Vehicle scheduling method and device

Through the combination of hybrid group intelligent algorithms, particle group and genetic algorithms, the scheduling plan of AGV vehicles is optimized, the problem of inflexible AGV scheduling in the existing technology is solved, and the flexible scheduling and resource efficiency improvement of various AGV models is achieved.

CN119067334APending Publication Date: 2024-12-03BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310651217.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-06-02
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing AGV application solutions can only plan individual shelves in different scenarios of picking volume requirements of storage shelves, and cannot flexibly schedule multiple AGV models, resulting in limited resource integration and efficiency improvement.

Method used

A hybrid group intelligent algorithm is used to generate a collection of vehicle scheduling plans, and a transportation cost and fixed cost function is constructed through decision variables. It combines particle swarm and genetic algorithm for iterative calculations, optimizes the vehicle path and location to achieve flexible scheduling of multiple AGV models.

Benefits of technology

It realizes vehicle scheduling in multiple AGV models and multi-destination scenarios, quickly obtains vehicle scheduling plans, improves resource integration and efficiency, and meets actual needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067334A_ABST
    Figure CN119067334A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle scheduling method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: in response to a scheduling request, obtaining vehicle information of a to-be-scheduled vehicle and information of at least one destination; generating a vehicle scheduling plan set according to the vehicle information and the destination information; and inputting the vehicle scheduling plan set into a pre-constructed planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan. According to the embodiment of the invention, an AGV vehicle scheduling scheme suitable for a multi-destination scene of multiple AGV models is realized, the vehicle scheduling plan can be rapidly obtained by using the hybrid swarm intelligence algorithm, each AGV model is flexibly scheduled, and resource integration and efficiency improvement are facilitated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a vehicle dispatching method and device. Background Art

[0002] In modern industrial automated logistics warehousing systems, automatic picking robots (AGVs) have been widely used as mobile robots with high automation, good flexibility and strong anti-interference ability. At present, in unmanned warehouses, single-function AGV models are usually used to pick goods on a certain shelf. The path planning of a single AGV model is carried out by using the A* algorithm or biological intelligence-inspired algorithms, such as the traditional particle swarm algorithm or genetic algorithm.

[0003] In the process of implementing the present invention, the inventors found that the prior art has the following problems:

[0004] The existing AGV application solutions can only plan each shelf individually in scenarios with different picking volume requirements on storage shelves, and cannot flexibly dispatch multiple AGV models, which is not conducive to resource integration and efficiency improvement, and cannot meet actual needs. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method and device for vehicle scheduling, which generates a vehicle scheduling plan set based on received vehicle information and at least one destination information, and selects a vehicle scheduling plan that meets the model requirements from the vehicle scheduling plan set based on a pre-built planning model using a hybrid swarm intelligence algorithm. An AGV vehicle scheduling solution suitable for multiple AGV models and multiple destinations is implemented. By using a hybrid swarm intelligence algorithm, a vehicle scheduling plan can be quickly obtained to flexibly schedule each AGV model, which is conducive to resource integration and efficiency improvement.

[0006] To achieve the above object, according to one aspect of an embodiment of the present invention, a vehicle scheduling method is provided, comprising:

[0007] In response to the dispatch request, obtaining vehicle information and at least one destination information of the vehicle to be dispatched;

[0008] Generate a vehicle dispatch plan set according to the vehicle information and the destination information;

[0009] The vehicle dispatch plan set is input into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle dispatch plan.

[0010] Optionally, before generating a vehicle scheduling plan set based on the vehicle information and the destination information, it also includes: constructing decision variables that characterize the vehicle usage status, the decision variables including the vehicle identification, the path starting point and the path destination; generating a vehicle scheduling plan set based on the vehicle information and the destination information, including: using the decision variables based on the vehicle identification in the vehicle information, the destination information, and the starting point information of the vehicle to be scheduled to obtain the vehicle scheduling plan set for the vehicle to be scheduled.

[0011] Optionally, the objective function of the planning model is constructed in the following manner: through the decision variables, the transportation cost function and the fixed cost function of the vehicle are established; according to the waypoints set in the path from the vehicle starting point to the vehicle destination, the turning angle sum function of the path is established; according to the transportation cost function, the fixed cost function and the turning angle sum function, the objective function is obtained; based on the objective function, constraint conditions are established, and the constraint conditions include: vehicle usage quantity constraint, vehicle starting point and end point location constraint, vehicle scheduling rule constraint, and vehicle load constraint.

[0012] Optionally, the vehicle scheduling plan set is input into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan, including: initializing the parameters of the planning model; clustering and grouping the vehicle scheduling plan set based on the input vehicle scheduling plan set to obtain at least one group of vehicle scheduling plan subpopulations; when the number of iterations is less than a preset maximum number of iterations, looping the following iterative calculations until the number of iterations reaches the maximum number of iterations, and selecting a global optimal solution from the vehicle scheduling plan solutions obtained from all iterative calculations as the vehicle scheduling plan: using a particle swarm algorithm to calculate individual optimal solutions and global optimal solutions for each group of vehicle scheduling subpopulations to obtain a vehicle scheduling plan solution; and performing a first update on the speed and position information of all vehicles based on the individual optimal solutions and the global optimal solutions.

[0013] Optionally, based on a distributed parallel framework, the vehicle scheduling plan set is input into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

[0014] Optionally, a particle swarm algorithm is used to calculate an individual optimal solution and a global optimal solution for each group of vehicle scheduling subpopulations, including: adjusting the individual inertia coefficient and acceleration factor of each group of vehicle scheduling subpopulations according to the individual fitness value of each group of vehicle scheduling subpopulations to obtain the adaptive inertia coefficient and adaptive acceleration factor of the individuals in each group of vehicle scheduling subpopulations; and using a particle swarm algorithm, in combination with the adaptive inertia coefficient and the adaptive acceleration factor, to calculate the individual optimal solution and the global optimal solution.

