example, a sub-rule of nearest dispatch can be set in combination with factors such as the vehicle's driving path and distance. The principle of allocating vehicles by applying this rule is that for the first batch of flights with similar vehicle usage times on the day, the driving path from the parking position of each vehicle to the aircraft stand of each flight is determined according to the principle of nearest dispatch and the order of priority from high to low according to the driving distance from near to far. The current priority order of each vehicle corresponding to each flight is set. Similarly, the priority order of each vehicle for other flights is determined, but the subsequent driving path is no longer the driving path from the parking position to the aircraft stand of the vehicle, but can be the dynamic driving path of the vehicle. For example, for a certain flight A corresponding to a vehicle, the vehicle performs the passenger transportation task of flight A immediately after performing the passenger transportation task of the previous flight B. The dynamic driving path corresponding to flight A is the driving path of the vehicle from the aircraft stand of flight B to the aircraft stand of flight A. Then, the priority order corresponding to the previous batch of flights can be adjusted accordingly according to the subsequent allocation situation. For example, when considering the first task of the vehicle, it is assigned to flight C rather than flight D. When considering subsequent tasks, assigning it to flight D will achieve better scheduling results. If the dynamic driving path distance is shorter, the priority order of the vehicle assigned to flight C and flight D can be readjusted.

[0055] S202: Input each information in the scheduling information set into the established neural network model, and after being processed by the neural network model, obtain a probability set corresponding to each of the vehicles, wherein the probability set corresponding to each of the vehicles includes multiple probabilities, and the multiple probabilities correspond to each of the flights one by one;

[0056] In the method provided by the embodiment of the present invention, a neural network model can be pre-constructed, and the neural network model can be trained using historical scheduling data so that the neural network model learns the dispatch results in the historical scheduling data, that is, the scheduling plan, to establish a neural network model with a certain learning ability. The vehicle information of each vehicle and the flight information of each flight in the current scheduling information set can be input into the established neural network model. After being processed by the neural network model, the output result of the neural network model can be obtained, and the probability set corresponding to each vehicle can be obtained, that is, the output of the neural network model is the probability of each vehicle being assigned to each flight. The historical scheduling data can be some empirical data with good scheduling effects.

[0057] S203: Determine a priority parameter set corresponding to each of the vehicles according to the first score set corresponding to each of the vehicles and the probability set corresponding to each of the vehicles.

[0058] In the method provided by the embodiment of the present invention, for each vehicle, its corresponding priority parameter set can be determined by combining the first score set obtained based on the dispatch rule and the probability set obtained based on the neural network model.

[0059] Based on the method provided by the embodiment of the present invention, the priority of each vehicle corresponding to each flight can be determined through a preset scheduling set. At the same time, the probability of each vehicle corresponding to each flight can be determined through the established neural network model. The outputs of the two processes are combined to determine the priority parameters of each vehicle corresponding to each flight. The embodiment of the present invention provides a vehicle scheduling method based on the combination of deep learning and sub-heuristic algorithms, which can make the priority parameters of each vehicle corresponding to each flight conform to the scheduling rules and are close to the historical dispatching rules, which can further optimize the scheduling effect of the vehicle scheduling plan and improve the scheduling efficiency.

[0060] Further, based on the method provided in the above embodiment, the embodiment of the present invention provides another vehicle scheduling method, wherein the process of determining the priority parameter set corresponding to each vehicle according to the first score set corresponding to each vehicle and the probability set corresponding to each vehicle mentioned in step S203 includes:

[0061] Determine a second score set corresponding to each of the vehicles, wherein the second score set corresponding to each of the vehicles includes a conversion score corresponding to each probability in the probability set corresponding to the vehicle;

[0062] In the method provided by the embodiment of the present invention, each probability in the probability set corresponding to each vehicle can be converted into a corresponding score according to a preset conversion strategy, and the greater the probability, the greater the corresponding score. In the specific implementation process, each probability in the probability set corresponding to each vehicle can be converted into a corresponding score to obtain a second score set, or only some probabilities with higher probabilities can be converted into corresponding scores, and the remaining probabilities are not converted, and their corresponding scores can be set to zero. For example, only the top ten probabilities with the highest probability corresponding to each flight are converted into scores.

[0063] For each of the vehicles, determining a one-to-one correspondence between each score in the first score set corresponding to the vehicle and each conversion score in the second score set corresponding to the vehicle;

[0064] In the method provided by the embodiment of the present invention, for each vehicle, each score in the first score set and each conversion score in the second score set can be determined according to the corresponding flight, and a one-to-one correspondence between each score and each conversion score can be determined, that is, the score and conversion score of the same flight correspond to each other.

