An artificial intelligence-based military aviation part supply management method and system

Abstract

The application relates to the technical field of warehouse management, and particularly discloses a military aviation part supply management method and system based on artificial intelligence, which comprises the following steps: obtaining a part storage score value of each type of aviation part at the current time based on all part storage data of each type of aviation part in a preset time period before the current time; obtaining a rational value of a storage location distribution of each type of aviation part at the current time based on the part storage score value of all types of aviation parts at the current time, and then obtaining a predicted storage location distribution point of each type of aviation part at the current time; and obtaining an aviation part supply management result at the current time based on the predicted storage location distribution point of each type of aviation part at the current time. The application accurately predicts an optimal path to be taken by each type of aviation part in a warehousing process at the current time, more effectively utilizes warehouse resources, and reduces the risk of resource idling and waste.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of warehouse management, and particularly relates to a military aviation part supply management method and system based on artificial intelligence. BACKGROUND

[0002] At present, the types of aviation parts are various, the specifications are different, and the supply management becomes extremely complex. The traditional management method often depends on manual experience and intuition, and it is difficult to efficiently and accurately process a large amount of data and information. With the rapid development of the aviation industry, the storage frequency and quantity of parts are increasing, and higher requirements are put forward for the efficiency of supply management. The most important part of supply management is the warehouse management, especially in the current field of military aviation part manufacturing, the types and specifications of military aviation parts produced by the factory are more special, and more detailed warehouse processing is needed, which puts forward higher requirements for the allocation of storage space. Random allocation of storage space will lead to great waste of space and difficulty in storage. This not only increases the operating cost of the military enterprise, but also reduces the overall operating efficiency.

[0003] However, the existing military aviation parts supply management method and system based on artificial intelligence only reduces the time of workers going back and forth between the main warehouse area and the production site by generating warehouse data for goods that pass the inspection of the incoming goods inspection module and matching the goods location information, without considering accurately predicting the optimal path that each type of aviation parts should take in the current time warehouse process to more effectively utilize warehouse resources and reduce the risk of resource idling and waste. For example, the patent with the publication number "CN110717708A" and the patent name "Military aviation warehouse system and operation method thereof" includes the following steps: the incoming goods inspection module is used to identify the information of the goods to be inspected, different inspection processes are performed according to the classification of the goods to be inspected, and the inspection results are tracked; the warehouse module generates warehouse data for goods that pass the inspection of the incoming goods inspection module and matches the goods location information; the warehouse module reads the information of the existing inventory and updates the inventory information according to the warehouse order; the main warehouse area is used to store goods that have completed the inspection of the incoming goods inspection module; the on-site goods cabinet is set in the production site area, and the on-site goods cabinet contains goods needed for production; the rear goods cabinet is located in the main warehouse area, and the rear goods cabinet corresponds to the on-site goods cabinet one by one, and the rear goods cabinet is used to replenish the on-site goods cabinet. The above-mentioned patent greatly reduces the time of workers going back and forth between the main warehouse area and the production site, increases the effective working time of workers, and improves the production efficiency. However, the patent only reduces the time of workers going back and forth between the main warehouse area and the production site by generating warehouse data for goods that pass the inspection of the incoming goods inspection module and matching the goods location information, without considering accurately predicting the optimal path that each type of aviation parts should take in the current time warehouse process to more effectively utilize warehouse resources and reduce the risk of resource idling and waste.

[0004] Therefore, the present application proposes a military aviation parts supply management method and system based on artificial intelligence. SUMMARY

[0005] The application provides a kind of military aviation parts supply management method and system based on artificial intelligence, to obtain the component storage score value of each aviation component at the current time according to the storage data of all parts of each aviation component in the preset time period before the current time, the difficulty of the storage component of each aviation component at the current time is quantified, according to the storage location node graph of each aviation component at the current time, the storage location node graph of each aviation component at the current time is obtained, which is convenient for subsequent calculation of reasonable value of location allocation, and then according to the storage location node graph and component storage score value of all aviation components at the current time, the reasonable value of location allocation of each aviation component at the current time is obtained, the reasonable degree of location allocation of each aviation component at the current time is quantified, and the most reasonable storage location node of each aviation component at the current time is accurately predicted according to the reasonable value of location allocation of all times in the preset time period before the current time of each aviation component at the current time, and then according to all predicted location allocation points of each aviation component at the current time and the preset carrying path model, the predicted best storage path of each aviation component at the current time is obtained, and the optimal path to be taken in the storage process of each aviation component at the current time is accurately predicted, and finally the aviation component supply management result at the current time is obtained according to the predicted best storage path of all aviation components at the current time, which effectively improves the storage efficiency and inventory management efficiency, more effectively utilizes warehouse resources, and reduces the risk of resource idling and waste.

[0006] The application provides a kind of military aviation parts supply management method based on artificial intelligence, comprising:

[0007] S1: obtain the component storage score value of each aviation component at the current time based on the storage data of all parts of each aviation component in the preset time period before the current time;

[0008] S2: obtain the storage location node graph of each aviation component at the current time based on all storage location areas of each aviation component at the current time, and obtain the reasonable value of location allocation of each aviation component at the current time based on the storage location node graph and component storage score value of all aviation components at the current time;

[0009] S3: obtain all predicted location allocation points of each aviation component at the current time based on the reasonable value of location allocation of all times in the preset time period before the current time of each aviation component at the current time;

[0010] S4: obtaining a predicted optimal storage path of each type of aviation part at the current time based on all predicted storage allocation points and a preset handling path model of each type of aviation part at the current time, and obtaining an aviation part supply management result at the current time based on the predicted optimal storage path of all types of aviation parts at the current time.

[0011] Preferably, the military aviation part supply management method based on artificial intelligence, S1: obtaining a part storage score value of each type of aviation part at the current time based on all part storage data of each type of aviation part within a preset time period before the current time, comprising:

[0012] Obtaining all part storage data of each type of aviation part within a preset time period before the current time, wherein each part storage data comprises part taking and delivering time, part taking and delivering distance, and part taking and delivering energy consumption;

[0013] Obtaining a part storage score value of each type of aviation part at the current time based on the number of part storage data of each type of aviation part within a preset time period before the current time.