[0015] Optionally, based on the individual optimal solution and the global optimal solution, the speed and position information of all vehicles are first updated, including: based on the individual optimal solution and the global optimal solution, obtaining first speed update information and second speed update information of all vehicles by a particle swarm algorithm and a clustering algorithm respectively; obtaining speed update information of all vehicles based on the first speed update information and the second speed update information; obtaining position update information of all vehicles based on the speed update information of all vehicles.

[0016] Optionally, after a first update is performed on the speed and position information of all vehicles according to the individual optimal solution and the global optimal solution, the method further includes: introducing a selection crossover operator and a mutation operator of a genetic algorithm into each group of vehicle scheduling subpopulations to perform a second update on the position information of all vehicles after the first update.

[0017] Optionally, a selection crossover operator and a mutation operator of a genetic algorithm are introduced into each group of vehicle scheduling subpopulations to perform a second update on the location information of all vehicles after the first update, including: using an activation function to adjust the individual selection probability, crossover probability and mutation probability introduced into each group of vehicle scheduling subpopulations according to the individual fitness values ​​of each group of vehicle scheduling subpopulations to obtain the adaptive selection probability, adaptive crossover probability and adaptive mutation probability of the individuals in each group of vehicle scheduling subpopulations; and performing a second update on the location information of all vehicles after the first update according to the adaptive selection probability, adaptive crossover probability and adaptive mutation probability.

[0018] Optionally, after performing a second update on the location information of all vehicles after the first update, the method further includes: introducing a deletion operation operator, a reversal operation operator and a cloning operation operator of a genetic algorithm into each group of vehicle scheduling subpopulations, and performing a third update on the location information of all vehicles after the second update.

[0019] Optionally, after obtaining the vehicle dispatch plan, the method includes: obtaining a planned path of the vehicle according to the vehicle dispatch plan.

[0020] According to a second aspect of an embodiment of the present invention, there is provided a vehicle dispatching device, comprising:

[0021] An information acquisition module, used for acquiring vehicle information and at least one destination information of a vehicle to be dispatched in response to a dispatch request;

[0022] A scheduling plan set generating module, used for generating a vehicle scheduling plan set according to the vehicle information and the destination information;

[0023] The scheduling plan acquisition module is used to input the vehicle scheduling plan set into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

[0024] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for vehicle dispatching, comprising:

[0025] one or more processors;

[0026] a storage device for storing one or more programs,

[0027] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0028] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0029] An embodiment of the invention has the following advantages or beneficial effects: by responding to a dispatch request, obtaining vehicle information and at least one destination information of the vehicle to be dispatched; generating a vehicle dispatch plan set based on the vehicle information and destination information; inputting the vehicle dispatch plan set into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a technical solution for a vehicle dispatch plan, realizing the generation of a vehicle dispatch plan set based on the received vehicle information and at least one destination information, and selecting a vehicle dispatch plan that meets the model requirements from the vehicle dispatch plan set based on the pre-built planning model obtained using a hybrid swarm intelligence algorithm. The method provided by the embodiment of the present invention provides an AGV vehicle dispatch plan suitable for multiple AGV models and multiple destination scenarios. By using a hybrid swarm intelligence algorithm, a vehicle dispatch plan can be quickly obtained to flexibly dispatch each AGV model, which is conducive to resource integration and efficiency improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0031] Figure 1 is a schematic diagram of the main process of the vehicle scheduling method according to an embodiment of the present invention;

[0032] Figure 2 It is a detailed flow chart of determining a vehicle dispatching plan by using a hybrid swarm intelligence algorithm according to an embodiment of the present invention;

[0033] Figure 3 is a schematic diagram of main modules of a vehicle dispatching device according to an embodiment of the present invention;

[0034] Figure 4 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0035] Figure 5 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0036] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0037] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0038] In modern industrial automated logistics warehousing systems, existing AGV application solutions can only plan each shelf individually in scenarios with different picking volume requirements on storage shelves. They cannot make overall coordinated plans, nor can they flexibly dispatch AGVs, which is not conducive to resource integration and efficiency improvement, and cannot meet actual needs.

[0039] In order to solve the above problems existing in the prior art, the present invention proposes a vehicle scheduling method, which generates a vehicle scheduling plan set based on the received vehicle information and at least one destination information; based on the pre-built planning model obtained by using the hybrid swarm intelligence algorithm, a vehicle scheduling plan that meets the model requirements is selected from the vehicle scheduling plan set. An AGV vehicle scheduling solution suitable for multiple AGV models and multiple destinations is implemented. By using the hybrid swarm intelligence algorithm, the vehicle scheduling plan can be quickly obtained to flexibly schedule each AGV model, which is conducive to resource integration and efficiency improvement.

[0040] In the introduction to the embodiments of the present invention, the terms and their meanings are as follows:

[0041] A* algorithm: A* (A-Star) algorithm is the most effective direct search method for solving the shortest path in a static road network, and is also an effective algorithm for solving many search problems;

[0042] keyBy: logically splits a stream into disjoint partitions, each containing elements with the same key, implemented internally in the form of hashing;

[0043] iterate: an iterative operation operator;

[0044] set Parallelism: The number of subtasks of a particular operator is called its parallelism. In general, the parallelism of a stream program can be considered as the maximum parallelism among all its operators.

