Intelligent aerial material inventory management method, system, equipment and medium

Abstract

The invention discloses an intelligent aerial material inventory management method, system and device and a medium. The method comprises the steps of obtaining aerial material inventory data and determining an initial K value of each piece of aerial material inventory data; determining the floating degree of each data point in each piece of aerial material inventory data; dividing the aerial material inventory data according to a preset step length to obtain a plurality of groups; according to the floating degree and the inventory value of each data point in each group, adjusting an initial K value of each air material inventory data to obtain a dynamic K value of each air material inventory data; performing anomaly detection on the aerial material inventory data by using an LOF algorithm according to the dynamic K value of each piece of aerial material inventory data, and obtaining an abnormal inventory value of the corresponding aerial material; and adjusting the management method of the aerial material inventory based on the abnormal inventory value. According to the method and the device, different K values can be set for different data in the aerial material inventory data, the anomaly detection precision is improved, and meanwhile, the seasonal influence of the aerial material inventory data is eliminated.

Description

Technical Field

[0001] This application relates to the technical field of aviation material management, and particularly to an intelligent aviation material inventory management method, system, device and medium. Background Art

[0002] With the continuous increase in the amount of data in the aviation industry, it is crucial to detect outliers in aviation material inventory data. By promptly identifying and correcting outliers, resource waste can be effectively prevented, unnecessary procurement or inventory backlogs can be avoided, thus saving costs. In addition, accurate data supports more efficient operations and decision-making, helps ensure the availability of aviation materials, and reduces the risk of downtime. At the same time, outlier detection can also enhance safety, ensure that the materials used comply with industry standards and regulations, and thus maintain the healthy operation of the overall supply chain.

[0003] In related technologies, the LOF algorithm is usually used to detect outliers in aviation material inventory data. However, in the traditional LOF algorithm, the K value needs to be set artificially in advance, and the data characteristics of aviation material inventory data are not considered when setting the K value, resulting in deviations in the obtained outliers, which is not conducive to the intelligent management of aviation material inventory data.

[0004] The above content is only used to assist in understanding the technical solution of this application, and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide an intelligent aviation material inventory management method, system, device and medium, aiming to solve the technical problem that when the traditional LOF algorithm is used to detect outliers in aviation material inventory data, the K value needs to be set in advance and improper setting will affect the outlier detection result.

[0006] To achieve the above purpose, this application provides an intelligent aviation material inventory management method, including: obtaining aviation material inventory data and determining the initial K value of each aviation material inventory data; determining the floating degree of each data point in each aviation material inventory data according to the inventory value difference between adjacent data points in each aviation material inventory data; dividing each aviation material inventory data into several groups according to a preset step size; adjusting the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data; using the LOF algorithm to detect outliers in the aviation material inventory data according to the dynamic K value of each aviation material inventory data and obtaining the abnormal inventory value of the corresponding aviation material; adjusting the management method of the aviation material inventory based on the abnormal inventory value.

[0007] Optionally, determining the initial K value of each aviation material inventory data includes: obtaining the service life data and the necessity degree data of each aviation material; determining the adjustment factor of each aviation material based on the service life data and the necessity degree data of each aviation material; and adjusting the preset K value of the LOF algorithm based on the adjustment factor of each aviation material to obtain the initial K value of each aviation material inventory data.

[0008] Optionally, adjusting the preset K value of the LOF algorithm based on the adjustment factor of each aviation material to obtain the initial K value of each aviation material inventory data includes: adjusting the preset K value of the LOF algorithm based on the adjustment factor of each aviation material using the following formula (1) to obtain the initial K value of each aviation material inventory data:

[0009]

[0010] where, K n represents the initial K value of the nth aviation material inventory data, K represents the preset K value of the LOF algorithm, and δ n represents the adjustment factor of the nth aviation material.

[0011] Optionally, determining the floating degree of each data point in each aviation material inventory data according to the inventory value difference between adjacent data points in each aviation material inventory data includes:

[0012] determining the floating degree of each data point in each aviation material inventory data using the following formula (2) according to the inventory value difference between adjacent data points in each aviation material inventory data:

[0013]

[0014] where, represents the floating degree of the qth data point in the nth aviation material inventory data, represents the inventory quantity of the qth data point in the nth aviation material inventory data, represents the inventory quantity of the (q - 1)th data point in the nth aviation material inventory data, represents the inventory quantity of the (q + 1)th data point in the nth aviation material inventory data.