[0065] For each score in the first score set corresponding to each vehicle, perform a weighted sum operation on the score and the conversion score corresponding to the score, and use the operation result as the final score corresponding to the score;

[0066] In the method provided by the embodiment of the present invention, for each vehicle, each score in the first score set and each conversion score in the second score set can be weighted and summed, specifically, each score and its corresponding conversion score can be weighted and summed, and the calculation result can be used as the final score corresponding to the score, that is, the final score of the vehicle corresponding to the flight corresponding to the score. The specific calculation weight can be determined according to the needs.

[0067] It should be noted that, in the specific implementation process, if only part of the probabilities in the probability set are converted into scores, then in the process of weighted calculation, for the scores whose corresponding conversion scores are zero, weighted summation does not need to be performed, and the score itself can be used as the corresponding final score, which does not affect the function of the method provided in the embodiment of the present invention.

[0068] The final scores corresponding to the scores in the first score set corresponding to each of the vehicles are determined as the priority parameters corresponding to the vehicle, and the priority parameters corresponding to the vehicle are combined into a priority parameter set corresponding to the vehicle.

[0069] In the method provided by the embodiment of the present invention, for each vehicle, the corresponding final scores are used as the corresponding priority parameters of the vehicle to obtain the priority parameter set corresponding to the vehicle.

[0070] Based on the method provided by the embodiment of the present invention, the probabilities in the probability set can be converted into scores to unify the measurement unit, so as to combine the two types of parameters to determine the final priority parameter, which is conducive to data identification. In addition, only the probabilities with higher probabilities can be converted into scores, which can reduce data processing work and improve processing efficiency.

[0071] In order to better illustrate the method provided by the embodiment of the present invention, Figure 2 Based on the method shown, an embodiment of the present invention provides another vehicle dispatching method. In the method provided by the embodiment of the present invention, the process of establishing the neural network model mentioned in step S202 includes:

[0072] Acquire historical scheduling data, and determine a training data set corresponding to the historical scheduling data;

[0073] In the method provided by the embodiment of the present invention, pre-recorded historical scheduling data can be obtained from the database, and the data may include scheduling information of multiple scheduling arrangements. Each scheduling information may include vehicle information of each vehicle that needs to be scheduled, such as the vehicle number, the location of the vehicle, etc., including flight information of each flight to which the vehicle needs to be assigned, such as the flight position, planned boarding time or landing time, etc., and also includes the final scheduling plan, that is, which flights each vehicle is assigned to. Based on the historical scheduling data, the corresponding training data set is determined, and the training data set contains multiple training samples. Each training sample corresponds to each scheduling information. The sample input of the training sample is the vehicle information of each vehicle in the scheduling information and the flight information of each flight, and the sample output is the allocation probability corresponding to the final scheduling plan.

[0074] Each training sample in the training data set is input into a pre-built deep neural network model, the deep neural network model is trained, and the trained deep neural network model is used as the neural network model.

[0075] In the method provided in the embodiment of the present invention, a deep neural network model (Deep Neural Networks, DNN) can be constructed, and the schematic diagram of its network structure can be as follows: Figure 3 As shown in the figure, the deep neural network model includes an input layer X, a hidden layer H and an output layer Y. The input layer X is loaded with input data (x_axis, y_axis), b1 and b2 are bias vectors, and W1 and W2 are weights. The activation function used in the hidden layer H is the linear rectifier function (RectifiedLinearUnit, ReLU), also known as the rectified linear unit. The activation function in the output layer Y is the Softmax function, and the loss function is the cross entropy error function (Cross EntropyError). The DNN model is an existing neural network model and will not be further explained here.

[0076] During the training process, the sample inputs in each training sample are loaded into the input layer of the DNN, and the output is obtained from the output layer. The weights in the DNN model are adjusted according to the output of the output layer and the sample output to train the DNN model so that it can master the scheduling rules corresponding to the training samples. When the predetermined training effect is achieved, the training of the DNN model can be terminated, and the trained DNN model can be used as the neural network model in the embodiment of the present invention.

[0077] Based on the method provided in the embodiment of the present invention, the DNN model can be used as the architecture of the neural network model. The construction process and the training process are relatively simple, which can further improve work efficiency, reduce workload, and reduce complexity.

[0078] Further, based on the above embodiment, an embodiment of the present invention provides another vehicle dispatching method, wherein the process of determining the training data set corresponding to the historical dispatching data mentioned in the process of establishing the neural network model includes:

[0079] Performing data preprocessing on the historical scheduling data to obtain processed historical scheduling data;

[0080] In the method provided in the embodiment of the present invention, data preprocessing can be performed on the historical scheduling data. Specifically, some outliers in the historical scheduling data can be removed, missing values ​​can be filled, and parts with more data loss can be removed, and the data can be vectorized, etc., to obtain the processed historical scheduling data.