[0045] Figure 1 Schematic diagram of the main process of the vehicle dispatching method according to an embodiment of the present invention. Figure 1 As shown, the vehicle dispatching method of the embodiment of the present invention includes the following steps S101 to S103.

[0046] Step S101: In response to a dispatch request, obtain vehicle information and at least one destination information of a vehicle to be dispatched.

[0047] Specifically, in the scenario of multiple AGV models and multiple target shelves, according to the dispatch request of the received vehicle, the vehicle information of the vehicle to be dispatched is obtained, which may specifically include the model information of the AGV vehicle to be dispatched, the number of each model of AGV vehicles to be dispatched, and multiple destination information, that is, the target shelves for AGV picking. The vehicle identification of the vehicle to be dispatched can be determined according to the model information of the AGV vehicle to be dispatched and the number of each model of AGV vehicles to be dispatched.

[0048] Step S102: Generate a vehicle dispatch plan set according to the vehicle information and the destination information.

[0049] According to one embodiment of the present invention, before generating a vehicle dispatch plan set according to the vehicle information and the destination information, it also includes: constructing decision variables characterizing the vehicle usage status, the decision variables including the vehicle identification, the path starting point and the path destination.

[0050] Specifically, a decision variable representing the vehicle usage status (used or not used) is constructed. In the embodiment of the present invention, As decision variables, the specific explanation is shown in Table 1:

[0051] Table 1

[0052]

[0053] The usage status of each vehicle type can be characterized through decision variables, which facilitates the construction and solution of subsequent planning models.

[0054] According to another embodiment of the present invention, a vehicle scheduling plan set is generated based on the vehicle information and the destination information, including: based on the vehicle identification in the vehicle information, the destination information, combined with the starting point information of the vehicle to be scheduled, using the decision variables, to obtain the vehicle scheduling plan set for the vehicle to be scheduled.

[0055] Specifically, in the embodiment of the present invention, it is set that all AGV vehicles to be dispatched start from the same starting point and eventually return to the starting point. AGV vehicles can return to the starting point after only going from the starting point to a destination, or they can go from the starting point to a destination, and then start from the destination to reach the next destination and return to the starting point. The starting point is the starting point of the first path, and when the AGV goes to multiple destinations to pick up goods, multiple paths need to be involved, and the destination of the previous path is the starting point of the next path. According to the vehicle information of the vehicle to be dispatched in the received dispatch request and at least one destination, the decision variables constructed above are used to combine and summarize each possible use state of all the vehicles to be dispatched to obtain the vehicle dispatch plan of all the vehicles to be dispatched. In the process of combining and summarizing each possible use state of all the vehicles to be dispatched, screening can also be performed to filter out impossible combinations to obtain a more feasible vehicle dispatch plan for all the vehicles to be dispatched; finally, the dispatch plans of all the vehicles to be dispatched are merged to obtain a set of vehicle dispatch plans for all the vehicles to be dispatched.

[0056] Step S103: input the vehicle scheduling plan set into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

[0057] According to one embodiment of the present invention, the objective function of the planning model is constructed in the following manner: through the decision variables, the transportation cost function and the fixed cost function of the vehicle are established; according to the waypoints set in the path from the vehicle starting point to the vehicle destination, the turning angle sum function of the path is established; according to the transportation cost function, the fixed cost function and the turning angle sum function, the objective function is obtained; based on the objective function, constraint conditions are established, and the constraint conditions include: vehicle usage quantity constraint, vehicle starting point and end point location constraint, vehicle scheduling rule constraint, and vehicle load constraint.

[0058] Specifically, according to the scenario of multi-AGV models and multi-objective shelves in the embodiment of the present invention, a MVMOPP (MultiVehicle Multi-Objective Path Planning) multi-model multi-objective path planning model is established. In order to minimize the total picking cost (including AGV transportation cost), make the motion trajectory of the AGV smooth enough, reduce the mechanical wear of the AGV, and ensure that the AGV can travel smoothly, the objective function of the planning model is constructed. According to the set of determined starting points (parking areas) and destinations, the set of AGV models, and the available number of various AGV models, the transportation cost function of the AGV vehicle is constructed in the following manner: for the path starting point to the path destination, the transportation cost of the AGV model from the path starting point to the path destination and the product of the decision variables from the path starting point to the path destination are used as the transportation cost function of the AGV vehicle. The fixed cost of each model and the product of the decision variables from the starting point to the destination are used as the fixed cost function of the AGV vehicle.

[0059] In addition, a set of planned waypoints is set between the path starting point and the path destination. Accordingly, the driving distance from the path starting point to the path destination can be expressed by the waypoint set. Correspondingly, the sum of the turning angles from the path starting point to the path destination can be obtained, and the sum of the turning angles and the above cost are adjusted to the same dimension through the weight coefficient to obtain the adjusted sum of the turning angles. According to the transportation cost function, fixed cost function, and sum of the turning angles of the above AGV vehicle, the objective function is obtained.

[0060] In the picking scenario of multiple models and multiple destinations in the embodiment of the present invention, all AGV vehicles start from the same starting point and travel at a constant speed. Each AGV model has different rated weight, fixed cost and driving cost; the number of goods to be picked at each destination (target shelf) is clear; based on the above premise, the constraints of the planning model are established, including: vehicle usage quantity constraint: the number of AGV vehicles of each type should not exceed the available number of vehicles of this type; the position constraints of the starting and ending points of the vehicles: all AGV vehicles start from the parking area and return to the parking area; vehicle scheduling rule constraints: in a picking task scheduling, each target shelf is picked only once; and after the AGV vehicle picks up the goods on the shelf, it arrives at the next target shelf or returns to the parking area; and vehicle load constraints: the total picking volume of each path is not higher than the AGV vehicle capacity of this path.