[0015] Optionally, adjusting the initial K value of each aviation material inventory data according to the floating degree and the inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data includes: constructing a two-dimensional scatter plot of each group according to the floating degree and the inventory value of each data point in each group; performing clustering processing on the two-dimensional scatter plot to obtain several clusters; and adjusting the initial K value of each aviation material inventory data according to the numerical difference of each cluster to obtain the dynamic K value of each aviation material inventory data.

[0016] Optionally, the abscissa of the two-dimensional scatter plot is the inventory value of each data point in each group, and the ordinate is the degree of fluctuation of each data point in each group.

[0017] Optionally, adjusting the initial K value of each aircraft material inventory data according to the numerical difference of each cluster to obtain the dynamic K value of each aircraft material inventory data includes: determining the number of data points in each cluster; determining the K value optimization factor of each cluster according to the number of data points in each cluster; and adjusting the initial K value of each aircraft material inventory data based on the K value optimization factor of each cluster in each aircraft material inventory data to obtain the dynamic K value of each aircraft material inventory data.

[0018] In addition, to achieve the above object, the present application further provides an intelligent aircraft material inventory management system, including: a data acquisition and initial K value acquisition module, configured to acquire aircraft material inventory data and determine the initial K value of each aircraft material inventory data; a fluctuation degree acquisition module, configured to determine the fluctuation degree of each data point in each aircraft material inventory data according to the inventory value difference between adjacent data points in each aircraft material inventory data; a group division module, configured to divide each aircraft material inventory data into several groups according to a preset step size; a K value adjustment module, configured to adjust the initial K value of each aircraft material inventory data according to the fluctuation degree and inventory value of each data point in each group to obtain the dynamic K value of each aircraft material inventory data; an abnormal data acquisition module, configured to perform abnormal detection on the aircraft material inventory data using the LOF algorithm according to the dynamic K value of each aircraft material inventory data and obtain the abnormal inventory value of the corresponding aircraft material; and an aircraft material inventory management module, configured to adjust the management method of the aircraft material inventory based on the abnormal inventory value.

[0019] The present application further provides an intelligent aircraft material inventory management device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned intelligent aircraft material inventory management method.

[0020] The present application further provides a computer-readable storage medium, including: a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned intelligent aircraft material inventory management method is implemented.

[0021] An intelligent aircraft material inventory management method, system, device and medium proposed by the present application, by acquiring aircraft material inventory data and determining the initial K value of each aircraft material inventory data, takes into account the service life and necessity of each aircraft material, and can achieve that when the necessity of an aircraft material is greater, the detection accuracy required when an abnormal value appears in the inventory of this aircraft material is higher, and when the service life of an aircraft material is shorter, the detection accuracy required when an abnormal value appears in the inventory of this aircraft material is also higher.

[0022] In addition, the inventory data of each aviation material is divided into several groups according to a preset step size; the initial K value of the inventory data of each aviation material is adjusted according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of the inventory data of each aviation material. In the embodiments of the present application, considering that the inventory in the aviation industry usually remains relatively consistent in specific months (such as holidays and travel peaks), and the regular aircraft maintenance and repair plans generally follow similar cycles, comparing and adjusting the K values of the inventory data in the same month can achieve setting different K values according to different data in the inventory data of each aviation material, thereby improving the accuracy of anomaly detection and eliminating the influence of seasonality of the inventory data of aviation materials at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 FIG. is a flowchart of an intelligent aviation material inventory management method according to an embodiment of the present application;

[0024] Figure 2 FIG. is a structural block diagram of an intelligent aviation material inventory management system according to an embodiment of the present application;

[0025] Figure 3 FIG. is a structural schematic diagram of an intelligent aviation material inventory management device according to an embodiment of the present application.