[0081] Feature engineering processing is performed based on the processed historical scheduling data to obtain various training samples, and the various training samples are combined into the training data set.

[0082] In the method provided by the embodiment of the present invention, the historical scheduling data obtained after data preprocessing is further subjected to feature engineering. Specifically, the Pearson correlation coefficient, variance inflation factor (VIF) and variance analysis can be used to process whether the features are linearly correlated and whether there is multicollinearity, and the features are combined and screened, and feature transformation is performed, and new features are generated through genetic algorithms. Based on all the features obtained after feature engineering, the corresponding training samples are obtained to form a training data set.

[0083] Based on the method provided in the embodiment of the present invention, data preprocessing and feature engineering can be further performed on the historical scheduling data to obtain various training samples, which is beneficial to improving the training effect of the neural network model.

[0084] In order to better illustrate the method provided by the embodiment of the present invention, Figure 1 On the basis of the method shown, an embodiment of the present invention provides another vehicle scheduling method, wherein the process of determining each transport flight corresponding to each vehicle in each flight according to the priority parameter set corresponding to each vehicle and a preset taboo search algorithm mentioned in step S104 includes:

[0085] Determine each scheduling set according to the priority parameter set corresponding to each of the vehicles, each of the scheduling sets includes a flight set corresponding to each of the vehicles, and each of the flight sets corresponding to the vehicles includes at least one flight;

[0086] In the method provided by the embodiment of the present invention, each scheduling set can be determined based on the priority parameter set corresponding to each vehicle, and each scheduling set represents a scheduling arrangement for each vehicle, which includes a flight set corresponding to each vehicle, that is, the vehicle is assigned to each flight in its corresponding flight set. Each scheduling set can be determined based on the priority parameters corresponding to each vehicle and the feasibility of complying with the scheduling rules. That is, each vehicle is assigned to a flight with a relatively high priority represented by its corresponding priority parameter, and there is no time conflict between the flights assigned to the vehicle. In the same scheduling set, the flight sets between vehicles do not conflict, that is, it is guaranteed that each flight can be assigned the required number of vehicles.

[0087] Determine the fitness corresponding to each of the scheduling sets;

[0088] In the method provided in the embodiment of the present invention, the fitness corresponding to each scheduling set can be determined based on the scheduling arrangement corresponding to each scheduling set and based on a preset evaluation function. The evaluation function can be customized according to actual needs, that is, the parameters used as the fitness can be selected according to actual needs. For example, the driving distance of the vehicle can be used as an evaluation, and the minimum driving distance can be used as a goal. Then, the fitness corresponding to each scheduling set is the sum of the driving distances of the vehicles under the scheduling arrangement corresponding to the scheduling set.

[0089] Determine a target scheduling set from among the scheduling sets according to the preset tabu search algorithm and the fitness corresponding to each of the scheduling sets;

[0090] In the method provided in the embodiment of the present invention, based on the fitness corresponding to each scheduling set, an iterative optimization can be performed in each scheduling set according to a preset tabu search algorithm, so that the optimization result is used as the target scheduling set.

[0091] The taboo search algorithm is a global neighborhood search algorithm. The algorithm starts from a given initial solution and searches for the best solution in the neighborhood based on certain rules. The taboo search algorithm records the searched paths and the generated local optimal solutions by establishing a taboo table. In the iterative optimization process of the algorithm, these objects are avoided as much as possible, thereby reducing repeated iterative searches, effectively ensuring the optimization of different search solutions, and improving the optimization efficiency of the algorithm. The following is a brief description of the relevant concepts in the taboo search algorithm:

[0092] Neighborhood: generally refers to the set of nodes in the problem domain obtained by transforming each vertex in the specified problem domain based on given rules.

[0093] Candidate solution: A solution evaluated based on the objective function in the current neighborhood.

[0094] Taboo table: records the current optimal candidate solution of the algorithm iteration process. The elements in the taboo table will not be referenced in the next search process.

[0095] Taboo length: It is forbidden to modify the taboo table during k iterations within the taboo length range.

[0096] Contempt criterion: Select the best candidate solution from each candidate solution and compare it with the current best solution.

[0097] Evaluation function: a function that evaluates the quality of a solution.