[0014] Preferably, the military aviation part supply management method based on artificial intelligence, obtaining a part storage score value of each type of aviation part at the current time based on the number of part storage data of each type of aviation part within a preset time period before the current time, comprising:

[0015] If the number of part storage data of each type of aviation part within a preset time period before the current time is zero, then the three part storage data closest to the current time sequence of the corresponding type of aviation part are regarded as the part storage data of the corresponding type of aviation part within a preset time period before the current time;

[0016] Obtaining a part storage score value of each type of aviation part at the current time based on all part storage data of each type of aviation part within a preset time period before the current time, that is:

[0017]

[0018] wherein β is the part storage score value of the currently calculated type of aviation part at the current time, z0 is the average value of the numerical value of the part taking and delivering time of all part storage data of the currently calculated type of aviation part within a preset time period before the current time, σ z is the standard deviation of the numerical value of the part taking and delivering time of all part storage data of the currently calculated type of aviation part within a preset time period before the current time, m is the number of part storage data of the currently calculated type of aviation part within a preset time period before the current time, z maxThe maximum value of the component taking and sending time in the current calculation of the aviation parts in the preset time period before the current time, z min The minimum value of the component taking and sending time in the current calculation of the aviation parts in the preset time period before the current time, c0 is the average value of the component taking and sending distance in the current calculation of the aviation parts in the preset time period before the current time, σ c The standard deviation of the component taking and sending distance in the current calculation of the aviation parts in the preset time period before the current time, c max The maximum value of the component taking and sending distance in the current calculation of the aviation parts in the preset time period before the current time, c min The minimum value of the component taking and sending distance in the current calculation of the aviation parts in the preset time period before the current time, b0 is the average value of the component taking and sending energy consumption in the current calculation of the aviation parts in the preset time period before the current time, σ b The standard deviation of the component taking and sending energy consumption in the current calculation of the aviation parts in the preset time period before the current time, b max The maximum value of the component taking and sending energy consumption in the current calculation of the aviation parts in the preset time period before the current time, b min The minimum value of the component taking and sending energy consumption in the current calculation of the aviation parts in the preset time period before the current time, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0019] Preferably, the military aviation parts supply management method based on artificial intelligence, S2: based on all storage location areas of each type of aviation parts at the current time, obtain the storage location node graph of each type of aviation parts at the current time, and based on the storage location node graph and the component storage score value of all types of aviation parts at the current time, obtain the reasonable value of the storage location of each type of aviation parts at the current time, including:

[0020] The sub-area in which each type of aviation parts is stored in all sub-areas of the current time is regarded as the storage location area of the corresponding type of aviation parts at the current time.

[0021] The sub-area in which each type of aviation parts is not stored in all sub-areas of the current time is regarded as the non-storage location area of the corresponding type of aviation parts at the current time.

[0022] Each storage location area of ​​each type of aviation component at the current moment is designated as the storage location node of the corresponding type of aviation component at the current moment, and each non-storage location area of ​​each type of aviation component at the current moment is designated as the non-storage location node of the corresponding type of aviation component at the current moment.

[0023] Based on all cargo location nodes and all non-cargo location nodes of each type of aviation component at the current moment, obtain the storage cargo location node diagram of each type of aviation component at the current moment.

[0024] Based on the storage location node diagram of all types of aviation parts at the current moment, obtain the location allocation entropy value of all types of aviation parts at the current moment;

[0025] Based on the entropy value of cargo location allocation and the component storage score of all types of aviation components at the current moment, the reasonable value of cargo location allocation for each type of aviation component at the current moment is obtained.

[0026] Preferred, the AI-based military aviation component supply management method obtains the storage location allocation entropy value of all types of aviation components at the current moment based on the storage location node graph of all types of aviation components at the current moment, including:

[0027] Using each storage location node in the current storage location node diagram of each type of aviation component as the origin and a preset distance as the radius, obtain the allocation circle of the corresponding storage location node, and take the number of other storage location nodes covered by the allocation circle of each storage location node as the number of associated points of the corresponding storage location node.

[0028] Among all the storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, the storage location node with the largest number of associated points is regarded as the central storage location node of the corresponding type of aviation parts at the current moment. And among all the storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, except for the central storage location node, the storage location nodes are regarded as the non-central storage location nodes of the corresponding type of aviation parts at the current moment.

[0029] The distance from each non-central storage location node to the central storage location node in the storage location node diagram of each type of aviation parts at the current moment is taken as the connection distance of the corresponding non-central storage location node in the storage location node diagram of the corresponding type of aviation parts at the current moment. Then, in order of ascending order of the connection distance of all non-central storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, an ordinal number starting from 1 is defined for all non-central storage location nodes to obtain the ordinal number definition result.

[0030] Based on the storage location node graph and ordinal definition results of each type of aviation component at the current moment, the location allocation entropy value of each type of aviation component at the current moment is obtained.

[0031] Preferably, the military aviation parts supply management method based on artificial intelligence obtains the storage space allocation entropy value of each type of aviation parts at the current time based on the storage space node graph and the ordinal definition result of each type of aviation parts at the current time, comprising:

[0032]

[0033] Wherein, γ is the storage space allocation entropy value of the current calculation type of aviation parts at the current time, δ i is the number of adjacent storage space nodes of the non-central storage space node with ordinal number i of the storage space node graph of the current calculation type of aviation parts at the current time, ε i is the number of adjacent non-storage space nodes of the non-central storage space node with ordinal number i of the storage space node graph of the current calculation type of aviation parts at the current time, n is the total number of non-central storage space nodes of the storage space node graph of the current calculation type of aviation parts at the current time, δ max is the maximum value of the number of adjacent storage space nodes in all non-central storage space nodes of the storage space node graph of the current calculation type of aviation parts at the current time, δ min is the minimum value of the number of adjacent storage space nodes in all non-central storage space nodes of the storage space node graph of the current calculation type of aviation parts at the current time, ε max is the maximum value of the number of adjacent non-storage space nodes in the non-central storage space node with ordinal number i of the storage space node graph of the current calculation type of aviation parts at the current time, ε min is the minimum value of the number of adjacent non-storage space nodes in the non-central storage space node with ordinal number i of the storage space node graph of the current calculation type of aviation parts at the current time, ln is the natural logarithm, and the value of natural constant e is 2.718.

[0034] Preferably, the military aviation parts supply management method based on artificial intelligence obtains the storage space allocation entropy value of each type of aviation parts at the current time based on the storage space node graph and the ordinal definition result of each type of aviation parts at the current time, comprising:

[0035]

[0036] Wherein, μ is the storage space allocation entropy value of the current calculation type of aviation parts at the current time, S β is the sum of the part storage score values of all types of aviation parts at the current time, S γ is the sum of the storage space allocation entropy values of all types of aviation parts at the current time, β is the part storage score value of the current calculation type of aviation parts at the current time, γ is the storage space allocation entropy value of the current calculation type of aviation parts at the current time, σ βAssign the standard deviation σ to the component storage scores of all types of aerospace components at the current moment. γ Assign the standard deviation of the entropy values ​​to the current location of all types of aviation parts, where ln is the natural logarithm and the natural constant e is 2.718.