[0026] The implementation, functional features and advantages of the object of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] When the existing technology uses the LOF algorithm to detect outliers in the inventory data of aviation materials, the K value in the LOF algorithm needs to be set artificially in advance, and the data characteristics of the inventory data of aviation materials are not considered when setting the K value. When the K value is too low, the LOF algorithm will be too sensitive to small fluctuations in the data, resulting in normal points being mislabeled as outliers, making it difficult for the algorithm to identify real abnormal situations. When the K value is too high, the LOF algorithm may ignore the local structure of the inventory data of aviation materials, resulting in a decrease in the sensitivity to outliers and being unable to effectively detect real outliers. At the same time, too large a K value will also cause more neighboring values to be calculated, increasing the computational burden and reducing the algorithm performance. When the K value in the LOF algorithm is set unreasonably, the obtained outliers will be biased, which is not conducive to the intelligent management of the inventory data of aviation materials.

[0029] To solve the above problems, the present application provides an intelligent aviation material inventory management method, and the solution of the present application will be introduced in detail below.

[0030] Figure 1FIG. 0 is a flowchart of an intelligent aviation material inventory management method according to an embodiment of the present application. The intelligent aviation material inventory management method can be executed by an intelligent aviation material inventory management device with data processing capabilities. Referring to Figure 1 , the intelligent aviation material inventory management method may include the following steps:

[0031] Step S10: Obtain aviation material inventory data and determine the initial K value of each aviation material inventory data.

[0032] In a specific implementation process, inventory data of multiple aviation materials for several years is extracted from the aviation material management library. Among them, the inventory data of each extracted aviation material is arranged in chronological order from small to large in units of months according to the year size. Exemplarily, the number of extracted years is 10.

[0033] In one embodiment, in step S10, determining the initial K value of each aviation material inventory data may specifically include:

[0034] S11: Obtain the service life data and necessity degree data of each aviation material;

[0035] S12: Determine the adjustment factor of each aviation material based on the service life data and necessity degree data of each aviation material;

[0036] S13: Adjust the preset K value of the LOF algorithm based on the adjustment factor of each aviation material to obtain the initial K value of each aviation material inventory data.

[0037] Among them, the adjustment factor can characterize the detection accuracy required when the inventory of each aviation material appears abnormal.

[0038] In a specific implementation process, the service life data of each aviation material is extracted from the aviation material management library, and the necessity degree data of each aviation material is determined according to the aviation material standard document issued by the aviation administration. The specific steps are as follows: Determine the necessity degree data of each aviation material according to the importance of each aviation material to flight, where the range of the necessity degree data is from 0 to 1. Exemplarily, for aviation materials necessary for aircraft flight, such as engines and braking systems, the necessity degree data can be set to 1; for aviation materials with a greater impact on aircraft flight, such as landing gears and fuel systems, the necessity degree data can be set to 0.8; for aviation materials with a smaller impact on aircraft flight, such as seat adjustment devices and air conditioning systems, the necessity degree data can be set to 0.4; for aviation materials that can be replaced during aircraft flight, such as electronic entertainment devices and decorative accessories, the necessity degree can be set to 0.1. Of course, in other embodiments of the present application, technical manuals and design documents provided by aircraft manufacturers can also be used to determine the importance degree of each aviation material.

[0039] Further, perform linear normalization on the service life data of all aviation materials, perform linear normalization on the necessity data of all aviation materials, and then perform linear normalization on the ratio of the service life data to the necessity data of each aviation material after linear normalization. Denote the ratio after linear normalization as the adjustment factor of each aviation material.

[0040] It should be noted that the shorter the service life of an aviation material, the higher the replacement frequency of the aviation material, that is, the higher the degree of change in its inventory level. Then, when an outlier appears in the inventory of the aviation material, the higher the detection accuracy required; the higher the necessity of the aviation material, the more important the aviation material is for aircraft navigation, and the higher the detection accuracy required when an outlier appears in the inventory of the aviation material. Furthermore, an adjustment factor can be constructed based on the service life and necessity of the aviation material. The adjustment factor can characterize the detection accuracy required when an outlier appears in the inventory of the aviation material. In this embodiment, the ratio of necessity to service life is used as the adjustment factor for each aviation material, and at the same time, normalization is performed, which can eliminate the influence of dimensions and make the greater the necessity of the aviation material, the higher the detection accuracy required when an outlier appears in the inventory of the aviation material, and the shorter the service life of the aviation material, the higher the detection accuracy required when an outlier appears in the inventory of the aviation material.