[0098] Next, combine Figure 4 The method flow chart shown briefly illustrates the processing process of the taboo search algorithm in the embodiment of the present invention, including:

[0099] S301: Initialize the taboo table and determine the taboo length;

[0100] S302: Generate an initial solution and determine its fitness function value;

[0101] In the process of applying the tabu search algorithm in the method provided by the embodiment of the present invention, each solution refers to each scheduling scheme, that is, each scheduling set.

[0102] According to the greedy strategy, a first scheduling set can be determined from various scheduling sets, the first scheduling set can be used as an initial solution of the taboo search algorithm, and the fitness corresponding to the first scheduling set can be used as its corresponding fitness function value.

[0103] During the first iteration of the taboo search algorithm, the current global optimal solution is also the initial solution.

[0104] S303: Neighborhood search generates candidate solutions;

[0105] In the method provided by the embodiment of the present invention, the current global optimal solution is taken as the center, and a search is performed in its neighborhood to obtain various candidate solutions corresponding to the global optimal solution.

[0106] S304: Determine the optimal solution among the candidate solutions, and judge whether the optimal solution is better than the current global optimal solution;

[0107] In the method provided by the embodiment of the present invention, the fitness corresponding to each candidate solution corresponding to the current global optimal solution can be determined, and the optimal solution among the candidate solutions can be determined based on the fitness, that is, the solution with the best degree of preference represented by the fitness among the candidate solutions. The fitness of the optimal solution is compared with the fitness of the current global optimal solution. If the fitness of the optimal solution is better than the fitness of the current global optimal solution, it is determined that the optimal solution is better than the current global optimal solution, and step S305 is entered, otherwise, step S306 is entered.

[0108] S305: Selecting the best solution among the candidate solutions;

[0109] In the method provided by the embodiment of the present invention, if the optimal solution among the candidate solutions corresponding to the current global optimal solution is better than the current global optimal solution, the optimal solution among the candidate solutions is taken as the selection target.

[0110] S306: Selecting the optimal solution that is not tabooed among the candidate solutions;

[0111] In the method provided by the embodiment of the present invention, if the optimal solution among the candidate solutions corresponding to the current global optimal solution is not better than the current global optimal solution, the optimal solution that is not taboo among all the candidate solutions searched by the current algorithm is selected as the target. It should be noted that the candidate solutions in this step refer to all the candidate solutions currently searched, not limited to the candidate solutions in the neighborhood of the current global optimal solution.

[0112] S307: Update the current global optimal solution based on the selected solution and update the taboo table;

[0113] In the method provided by the embodiment of the present invention, the currently selected target, that is, the optimal solution among the currently selected candidate solutions, can be used as a new global optimal solution to update the current global optimal solution, and the new global optimal solution can be added to the taboo table to update the taboo table.

[0114] S308: Determine whether the number of iteration terminations has been reached;

[0115] In the method provided by the embodiment of the present invention, the search iteration termination number can be preset, and the current iteration number is compared with a preset threshold to determine whether the iteration termination number has been reached. If the iteration termination number has been reached, the process proceeds to step S309.

[0116] If the number of iteration termination times has not been reached, the process returns to step S303 and enters the search process of the next iteration cycle, and uses the new global optimal solution obtained in the current iteration cycle as the current global optimal solution in the next iteration cycle.

[0117] S309: End.

[0118] When the number of iteration terminations is reached, the search process ends and the current global optimal solution is used as the optimal solution for the final output. That is, the scheduling set corresponding to the current global optimal solution is the target scheduling set.

[0119] The flight set corresponding to each of the vehicles in the target scheduling set is used as the target flight set corresponding to each of the vehicles; and each flight in the target flight set corresponding to each of the vehicles is used as the transport flight corresponding to the vehicle.

[0120] In the method provided by the embodiment of the present invention, each flight in the flight set corresponding to each vehicle in the target scheduling set finally output by the taboo search algorithm can be assigned to the vehicle corresponding to the flight set, that is, the flight set corresponding to each vehicle in the target scheduling set is the transport flight set of each vehicle, and each vehicle needs to undertake the passenger transportation task of each flight in its transport flight set.

[0121] Furthermore, the process of determining the fitness corresponding to each scheduling set mentioned in the method provided in the above embodiment includes:

[0122] The vehicle driving distance corresponding to each of the scheduling sets is determined, and the vehicle driving distance corresponding to each of the scheduling sets is used as the fitness corresponding to the scheduling set.