[0037] Preferred, the AI-based military aviation component supply management method, S3: Based on the reasonable values ​​of cargo location allocation for each type of aviation component within a preset time period prior to the current moment, obtain all predicted cargo location allocation points for each type of aviation component at the current moment, including:

[0038] Obtain the reasonable space allocation value for each type of aviation component at all times within a preset time period before the current time;

[0039] For each type of aviation component, the time corresponding to the largest reasonable value of cargo location allocation within the preset time period before the current time is taken as the predicted time for that type of aviation component.

[0040] All cargo location nodes of each type of aviation component at the predicted time are used as the predicted cargo location allocation points of the corresponding type of aviation component at the current time.

[0041] Preferred, the AI-based military aviation parts supply management method, S4: Based on all predicted storage location allocation points and preset handling path models for each type of aviation parts at the current moment, obtain the predicted optimal warehousing path for each type of aviation parts at the current moment, and based on the predicted optimal warehousing paths for all types of aviation parts at the current moment, obtain the aviation parts supply management results for the current moment, including:

[0042] Obtain the initial location of each type of aviation component when it is put into storage at the current moment;

[0043] For each type of aviation component, the predicted storage location closest to the initial storage location of the corresponding aviation component at the current moment among all predicted storage location allocation points at the current moment shall be taken as the storage location allocation point for the corresponding aviation component at the current moment.

[0044] Based on the current storage location allocation point, initial position, and preset handling path model of each type of aviation component, the predicted optimal storage path of the corresponding type of aviation component at the current moment is obtained. Based on the predicted optimal storage paths of all types of aviation components at the current moment, the aviation component supply management result at the current moment is obtained.

[0045] This invention provides an artificial intelligence-based military aviation parts supply management system for executing any one of the artificial intelligence-based military aviation parts supply management methods in Examples 1 to 9, comprising:

[0046] The scoring module is used to obtain the component storage score of each type of aviation component at the current time based on all component storage data within a preset time period before the current time.

[0047] The calculation module is used to obtain the storage location node map of each type of aviation component at the current time based on all storage location areas of each type of aviation component at the current time, and to obtain the reasonable value of storage location allocation for each type of aviation component at the current time based on the storage location node map of all types of aviation components at the current time and the component storage score.

[0048] The prediction module is used to obtain all predicted cargo location allocation points for each type of aviation component at the current time, based on the reasonable values ​​of cargo location allocation for all times within a preset time period before the current time.

[0049] The management module is used to obtain the predicted optimal warehousing route for each type of aviation component at the current moment based on all predicted storage location allocation points and preset handling route models at the current moment, and to obtain the aviation component supply management results at the current moment based on the predicted optimal warehousing routes for all types of aviation components at the current moment.

[0050] The beneficial effects of this invention compared to existing technologies are as follows: Based on the storage data of all components of each type of aviation component within a preset time period prior to the current moment, a component storage score is obtained for each type of aviation component at the current moment, quantifying the difficulty of storing each type of aviation component at the current moment. Based on all storage location areas of each type of aviation component at the current moment, a storage location node diagram is obtained for each type of aviation component at the current moment, facilitating the calculation of reasonable location allocation values ​​in subsequent calculations. Furthermore, based on the storage location node diagram and component storage score of all types of aviation components at the current moment, a reasonable location allocation value for each type of aviation component at the current moment is obtained, quantifying the rationality of location allocation for each type of aviation component at the current moment. By calculating the reasonable values ​​of cargo location allocation for all times within a preset time period prior to the current moment, all predicted cargo location allocation points for each type of aviation component at the current moment are obtained. This accurately predicts the most reasonable cargo location node for storing each type of aviation component at the current moment. Furthermore, based on all predicted cargo location allocation points for each type of aviation component at the current moment and the preset handling path model, the predicted optimal warehousing path for each type of aviation component at the current moment is obtained. This accurately predicts the optimal path that should be taken during the warehousing process for each type of aviation component at the current moment. Finally, based on the predicted optimal warehousing path for all types of aviation components at the current moment, the supply management results for aviation components at the current moment are obtained. This effectively improves warehousing efficiency and inventory management efficiency, makes more effective use of warehouse resources, and reduces the risk of resource idleness and waste.

[0051] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written documents of this application.

[0052] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0053] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0054] Figure 1 This is a flowchart of a military aviation parts supply management method based on artificial intelligence, as described in an embodiment of the present invention.

[0055] Figure 2 This is a schematic diagram of an artificial intelligence-based military aviation parts supply management system according to an embodiment of the present invention. Detailed Implementation

[0056] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0057] Example 1:

[0058] This invention provides an artificial intelligence-based method for managing the supply of military aviation components, with reference to... Figure 1 ,include:

[0059] S1: Based on the storage data of all components of each type of aviation component within a preset time period before the current time, obtain the component storage score of each type of aviation component at the current time.

[0060] S2: Based on all storage location areas of each type of aviation component at the current moment, obtain the storage location node map of each type of aviation component at the current moment, and based on the storage location node map of all types of aviation components at the current moment and the component storage score, obtain the reasonable value of storage location allocation for each type of aviation component at the current moment.

[0061] S3: Based on the reasonable value of cargo location allocation for each type of aviation component within the preset time period before the current time, obtain all predicted cargo location allocation points for each type of aviation component at the current time.

[0062] S4: Based on all predicted storage location allocation points and preset handling path models for each type of aviation component at the current moment, obtain the predicted optimal warehousing path for each type of aviation component at the current moment, and based on the predicted optimal warehousing paths for all types of aviation components at the current moment, obtain the aviation component supply management results for the current moment.

[0063] In this embodiment, aviation components refer to various parts and assemblies that make up the aircraft body, engine, and airborne equipment.

[0064] In this embodiment, the preset time period is a pre-set time period used to obtain component storage data for each type of aviation component.

[0065] In this embodiment, the component storage data includes the component retrieval time, component retrieval distance, and component retrieval energy consumption of all component storage data (each component storage data is the data generated each time an aviation component is put into storage) within a preset time period before the current time for each type of aviation component.

[0066] In this embodiment, the component storage score for each type of aviation component at the current moment is a score obtained based on all component storage data of each type of aviation component within a preset time period before the current moment, which can characterize the difficulty of storing components for each type of aviation component at the current moment.

