Aerial material scheduling method based on artificial intelligence

Abstract

The invention discloses an aerial material scheduling method based on artificial intelligence, and belongs to the technical field of aerial material scheduling, and the method comprises the steps: querying inventory data through an aerial material scheduling demand, so as to determine an aerial material storage position corresponding to the aerial material scheduling demand, and carrying out the aerial material scheduling according to the aerial material storage position corresponding to the aerial material scheduling demand; an improved artificial intelligence algorithm is adopted for aerial material scheduling route planning, finally, an artificial intelligence robot is scheduled to sequentially reach each aerial material storage position corresponding to the aerial material scheduling requirement on the basis of the aerial material scheduling route, and aerial material scheduling is performed, so that automatic route planning and aerial material scheduling can be effectively realized; therefore, the aviation material scheduling efficiency can be effectively improved.

Description

Technical Field

[0001] The invention belongs to the technical field of aviation material scheduling, and in particular relates to an aviation material scheduling method based on artificial intelligence. Background Art

[0002] Aviation materials, also known as aviation equipment, refer to various parts, materials, tools and equipment required for the manufacture, maintenance and operation of aircraft. Aviation materials cover a wide range, from aircraft engines, fuselage structures, avionics equipment to all necessities such as the smallest screws and gaskets. With the rapid development of the aviation industry, the importance of aviation material scheduling in aviation operations has become increasingly prominent. Generally, aviation materials are stored in warehouses, and when they are needed for scheduling, the storage location of the aviation materials is manually searched and scheduled, which is time-consuming, labor-intensive and has low scheduling efficiency. Summary of the invention

[0003] The present invention provides an aviation material scheduling method based on artificial intelligence, which is used to solve the problems of the prior art that the aviation material storage location is manually searched and scheduled, which is time-consuming and labor-intensive and has low scheduling efficiency.

[0004] An aviation material scheduling method based on artificial intelligence, comprising: Obtaining the aviation material dispatching demand input by the staff through human-computer interaction; wherein the aviation material dispatching demand includes at least one aviation material identity code and aviation material demand quantity; Querying inventory data according to the aviation material dispatching requirements to determine the aviation material storage location corresponding to the aviation material dispatching requirements; wherein the inventory data includes the association between the aviation material identity code and the aviation material storage location; According to the storage location of aviation materials corresponding to the aviation material dispatching demand, the improved artificial intelligence algorithm is used to plan the aviation material dispatching route to obtain the aviation material dispatching route; Based on the aviation material dispatching route, the artificial intelligence robot is dispatched to arrive at each aviation material storage location corresponding to the aviation material dispatching demand in turn, and the aviation material dispatching is performed.

[0005] Furthermore, the inventory data is queried according to the aviation material scheduling requirements to determine the aviation material storage location corresponding to the aviation material scheduling requirements, including: Based on the aviation material identity code in the aviation material scheduling demand, a cosine similarity matching method is used to query in the inventory data to determine the target aviation material identity code in the inventory data; Query the aviation material storage location corresponding to the target aviation material identity code to obtain the aviation material storage location corresponding to the aviation material scheduling demand.

[0006] Furthermore, according to the storage location of the aviation materials corresponding to the aviation material scheduling demand, the improved artificial intelligence algorithm is used to plan the aviation material scheduling route, and the aviation material scheduling route is obtained, including: Generate multiple initial route codes based on the storage locations of aviation materials corresponding to aviation material scheduling requirements; The GA-ACO algorithm is used to optimize multiple initial route codes to obtain the optimal route code. After decoding the optimal route code, the aviation material scheduling route is obtained.

[0007] Furthermore, based on the storage location of the aviation materials corresponding to the aviation material scheduling requirements, multiple initial route codes are generated, including: Based on the storage location of the aviation materials corresponding to the aviation materials scheduling demand, a unique number is assigned to each aviation materials storage location; The numbers corresponding to each aviation material storage location are encoded into a vector in random order to obtain an initial route code, and multiple different initial route codes are repeatedly obtained.