[0123] In the method provided by the embodiment of the present invention, for each scheduling set, the dynamic driving distance of each vehicle in the process of performing the transportation task of its corresponding flight set can be determined based on the flight set corresponding to each vehicle, that is, the sum of the distances that the vehicle needs to travel in the process of completing all flight transportation tasks. For each scheduling set, the dynamic driving distances of each vehicle obtained based on the flight set of each vehicle, that is, the corresponding scheduling arrangement, can be added, and the sum of the dynamic driving distances of all vehicles can be used as the vehicle driving distance corresponding to the scheduling set. The vehicle driving distance corresponding to each scheduling set is used as the fitness corresponding to each scheduling set. The specific evaluation function used to calculate the fitness can be designed based on the calculation of the vehicle driving distance.

[0124] Based on the method provided in the embodiment of the present invention, the distance traveled by the vehicle can be used as a parameter to evaluate the quality of the scheduling scheme. The distance traveled by the vehicle represents the running time of the vehicle. With the goal of saving time, work efficiency can be further improved, which is conducive to improving the utilization rate of vehicle resources. The calculation is relatively simple, which can further improve processing efficiency.

[0125] Although operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.

[0126] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0127] and Figure 1 Corresponding to the vehicle dispatching method shown in FIG. 1 , the embodiment of the present invention further provides a vehicle dispatching device for dispatching Figure 1 The specific implementation of the method shown in the embodiment of the present invention is that the vehicle dispatching device provided by the embodiment of the present invention can be applied to a computer terminal or various mobile devices, and its structural schematic diagram is as follows Figure 5 As shown, including:

[0128] The first determining unit 401 is used to determine each flight to which vehicles need to be allocated when receiving a trigger instruction for scheduling each vehicle;

[0129] A second determining unit 402 is used to determine a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights;

[0130] A third determining unit 403 is used to determine a priority parameter set corresponding to each of the vehicles based on the scheduling information set, wherein the priority parameter set corresponding to each of the vehicles includes multiple priority parameters, and the multiple priority parameters correspond to each of the flights one by one;

[0131] The fourth determining unit 404 is used to determine each transport flight corresponding to each of the vehicles in each of the flights according to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, so as to schedule each of the vehicles.

[0132] Based on the device provided by the embodiment of the present invention, when it is necessary to dispatch each vehicle, each flight to which the vehicle needs to be assigned can be determined, and the dispatch information set corresponding to each vehicle and each flight can be determined. Based on the dispatch information set, the priority parameter set corresponding to each vehicle and each flight can be determined. According to the priority parameter set corresponding to each vehicle and the preset taboo search algorithm, each transport flight corresponding to each vehicle is determined in each flight to dispatch each vehicle. By applying the device provided by the embodiment of the present invention, a relatively good dispatching scheme can be quickly obtained by combining the global information of all vehicles and all flights, without the need for manual dispatching, and the limitations of manual dispatching can be avoided. The overall dispatching effect is good, which is conducive to ensuring that each vehicle can transport passengers to and from the terminal in a timely manner to ensure that passengers can board or disembark normally, which is conducive to ensuring passenger safety and improving passenger service experience. In addition, human resources for manual dispatching can also be saved, and airport operating costs can be reduced.

[0133] On the basis of the above device, in the device provided by the embodiment of the present invention, the third determining unit 403 includes:

[0134] A first determining subunit is used to determine a first score set corresponding to each of the vehicles according to a preset dispatch rule and the dispatch information set, wherein the first score set corresponding to each of the vehicles includes a plurality of scores, the plurality of scores correspond to the respective flights one by one, and the plurality of scores represent the allocation priority of the vehicle corresponding to the respective flights;

[0135] An input subunit, used for inputting each information in the scheduling information set into the established neural network model, and obtaining a probability set corresponding to each vehicle after being processed by the neural network model, wherein the probability set corresponding to each vehicle includes multiple probabilities, and the multiple probabilities correspond to each flight one by one;

[0136] The second determining subunit is used to determine the priority parameter set corresponding to each of the vehicles according to the first score set corresponding to each of the vehicles and the probability set corresponding to each of the vehicles.

[0137] On the basis of the above device, in the device provided by an embodiment of the present invention, the first determining subunit includes:

[0138] A third determining subunit is used to determine a second score set corresponding to each of the vehicles, wherein the second score set corresponding to each of the vehicles includes a conversion score corresponding to each probability in the probability set corresponding to the vehicle;

[0139] A fourth determining subunit is used to determine, for each of the vehicles, a one-to-one correspondence between each score in the first score set corresponding to the vehicle and each conversion score in the second score set corresponding to the vehicle;

[0140] an operation subunit, configured to perform a weighted sum operation on each score in the first score set corresponding to each vehicle and the conversion score corresponding to the score, and use the operation result as the final score corresponding to the score;

[0141] The fifth determination subunit is used to determine the final scores corresponding to the scores in the first score set corresponding to each of the vehicles as the priority parameters corresponding to the vehicle, and to form the priority parameter set corresponding to the vehicle with the priority parameters corresponding to the vehicle.