[0067] In this embodiment, the storage location area is all the sub-areas of the cargo storage area at the current moment, and the sub-area stores each type of aviation parts.

[0068] In this embodiment, the storage location node diagram of each type of aviation component at the current moment is a node diagram obtained based on all storage location areas of each type of aviation component at the current moment, which can reflect the storage status of the cargo storage area of ​​each type of aviation component at the current moment.

[0069] In this embodiment, the reasonable value of the storage location allocation for each type of aviation component at the current moment is a value obtained based on the storage location node diagram and component storage score of all types of aviation components at the current moment, which can characterize the reasonableness of the storage location allocation for each type of aviation component at the current moment.

[0070] In this embodiment, all moments are selected from a preset time period before the current moment, and the time length between each adjacent moment is the same.

[0071] In this embodiment, the predicted cargo location allocation point for each type of aviation component at the current moment is the most reasonable cargo location node for storing each type of aviation component at the current moment, based on the reasonable cargo location allocation values ​​of each type of aviation component at all times within a preset time period before the current moment.

[0072] In this embodiment, the preset handling path model is a neural network model that takes the pre-collected warehouse location allocation points of multiple types of aviation parts at multiple times (the most suitable warehouse location node selected from all predicted warehouse location allocation points of each type of aviation part at the current time) and the initial warehouse location of the corresponding type of aviation parts at the corresponding time as input to the model. The manually labeled parts handling trajectory between the warehouse location allocation point of each type of aviation part at each time and the initial warehouse location of the corresponding type of aviation parts at the corresponding time is used as the model output. The trained model can take the warehouse location allocation point of each type of aviation part at each time and the initial warehouse location of the corresponding type of aviation parts at the corresponding time as input, and can output the parts handling trajectory between the warehouse location allocation point of each type of aviation part at each time and the initial warehouse location of the corresponding type of aviation parts at the corresponding time (the predicted best warehouse location path of each type of aviation part at the current time).

[0073] In this embodiment, the predicted optimal warehousing path for each type of aviation component at the current moment is the optimal path that each type of aviation component should take during the warehousing process at the current moment.

[0074] In this embodiment, the current aviation parts supply management result is the management result obtained by storing all types of aviation parts (all types of aviation parts that are stored in the warehouse at the current time) according to the predicted optimal storage path of the corresponding type of aviation parts at the current time.

[0075] The beneficial effects of the above technology are as follows: Based on the storage data of all components of each type of aviation component within a preset time period before the current moment, the component storage score of each type of aviation component at the current moment is obtained, thus quantifying the difficulty of storing each type of aviation component at the current moment. Based on all storage location areas of each type of aviation component at the current moment, a storage location node map of each type of aviation component at the current moment is obtained, facilitating the calculation of reasonable location allocation values ​​in subsequent calculations. Furthermore, based on the storage location node map and component storage score of all types of aviation components at the current moment, a reasonable location allocation value for each type of aviation component at the current moment is obtained, thus quantifying the rationality of location allocation for each type of aviation component at the current moment. By calculating the reasonable values ​​of cargo location allocation at all times within a pre-set time period, the predicted cargo location allocation points for each type of aviation component at the current time are obtained. This accurately predicts the most reasonable cargo location node for storing each type of aviation component at the current time. Furthermore, based on all the predicted cargo location allocation points for each type of aviation component at the current time and the pre-set handling path model, the predicted optimal warehousing path for each type of aviation component at the current time is obtained. This accurately predicts the optimal path that should be taken during the warehousing process for each type of aviation component at the current time. Finally, based on the predicted optimal warehousing path for all types of aviation components at the current time, the supply management results for aviation components at the current time are obtained. This effectively improves warehousing efficiency and inventory management efficiency, makes more effective use of warehouse resources, and reduces the risk of resource idleness and waste.

[0076] Example 2:

[0077] Based on Example 1, the AI-based military aviation component supply management method, S1: Based on all component storage data of each type of aviation component within a preset time period before the current moment, obtain the component storage score of each type of aviation component at the current moment, including:

[0078] Acquire all component storage data for each type of aviation component within a preset time period before the current moment. Each component storage data includes component retrieval and delivery time, component retrieval and delivery distance, and component retrieval and delivery energy consumption.

[0079] Based on the number of data entries stored in each type of aviation component within a preset time period before the current moment, the component storage score for each type of aviation component at the current moment is obtained.

[0080] In this embodiment, the component retrieval time is the time (in seconds) consumed during the warehousing process of the aviation parts corresponding to each component storage data.

[0081] In this embodiment, the component retrieval distance is the length (in meters) of the handling path during the warehousing process of the aviation parts corresponding to each component storage data.

[0082] In this embodiment, the energy consumption for component retrieval is the energy consumption (joules) during the warehousing process of the aviation parts corresponding to each component storage data.

[0083] The beneficial effects of the above technology are: based on the number of component storage data entries for each type of aviation component within a preset time period before the current moment, the component storage score for each type of aviation component at the current moment can be obtained, which facilitates the calculation of reasonable values ​​for subsequent cargo space allocation.

[0084] Example 3:

[0085] Based on Example 2, the AI-based military aviation component supply management method obtains a component storage score for each type of aviation component at the current moment based on the number of component storage data entries within a preset time period prior to the current moment, including:

[0086] If the number of component storage data entries for each type of aviation component within a preset time period before the current time is zero, then the three component storage data entries for the corresponding type of aviation component that are closest in time to the current time will be regarded as the component storage data for the corresponding type of aviation component within the preset time period before the current time.

[0087] Based on the storage data of all components for each type of aviation component within a preset time period prior to the current moment, the component storage score for the corresponding type of aviation component at the current moment is obtained, which is:

[0088]

[0089] Where β is the component storage score of the current computational aerospace component at the current moment, z0 is the average value of the component retrieval time of all component storage data of the current computational aerospace component within a preset time period before the current moment, and σ z Let m be the standard deviation of the component retrieval and delivery times for all data stored in the current computational aerospace component within a preset time period prior to the current time, and z be the number of data entries stored in the current computational aerospace component within the preset time period prior to the current time. max z is the maximum value of the component retrieval time value among all component storage data within a preset time period before the current time for the current computational aerospace component. min Let c0 be the minimum value of the component retrieval time among all component storage data within a preset time period before the current time for the current computational aerospace component, and σ be the average value of the component retrieval distance among all component storage data within a preset time period before the current time for the current computational aerospace component. c c is the standard deviation of the component retrieval and delivery distance values ​​for all component storage data within a preset time period prior to the current moment for the current computational aerospace component. maxc is the maximum value of the component retrieval distance value among all component storage data within a preset time period before the current time for the currently computed aerospace component. min Let b0 be the minimum value of the component retrieval distance among all component storage data within a preset time period before the current time for the current computing-type aerospace component, and let σ be the average value of the component retrieval energy consumption among all component storage data within a preset time period before the current time for the current computing-type aerospace component. b b is the standard deviation of the energy consumption for retrieving and sending data from all components within a preset time period prior to the current moment for the current computational aerospace component. max b is the maximum value of the component's energy consumption for retrieval and transmission among all component storage data within a preset time period before the current moment for the current computational aerospace component. min The minimum value of energy consumption for component retrieval and transmission among all component storage data within a preset time period before the current time for the current computational aerospace component is given, where ln is the natural logarithm and the natural constant e is 2.718.

