A method and system for processing air ticket orders based on big data
By extending the data and filtering the feature quantity of air ticket order data, an abnormal order feature set is formed, which solves the problem of insufficient abnormal feature quantity and improves the accuracy and efficiency of abnormal identification of air ticket orders.
Patent Information
- Application Number
- CN202410148387.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-02
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-02-02
AI Technical Summary
In the prior art, in the processing of air ticket order data, the abnormal order feature volume is too large or too small, resulting in a decrease in the accuracy of abnormal identification, making it difficult to accurately identify abnormal air ticket orders.
By extending the historical air ticket order data from different big data sources, obtaining the secondary center distance matrix and extension core, determining the singular entropy and data drift, filtering out the abnormal order feature quantity, and performing spatial clustering to form anomalies to form anomalies The order feature set is used for exception detection.
It improves the accuracy of abnormal identification of air ticket orders, enhances the integrity and recognition efficiency of abnormal characteristics, and can more accurately identify and handle abnormal situations.
Smart Images

Figure CN117952717B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of order data processing, and more specifically, to a method and system for processing air ticket orders based on big data. Background Art
[0002] Ticket order data processing involves collecting, integrating and analyzing a large amount of order information, including passenger, flight and payment data, in order to predict demand, optimize prices and provide personalized services. Ticket order exception handling issues may involve order duplication, payment failure, flight cancellation and ticket order data exceptions, etc. It is necessary to establish an effective monitoring system and exception handling mechanism to ensure timely identification and resolution of ticket order exceptions.
[0003] In the prior art, the order data, flight information, passenger preferences and other information of abnormal order information are often collected from multiple data sources through the air ticket order processing system, and the abnormal order features are clustered and integrated into the centralized data warehouse of the air ticket order processing system. The air ticket order processing system uses machine learning models and data mining technology to accurately identify abnormalities based on abnormal order features in order to facilitate better data-driven decision-making. However, in the process of collecting abnormal order features, the amount of abnormal order features directly determines the accuracy of abnormal identification. When the amount of abnormal order features is too large, similar order abnormal features will be divided into multiple sub-features, which are difficult to use for abnormal identification of air ticket orders. When the amount of abnormal order features is too small, due to feature overfitting, the inherent structure and distribution characteristics of the abnormal order features will be lost. Therefore, how to obtain accurate abnormal order feature quantities for abnormal identification of air ticket orders in the data processing of air ticket orders has become an urgent problem to be solved. Summary of the invention
[0004] The present application provides a method and system for processing air ticket orders based on big data, which can obtain accurate abnormal order feature quantities for air ticket order anomaly identification during the data processing of air ticket orders, thereby improving the accuracy of air ticket anomaly identification.
[0005] In a first aspect, the present application provides a method for processing air ticket orders based on big data, comprising the following steps:
[0006] Perform data extension on the historical air ticket order data obtained from different big data sources to obtain the order data extension space;
[0007] Obtaining a secondary center distance matrix of the order data extension space, and determining a singular entropy corresponding to each air ticket order data in the order data extension space according to the secondary center distance matrix;
[0008] Acquire an extension core of the order data extension space, and determine the data drift amount corresponding to each air ticket order data in the order data extension space through the extension core;
[0009] Determine the abnormal order feature quantity according to the data drift and singular entropy corresponding to each air ticket order data, and perform spatial clustering on the order data extension space based on the abnormal order feature quantity to obtain an abnormal order feature set;
[0010] Anomaly detection is performed on the air ticket order to be detected according to the abnormal order feature set.
[0011] In some embodiments, the historical air ticket order data obtained from different big data sources are extended to obtain the order data extension space, which specifically includes:
[0012] Integrate the historical air ticket order data obtained from different big data sources to obtain the air ticket order data domain;
[0013] Taking the flight distance as the data dimension of the air ticket order data domain, obtaining the air ticket order data space;
[0014] Determine the extended extreme point and extended range of the air ticket order data space;
[0015] Generate a flight distance extension domain according to the extension pole and the extension range;
[0016] The air ticket order data space is extended according to the flight distance extension domain to obtain an order data extension space.
[0017] In some embodiments, determining the extended extreme point and extended range of the air ticket order data space specifically includes:
[0018] Obtaining all data points in the air ticket order data space, and then taking the average value of all data points as the extension point of the air ticket order data space;
[0019] Obtain the total number of data and data dimensions of the air ticket order data space;
[0020] The extended range of the air ticket order data space is determined by the total number of data and the data dimension of the air ticket order data space.
[0021] In some embodiments, the ticket order data space is extended according to the flight distance extension domain to obtain the order data extension space, which means that the data space obtained by merging the flight distance extension domain and the ticket order data space is used as the order data extension space.
[0022] In some embodiments, determining the data drift amount corresponding to each air ticket order data in the order data extension space by the extension core specifically includes:
[0023] For each air ticket order data in the order data extension space, obtaining the singular entropy corresponding to the air ticket order data;
[0024] The data drift amount corresponding to the air ticket order data is determined by the singular entropy and the extension kernel, and then the data drift amount corresponding to each air ticket order data in the order data extension space is obtained.
[0025] In some embodiments, according to the data drift and singular entropy corresponding to each air ticket order data, determining the abnormal order feature specifically includes:
[0026] Determine a maximum data drift amount among all data drift amounts, and then obtain a sequence position corresponding to the maximum data drift amount among all data drift amounts;
[0027] Determine the maximum singular entropy among all singular entropies; and then obtain the sequence position corresponding to the maximum singular entropy among all singular entropies;
[0028] The abnormal order feature quantity is determined by the maximum data drift, the sequence position corresponding to the maximum data drift, the maximum singular entropy, and the sequence position corresponding to the maximum singular entropy.