[0142] On the basis of the above device, the device provided in the embodiment of the present invention further includes:

[0143] An acquisition unit, used to acquire historical scheduling data and determine a training data set corresponding to the historical scheduling data;

[0144] A training unit is used to input each training sample in the training data set into a pre-built deep neural network model, train the deep neural network model, and use the trained deep neural network model as the neural network model.

[0145] On the basis of the above device, in the device provided by the embodiment of the present invention, the acquisition unit includes:

[0146] A preprocessing subunit, used for performing data preprocessing on the historical scheduling data to obtain processed historical scheduling data;

[0147] The feature processing subunit is used to perform feature engineering processing based on the processed historical scheduling data to obtain various training samples, and form the various training samples into the training data set.

[0148] On the basis of the above device, in the device provided by the embodiment of the present invention, the fourth determining unit 404 includes:

[0149] a sixth determining subunit, configured to determine each scheduling set according to the priority parameter set corresponding to each of the vehicles, each of the scheduling sets including a flight set corresponding to each of the vehicles, and each of the flight sets corresponding to the vehicles including at least one flight;

[0150] A seventh determination subunit, configured to determine the fitness corresponding to each of the scheduling sets;

[0151] an eighth determination subunit, configured to determine a target scheduling set from among the scheduling sets according to the preset taboo search algorithm and the fitness corresponding to each of the scheduling sets;

[0152] The ninth determination subunit is used to use the flight set corresponding to each of the vehicles in the target scheduling set as the target flight set corresponding to each of the vehicles; and use each flight in the target flight set corresponding to each of the vehicles as the transport flight corresponding to the vehicle.

[0153] On the basis of the above device, in the device provided by the embodiment of the present invention, the seventh determining subunit includes:

[0154] The tenth determining subunit is used to determine the vehicle driving distance corresponding to each of the scheduling sets, and use the vehicle driving distance corresponding to each of the scheduling sets as the fitness corresponding to the scheduling set.

[0155] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0156] The embodiment of the present invention also provides an electronic device for a vehicle dispatching method, and its structural diagram is shown in FIG. Figure 6 As shown, Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0157] like Figure 6 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0158] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 506 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0159] An embodiment of the present invention further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned vehicle scheduling method.

[0160] The storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: when receiving a trigger instruction for scheduling each vehicle, determines each flight to which the vehicle needs to be assigned; determines a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights; based on the scheduling information set, determines a priority parameter set corresponding to each of the vehicles, wherein the priority parameter set corresponding to each of the vehicles includes multiple priority parameters, and the multiple priority parameters correspond one-to-one to each of the flights; and according to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, determines each of the transport flights corresponding to each of the vehicles in each of the flights to schedule the vehicles.

[0161] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

[0162] Although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present invention. Certain features described in the context of a separate embodiment may also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0163] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

[0164] In the detailed description section, this application repeats all the contents protected in the form of claims in the following form:

[0165] According to one or more embodiments disclosed in this application, Figure 1A vehicle scheduling method is provided, comprising: when a trigger instruction for scheduling each vehicle is received, determining each flight to which the vehicle needs to be assigned; determining a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights; based on the scheduling information set, determining a priority parameter set corresponding to each of the vehicles, wherein the priority parameter set corresponding to each of the vehicles includes a plurality of priority parameters, and the plurality of priority parameters correspond to each of the flights one-to-one; and determining, in each of the flights, each transport flight corresponding to each of the vehicles according to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, so as to schedule each of the vehicles.

[0166] According to one or more embodiments disclosed in this application, Figure 2 Another vehicle scheduling method is provided, comprising: determining a first score set corresponding to each of the vehicles according to a preset scheduling rule and the scheduling information set, the first score set corresponding to each of the vehicles including a plurality of scores, the plurality of scores corresponding one-to-one to each of the flights, and the plurality of scores representing the allocation priority of the vehicle corresponding to each of the flights; inputting each information in the scheduling information set into an established neural network model, obtaining a probability set corresponding to each of the vehicles after being processed by the neural network model, the probability set corresponding to each of the vehicles including a plurality of probabilities, the plurality of probabilities corresponding one-to-one to each of the flights; and determining a priority parameter set corresponding to each of the vehicles according to the first score set corresponding to each of the vehicles and the probability set corresponding to each of the vehicles.