[0090] The beneficial effects of the above technology are as follows: Based on the storage data of all components of each type of aviation component within a preset time period before the current time, the component storage score of each type of aviation component at the current time is obtained, thereby realizing the quantification of the difficulty of storing components of each type of aviation component at the current time. This embodiment provides a detailed method for quantifying the difficulty of storing components of each type of aviation component at the current time.

[0091] Example 4:

[0092] Based on Example 1, the AI-based military aviation component supply management method, S2: Based on all storage location areas for each type of aviation component at the current moment, obtain the storage location node map for each type of aviation component at the current moment, and based on the storage location node map of all types of aviation components at the current moment and the component storage score, obtain the reasonable location allocation value for each type of aviation component at the current moment, including:

[0093] Within all sub-areas of the current cargo storage area, the sub-area containing each type of aviation parts is taken as the storage location area for the corresponding type of aviation parts at the current moment.

[0094] In the current cargo storage area, any sub-area that does not store each type of aviation component is considered as the non-stored cargo location area for the corresponding type of aviation component at the current moment.

[0095] Each storage location area of ​​each type of aviation component at the current moment is designated as the storage location node of the corresponding type of aviation component at the current moment, and each non-storage location area of ​​each type of aviation component at the current moment is designated as the non-storage location node of the corresponding type of aviation component at the current moment.

[0096] Based on all cargo location nodes and all non-cargo location nodes of each type of aviation component at the current moment, obtain the storage cargo location node diagram of each type of aviation component at the current moment.

[0097] Based on the storage location node diagram of all types of aviation parts at the current moment, obtain the location allocation entropy value of all types of aviation parts at the current moment;

[0098] Based on the entropy value of cargo location allocation and the component storage score of all types of aviation components at the current moment, the reasonable value of cargo location allocation for each type of aviation component at the current moment is obtained.

[0099] In this embodiment, the cargo storage area is a warehouse area used to store military aviation parts.

[0100] In this embodiment, the sub-region is a sub-storage area pre-divided from the cargo storage area.

[0101] In this embodiment, based on all cargo location nodes and all non-cargo location nodes of each type of aviation component at the current moment, a storage cargo location node diagram for each type of aviation component at the current moment is obtained, which is:

[0102] For each type of aviation component, select any two nodes (not the same node) from all cargo location nodes and all non-cargo location nodes at the current moment to form a node group, and obtain all groups of nodes for each type of aviation component.

[0103] If the sub-regions corresponding to two nodes in each group of nodes for each type of aviation component are connected (whether the actual range is connected or not), then the two nodes in the corresponding group of nodes for the corresponding type of aviation component are connected to obtain the storage location node diagram of each type of aviation component at the current time.

[0104] In this embodiment, the entropy value of the cargo location allocation of aviation components at the current moment is a value obtained based on the storage cargo location node graph of all types of aviation components at the current moment, which can characterize the degree of disorder in the cargo location allocation state of each type of aviation component at the current moment. The larger the cargo location allocation entropy value, the more disordered the cargo location allocation.

[0105] The beneficial effects of the above technology are as follows: Based on all storage location areas of each type of aviation component at the current time, all storage location nodes and all non-storage location nodes of each type of aviation component at the current time are obtained. Then, based on all storage location nodes and all non-storage location nodes of each type of aviation component at the current time, a storage location node diagram of each type of aviation component at the current time is obtained. This embodiment provides a detailed method for drawing a storage location node diagram of each type of aviation component at the current time, which facilitates the calculation of reasonable values ​​for subsequent storage location allocation.

[0106] Example 5:

[0107] Based on Example 4, the AI-based military aviation component supply management method obtains the storage location allocation entropy value of all types of aviation components at the current moment based on the storage location node graph of all types of aviation components at the current moment, including:

[0108] Using each storage location node in the current storage location node diagram of each type of aviation component as the origin and a preset distance as the radius, obtain the allocation circle of the corresponding storage location node, and take the number of other storage location nodes covered by the allocation circle of each storage location node as the number of associated points of the corresponding storage location node.

[0109] Among all the storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, the storage location node with the largest number of associated points is regarded as the central storage location node of the corresponding type of aviation parts at the current moment. And among all the storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, except for the central storage location node, the storage location nodes are regarded as the non-central storage location nodes of the corresponding type of aviation parts at the current moment.

[0110] The distance from each non-central storage location node to the central storage location node in the storage location node diagram of each type of aviation parts at the current moment is taken as the connection distance of the corresponding non-central storage location node in the storage location node diagram of the corresponding type of aviation parts at the current moment. Then, in order of ascending order of the connection distance of all non-central storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, an ordinal number starting from 1 is defined for all non-central storage location nodes to obtain the ordinal number definition result.

[0111] Based on the storage location node graph and ordinal definition results of each type of aviation component at the current moment, the location allocation entropy value of each type of aviation component at the current moment is obtained.

[0112] In this embodiment, the preset distance is a pre-set distance threshold used to obtain the allocation circle of each storage location node.

[0113] In this embodiment, the number of associated points of a storage location node is the number of other storage location nodes covered by the allocation circle of the storage location node.

[0114] The beneficial effects of the above technology are as follows: Based on the storage location node diagram of each type of aviation component at the current moment, all non-central storage location nodes and central storage location nodes of each type of aviation component at the current moment are obtained. Then, based on all non-central storage location nodes and central storage location nodes of each type of aviation component at the current moment, the ordinal definition result is obtained, which facilitates the calculation of the entropy value of subsequent storage location allocation.