[0008] Furthermore, the GA-ACO algorithm is used to optimize multiple initial route codes to obtain the optimal route code, and after decoding the optimal route code, the aviation material scheduling route is obtained, including: For any initial route code, after decoding the initial route code, the aviation material dispatching route corresponding to the initial route code is obtained; For any aviation material dispatching route corresponding to an initial route code, the objective function of path and energy consumption is used to obtain the objective function value corresponding to the initial route code; The initial route is encoded as the parent individual in the first optimization process of the GA algorithm; Based on the objective function value corresponding to the initial route code, the crossover probability and mutation probability corresponding to each parent individual are obtained, and a crossover operation is performed according to the crossover probability and a mutation operation is performed according to the mutation probability to obtain multiple offspring individuals; Determine whether the optimization times of the GA algorithm reaches the preset first maximum optimization times. If so, obtain the first intermediate line code according to the offspring individuals and the parent individuals in the last optimization process. Otherwise, re-obtain multiple parent individuals according to the current parent individuals and the offspring individuals, and return to the step of obtaining offspring individuals based on the re-obtained parent individuals. Based on the first intermediate line coding, the pheromone concentration of the ACO algorithm and the ant colony of the ACO algorithm are initialized; Based on the pheromone concentration, each ant in the ant colony is made to crawl, obtain a plurality of second intermediate line codes, and update the pheromone concentration according to the plurality of second intermediate line codes to obtain an updated pheromone concentration; Determine whether the number of ACO optimizations reaches the preset second maximum number of optimizations. If so, obtain the optimal route code according to the second intermediate route code, otherwise return to the ant crawling step; After decoding the optimal route code, the aviation material scheduling route is obtained.

[0009] Furthermore, the crossover probability corresponding to each parent individual is obtained as: Obtain the objective function value corresponding to the parent individual, and determine the optimal parent individual based on the objective function value; Determine the adaptive probability control factor according to the objective function value corresponding to the parent individual and the objective function value corresponding to the optimal parent individual; When the adaptive probability control factor is less than the preset threshold, the corresponding crossover probability of the parent individual is determined as: ; When the adaptive probability control factor is greater than or equal to the preset threshold, the corresponding crossover probability of the parent individual is determined as: ;in, Indicates a The crossover probability corresponding to the parent individuals is represents pi, Indicates a The objective function value corresponding to the parent individuals is: represents the objective function value corresponding to the optimal parent individual, arcsin represents the inverse sine function, represents the cross-process control coefficient.

[0010] Furthermore, the mutation probability corresponding to each parent individual is obtained as: When the adaptive probability control factor is less than the preset threshold, the mutation probability corresponding to the parent individual is determined as: ; When the adaptive probability control factor is greater than or equal to the preset threshold, the mutation probability corresponding to the parent individual is determined as: ;in, Indicates a The mutation probability corresponding to each parent individual is represents the coefficient of variation of the process control.

[0011] Further, based on the first intermediate line code, the pheromone concentration of the ACO algorithm and the ant colony of the ACO algorithm are initialized, including: Determine the storage location of the aviation materials corresponding to the aviation materials scheduling needs, and regard each aviation materials storage location as a node; For the mth node, based on the first intermediate line code, determine the number of transfers between the mth node and the nth other node as C; The pheromone concentration between the mth node and the nth other node is C / 2M, where M represents the total number of nodes.

[0012] Furthermore, based on the pheromone concentration, each ant in the ant colony is made to crawl to obtain multiple second intermediate line codes, including: Based on the pheromone concentration, the transfer probability between any two nodes is obtained as:

[0013] in, Indicates k The ants from i The node is transferred to j The transition probability of a node, Indicates i The node and j The pheromone concentration of the path between nodes, Indicates i The node and j The heuristic function value between nodes, represents the pheromone impact factor, represents the influence factor of the heuristic function, Indicates i The node and k The pheromone concentration of the path between nodes, Indicates i The node and h The heuristic function value between nodes, Indicates k The path candidate nodes of each ant; the heuristic function value is obtained by dividing the pheromone intensity by the path length between two nodes; Based on the transfer probability between any two nodes, each ant in the ant colony is made to crawl to obtain multiple second intermediate line codes.

[0014] Furthermore, the pheromone concentration is updated according to the plurality of second intermediate line codes, and the updated pheromone concentration is obtained as follows:

[0015]

[0016] in, Indicates the updated pheromone concentration, represents the evaporation coefficient of the pheromone, Indicates the increment of pheromone concentration, A+B=C, Indicates the weight corresponding to the optimal path in the current optimization process, Represents the weight corresponding to the optimal path in all optimization processes, C represents the total number of nodes in the planning process, Indicates the optimal path corresponding to the current optimization process.i The node and j The path length between nodes, Indicates the optimal path corresponding to all optimization processes i The node and j The path length between nodes.