[0167] Determine a second score set corresponding to each of the vehicles, wherein the second score set corresponding to each of the vehicles includes conversion scores corresponding to each probability in the probability set corresponding to the vehicle; for each of the vehicles, determine a one-to-one correspondence between each score in the first score set corresponding to the vehicle and each conversion score in the second score set corresponding to the vehicle; for each score in the first score set corresponding to each of the vehicles, perform a weighted sum operation on the score and the conversion score corresponding to the score, and use the operation result as the final score corresponding to the score; determine the final scores corresponding to each score in the first score set corresponding to each of the vehicles as the priority parameters corresponding to the vehicle, and form the priority parameter set corresponding to the vehicle with the priority parameters corresponding to the vehicle.

[0168] Obtain historical scheduling data and determine a training data set corresponding to the historical scheduling data; input each training sample in the training data set into a pre-built deep neural network model, train the deep neural network model, and use the trained deep neural network model as the neural network model.

[0169] The historical scheduling data is preprocessed to obtain processed historical scheduling data; feature engineering is performed based on the processed historical scheduling data to obtain various training samples, and the various training samples are combined into the training data set.

[0170] Determine each scheduling set based on the priority parameter set corresponding to each of the vehicles, each of the scheduling sets includes a flight set corresponding to each of the vehicles, and each of the flight sets corresponding to the vehicles includes at least one flight; determine the fitness corresponding to each of the scheduling sets; determine a target scheduling set in each of the scheduling sets according to the preset taboo search algorithm and the fitness corresponding to each of the scheduling sets; use the flight set corresponding to each of the vehicles in the target scheduling set as the target flight set corresponding to each of the vehicles; use each flight in the target flight set corresponding to each of the vehicles as the transport flight corresponding to the vehicle.

[0171] The vehicle driving distance corresponding to each of the scheduling sets is determined, and the vehicle driving distance corresponding to each of the scheduling sets is used as the fitness corresponding to the scheduling set.

[0172] According to one or more embodiments disclosed in this application, Figure 5 A vehicle scheduling device is provided, comprising: a first determining unit, for determining each flight to which a vehicle needs to be assigned when a trigger instruction for scheduling each vehicle is received; a second determining unit, for determining a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights; a third determining unit, for determining a priority parameter set corresponding to each of the vehicles based on the scheduling information set, wherein the priority parameter set corresponding to each of the vehicles includes a plurality of priority parameters, and the plurality of priority parameters correspond one-to-one to each of the flights; and a fourth determining unit, for determining, in each of the flights, each of the transport flights corresponding to each of the vehicles, based on the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, so as to schedule each of the vehicles.

[0173] According to one or more embodiments disclosed in the present application, the present application provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned vehicle scheduling method.

[0174] According to one or more embodiments disclosed in this application, Figure 6 An electronic device is provided, comprising a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to execute the above-mentioned vehicle dispatching method.

Claims

1. A vehicle dispatching method, characterized in that: include: When a trigger instruction for scheduling each vehicle is received, each flight to which the vehicle needs to be allocated is determined; Determine a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights; Based on the scheduling information set, determining a priority parameter set corresponding to each of the vehicles, wherein the priority parameter set corresponding to each of the vehicles includes a plurality of priority parameters, and the plurality of priority parameters correspond to each of the flights one by one; According to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, in each of the flights, each of the transport flights corresponding to each of the vehicles is determined to schedule each of the vehicles; Determining the priority parameter set corresponding to each of the vehicles based on the scheduling information set includes: determining a first score set corresponding to each of the vehicles according to a preset scheduling rule and the scheduling information set, wherein the first score set corresponding to each of the vehicles includes a plurality of scores, and the plurality of scores correspond one-to-one to each of the flights, and the plurality of scores represent the allocation priority of the vehicle corresponding to each of the flights; inputting each of the information in the scheduling information set into an established neural network model, and obtaining a probability set corresponding to each of the vehicles after being processed by the neural network model, wherein the probability set corresponding to each of the vehicles includes a plurality of probabilities, and the plurality of probabilities correspond one-to-one to each of the flights; determining a priority parameter set corresponding to each of the vehicles according to the first score set corresponding to each of the vehicles and the probability set corresponding to each of the vehicles; The method of determining a priority parameter set corresponding to each vehicle based on a first score set corresponding to each vehicle and a probability set corresponding to each vehicle includes: determining a second score set corresponding to each vehicle, wherein the second score set corresponding to each vehicle includes conversion scores corresponding to each probability in the probability set corresponding to the vehicle; for each vehicle, determining a one-to-one correspondence between each score in the first score set corresponding to the vehicle and each conversion score in the second score set corresponding to the vehicle; for each score in the first score set corresponding to each vehicle, performing a weighted sum operation on the score and the conversion score corresponding to the score, and using the operation result as the final score corresponding to the score; determining the final scores corresponding to each score in the first score set corresponding to each vehicle as the priority parameters corresponding to the vehicle, and forming the priority parameter set corresponding to the vehicle with the priority parameters corresponding to the vehicle.