[0061] According to another embodiment of the present invention, the vehicle scheduling plan set is input into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan, including: initializing the parameters of the planning model; clustering and grouping the vehicle scheduling plan set based on the input vehicle scheduling plan set to obtain at least one group of vehicle scheduling plan sub-populations; when the number of iterations is less than a preset maximum number of iterations, looping the following iterative calculations until the number of iterations reaches the maximum number of iterations, selecting a global optimal solution from the vehicle scheduling plan solutions obtained from all iterative calculations as the vehicle scheduling plan: using a particle swarm algorithm to calculate individual optimal solutions and global optimal solutions for each group of vehicle scheduling sub-populations to obtain a vehicle scheduling plan solution; and performing a first update on the speed and position information of all vehicles based on the individual optimal solutions and the global optimal solutions.

[0062] According to another embodiment of the present invention, the speed and position information of all vehicles are first updated according to the individual optimal solution and the global optimal solution, including: according to the individual optimal solution and the global optimal solution, first speed update information and second speed update information of all vehicles are obtained by particle swarm algorithm and clustering algorithm respectively; according to the first speed update information and the second speed update information, the speed update information of all vehicles is obtained; according to the speed update information of all vehicles, the position update information of all vehicles is obtained.

[0063] Specifically, the solution of the above MVMOPP planning model is an NP-hard problem. The embodiment of the present invention uses a hybrid swarm intelligence algorithm of a heuristic intelligent algorithm particle swarm and a genetic algorithm. In order to maintain the diversity of the particle population, the K-means clustering algorithm is introduced. The K-means clustering algorithm is a prototype-based objective function clustering method. It is a process of grouping a batch of real or abstract data objects into multiple classes or clusters. According to the coding design of the target particles, the metric function of the distance between two particles is defined. The embodiment of the present invention adopts the method based on the initial clustering centroid generation. The particles in the initial population are divided into several sub-populations according to the K-means algorithm. In each sub-population, the particle swarm algorithm is used to determine the individual optimal solution of each sub-population and the global optimal solution of the population to update the speed and position information.

[0064] Further, in combination with the application scenario of the embodiment of the present invention, the parameters in the above-mentioned planning model are first initialized, the maximum number of iterations is set, the vehicle scheduling plan set is input into the planning model, the positions and speeds of all vehicles in the vehicle scheduling plan set are initialized, and the initial vehicle scheduling plan set is obtained; the initial vehicle scheduling plan set is divided into at least one group of vehicle scheduling plan subpopulations according to the K-means algorithm; the particle swarm algorithm is used to calculate the individual optimal solution and the global optimal solution for each group of vehicle scheduling plan subpopulations to obtain the vehicle scheduling plan solution solved in this iteration. According to the individual optimal solution and the global optimal solution, the first speed update information and the second speed update information of all vehicles are obtained respectively by the particle swarm algorithm and the clustering algorithm; the first speed update information and the second speed update information are summed to obtain the speed update information of all vehicles; finally, according to the speed update information of all vehicles, the position update information of all vehicles is obtained. The specific method for performing the first update on the speed and position information of all vehicles in the vehicle scheduling plan set is: a speed update method based on a traditional particle swarm algorithm, calculating the first speed update information through the inertia coefficient, the dimension of the particles, the acceleration factor, the individual optimal position information, and the group optimal position information, and then combining the optimal position and acceleration factor searched by the particles in each clustering area based on the clustering algorithm to calculate the second speed update information, and obtaining the speed update information of all vehicles in the vehicle scheduling plan set according to the first speed update information and the second speed update information, and then obtaining the position update information of all vehicles according to the speed update information of all vehicles.

[0065] Furthermore, it is determined whether the current number of iterations is less than the preset maximum number of iterations. If the current number of iterations is less than the preset maximum number of iterations, the speed and position information after the first update is used to guide the next iteration to calculate the individual optimal solution, the global optimal solution, and the corresponding speed update information and position update information of each group of vehicle scheduling subpopulations until the current number of iterations is equal to or greater than the maximum number of iterations, and the global optimal solution is selected from all vehicle scheduling plan solutions calculated by iterative calculations as the vehicle scheduling plan.

[0066] According to yet another embodiment of the present invention, based on a distributed parallel framework, the vehicle scheduling plan set is input into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

[0067] Specifically, since the particle swarm algorithm and the genetic algorithm have natural parallelism, they are particularly suitable for calculation using the Flink distributed parallel framework to speed up the solution of the MVMOPP model. The embodiment of the present invention introduces the above-mentioned initial vehicle scheduling plan set into the Flink stream; based on the initial vehicle scheduling plan set, the K-means algorithm is implemented based on the Flink framework: based on the determined centroid, the custom Map operator is called to calculate the distance of each point from the centroid, and to which centroid each node belongs, based on the custom abstract operator, the previously calculated centroid set is obtained from the Flink broadcast variable, and this is used as an input parameter to calculate which centroid the current node is closest to, and at least one group of vehicle scheduling plan subpopulations is obtained; iterative calculations are performed through the iterate method, and the particle swarm algorithm is used to calculate the individual optimal solution for each group of vehicle scheduling plan subpopulations, and distributed calculations are performed through Flink's keyBy to obtain the global optimal solution and obtain the vehicle scheduling plan solution; according to the individual optimal solution and the global optimal solution, the first update of all vehicle speed and position information in the vehicle scheduling plan set is performed according to the update formula of the above-mentioned hybrid swarm intelligent algorithm. Then, it is determined whether the current number of iterations is less than the preset maximum number of iterations. If the current number of iterations is less than the preset maximum number of iterations, the speed and position information after the first update is used to guide the next iteration to calculate the individual optimal solution, the global optimal solution, and the corresponding speed update information and position update information of each group of vehicle scheduling subpopulations until the current number of iterations is equal to or greater than the maximum number of iterations. The global optimal solution is obtained from the vehicle scheduling plan solutions obtained by all iterative calculations through window statistics as the vehicle scheduling plan.