[0017] The present invention provides an aviation material scheduling method based on artificial intelligence. The method queries inventory data through aviation material scheduling needs to determine the aviation material storage location corresponding to the aviation material scheduling needs. According to the aviation material storage location corresponding to the aviation material scheduling needs, an improved artificial intelligence algorithm is used to plan the aviation material scheduling route. Finally, based on the aviation material scheduling route, an artificial intelligence robot is scheduled to arrive at each aviation material storage location corresponding to the aviation material scheduling needs in turn, and aviation material scheduling is performed. This method can effectively realize automatic route planning and aviation material scheduling, thereby effectively improving the efficiency of aviation material scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0019] Figure 1 A flowchart of an aviation material scheduling method based on artificial intelligence is provided in an embodiment of the present invention.

[0020] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0021] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0022] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0023] like Figure 1 As shown, an embodiment of the present invention provides an aviation material scheduling method based on artificial intelligence, comprising: S1. Obtaining the aviation material dispatching demand input by the staff through human-computer interaction; wherein the aviation material dispatching demand includes at least one aviation material identity code and aviation material demand quantity; The demand for aviation materials can be expressed in quantity or weight, and each type of aviation material is stored in unit specifications. After determining the demand for aviation material dispatch, it can be determined how many copies of each type of aviation material need to be dispatched.

[0024] S2. querying inventory data according to the aviation material dispatching demand to determine the aviation material storage location corresponding to the aviation material dispatching demand; wherein the inventory data includes the association between the aviation material identity code and the aviation material storage location; The relationship between the aviation material identity code and the aviation material storage location can be set by the staff during warehousing. Once the aviation material identity code is determined, it can be determined in which area the aviation material is stored, thereby enabling scheduling.

[0025] S3. According to the storage location of the aviation materials corresponding to the aviation material dispatching demand, the aviation material dispatching route is planned by using the improved artificial intelligence algorithm to obtain the aviation material dispatching route; By improving the artificial intelligence algorithm for aviation material dispatch route planning, the aviation material dispatch route can be optimized, and the aviation material dispatch efficiency can be improved while ensuring that all required aviation materials are dispatched.

[0026] S4. Based on the aviation material dispatching route, dispatch the artificial intelligence robot to arrive at each aviation material storage location corresponding to the aviation material dispatching demand in turn, and perform aviation material dispatching.

[0027] The artificial intelligence robot can be set up as an AGV (Automated Guided Vehicle) robot, and a freight robot can also be set up. The AGV robot can be used to pick up items, and the freight robot can be used to pull goods, so that multiple aviation materials can be dispatched at one time, improving the efficiency of aviation material dispatch.

[0028] In an embodiment of the present invention, querying inventory data according to the aviation material scheduling demand to determine the aviation material storage location corresponding to the aviation material scheduling demand includes: Based on the aviation material identity code in the aviation material scheduling demand, a cosine similarity matching method is used to query in the inventory data to determine the target aviation material identity code in the inventory data; Query the aviation material storage location corresponding to the target aviation material identity code to obtain the aviation material storage location corresponding to the aviation material scheduling demand.

[0029] The aviation material identity code can be set as a digital code. For example, it can be composed of the aviation material type code, storage area code and storage shelf code, so that each aviation material has a unique code. The similarity between the aviation material identity codes can be determined through cosine similarity, and finally the query of the aviation material storage location can be realized.

[0030] In an embodiment of the present invention, an improved artificial intelligence algorithm is used to plan an aviation material scheduling route according to the aviation material storage location corresponding to the aviation material scheduling demand, and the aviation material scheduling route is obtained, including: Generate multiple initial route codes based on the storage locations of aviation materials corresponding to aviation material scheduling requirements; The GA-ACO (Genetic Algorithm-Ant Colony Optimization) algorithm is used to optimize multiple initial route codes to obtain the optimal route code. After decoding the optimal route code, the aviation material scheduling route is obtained.