[0041] Further, adjust the preset K value of the LOF algorithm according to the adjustment factor of each aviation material, so that when the adjustment factor is large, that is, when a high detection accuracy is required when an outlier appears in the inventory of the aviation material, the K value is relatively small; when the adjustment factor is small, that is, when a low detection accuracy is required when an outlier appears in the inventory of the aviation material, the K value is relatively large. It should be noted that the smaller the K value in the LOF algorithm, the higher the accuracy of outlier detection.

[0042] Specifically, taking the nth aviation material as an example, adjust the preset K value of the LOF algorithm based on the adjustment factor of the nth aviation material to obtain the initial K value K n of the inventory data of the nth aviation material, and the calculation formula is:

[0043]

[0044] where K represents the preset K value of the LOF algorithm, and δ n represents the adjustment factor of the nth aviation material. Exemplarily, K is 3.

[0045] It should be noted that when using the LOF algorithm for anomaly detection, its threshold range is usually set from 1.5 to 3, and the value range of the adjustment factor is from 0 to 1. Specifically, in the calculation formula of the initial K value of each aviation material constructed in this embodiment, when the adjustment factor of the aviation material is 0, the initial K value of this aviation material is the largest, equal to the preset K value of 3, that is, the K value of this aviation material is not adjusted; when the adjustment factor is getting larger and larger, the initial K value of the aviation material is getting smaller and smaller, that is, a higher detection accuracy can be provided when an abnormal value appears in the inventory of the aviation material. When the adjustment factor of the aviation material is 1, the initial K value of this aviation material is the smallest, equal to half of the preset K value, that is, the detection accuracy is also the highest when an abnormal value appears in the inventory of this aviation material.

[0046] Step S20: Determine the floating degree of each data point in each aviation material inventory data according to the inventory value difference between adjacent data points in each aviation material inventory data.

[0047] It should be noted that in this embodiment, based on the numerical difference situation and the change trend situation between each data point in each aviation material inventory data and its two adjacent data points in time sequence, the floating degree of each data point is constructed.

[0048] Specifically, taking the q-th data point in the inventory data of the n-th aviation material as an example, determine the floating degree of the q-th data point in the inventory data of the n-th aviation material The calculation formula is:

[0049]

[0050] Among them, represents the inventory quantity of the q-th data point in the inventory data of the n-th aviation material, represents the inventory quantity of the (q - 1)-th data point in the inventory data of the n-th aviation material, represents the inventory quantity of the (q + 1)-th data point in the inventory data of the n-th aviation material. It can be understood that the inventory quantity of each data point is the value corresponding to this data point in the aviation material inventory data.

[0051] Step S30: Divide each aviation material inventory data into several groups according to a preset step size.

[0052] It should be noted that since the inventory in the aviation industry usually remains relatively consistent in specific months (such as holidays, peak tourist seasons, etc.), and the regular aircraft maintenance and repair plans generally follow similar cycles, the inventory levels of aviation materials in the same month of different years vary little. Therefore, it is not accurate enough to characterize the abnormality of each data only based on the floating degree obtained in step S20. For example, the inventory levels of a certain aviation material in June, July, and August 2022 are 70, 9, and 80 respectively, and the inventory levels in June, July, and August 2023 are 80, 10, and 90 respectively. At this time, when detecting abnormalities only based on the numerical differences between adjacent data points in the time series of aviation material inventory data, the inventory levels in July 2022 and July 2023 will be directly judged as abnormal data. However, when comparing the inventory data of the same month in 2022 and 2023, the numerical differences between the same months are small. Furthermore, the inventory levels in July 2022 and July 2023 may be caused by seasonal fluctuations of flights, rather than abnormal data resulting from procedural errors in the inventory management system or data entry errors. Therefore, in this embodiment, considering the seasonal characteristics of the changes in aviation inventory data, the inventory data of each aviation material is divided into several groups, and the floating degrees of the data points in each group are similar.