[0115] Example 6:

[0116] Based on Example 5, the AI-based military aviation component supply management method obtains the storage location allocation entropy value of each type of aviation component at the current moment based on the storage location node graph and ordinal definition results at the current moment, including:

[0117]

[0118] Where γ is the entropy value of the current location allocation for the calculated aviation component at the current moment, and δ i Let ε be the number of adjacent storage location nodes of the non-central storage location node with ordinal number i in the storage location node node graph of the current computational aerospace component at the current moment. i Let δ be the number of non-central storage nodes adjacent to the non-central storage node i in the storage location node graph of the current computing-type aerospace component at the current moment, and let n be the total number of non-central storage nodes in the storage location node graph of the current computing-type aerospace component at the current moment. max δ represents the maximum number of adjacent storage location nodes among all non-central storage location nodes in the storage location node graph of the currently computed aerospace parts at the current moment. min ε is the minimum number of adjacent storage location nodes among all non-central storage location nodes in the storage location node graph of the currently computed aerospace parts at the current moment. max ε is the maximum number of adjacent non-location nodes among the non-central location node with ordinal number i in the storage location node graph of the current computational aerospace component at the current moment. min Let ln be the minimum number of adjacent non-location nodes among the non-central location nodes of the storage location node graph of the current computing class aviation parts at the current time with ordinal number i, where ln is the natural logarithm and the natural constant e is 2.718.

[0119] In this embodiment, adjacent nodes are two nodes connected within the corresponding storage location node diagram.

[0120] The beneficial effects of the above technology are as follows: based on the storage location node diagram and ordinal definition results of each type of aviation component at the current moment, the location allocation entropy value of each type of aviation component at the current moment is accurately obtained. This embodiment provides a detailed method for accurately quantifying the degree of disorder in the location allocation state of each type of aviation component at the current moment.

[0121] Example 7:

[0122] Building upon Example 4, the AI-based military aviation component supply management method obtains a reasonable allocation value for each type of aviation component at the current moment based on the entropy value of the storage location allocation and the component storage score of all types of aviation components at the current time. This includes:

[0123]

[0124] Where μ is the reasonable value for the current location allocation of the calculated aviation parts at the current moment, and S β S represents the sum of the component storage scores for all types of aerospace parts at the current moment. γ Let β be the sum of the entropy values ​​assigned to the storage locations of all types of aviation components at the current moment, γ be the component storage score assigned to the current type of aviation component at the current moment, and σ be the entropy value assigned to the storage locations of the current type of aviation component at the current moment. β Assign the standard deviation σ to the component storage scores of all types of aerospace components at the current moment. γ Assign the standard deviation of the entropy values ​​to the current location of all types of aviation parts, where ln is the natural logarithm and the natural constant e is 2.718.

[0125] The beneficial effects of the above technology are as follows: Based on the storage location node diagram and component storage score of all types of aviation parts at the current moment, the reasonable value of the storage location allocation for each type of aviation parts at the current moment is obtained, which realizes the quantification of the reasonableness of the storage location allocation for each type of aviation parts at the current moment, which helps to allocate storage locations more efficiently, improve storage efficiency, and reduce handling time and costs.

[0126] Example 8:

[0127] Based on Example 1, the AI-based military aviation component supply management method, S3: Based on the reasonable values ​​of cargo location allocation for each type of aviation component at all times within a preset time period before the current time, obtain all predicted cargo location allocation points for each type of aviation component at the current time, including:

[0128] Obtain the reasonable space allocation value for each type of aviation component at all times within a preset time period before the current time;

[0129] For each type of aviation component, the time corresponding to the largest reasonable value of cargo location allocation within the preset time period before the current time is taken as the predicted time for that type of aviation component.

[0130] All cargo location nodes of each type of aviation component at the predicted time are used as the predicted cargo location allocation points of the corresponding type of aviation component at the current time.

[0131] The beneficial effects of the above technology are as follows: Based on the reasonable value of the cargo location allocation for each type of aviation component within the preset time period before the current time, all predicted cargo location allocation points for each type of aviation component at the current time are obtained, and the most reasonable cargo location node for storing each type of aviation component at the current time is accurately predicted, which facilitates the subsequent prediction of the best warehousing path and improves storage efficiency.

[0132] Example 9:

[0133] Based on Example 1, the AI-based military aviation parts supply management method, S4: Based on all predicted storage location allocation points and preset handling path models for each type of aviation parts at the current moment, obtain the predicted optimal warehousing path for each type of aviation parts at the current moment, and based on the predicted optimal warehousing paths for all types of aviation parts at the current moment, obtain the aviation parts supply management results for the current moment, including:

[0134] Obtain the initial location of each type of aviation component when it is put into storage at the current moment;

[0135] For each type of aviation component, the predicted storage location closest to the initial storage location of the corresponding aviation component at the current moment among all predicted storage location allocation points at the current moment shall be taken as the storage location allocation point for the corresponding aviation component at the current moment.

[0136] Based on the current storage location allocation point, initial position, and preset handling path model of each type of aviation component, the predicted optimal storage path of the corresponding type of aviation component at the current moment is obtained. Based on the predicted optimal storage paths of all types of aviation components at the current moment, the aviation component supply management result at the current moment is obtained.

[0137] In this embodiment, the initial location for warehousing is the location where each type of aerospace component is transported into the warehouse (which has multiple entrances and exits) immediately after production.

[0138] The beneficial effects of the above technology are as follows: Based on all predicted storage location allocation points and preset handling path models for each type of aviation component at the current moment, the predicted optimal warehousing path for each type of aviation component at the current moment is obtained. The optimal path to be taken during the warehousing process of each type of aviation component at the current moment is accurately predicted. Finally, based on the predicted optimal warehousing paths of all types of aviation components at the current moment, the supply management results of aviation components at the current moment are obtained. This effectively improves warehousing efficiency and inventory management efficiency, makes more effective use of warehouse resources, and reduces the risk of resource idleness and waste.

[0139] Example 10:

[0140] This invention provides an artificial intelligence-based military aviation parts supply management system for executing any one of the artificial intelligence-based military aviation parts supply management methods in Examples 1 to 9, with reference to... Figure 2 ,include:

[0141] The scoring module is used to obtain the component storage score of each type of aviation component at the current time based on all component storage data within a preset time period before the current time.

[0142] The calculation module is used to obtain the storage location node map of each type of aviation component at the current time based on all storage location areas of each type of aviation component at the current time, and to obtain the reasonable value of storage location allocation for each type of aviation component at the current time based on the storage location node map of all types of aviation components at the current time and the component storage score.

[0143] The prediction module is used to obtain all predicted cargo location allocation points for each type of aviation component at the current time, based on the reasonable values ​​of cargo location allocation for all times within a preset time period before the current time.