[0031] This algorithm combines the global search capability of the genetic algorithm and the excellent local search capability of the ant colony optimization algorithm, aiming to solve some complex optimization problems, especially when the problem scale is large or the search space is complex. Therefore, the embodiment of the present invention uses the GA-ACO algorithm to optimize multiple initial route codes, thereby realizing the planning of the optimal aviation material scheduling route.

[0032] In the embodiment of the present invention, based on the storage location of the aviation materials corresponding to the aviation material scheduling demand, multiple initial route codes are generated, including: Based on the storage location of the aviation materials corresponding to the aviation materials scheduling demand, a unique number is assigned to each aviation materials storage location; The numbers corresponding to each aviation material storage location are encoded into a vector in random order to obtain an initial route code, and multiple different initial route codes are repeatedly obtained.

[0033] For example, there are 6 aviation material storage locations, plus the starting point and the shipping point of the artificial intelligence robot, and the starting point and the shipping point are also used as aviation material storage locations, which is 8 aviation material storage locations, and then the numbers 1-8 are assigned respectively, 1 represents the starting point, and 8 represents the shipping point. It is necessary to put it as a constraint condition in the first position and the last position of all paths. Therefore, the initial route code can be generated as (1,2,3,4,5,6,7,8), (1,4,5,6, 2,3,7,8), (1, 2,3,4,5,6,7,8) and other identical routes. It is worth noting that the above initial route code is only the distance of the embodiment of the present invention, and other initial route codes can also be generated.

[0034] In the embodiment of the present invention, the GA-ACO algorithm is used to optimize multiple initial route codes to obtain the optimal route code, and after decoding the optimal route code, the aviation material scheduling route is obtained, including: For any initial route code, after decoding the initial route code, the aviation material dispatching route corresponding to the initial route code is obtained; For example, the initial route code is (1,2,3,4,5,6,7,8), 1 represents the starting point, then you should start from the aviation material storage location represented by 2, start from the aviation material storage location represented by 3, and so on. The aviation material scheduling route can be planned in combination with the warehouse map.

[0035] For any aviation material dispatching route corresponding to an initial route code, the objective function of path and energy consumption is used to obtain the objective function value corresponding to the initial route code; For example, after increasing the unit weight, the energy consumption required for the artificial intelligence robot to travel a unit distance. Therefore, after determining the aviation material scheduling route, the path length of the route can be determined, and the energy consumption between each two nodes can be determined according to the weight added to different nodes. After weighting the path length with the preset first weighting coefficient, the weighted path length is obtained; after weighting the energy consumption corresponding to the aviation material scheduling route with the preset second weighting coefficient, the weighted energy consumption is obtained; the weighted path length is added to the weighted energy consumption to obtain the objective function value. The smaller the objective function value, the better the aviation material scheduling route.

[0036] The initial route is encoded as the parent individual in the first optimization process of the GA algorithm; Based on the objective function value corresponding to the initial route code, the crossover probability and mutation probability corresponding to each parent individual are obtained, and a crossover operation is performed according to the crossover probability and a mutation operation is performed according to the mutation probability to obtain multiple offspring individuals; It is worth noting that, regardless of whether it is a crossover operation or a mutation operation, the first element in the parent individual should always represent the starting point, and the last element always represents the shipping point. Only the middle elements are mutated and crossed to ensure the accuracy of the route.

[0037] Determine whether the optimization times of the GA algorithm reaches the preset first maximum optimization times. If so, obtain the first intermediate line code according to the offspring individuals and the parent individuals in the last optimization process. Otherwise, re-obtain multiple parent individuals according to the current parent individuals and the offspring individuals, and return to the step of obtaining offspring individuals based on the re-obtained parent individuals. After each generation of offspring individuals, the offspring individuals and parent individuals can be merged into a population, and then a number of individuals (fixed number) with the smallest objective function value are determined as new parent individuals.

[0038] Based on the first intermediate line coding, the pheromone concentration of the ACO algorithm and the ant colony of the ACO algorithm are initialized; Based on the pheromone concentration, each ant in the ant colony is made to crawl, obtain a plurality of second intermediate line codes, and update the pheromone concentration according to the plurality of second intermediate line codes to obtain an updated pheromone concentration; Determine whether the number of ACO optimizations reaches the preset second maximum number of optimizations. If so, obtain the optimal route code according to the second intermediate route code, otherwise return to the ant crawling step; After decoding the optimal route code, the aviation material scheduling route is obtained.