[0053] In a specific implementation process, taking the inventory data of the nth type of aviation material as an example, the inventory data of the nth type of aviation material is divided into several groups. Among them, the distance between two adjacent data points arranged in chronological order in each group is a preset step length. Exemplarily, the preset step length is 11.

[0054] Step S40, adjust the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data.

[0055] In one embodiment, in step S40, adjusting the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data may specifically include:

[0056] S41. Construct a two-dimensional scatter plot for each group according to the floating degree and inventory value of each data point in each group;

[0057] S42. Perform clustering processing on the two-dimensional scatter plot to obtain several clusters;

[0058] S43. Adjust the initial K value of each aviation material inventory data according to the numerical differences of each cluster to obtain the dynamic K value of each aviation material inventory data.

[0059] In a specific implementation process, taking the mth group of the inventory data of the nth type of aviation material as an example, taking the inventory values of each data point in the mth group as the abscissa and the floating degrees of each inventory value in the mth group as the ordinate, construct a two-dimensional scatter plot of the mth group of the inventory data of the nth type of aviation material.

[0060] Further, a clustering algorithm is used to perform clustering on the two-dimensional scatter plot of the m-th group of the n-th type of aviation material inventory data, obtaining several clusters. The clustering algorithm can be, for example, DBSCAN. It should be noted that the clustering algorithm divides the data points into several clusters, making the data points within the same cluster similar.

[0061] In one embodiment, in step S43, adjusting the initial K value of each aviation material inventory data according to the numerical differences of each cluster specifically may include:

[0062] S431. Determine the number of data points in each cluster;

[0063] S432. Determine the K value optimization factor of each cluster according to the number of data points in each cluster;

[0064] S433. Based on the K value optimization factors of each cluster in each aviation material inventory data, adjust the initial K value of each aviation material inventory data to obtain the dynamic K value of each aviation material inventory data.

[0065] It can be understood that the more the number of data points in a cluster, the smaller the possibility that the data points in this cluster are outliers, and vice versa. For example, the number of each cluster in the m-th group of the n-th type of aviation material inventory data is respectively: 9, 8, 7, 2, 1. Then the possibility that the data points belonging to the cluster corresponding to 9 are outliers is smaller, and the possibility that the data points belonging to the cluster corresponding to 1 are outliers is larger.

[0066] Further, count the number of data points in each cluster in the m-th group of the n-th type of aviation material inventory data, and perform linear normalization processing. Denote 1 minus the number of data points in each cluster after linear normalization as the K value optimization factor of each cluster.

[0067] Further, taking the r-th cluster in the m-th group of the n-th type of aviation material inventory data as an example, adjust the initial K value of the data points belonging to the r-th cluster in the m-th group of the n-th type of aviation material inventory data. The calculation formula is as follows:

[0068]

[0069] where, K nmr represents the adjusted K value of the data points belonging to the r-th cluster in the m-th group of the n-th type of aviation material inventory data, K n represents the initial K value of the n-th type of aviation material inventory data, represents the K value optimization factor of the r-th cluster in the m-th group of the n-th type of aviation material inventory data.

[0070] It should be understood that for a certain aviation material inventory data, the initial K value of each data point in each cluster within each group is the initial K value of the aviation material inventory data.

[0071] It should be noted that when the K value optimization factor of a certain cluster is larger, it indicates that the possibility of the data belonging to this cluster being abnormal is smaller, and thus the initial K value needs to be adjusted to a larger value; on the contrary, when the K value optimization factor of a certain cluster is smaller, it indicates that the possibility of the data belonging to this cluster being abnormal is larger, and thus the initial K value needs to be adjusted to a smaller value. In this way, through the above adjustment, different K values can be set for different data in each aviation material inventory data, thereby improving the accuracy of anomaly detection.

[0072] Furthermore, the adjusted K values of each data point in each aviation material inventory data are combined to form the dynamic K value of each aviation material inventory data.

[0073] Step S50: Based on the dynamic K value of each aviation material inventory data, use the LOF algorithm to perform anomaly detection on the aviation material inventory data and obtain the abnormal inventory value of the corresponding aviation material.