[0068] According to another embodiment of the present invention, a particle swarm algorithm is used to calculate an individual optimal solution and a global optimal solution for each group of vehicle scheduling subpopulations, including: adjusting the individual inertia coefficient and acceleration factor of each group of vehicle scheduling subpopulations according to the individual fitness value of each group of vehicle scheduling subpopulations to obtain the adaptive inertia coefficient and adaptive acceleration factor of the individuals of each group of vehicle scheduling subpopulations; and using the particle swarm algorithm, in combination with the adaptive inertia coefficient and the adaptive acceleration factor, to calculate the individual optimal solution and the global optimal solution.

[0069] Specifically, in order to improve the convergence speed and quality of the particle swarm algorithm, according to the fitness value of the current individual of each group of vehicle scheduling subpopulations, when the current individual fitness value is less than the average fitness value of the vehicle scheduling subpopulation to which the current individual belongs, it means that the individual fitness is lower than the population fitness, and the inertia system and the acceleration factor are adjusted to grow exponentially to increase the exploration ability of the individual. Specifically, the natural number e can be used as the base, and the power operation of e can be performed with the preset constant adjustment coefficient as the exponent, and then the upper and lower limits of the inertia weight and the upper and lower limits of the adaptive acceleration factor are respectively combined to adjust the adaptive inertia coefficient and the adaptive acceleration factor. When the current individual fitness value is greater than or equal to the average fitness value of the vehicle scheduling subpopulation where the current individual is located, it means that the individual's fitness is relatively good. The individual's exploration ability can be appropriately reduced, while the self-learning ability can be increased. Specifically, the natural number e can be used as the base, and the ratio of the difference between the fitness value of the current individual in the population and the minimum fitness value of the individual in the population and the difference between the maximum fitness value of the individual in the population and the average fitness value can be used as the exponent to perform a power operation of e, and then the upper and lower limits of the inertia weight and the upper and lower limits of the adaptive acceleration factor can be combined to adjust the adaptive inertia coefficient and the adaptive acceleration factor.

[0070] According to one embodiment of the present invention, after a first update is performed on the speed and position information of all vehicles according to the individual optimal solution and the global optimal solution, the method includes: introducing a selection crossover operator and a mutation operator of a genetic algorithm into each group of vehicle scheduling subpopulations, and performing a second update on the position information of all vehicles after the first update.

[0071] According to another embodiment of the present invention, a selection crossover operator and a mutation operator of a genetic algorithm are introduced into each group of vehicle scheduling subpopulations, and a second update is performed on the location information of all vehicles after the first update, including: using an activation function, according to the individual fitness values ​​of each group of vehicle scheduling subpopulations, adjusting the individual selection probability, crossover probability and mutation probability introduced into each group of vehicle scheduling subpopulations, to obtain the adaptive selection probability, adaptive crossover probability and adaptive mutation probability of the individuals in each group of vehicle scheduling subpopulations; and performing a second update on the location information of all vehicles after the first update according to the adaptive selection probability, adaptive crossover probability and adaptive mutation probability.

[0072] Specifically, in order to further accelerate the convergence of the MVMOPP model, the selection crossover and mutation operators of the genetic algorithm are introduced into the particle swarm algorithm to avoid the population from falling into the local optimal solution. In order to retain the elite individuals, the Tanh activation function is introduced. According to the fitness value of the current individual of each vehicle scheduling subpopulation, when the current individual fitness value is less than the average fitness value of the vehicle scheduling subpopulation where the current individual is located, it means that the individual is relatively general. At this time, its selection, crossover and mutation probabilities should be reduced to reduce the possibility of generating new individuals; when the current individual fitness value is greater than or equal to the average fitness value of the vehicle scheduling subpopulation where the current individual is located, the individual is relatively excellent. By increasing the selection probability, crossover probability and mutation probability, the evolutionary ability of the individual is increased, and the possibility of generating better individuals is expected. Specifically, the natural number e can be used as the base, the difference between the current individual fitness value and the average fitness value is used as the exponent, and the power operation of e is performed, and then the maximum and minimum values ​​of the selection probability, the maximum and minimum values ​​of the crossover probability, and the maximum and minimum values ​​of the mutation probability are combined to calculate the adaptive selection probability, the adaptive crossover probability and the adaptive mutation probability.

[0073] Furthermore, according to the adaptive selection probability, the adaptive crossover probability and the adaptive mutation probability, the position information of all vehicles after the first update is second updated.

[0074] According to another embodiment of the present invention, after performing a second update on the location information of all vehicles after the first update, the method further includes: introducing a deletion operation operator, a reversal operation operator and a cloning operation operator of a genetic algorithm into each group of vehicle scheduling subpopulations to perform a third update on the location information of all vehicles after the second update.