[0144] The management module is used to obtain the predicted optimal warehousing route for each type of aviation component at the current moment based on all predicted storage location allocation points and preset handling route models at the current moment, and to obtain the aviation component supply management results at the current moment based on the predicted optimal warehousing routes for all types of aviation components at the current moment.

[0145] The beneficial effects of the above technology are as follows: Based on the storage data of all components of each type of aviation component within a preset time period before the current moment, the component storage score of each type of aviation component at the current moment is obtained, thus quantifying the difficulty of storing each type of aviation component at the current moment. Based on all storage location areas of each type of aviation component at the current moment, a storage location node map of each type of aviation component at the current moment is obtained, facilitating the calculation of reasonable location allocation values ​​in subsequent calculations. Furthermore, based on the storage location node map and component storage score of all types of aviation components at the current moment, a reasonable location allocation value for each type of aviation component at the current moment is obtained, thus quantifying the rationality of location allocation for each type of aviation component at the current moment. By calculating the reasonable values ​​of cargo location allocation at all times within a pre-set time period, the predicted cargo location allocation points for each type of aviation component at the current time are obtained. This accurately predicts the most reasonable cargo location node for storing each type of aviation component at the current time. Furthermore, based on all the predicted cargo location allocation points for each type of aviation component at the current time and the pre-set handling path model, the predicted optimal warehousing path for each type of aviation component at the current time is obtained. This accurately predicts the optimal path that should be taken during the warehousing process for each type of aviation component at the current time. Finally, based on the predicted optimal warehousing path for all types of aviation components at the current time, the supply management results for aviation components at the current time are obtained. This effectively improves warehousing efficiency and inventory management efficiency, makes more effective use of warehouse resources, and reduces the risk of resource idleness and waste.

[0146] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from the spirit and scope of this invention, and this invention is also intended to include these modifications and variations.

Claims

1. A method for managing the supply of military aviation components based on artificial intelligence, characterized in that, include: S1: Based on the storage data of all components of each type of aviation component within a preset time period before the current time, obtain the component storage score of each type of aviation component at the current time. The storage data of all components is the data generated each time an aviation component is put into storage. S2: Based on all storage location areas of each type of aviation component at the current moment, obtain the storage location node map of each type of aviation component at the current moment, and based on the storage location node map of all types of aviation components at the current moment and the component storage score, obtain the reasonable value of storage location allocation for each type of aviation component at the current moment. S3: Based on the reasonable value of cargo location allocation for each type of aviation component within the preset time period before the current time, obtain all predicted cargo location allocation points for each type of aviation component at the current time. S4: Based on all predicted storage location allocation points and preset handling path models for each type of aviation component at the current moment, obtain the predicted optimal warehousing path for each type of aviation component at the current moment, and based on the predicted optimal warehousing paths for all types of aviation components at the current moment, obtain the aviation component supply management results for the current moment. Specifically, based on all storage location areas for each type of aviation component at the current moment, a storage location node map for each type of aviation component at the current moment is obtained. Furthermore, based on the storage location node maps of all types of aviation components at the current moment and the component storage score, a reasonable location allocation value for each type of aviation component at the current moment is obtained, including: Within all sub-areas of the current cargo storage area, the sub-area containing each type of aviation parts is taken as the storage location area for the corresponding type of aviation parts at the current moment. In the current cargo storage area, any sub-area that does not store each type of aviation component is considered as the non-stored cargo location area for the corresponding type of aviation component at the current moment. Each storage location area of ​​each type of aviation component at the current moment is designated as the storage location node of the corresponding type of aviation component at the current moment, and each non-storage location area of ​​each type of aviation component at the current moment is designated as the non-storage location node of the corresponding type of aviation component at the current moment. Based on all cargo location nodes and all non-cargo location nodes of each type of aviation component at the current moment, obtain the storage cargo location node diagram of each type of aviation component at the current moment. Based on the storage location node diagram of all types of aviation parts at the current moment, obtain the location allocation entropy value of all types of aviation parts at the current moment; Based on the entropy value of cargo location allocation and the component storage score of all types of aviation components at the current moment, the reasonable value of cargo location allocation for each type of aviation component at the current moment is obtained.

2. The method for managing the supply of military aviation components based on artificial intelligence according to claim 1, characterized in that, S1: Based on the storage data of all components for each type of aviation component within a preset time period prior to the current moment, obtain the component storage score for each type of aviation component at the current moment, including: Acquire all component storage data for each type of aviation component within a preset time period before the current moment. Each component storage data includes component retrieval and delivery time, component retrieval and delivery distance, and component retrieval and delivery energy consumption. Based on the number of data entries stored in each type of aviation component within a preset time period before the current moment, the component storage score for each type of aviation component at the current moment is obtained.

3. The method for managing the supply of military aviation components based on artificial intelligence according to claim 2, characterized in that, Based on the number of data entries stored in each type of aviation component within a preset time period prior to the current moment, a component storage score is obtained for each type of aviation component at the current moment, including: If the number of component storage data entries for each type of aviation component within a preset time period before the current time is zero, then the three component storage data entries for the corresponding type of aviation component that are closest in time to the current time will be regarded as the component storage data for the corresponding type of aviation component within the preset time period before the current time. Based on the storage data of all components for each type of aviation component within a preset time period prior to the current moment, the component storage score for the corresponding type of aviation component at the current moment is obtained, which is: ； in, Assign a score to the component storage of the current computational aerospace component at the current moment. This is the average of the component retrieval and delivery times for all components storing data within a preset time period prior to the current moment, representing the current computational aerospace component. This is the standard deviation of the component retrieval and delivery times for all component-stored data within a preset time period prior to the current moment for the current computational aerospace component. The number of data entries stored for the current computational aerospace component within a preset time period prior to the current moment. This represents the maximum value of the component retrieval time among all component storage data within a preset time period prior to the current moment for the currently computed aerospace component. This is the minimum value of the component retrieval time among all component storage data within a preset time period prior to the current moment for the currently computed aerospace component. This is the average of the component retrieval and delivery distances for all components storing data within a preset time period prior to the current moment, representing the current computational aerospace component. This represents the standard deviation of the component retrieval and delivery distance values ​​for all component-stored data within a preset time period prior to the current moment for the current computational aerospace component. This represents the maximum value of the component retrieval distance among all component storage data for the currently computed aerospace component within a preset time period prior to the current moment. This is the minimum value of the component retrieval distance among all component storage data within a preset time period prior to the current moment for the currently computed aerospace component. This is the average energy consumption for retrieving and sending data from all components within a preset time period prior to the current moment for the current computational aerospace component. This represents the standard deviation of the energy consumption for retrieving and sending data from all components within a preset time period prior to the current moment for all computational aerospace components. This represents the maximum energy consumption value for component retrieval and transmission among all component storage data within a preset time period prior to the current moment for the current computational aerospace component. This is the minimum energy consumption value for component retrieval and transmission among all component storage data within a preset time period prior to the current moment for the current computational aerospace component. It is the natural logarithm, and the natural constant e has a value of 2.