[0074] In the specific implementation process, based on the dynamic K value of each aviation material inventory data, use the LOF algorithm to perform anomaly detection on each aviation material inventory data to obtain the abnormal inventory value of each aviation material inventory data.

[0075] It should be noted that compared with the traditional LOF algorithm which needs to preset the K value and the K value is unique, in this embodiment, the dynamic K value is set, which can dynamically adjust the K value for different data, and the set K value takes into account the seasonal fluctuations of the aviation material inventory data itself, so that anomalies can be better captured and the accuracy of anomaly detection of the LOF algorithm can be improved.

[0076] Step S60: Adjust the management method of aviation material inventory based on the abnormal inventory value.

[0077] It should be noted that after obtaining the abnormal inventory value, it is necessary to further analyze the cause of the anomaly, judge whether it is caused by data entry errors, inventory management problems, or actual demand fluctuations, and at the same time, it is necessary to identify which types of aviation materials are more likely to have anomalies for subsequent targeted management.

[0078] In the specific implementation process, first, set the upper and lower threshold values according to the abnormal values and evaluate the influencing factors leading to abnormal inventory. Subsequently, formulate an adjustment plan, classify and manage the inventory and select appropriate adjustment methods. When implementing the adjustment measures, monitor the inventory changes in real time to ensure the effectiveness of the measures. After adjustment, evaluate the effect and optimize the strategy, and establish an early warning mechanism to regularly check the inventory and timely identify new abnormal values, so as to achieve continuous improvement of aviation material inventory management.

[0079] On the basis of the above embodiments, Figure 2The structural block diagram of an intelligent aviation material inventory management system according to an embodiment of the present application is as follows: Figure 2 As shown, the intelligent aviation material inventory management system may include: a data acquisition and initial K value acquisition module 210, a floating degree acquisition module 220, a group division module 230, a K value adjustment module 240, an abnormal data acquisition module 250, and an aviation material inventory management module 260. Among them,

[0080] The data acquisition and initial K value acquisition module 210 is used to acquire aviation material inventory data and determine the initial K value of each aviation material inventory data;

[0081] The floating degree acquisition module 220 is used to determine the floating degree of each data point in each aviation material inventory data based on the inventory value difference between adjacent data points in each aviation material inventory data;

[0082] The group division module 230 is used to divide each aviation material inventory data into several groups according to a preset step size;

[0083] The K value adjustment module 240 is used to adjust the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data;

[0084] The abnormal data acquisition module 250 is used to perform abnormal detection on the aviation material inventory data using the LOF algorithm according to the dynamic K value of each aviation material inventory data and obtain the abnormal inventory value of the corresponding aviation material;

[0085] The aviation material inventory management module 260 is used to adjust the management method of the aviation material inventory based on the abnormal inventory value.

[0086] In an exemplary embodiment, the data acquisition and initial K value acquisition module 210 may also be used to acquire the service life data and necessity degree data of each aviation material; determine the adjustment factor of each aviation material based on the service life data and necessity degree data of each aviation material; and adjust the preset K value of the LOF algorithm based on the adjustment factor of each aviation material to obtain the initial K value of each aviation material inventory data.

[0087] In an exemplary embodiment, the data acquisition and initial K value acquisition module 210 may use the following formula (1) to obtain the initial K value of each aviation material inventory data:

[0088]

[0089] Wherein, K n represents the initial K value of the nth type of aviation material inventory data, K represents the preset K value of the LOF algorithm, and δ n represents the adjustment factor of the nth type of aviation material.

[0090] In an exemplary embodiment, the floating degree acquisition module 220 may determine the floating degree of each data point in each aviation material inventory data by using the following formula (2).

[0091]

[0092] Wherein, represents the floating degree of the q-th data point in the n-th aviation material inventory data, represents the inventory quantity of the q-th data point in the n-th aviation material inventory data, represents the inventory quantity of the (q - 1)-th data point in the n-th aviation material inventory data, represents the inventory quantity of the (q + 1)-th data point in the n-th aviation material inventory data.