2. The method according to claim 1, characterized in that The process of establishing the neural network model includes: Acquire historical scheduling data, and determine a training data set corresponding to the historical scheduling data; Each training sample in the training data set is input into a pre-built deep neural network model, the deep neural network model is trained, and the trained deep neural network model is used as the neural network model.

3. The method according to claim 2, characterized in that The determining of the training data set corresponding to the historical scheduling data includes: Performing data preprocessing on the historical scheduling data to obtain processed historical scheduling data; Feature engineering processing is performed based on the processed historical scheduling data to obtain various training samples, and the various training samples are combined into the training data set.

4. The method according to claim 1, characterized in that: The step of determining each transport flight corresponding to each vehicle in each flight according to the priority parameter set corresponding to each vehicle and a preset taboo search algorithm includes: Determine each scheduling set according to the priority parameter set corresponding to each of the vehicles, each of the scheduling sets includes a flight set corresponding to each of the vehicles, and each of the flight sets corresponding to the vehicles includes at least one flight; Determine the fitness corresponding to each of the scheduling sets; Determine a target scheduling set from among the scheduling sets according to the preset tabu search algorithm and the fitness corresponding to each of the scheduling sets; The flight set corresponding to each of the vehicles in the target scheduling set is used as the target flight set corresponding to each of the vehicles; Each flight in the target flight set corresponding to each of the vehicles is used as a transport flight corresponding to the vehicle.

5. The method according to claim 4, characterized in that The determining the fitness corresponding to each of the scheduling sets includes: The vehicle driving distance corresponding to each of the scheduling sets is determined, and the vehicle driving distance corresponding to each of the scheduling sets is used as the fitness corresponding to the scheduling set.

6. A vehicle dispatching device, characterized in that: include: A first determining unit is used to determine each flight to which vehicles need to be allocated when receiving a trigger instruction for scheduling each vehicle; A second determining unit, configured to determine a scheduling information set, wherein the scheduling information set includes vehicle information of each of the vehicles and flight information of each of the flights; A third determining unit is used to determine a priority parameter set corresponding to each of the vehicles based on the scheduling information set, wherein the priority parameter set corresponding to each of the vehicles includes a plurality of priority parameters, and the plurality of priority parameters correspond to each of the flights one by one; a fourth determining unit, configured to determine, in each of the flights, the respective transport flights corresponding to each of the vehicles according to the priority parameter set corresponding to each of the vehicles and a preset taboo search algorithm, so as to schedule each of the vehicles; Determining the priority parameter set corresponding to each of the vehicles based on the scheduling information set includes: determining a first score set corresponding to each of the vehicles according to a preset scheduling rule and the scheduling information set, wherein the first score set corresponding to each of the vehicles includes a plurality of scores, and the plurality of scores correspond one-to-one to each of the flights, and the plurality of scores represent the allocation priority of the vehicle corresponding to each of the flights; inputting each of the information in the scheduling information set into an established neural network model, and obtaining a probability set corresponding to each of the vehicles after being processed by the neural network model, wherein the probability set corresponding to each of the vehicles includes a plurality of probabilities, and the plurality of probabilities correspond one-to-one to each of the flights; determining a priority parameter set corresponding to each of the vehicles according to the first score set corresponding to each of the vehicles and the probability set corresponding to each of the vehicles; The method of determining a priority parameter set corresponding to each vehicle based on a first score set corresponding to each vehicle and a probability set corresponding to each vehicle includes: determining a second score set corresponding to each vehicle, wherein the second score set corresponding to each vehicle includes conversion scores corresponding to each probability in the probability set corresponding to the vehicle; for each vehicle, determining a one-to-one correspondence between each score in the first score set corresponding to the vehicle and each conversion score in the second score set corresponding to the vehicle; for each score in the first score set corresponding to each vehicle, performing a weighted sum operation on the score and the conversion score corresponding to the score, and using the operation result as the final score corresponding to the score; determining the final scores corresponding to each score in the first score set corresponding to each vehicle as the priority parameters corresponding to the vehicle, and forming the priority parameter set corresponding to the vehicle with the priority parameters corresponding to the vehicle.

7. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the vehicle dispatching method according to any one of claims 1 to 5.

Images