[0075] Specifically, in order to further improve the convergence speed and effect of the hybrid swarm intelligence algorithm of the embodiment of the present invention, after the above selection probability, crossover probability, and mutation probability, operators such as deletion operation operators, reversal operation operators, and cloning operation operators can be added to perform a third update on the location information of all vehicles after the second update. These operators can be well combined with the operator concept in Flink for coding, and the parallelism of these operation operators can be flexibly set through Flink's set Parallelism, thereby cleverly utilizing the advantages of Flink's parallel computing and greatly improving the solution speed and solution quality of the MVMOPP model.

[0076] Figure 2The detailed flow chart of the hybrid swarm intelligence algorithm for determining the vehicle scheduling plan in the embodiment of the present invention is as follows. The parameters in the planning model are initialized, the maximum number of iterations and the initial number of iterations k are set to 1, the positions and speeds of all vehicles in the vehicle scheduling plan set are initialized, and the initial vehicle scheduling plan set is obtained; the initial vehicle scheduling plan set is divided into at least one group of vehicle scheduling plan subpopulations f1 (x1, x2, ..., x t ), …, f u (x1,x2,…,x t ); for each group of vehicle scheduling plan subpopulations, the particle swarm algorithm is used to calculate the individual optimal solution and the global optimal solution to obtain the vehicle scheduling plan solution solved in this iteration; according to the individual optimal solution and the global optimal solution, the speed and position information of all vehicles in the vehicle scheduling plan set are first updated according to the update formula of the hybrid swarm intelligent algorithm; according to the adaptive selection probability, the adaptive crossover probability and the adaptive mutation probability, the position information of all vehicles after the first update is second updated; the deletion operation operator, the reversal operation operator and the cloning operation operator of the genetic algorithm are introduced into each group of vehicle scheduling subpopulations to perform a third update on the position information of all vehicles after the second update; it is determined whether the current iteration number value is less than the maximum iteration number, if it is less than, the current iteration number is added by 1, and the vehicle scheduling plan solution of each group of vehicle scheduling plan subpopulations is continued to be solved, if the current iteration value is equal to or exceeds the maximum iteration number, the iteration ends, and the global optimal solution is selected from the vehicle scheduling plan solutions obtained by all iterative calculations as the vehicle scheduling plan output.

[0077] The planning model obtained by using the hybrid swarm intelligence algorithm in the embodiment of the present invention can improve the solution speed of the planning model, especially based on the Flink distributed parallel framework, the vehicle scheduling plan can be quickly obtained, and flexible scheduling of various AGV models can be realized, which is conducive to resource integration and efficiency improvement.

[0078] According to yet another embodiment of the present invention, after obtaining the vehicle dispatch plan, the method includes: obtaining a planned path of the vehicle according to the vehicle dispatch plan.

[0079] Specifically, the vehicle scheduling plan determined above is composed of decision variables of the vehicles to be scheduled. Based on the fact that the decision variables include the path starting point and the path destination, the vehicle planning path corresponding to the vehicle scheduling plan is obtained according to the path starting point and the path destination of the decision variables whose values ​​of each decision variable of the vehicle scheduling plan are 1.

[0080] Based on the above vehicle dispatch plan, the vehicle planning path obtained is conducive to ensuring the rationality, safety and effectiveness of the planned path.

[0081] Figure 3 Schematic diagram of the main modules of the vehicle dispatching device according to an embodiment of the present invention. Figure 3 As shown, the vehicle scheduling device 300 mainly includes an information acquisition module 301, a scheduling plan set generation module 302 and a scheduling plan acquisition module 303.

[0082] The information acquisition module 301 is used to obtain vehicle information and at least one destination information of the vehicle to be dispatched in response to the dispatch request;

[0083] A scheduling plan set generating module 302, used to generate a vehicle scheduling plan set according to the vehicle information and the destination information;

[0084] The scheduling plan acquisition module 303 is used to input the vehicle scheduling plan set into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

[0085] According to one embodiment of the present invention, the vehicle scheduling device 300 may also include a decision variable construction module (not shown in the figure), which is used to: before generating a vehicle scheduling plan set based on the vehicle information and the destination information, construct a decision variable that characterizes the vehicle usage status, and the decision variable includes a vehicle identification, a path starting point and a path destination; the scheduling plan set generation module 302 is also used to: based on the vehicle identification in the vehicle information, the destination information, combined with the starting point information of the vehicle to be scheduled, use the decision variable to obtain a vehicle scheduling plan set for the vehicle to be scheduled.

[0086] According to another embodiment of the present invention, the objective function of the planning model is constructed in the following manner: through the decision variables, the transportation cost function and the fixed cost function of the vehicle are established; according to the waypoints set in the path from the vehicle starting point to the vehicle destination, the turning angle sum function of the path is established; according to the transportation cost function, the fixed cost function and the turning angle sum function, the objective function is obtained; based on the objective function, constraints are established, and the constraints include: vehicle usage quantity constraints, vehicle starting point and end point location constraints, vehicle scheduling rule constraints, and vehicle load constraints.

[0087] According to another embodiment of the present invention, the scheduling plan acquisition module 303 is also used to: initialize the parameters of the planning model; cluster and group the vehicle scheduling plan set based on the input vehicle scheduling plan set to obtain at least one group of vehicle scheduling plan subpopulations; when the number of iterations is less than the preset maximum number of iterations, loop the following iterative calculations until the number of iterations reaches the maximum number of iterations, and select the global optimal solution from the vehicle scheduling plan solutions obtained by all iterative calculations as the vehicle scheduling plan: use the particle swarm algorithm to calculate the individual optimal solution and the global optimal solution for each group of vehicle scheduling subpopulations to obtain a vehicle scheduling plan solution; and perform a first update on the speed and position information of all vehicles based on the individual optimal solution and the global optimal solution.