[0093] In an exemplary embodiment, the K value adjustment module 240 may also be used to construct a two-dimensional scatter plot for each group based on the floating degree and inventory value of each data point in each group; perform clustering processing on the two-dimensional scatter plot to obtain several clusters; adjust the initial K value of each aviation material inventory data according to the numerical differences of each cluster to obtain the dynamic K value of each aviation material inventory data.

[0094] In an exemplary embodiment, the abscissa of the two-dimensional scatter plot in the K value adjustment module 240 is the inventory value of each data point in each group, and the ordinate is the floating degree of each data point in each group.

[0095] In an exemplary embodiment, the K value adjustment module 240 may also be used to determine the number of data points in each cluster; determine the K value optimization factor of each cluster according to the number of data points in each cluster; adjust the initial K value of each aviation material inventory data based on the K value optimization factor of each cluster in each aviation material inventory data to obtain the dynamic K value of each aviation material inventory data.

[0096] Those skilled in the art should understand that the division of each module in the embodiment is only a logical function division. In actual application, it can be fully or partially integrated into one or more actual carriers, and these modules can all be implemented in the form of software called by a processing unit, or all be implemented in the form of hardware, or be implemented in the form of a combination of software and hardware. It should be noted that each module in an intelligent aviation material inventory management system in this embodiment corresponds to each step in an intelligent aviation material inventory management method in the foregoing embodiment. Therefore, the specific implementation manner of this embodiment may refer to the implementation manner of the foregoing intelligent aviation material inventory management method, which will not be elaborated here.

[0097] On the basis of the above embodiments, Figure 3 is a structural schematic diagram of an intelligent aviation material inventory management device according to an embodiment of the present application, as Figure 3As shown in the figure, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 complete communication with each other through the communication bus 340. The processor 310 may call the logical instructions in the memory 330 to execute an intelligent aviation material inventory management method, which includes: obtaining aviation material inventory data and determining the initial K value of each aviation material inventory data; determining the floating degree of each data point in each aviation material inventory data according to the inventory value difference between adjacent data points in each aviation material inventory data; dividing each aviation material inventory data into several groups according to a preset step size; adjusting the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data; using the LOF algorithm to perform anomaly detection on the aviation material inventory data according to the dynamic K value of each aviation material inventory data and obtaining the abnormal inventory value of the corresponding aviation material; and adjusting the management method of the aviation material inventory based on the abnormal inventory value.

[0098] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0099] Based on the above embodiments, on the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the intelligent aviation material inventory management method provided by the above-mentioned various methods. The method includes: obtaining aviation material inventory data and determining the initial K value of each aviation material inventory data; determining the floating degree of each data point in each aviation material inventory data according to the inventory value difference between adjacent data points in each aviation material inventory data; dividing each aviation material inventory data into several groups according to a preset step size; adjusting the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data; using the LOF algorithm to perform anomaly detection on the aviation material inventory data according to the dynamic K value of each aviation material inventory data and obtaining the abnormal inventory value of the corresponding aviation material; adjusting the management method of the aviation material inventory based on the abnormal inventory value.

[0100] Based on the above embodiments, on another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes the intelligent aviation material inventory management method provided by the above-mentioned various methods. The method includes: obtaining aviation material inventory data and determining the initial K value of each aviation material inventory data; determining the floating degree of each data point in each aviation material inventory data according to the inventory value difference between adjacent data points in each aviation material inventory data; dividing each aviation material inventory data into several groups according to a preset step size; adjusting the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data; using the LOF algorithm to perform anomaly detection on the aviation material inventory data according to the dynamic K value of each aviation material inventory data and obtaining the abnormal inventory value of the corresponding aviation material; adjusting the management method of the aviation material inventory based on the abnormal inventory value.

Claims

1. An intelligent aviation material inventory management method, characterized in that, The intelligent aviation material inventory management method includes: Obtaining aviation material inventory data and determining the initial K value of each aviation material inventory data; Determining the floating degree of each data point in each aviation material inventory data based on the inventory value difference between adjacent data points in each aviation material inventory data; Dividing each aviation material inventory data into several groups according to a preset step size; Adjusting the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data; Using the LOF algorithm to perform anomaly detection on the aviation material inventory data based on the dynamic K value of each aviation material inventory data and obtaining the abnormal inventory value of the corresponding aviation material; Adjusting the management method of the aviation material inventory based on the abnormal inventory value.