[0039] During the execution of the ant colony algorithm, the starting point is used as the starting point for each ant, and then the delivery point is used as the target point for route planning.

[0040] In this embodiment of the present invention, the crossover probability corresponding to each parent individual is obtained as follows: Obtain the objective function value corresponding to the parent individual, and determine the optimal parent individual based on the objective function value; Determine the adaptive probability control factor according to the objective function value corresponding to the parent individual and the objective function value corresponding to the optimal parent individual; When the adaptive probability control factor is less than the preset threshold, the corresponding crossover probability of the parent individual is determined as: ; When the adaptive probability control factor is greater than or equal to the preset threshold, the corresponding crossover probability of the parent individual is determined as: ;in, Indicates a The crossover probability corresponding to the parent individuals is represents pi, Indicates a The objective function value corresponding to the parent individuals is: represents the objective function value corresponding to the optimal parent individual, arcsin represents the inverse sine function, represents the cross-process control coefficient.

[0041] The adaptive probability control factor provided by the embodiment of the present invention can generate more diverse individuals in the crossover process to enrich the population while retaining excellent genetic inheritance and strengthening the global search capability. Adaptive increases the probability of mutation at the beginning and end of the algorithm, speeds up the convergence of the algorithm, and gives the algorithm a stronger ability to jump out of the local optimum.

[0042] In this embodiment of the present invention, the mutation probability corresponding to each parent individual is obtained as follows: When the adaptive probability control factor is less than the preset threshold, the mutation probability corresponding to the parent individual is determined as: ; When the adaptive probability control factor is greater than or equal to the preset threshold, the mutation probability corresponding to the parent individual is determined as: ;in, Indicates a The mutation probability corresponding to each parent individual is represents the coefficient of variation of the process control.

[0043] Optionally, the crossover operation can be: except for the first element and the last element, other elements are randomly exchanged (such as randomly exchanging one element, randomly exchanging two elements, randomly exchanging three elements, etc.). After exchanging the elements, if there are elements with the same number, the number corresponding to the previous element is retained, and the number of the subsequent element is reset to zero. After all repeated elements are processed, the numbers that have not appeared are randomly filled into the zeroed positions, thereby ensuring the correctness of route planning.

[0044] The mutation operation can be: except for the first element and the last element, at least one element can be randomly selected, and the selected element is randomly transformed within the range of digital values, and then the same number is processed to achieve mutation.

[0045] In the embodiment of the present invention, based on the first intermediate line code, the pheromone concentration of the ACO algorithm and the ant colony of the ACO algorithm are initialized, including: Determine the storage location of the aviation materials corresponding to the aviation materials scheduling needs, and regard each aviation materials storage location as a node; For the mth node, based on the first intermediate line code, determine the number of transfers between the mth node and the nth other node as C; The pheromone concentration between the mth node and the nth other node is C / 2M, where M represents the total number of nodes.

[0046] In the embodiment of the present invention, based on the pheromone concentration, each ant in the ant colony is made to crawl to obtain a plurality of second intermediate line codes, including: Based on the pheromone concentration, the transfer probability between any two nodes is obtained as:

[0047] in, Indicates k The ants from i The node is transferred to j The transition probability of a node, Indicates i The node and j The pheromone concentration of the path between nodes, Indicates i The node and j The heuristic function value between nodes, represents the pheromone impact factor, represents the influence factor of the heuristic function, Indicates i The node and k The pheromone concentration of the path between nodes, Indicates i The node and h The heuristic function value between nodes, Indicates k The path candidate nodes of each ant; the heuristic function value is obtained by dividing the pheromone intensity by the path length between two nodes; Based on the transfer probability between any two nodes, each ant in the ant colony is made to crawl to obtain multiple second intermediate line codes.

[0048] In the embodiment of the present invention, the pheromone concentration is updated according to the plurality of second intermediate line codes, and the updated pheromone concentration is obtained as follows:

[0049]

[0050] in, Indicates the updated pheromone concentration, represents the evaporation coefficient of the pheromone, Indicates the increment of pheromone concentration, A+B=C, Indicates the weight corresponding to the optimal path in the current optimization process, Represents the weight corresponding to the optimal path in all optimization processes, C represents the total number of nodes in the planning process, Indicates the optimal path corresponding to the current optimization process. i The node and j The path length between nodes, Indicates the optimal path corresponding to all optimization processes i The node and j The path length between nodes.