[0088] According to another embodiment of the present invention, the scheduling plan acquisition module 303 is also used to: based on a distributed parallel framework, input the vehicle scheduling plan set into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

[0089] According to one embodiment of the present invention, the scheduling plan acquisition module 303 is also used to: adjust the individual inertia coefficient and acceleration factor of each group of vehicle scheduling subpopulations according to the individual fitness value of each group of vehicle scheduling subpopulations to obtain the adaptive inertia coefficient and adaptive acceleration factor of the individuals in each group of vehicle scheduling subpopulations; and use a particle swarm algorithm, combined with the adaptive inertia coefficient and the adaptive acceleration factor, to calculate the individual optimal solution and the global optimal solution.

[0090] According to another embodiment of the present invention, the scheduling plan acquisition module 303 is also used to: obtain the first speed update information and the second speed update information of all vehicles respectively through the particle swarm algorithm and the clustering algorithm according to the individual optimal solution and the global optimal solution; obtain the speed update information of all vehicles according to the first speed update information and the second speed update information; obtain the position update information of all vehicles according to the speed update information of all vehicles.

[0091] According to another embodiment of the present invention, the vehicle scheduling device 300 may further include a second updating module (not shown in the figure), which is used to: after performing a first update on the speed and position information of all vehicles according to the individual optimal solution and the global optimal solution, introduce a selection crossover operator and a mutation operation operator of a genetic algorithm into each group of vehicle scheduling subpopulations to perform a second update on the position information of all vehicles after the first update.

[0092] According to another embodiment of the present invention, the second updating module (not shown in the figure) is also used to: use an activation function to adjust the individual selection probability, crossover probability and mutation probability introduced by each group of vehicle scheduling subpopulations according to the individual fitness values ​​of each group of vehicle scheduling subpopulations, so as to obtain the adaptive selection probability, adaptive crossover probability and adaptive mutation probability of the individuals in each group of vehicle scheduling subpopulations; and perform a second update on the location information of all vehicles after the first update according to the adaptive selection probability, adaptive crossover probability and adaptive mutation probability.

[0093] According to another embodiment of the present invention, the vehicle scheduling device 300 may further include a third update module (not shown in the figure), which is used to: after performing a second update on the position information of all vehicles after the first update, introduce a deletion operation operator, a reversal operation operator and a cloning operation operator of the genetic algorithm into each group of vehicle scheduling subpopulations, and perform a third update on the position information of all vehicles after the second update.

[0094] According to an embodiment of the present invention, the vehicle scheduling device 300 may further include a planned path determination module (not shown in the figure) for obtaining a planned path of the vehicle according to the vehicle scheduling plan after obtaining the vehicle scheduling plan.

[0095] Figure 4 is an exemplary system architecture diagram to which embodiments of the present invention can be applied.

[0096] like Figure 4 As shown, system architecture 400 may include terminal devices 401, 402, 403, network 404 and server 405. Network 404 is used to provide a medium for communication links between terminal devices 401, 402, 403 and server 405. Network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0097] Users can use terminal devices 401, 402, 403 to interact with server 405 through network 404 to receive or send messages, etc. Various communication client applications, such as vehicle dispatching applications, etc., can be installed on terminal devices 401, 402, 403 (only as an example).

[0098] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0099] The server 405 may be a server that provides various services, such as a background management server (only an example) that provides support for vehicle dispatching performed by users using the terminal devices 401, 402, and 403. The background management server may respond to the dispatching request, obtain vehicle information and at least one destination information of the vehicle to be dispatched; generate a vehicle dispatching plan set based on the vehicle information and the destination information; input the vehicle dispatching plan set into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a vehicle dispatching plan, etc., and feed back the processing result (such as a vehicle dispatching plan, etc. - only an example) to the terminal device.

[0100] It should be noted that the vehicle dispatching method provided in the embodiment of the present invention is generally executed by the server 405 , and accordingly, the vehicle dispatching device is generally arranged in the server 405 .

[0101] It should be understood that Figure 4 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0102] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of a terminal device or a server suitable for implementing an embodiment of the present invention. Figure 5 The terminal device or server 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.

[0103] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 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 part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 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.

[0104] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0105] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0106] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0107] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes: an information acquisition module, a scheduling plan set generation module and a scheduling plan acquisition module.

[0109] The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the information acquisition module may also be described as “a module for acquiring vehicle information and at least one destination information of a vehicle to be dispatched in response to a dispatch request”.

[0110] On the other hand, the present invention also provides a computer-readable medium, which may be included in the device described in the embodiment; or may exist independently without being assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: in response to a scheduling request, obtaining vehicle information and at least one destination information of a vehicle to be scheduled; generating a vehicle scheduling plan set based on the vehicle information and the destination information; inputting the vehicle scheduling plan set into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

[0111] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by responding to a dispatch request, the vehicle information and at least one destination information of the vehicle to be dispatched are obtained; based on the vehicle information and the destination information, a vehicle dispatch plan set is generated; the vehicle dispatch plan set is input into a pre-built planning model obtained using a hybrid swarm intelligence algorithm to obtain a technical solution of a vehicle dispatch plan, which realizes the generation of a vehicle dispatch plan set according to the received vehicle information and at least one destination information; based on the pre-built planning model obtained using a hybrid swarm intelligence algorithm, a vehicle dispatch plan that meets the requirements of the model is selected from the vehicle dispatch plan set. The method provided by the embodiment of the present invention provides an AGV vehicle dispatch plan suitable for multiple AGV models and multiple destination scenarios. By using a hybrid swarm intelligence algorithm, a vehicle dispatch plan can be quickly obtained to flexibly dispatch each AGV model, which is conducive to resource integration and efficiency improvement.