2. The intelligent aviation material inventory management method according to claim 1, wherein, The determining the initial K value of each aviation material inventory data includes: Obtaining the service life data and necessity data of each aviation material; Determining the adjustment factor of each aviation material based on the service life data and necessity data of each aviation material; Adjusting the preset K value of the LOF algorithm based on the adjustment factor of each aviation material to obtain the initial K value of each aviation material inventory data.

3. The intelligent aviation material inventory management method according to claim 2, wherein, The adjusting the preset K value of the LOF algorithm based on the adjustment factor of each aviation material to obtain the initial K value of each aviation material inventory data includes: Adjusting the preset K value of the LOF algorithm based on the adjustment factor of each aviation material using the following formula (1) to obtain the initial K value of each aviation material inventory data: Among them, K n represents the initial K value of the inventory data of the nth type of aviation material, and K represents the preset K value of the LOF algorithm, and δ n represents the adjustment factor of the nth type of aviation material.

4. The intelligent aviation material inventory management method according to claim 1, wherein The determining the floating degree of each data point in each aviation material inventory data based on the inventory value difference between adjacent data points in each aviation material inventory data includes: Determining the floating degree of each data point in each aviation material inventory data using the following formula (2) based on the inventory value difference between adjacent data points in each aviation material inventory data: Among them, represents the degree of fluctuation of the q-th data point in the inventory data of the n-th aviation material, represents the inventory quantity of the q-th data point in the inventory data of the n-th aviation material, represents the inventory quantity of the (q - 1)-th data point in the inventory data of the n-th aviation material, represents the inventory quantity of the (q + 1)-th data point in the inventory data of the n-th aviation material.

5. The intelligent aviation material inventory management method according to claim 1, wherein The adjusting the initial K value of each aviation material inventory data according to the floating degree and inventory value of each data point in each group to obtain the dynamic K value of each aviation material inventory data includes: Constructing a two-dimensional scatter plot of each group according to the floating degree and inventory value of each data point in each group; Performing clustering processing on the two-dimensional scatter plot to obtain several clusters; Adjusting the initial K value of each aviation material inventory data according to the numerical difference of each cluster to obtain the dynamic K value of each aviation material inventory data.

6. The intelligent aviation material inventory management method according to claim 5, wherein The abscissa of the two-dimensional scatter plot is the inventory value of each data point in each group, and the ordinate is the floating degree of each data point in each group.

7. The intelligent aviation material inventory management method according to claim 5, wherein The adjusting the initial K value of each aviation material inventory data according to the numerical difference of each cluster to obtain the dynamic K value of each aviation material inventory data includes: Determining the number of data points in each cluster; Determining the K value optimization factor of each cluster based on the number of data points in each cluster; Adjusting the initial K value of each aviation material inventory data based on the K value optimization factor of each cluster in each aviation material inventory data to obtain the dynamic K value of each aviation material inventory data.

8. An intelligent aviation material inventory management system, characterized in that, The intelligent aviation material inventory management system includes: A data collection and initial K value acquisition module, which is used to obtain aviation material inventory data and determine the initial K value of each aviation material inventory data; A floating degree acquisition module, which is used to determine the floating degree of each data point in each aviation material inventory data based on the inventory value difference between adjacent data points in each aviation material inventory data; The group division module is used to divide each aviation material inventory data into several groups according to a preset step size; The K-value adjustment module is used to adjust the initial K-value of each aviation material inventory data based on the floating degree and inventory value of each data point in each group to obtain the dynamic K-value of each aviation material inventory data; The abnormal data acquisition module is used to perform abnormal detection on the aviation material inventory data using the LOF algorithm based on the dynamic K-value of each aviation material inventory data and obtain the abnormal inventory value of the corresponding aviation material; The aviation material inventory management module is used to adjust the management method of the aviation material inventory based on the abnormal inventory value.

9. An intelligent aviation material inventory management device, characterized in that, The intelligent aviation material inventory management device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent aviation material inventory management method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent aviation material inventory management method according to any one of claims 1 to 7.

Images