718.

4. The method for managing the supply of military aviation components based on artificial intelligence according to claim 1, characterized in that, Based on the storage location node graph of all types of aviation components at the current moment, obtain the location allocation entropy value of all types of aviation components at the current moment, including: Using each storage location node in the current storage location node diagram of each type of aviation component as the origin and a preset distance as the radius, obtain the allocation circle of the corresponding storage location node, and take the number of other storage location nodes covered by the allocation circle of each storage location node as the number of associated points of the corresponding storage location node. Among all the storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, the storage location node with the largest number of associated points is regarded as the central storage location node of the corresponding type of aviation parts at the current moment. And among all the storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, except for the central storage location node, the storage location nodes are regarded as the non-central storage location nodes of the corresponding type of aviation parts at the current moment. The distance from each non-central storage location node to the central storage location node in the storage location node diagram of each type of aviation parts at the current moment is taken as the connection distance of the corresponding non-central storage location node in the storage location node diagram of the corresponding type of aviation parts at the current moment. Then, in order of ascending order of the connection distance of all non-central storage location nodes in the storage location node diagram of each type of aviation parts at the current moment, an ordinal number starting from 1 is defined for all non-central storage location nodes to obtain the ordinal number definition result. Based on the storage location node graph and ordinal definition results of each type of aviation component at the current moment, the location allocation entropy value of each type of aviation component at the current moment is obtained.

5. The method for managing the supply of military aviation components based on artificial intelligence according to claim 4, characterized in that, Based on the storage location node graph and ordinal definition results of each type of aviation component at the current moment, the location allocation entropy value of each type of aviation component at the current moment is obtained, including: ； in, Assign an entropy value to the current location of the calculated aviation component at the current moment. The ordinal number of the storage location node in the current computational aerospace component at the current moment is: The number of adjacent storage location nodes of a non-central storage location node. The ordinal number of the storage location node in the current computational aerospace component at the current moment is: The number of non-positional nodes adjacent to a non-central positional node. This represents the total number of non-central storage location nodes in the storage location node graph of the current computational aerospace parts at the current moment. This represents the maximum number of adjacent storage location nodes among all non-central storage location nodes in the storage location node graph of the currently computed aerospace parts at the current moment. This represents the minimum number of adjacent storage location nodes among all non-central storage location nodes in the storage location node graph of the currently computed aerospace parts at the current moment. The ordinal number of the storage location node in the current computational aerospace component at the current moment is: The maximum number of adjacent non-position nodes in a non-central position node. The ordinal number of the storage location node in the current computational aerospace component at the current moment is: The minimum number of adjacent non-position nodes in a non-central position node. It is the natural logarithm, and the natural constant e has a value of 2.

718. e is a natural number with a value of 2.

718.

6. The method for managing the supply of military aviation components based on artificial intelligence according to claim 1, characterized in that, Based on the entropy value of cargo location allocation and the component storage score of all types of aviation components at the current moment, the reasonable value of cargo location allocation for each type of aviation component at the current moment is obtained, including: ； in, Assign a reasonable value to the storage location of the currently computed aerospace components at the current moment. The sum of the component scores for all types of aviation parts at the current moment is stored. Assign the sum of entropy values ​​to the storage locations of all types of aviation parts at the current moment. Assign a score to the component storage of the current computational aerospace component at the current moment. Assign an entropy value to the current location of the calculated aviation component at the current moment. Assign the standard deviation of the component storage scores for all types of aviation parts at the current moment. Assign the standard deviation of the entropy values ​​to the storage locations of all types of aviation parts at the current moment. It is the natural logarithm, and the natural constant e has a value of 2.

718.

7. The method for managing the supply of military aviation components based on artificial intelligence according to claim 1, characterized in that, S3: Based on the reasonable space allocation values ​​for each type of aviation component at all times within a preset time period prior to the current time, obtain all predicted space allocation points for each type of aviation component at the current time, including: Obtain the reasonable space allocation value for each type of aviation component at all times within a preset time period before the current time; For each type of aviation component, the time corresponding to the largest reasonable value of cargo location allocation within the preset time period before the current time is taken as the predicted time for that type of aviation component. All cargo location nodes of each type of aviation component at the predicted time are used as the predicted cargo location allocation points of the corresponding type of aviation component at the current time.

8. The method for managing the supply of military aviation components based on artificial intelligence according to claim 1, characterized in that, S4: Based on all predicted storage location allocation points and preset handling path models for each type of aviation component at the current moment, obtain the predicted optimal warehousing path for each type of aviation component at the current moment. Based on the predicted optimal warehousing paths for all types of aviation components at the current moment, obtain the aviation component supply management results for the current moment, including: Obtain the initial location of each type of aviation component when it is put into storage at the current moment; For each type of aviation component, the predicted storage location closest to the initial storage location of the corresponding aviation component at the current moment among all predicted storage location allocation points at the current moment shall be taken as the storage location allocation point for the corresponding aviation component at the current moment. Based on the current storage location allocation point, initial position, and preset handling path model of each type of aviation component, the predicted optimal storage path of the corresponding type of aviation component at the current moment is obtained. Based on the predicted optimal storage paths of all types of aviation components at the current moment, the aviation component supply management result at the current moment is obtained.

9. A military aviation parts supply management system based on artificial intelligence, characterized in that, A method for implementing an artificial intelligence-based military aviation parts supply management system as described in any one of claims 1 to 8, comprising: The scoring module is used to obtain the component storage score of each type of aviation component at the current time based on all component storage data within a preset time period before the current time. The calculation module is used to obtain the storage location node map of each type of aviation component at the current time based on all storage location areas of each type of aviation component at the current time, and to obtain the reasonable value of storage location allocation for each type of aviation component at the current time based on the storage location node map of all types of aviation components at the current time and the component storage score. The prediction module is used to obtain all predicted cargo location allocation points for each type of aviation component at the current time, based on the reasonable values ​​of cargo location allocation for all times within a preset time period before the current time. The management module is used to obtain the predicted optimal warehousing route for each type of aviation component at the current moment based on all predicted storage location allocation points and preset handling route models at the current moment, and to obtain the aviation component supply management results at the current moment based on the predicted optimal warehousing routes for all types of aviation components at the current moment.

Images