[0112] The specific implementation methods described herein do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A vehicle dispatching method, It is characterized in that include: In response to the dispatch request, obtaining vehicle information and at least one destination information of the vehicle to be dispatched; Generate a vehicle dispatch plan set according to the vehicle information and the destination information; The vehicle dispatch plan set is input into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle dispatch plan.

2. The method according to claim 1, It is characterized in that Before generating a vehicle dispatch plan set according to the vehicle information and the destination information, the method further includes: Constructing decision variables representing the vehicle usage status, wherein the decision variables include a vehicle identification, a path starting point, and a path destination; Generate a vehicle dispatch plan set according to the vehicle information and the destination information, including: According to the vehicle identification in the vehicle information, the destination information, combined with the starting point information of the vehicle to be dispatched, and using the decision variables, a vehicle dispatch plan set of the vehicle to be dispatched is obtained.

3. The method according to claim 2, It is characterized in that The objective function of the planning model is constructed in the following way: By using the decision variables, a transportation cost function and a fixed cost function of the vehicle are established; According to the waypoints set in the path from the vehicle starting point to the vehicle destination, a turning angle sum function of the path is established; Obtaining an objective function according to the transportation cost function, the fixed cost function and the turning angle sum function; Based on the objective function, constraint conditions are established, and the constraint conditions include: vehicle usage quantity constraint, vehicle start and end point location constraint, vehicle scheduling rule constraint, and vehicle load constraint.

4. The method according to claim 1, It is characterized in that The vehicle scheduling plan set is input into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan, including: Initializing parameters of the planning model; Based on the input vehicle scheduling plan set, clustering and grouping the vehicle scheduling plan set to obtain at least one group of vehicle scheduling plan sub-populations; When the number of iterations is less than the preset maximum number of iterations, the following iterative calculation is performed in a loop until the number of iterations reaches the maximum number of iterations, and the global optimal solution is selected from the vehicle scheduling plan solutions obtained by all iterative calculations as the vehicle scheduling plan: The particle swarm algorithm is used to calculate the individual optimal solution and the global optimal solution for each group of vehicle scheduling subpopulations to obtain a vehicle scheduling plan solution; and the speed and position information of all vehicles are first updated according to the individual optimal solution and the global optimal solution.

5. The method according to claim 1, It is characterized in that Based on a distributed parallel framework, the vehicle scheduling plan set is input into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

6. The method according to claim 4 or 5, It is characterized in that The particle swarm algorithm is used to calculate the individual optimal solution and the global optimal solution for each group of vehicle scheduling subpopulations, including: According to the individual fitness values ​​of each group of vehicle scheduling subpopulations, the individual inertia coefficient and acceleration factor of each group of vehicle scheduling subpopulations are adjusted to obtain the adaptive inertia coefficient and adaptive acceleration factor of the individuals of each group of vehicle scheduling subpopulations; The particle swarm algorithm is used to calculate the individual optimal solution and the global optimal solution in combination with the adaptive inertia coefficient and the adaptive acceleration factor.

7. The method according to claim 4 or 5, It is characterized in that According to the individual optimal solution and the global optimal solution, the speed and position information of all vehicles are first updated, including: According to the individual optimal solution and the global optimal solution, first speed update information and second speed update information of all vehicles are obtained by using a particle swarm algorithm and a clustering algorithm respectively; Obtaining speed update information of all vehicles according to the first speed update information and the second speed update information; According to the speed update information of all the vehicles, the position update information of all the vehicles is obtained.

8. The method according to claim 4 or 5, It is characterized in that After first updating the speed and position information of all vehicles according to the individual optimal solution and the global optimal solution, the method includes: Introducing a selection crossover operator and a mutation operator of a genetic algorithm into each group of vehicle scheduling subpopulations, and performing a second update on the position information of all vehicles after the first update.

9. The method according to claim 8, It is characterized in that Introducing a selection crossover operator and a mutation operator of a genetic algorithm into each group of vehicle scheduling subpopulations, and performing a second update on the speed and position information of all vehicles after the first update, including: Using an activation function, according to the individual fitness values ​​of each group of vehicle scheduling subpopulations, the individual selection probability, crossover probability and mutation probability introduced by each group of vehicle scheduling subpopulations are adjusted to obtain the adaptive selection probability, adaptive crossover probability and adaptive mutation probability of the individuals of each group of vehicle scheduling subpopulations; According to the adaptive selection probability, the adaptive crossover probability and the adaptive mutation probability, a second update is performed on the position information of all vehicles after the first update.

10. The method according to claim 8, It is characterized in that After performing a second update on the position information of all vehicles after the first update, the method further includes: A deletion operator, a reversal operator and a cloning operator of a genetic algorithm are introduced into each group of vehicle scheduling subpopulations to perform a third update on the position information of all vehicles after the second update.

11. The method according to claim 1, It is characterized in that After obtaining the vehicle dispatch plan, the method includes: According to the vehicle dispatch plan, a planned path of the vehicle is obtained.

12. A vehicle dispatching device, It is characterized in that include: An information acquisition module, used for acquiring vehicle information and at least one destination information of a vehicle to be dispatched in response to a dispatch request; A scheduling plan set generating module, used to generate a vehicle scheduling plan set according to the vehicle information and the destination information; The scheduling plan acquisition module is used to input the vehicle scheduling plan set into a pre-built planning model obtained by using a hybrid swarm intelligence algorithm to obtain a vehicle scheduling plan.

13. A mobile electronic device terminal, It is characterized in that include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 11.

14. A computer readable medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.