[0051] The present invention provides an aviation material scheduling method based on artificial intelligence. The method queries inventory data through aviation material scheduling needs to determine the aviation material storage location corresponding to the aviation material scheduling needs. According to the aviation material storage location corresponding to the aviation material scheduling needs, an improved artificial intelligence algorithm is used to plan the aviation material scheduling route. Finally, based on the aviation material scheduling route, an artificial intelligence robot is scheduled to arrive at each aviation material storage location corresponding to the aviation material scheduling needs in turn, and aviation material scheduling is performed. This method can effectively realize automatic route planning and aviation material scheduling, thereby effectively improving the efficiency of aviation material scheduling.

[0052] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0054] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0055] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0056] A person of ordinary skill in the art can understand that all or part of the steps in realizing the above-mentioned facts and methods can be completed by instructing the relevant hardware through a program, and the program involved or the program described can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: At this time, the corresponding method steps are derived, and the storage medium can be ROM / RAM, a disk, an optical disk, etc.

[0057] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An aviation material scheduling method based on artificial intelligence, characterized in that: include: Obtaining the aviation material dispatching demand input by the staff through human-computer interaction; wherein the aviation material dispatching demand includes at least one aviation material identity code and aviation material demand quantity; Querying inventory data according to the aviation material dispatching requirements to determine the aviation material storage location corresponding to the aviation material dispatching requirements; wherein the inventory data includes the association between the aviation material identity code and the aviation material storage location; According to the storage location of aviation materials corresponding to the aviation material dispatching demand, the improved artificial intelligence algorithm is used to plan the aviation material dispatching route to obtain the aviation material dispatching route; Based on the aviation material dispatching route, the artificial intelligence robot is dispatched to arrive at each aviation material storage location corresponding to the aviation material dispatching demand in turn, and the aviation material dispatching is performed.

2. The method for scheduling aviation materials based on artificial intelligence according to claim 1, characterized in that: Query inventory data based on aviation material scheduling requirements to determine the storage location of aviation materials corresponding to aviation material scheduling requirements, including: Based on the aviation material identity code in the aviation material scheduling demand, a cosine similarity matching method is used to query in the inventory data to determine the target aviation material identity code in the inventory data; Query the aviation material storage location corresponding to the target aviation material identity code to obtain the aviation material storage location corresponding to the aviation material scheduling demand.

3. The method for scheduling aviation materials based on artificial intelligence according to claim 1, characterized in that: According to the storage location of aviation materials corresponding to the aviation material dispatching demand, the improved artificial intelligence algorithm is used to plan the aviation material dispatching route, and the aviation material dispatching route is obtained, including: Generate multiple initial route codes based on the storage locations of aviation materials corresponding to aviation material scheduling requirements; The GA-ACO algorithm is used to optimize multiple initial route codes to obtain the optimal route code. After decoding the optimal route code, the aviation material scheduling route is obtained.

4. The method for scheduling aviation materials based on artificial intelligence according to claim 3, characterized in that: Based on the storage location of the aviation materials corresponding to the aviation materials scheduling requirements, multiple initial route codes are generated, including: Based on the storage location of the aviation materials corresponding to the aviation materials scheduling demand, a unique number is assigned to each aviation materials storage location; The numbers corresponding to each aviation material storage location are encoded into a vector in random order to obtain an initial route code, and multiple different initial route codes are repeatedly obtained.

5. The method for scheduling aviation materials based on artificial intelligence according to claim 3, characterized in that: The GA-ACO algorithm is used to optimize multiple initial route codes to obtain the optimal route code. After decoding the optimal route code, the aviation material scheduling route is obtained, including: For any initial route code, after decoding the initial route code, the aviation material dispatching route corresponding to the initial route code is obtained; For any aviation material dispatching route corresponding to an initial route code, the objective function of path and energy consumption is used to obtain the objective function value corresponding to the initial route code; The initial route is encoded as the parent individual in the first optimization process of the GA algorithm; Based on the objective function value corresponding to the initial route code, the crossover probability and mutation probability corresponding to each parent individual are obtained, and a crossover operation is performed according to the crossover probability and a mutation operation is performed according to the mutation probability to obtain multiple offspring individuals; Determine whether the optimization times of the GA algorithm reaches the preset first maximum optimization times. If so, obtain the first intermediate line code according to the offspring individuals and the parent individuals in the last optimization process. Otherwise, re-obtain multiple parent individuals according to the current parent individuals and the offspring individuals, and return to the step of obtaining offspring individuals based on the re-obtained parent individuals. Based on the first intermediate line coding, the pheromone concentration of the ACO algorithm and the ant colony of the ACO algorithm are initialized; Based on the pheromone concentration, each ant in the ant colony is made to crawl, obtain a plurality of second intermediate line codes, and update the pheromone concentration according to the plurality of second intermediate line codes to obtain an updated pheromone concentration; Determine whether the number of ACO optimizations reaches the preset second maximum number of optimizations. If so, obtain the optimal route code according to the second intermediate route code, otherwise return to the ant crawling step; After decoding the optimal route code, the aviation material scheduling route is obtained.

6. The method for scheduling aviation materials based on artificial intelligence according to claim 5, characterized in that: Get the crossover probability corresponding to each parent individual: Obtain the objective function value corresponding to the parent individual, and determine the optimal parent individual based on the objective function value; Determine the adaptive probability control factor according to the objective function value corresponding to the parent individual and the objective function value corresponding to the optimal parent individual; When the adaptive probability control factor is less than the preset threshold, the corresponding crossover probability of the parent individual is determined as: ; When the adaptive probability control factor is greater than or equal to the preset threshold, the corresponding crossover probability of the parent individual is determined as: ;in, Indicates a The crossover probability corresponding to the parent individuals is represents pi, Indicates a The objective function value corresponding to the parent individuals is: represents the objective function value corresponding to the optimal parent individual, arcsin represents the inverse sine function, represents the cross-process control coefficient.

7. The method for scheduling aviation materials based on artificial intelligence according to claim 6, characterized in that: The mutation probability corresponding to each parent individual is obtained as follows: When the adaptive probability control factor is less than the preset threshold, the mutation probability corresponding to the parent individual is determined as: ; When the adaptive probability control factor is greater than or equal to the preset threshold, the mutation probability corresponding to the parent individual is determined as: ;in, Indicates a The mutation probability corresponding to each parent individual is represents the coefficient of variation of the process control.

8. The method for scheduling aviation materials based on artificial intelligence according to claim 7, characterized in that: Based on the first intermediate line coding, the pheromone concentration of the ACO algorithm and the ant colony of the ACO algorithm are initialized, including: Determine the storage location of the aviation materials corresponding to the aviation materials scheduling needs, and regard each aviation materials storage location as a node; For the mth node, based on the first intermediate line code, determine the number of transfers between the mth node and the nth other node as C; The pheromone concentration between the mth node and the nth other node is C / 2M, where M represents the total number of nodes.

9. The method for scheduling aviation materials based on artificial intelligence according to claim 8, characterized in that: Based on the pheromone concentration, each ant in the ant colony is asked to crawl to obtain multiple second intermediate line codes, including: Based on the pheromone concentration, the transfer probability between any two nodes is obtained as: in, Indicates k The ants from i The node is transferred to j The transition probability of a node, Indicates i The node and j The pheromone concentration of the path between nodes, Indicates i The node and j The heuristic function value between nodes, represents the pheromone impact factor, represents the influence factor of the heuristic function, Indicates i The node and k The pheromone concentration of the path between nodes, Indicates i The node and h The heuristic function value between nodes, Indicates k The path candidate nodes of each ant; the heuristic function value is obtained by dividing the pheromone intensity by the path length between two nodes; Based on the transfer probability between any two nodes, each ant in the ant colony is made to crawl to obtain multiple second intermediate line codes.

10. The method for scheduling aviation materials based on artificial intelligence according to claim 9, characterized in that: The pheromone concentration is updated according to the multiple second intermediate line codes, and the updated pheromone concentration is obtained as follows: in, Indicates the updated pheromone concentration, represents the evaporation coefficient of the pheromone, Indicates the increment of pheromone concentration, A+B=C, Indicates the weight corresponding to the optimal path in the current optimization process, Represents the weight corresponding to the optimal path in all optimization processes, C represents the total number of nodes in the planning process, Indicates the optimal path corresponding to the current optimization process. i The node and j The path length between nodes, Indicates the optimal path corresponding to all optimization processes i The node and j The path length between nodes.

Images