[0029] In some embodiments, spatial clustering is performed on the order data extension space based on the abnormal order feature quantity to obtain the abnormal order feature set, which specifically includes:
[0030] Determining the number of spatial clustering centers by using the abnormal order feature quantity;
[0031] The order data extension space is spatially clustered based on the number of spatial clustering centers to obtain a set of abnormal order features.
[0032] In a second aspect, the present application provides a ticket order processing system based on big data, including a ticket order processing unit, wherein the ticket order processing unit includes:
[0033] The extension module is used to extend the historical air ticket order data obtained from different big data sources to obtain the order data extension space;
[0034] A processing module, used for obtaining a secondary center distance matrix of the order data extension space, and determining the singular entropy corresponding to each air ticket order data in the order data extension space according to the secondary center distance matrix;
[0035] The processing module is further used to obtain an extension core of the order data extension space, and determine the data drift amount corresponding to each air ticket order data in the order data extension space through the extension core;
[0036] The processing module is further used to determine the abnormal order feature quantity according to the data drift amount and singular entropy corresponding to each air ticket order data, and perform spatial clustering on the order data extension space based on the abnormal order feature quantity to obtain the abnormal order feature set;
[0037] The anomaly detection module is used to perform anomaly detection on the air ticket order to be detected according to the abnormal order feature set.
[0038] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data-based air ticket order processing method.
[0039] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned big data-based air ticket order processing method when executed.
[0040] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:
[0041] In the present application, firstly, the historical air ticket order data obtained from different big data sources are extended to obtain the order data extension space, which can make the data space composed of the historical air ticket order data from different big data sources more complete and robust, and the data redundancy in the order data extension space is less, and the focus can be focused on the most recent and more valuable reference air ticket order data, so as to more accurately identify the current possible abnormal air ticket order situation, and then, the quadratic center distance matrix of the order data extension space is obtained, and the singular entropy corresponding to each air ticket order data in the order data extension space is determined by the quadratic center distance matrix. According to the singular entropy, the intrinsic characteristics of the air ticket order data can be represented and the historical air ticket order data with abnormal characteristics in the order data extension space can be found, so that the air ticket order processing system can more accurately identify and handle abnormal situations. Secondly, an extension kernel of the order data extension space is obtained, and the data drift corresponding to each air ticket order data in the order data extension space is determined by the extension kernel, so as to measure the degree of deviation and distribution characteristics of each air ticket order data from the data center in the order data extension space. Then, according to the data drift and singular entropy corresponding to each air ticket order data, the abnormal order feature quantity is determined to obtain accurate abnormal order feature quantity, which is used to increase the completeness of the order abnormal feature set. Finally, the order data extension space is spatially clustered based on the abnormal order feature quantity to obtain the abnormal order feature set. According to the abnormal order feature set, anomaly detection is performed on the air ticket order to be detected. In the data processing process of the air ticket order, accurate abnormal order feature quantity can be obtained for air ticket order anomaly identification, thereby improving the accuracy of air ticket anomaly identification. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0043] Figure 1 is an exemplary flow chart of a method for processing air ticket orders based on big data according to some embodiments of the present application;
[0044] Figure 2 is an exemplary flow chart for determining the extension extreme point and extension range of the air ticket order data space according to some embodiments of the present application;
[0045] Figure 3 is an exemplary flow chart for determining characteristic quantities of abnormal orders according to some embodiments of the present application;
[0046] Figure 4is a schematic diagram of exemplary hardware and / or software of a ticket order processing unit according to some embodiments of the present application;
[0047] Figure 5 It is a structural diagram of a computer device for implementing a big data-based air ticket order processing method according to some embodiments of the present application. DETAILED DESCRIPTION
[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0049] The embodiment of the present application provides a big data-based air ticket order processing method and system, the core of which is to perform data extension on historical air ticket order data obtained from different big data sources to obtain an order data extension space; obtain a quadratic center distance matrix of the order data extension space, and determine the singular entropy corresponding to each air ticket order data in the order data extension space by the quadratic center distance matrix; obtain an extension core of the order data extension space, and determine the data drift corresponding to each air ticket order data in the order data extension space by the extension core; determine an abnormal order feature quantity according to the data drift quantity and singular entropy corresponding to each air ticket order data, and perform spatial clustering on the order data extension space based on the abnormal order feature quantity to obtain an abnormal order feature set; perform anomaly detection on the air ticket order to be detected according to the abnormal order feature set, so that accurate abnormal order feature quantities can be obtained during the data processing of the air ticket order for use in air ticket order anomaly identification, thereby improving the accuracy of air ticket anomaly identification.
[0050] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a method for processing air ticket orders based on big data according to some embodiments of the present application. The method 100 for processing air ticket orders based on big data mainly includes the following steps:
[0051] In step 101, data extension is performed on historical air ticket order data obtained from different big data sources to obtain an order data extension space.
[0052] In some embodiments, the historical air ticket order data obtained from different big data sources are extended to obtain the order data extension space in the following manner, namely:
[0053] Integrate the historical air ticket order data obtained from different big data sources to obtain the air ticket order data domain;
[0054] Taking the flight distance as the data dimension of the air ticket order data domain, obtaining the air ticket order data space;
[0055] Determine the extended extreme point and extended range of the air ticket order data space;
[0056] Generate a flight distance extension domain according to the extension pole and the extension range;
[0057] The air ticket order data space is extended according to the flight distance extension domain to obtain an order data extension space.
[0058] In specific implementation, first, historical air ticket order data can be collected from multiple big data sources through the data collection unit in the air ticket order processing system, such as airlines, travel websites, booking platforms, etc. It should be noted that in this application, the air ticket order data is a multi-dimensional data containing basic information of the air ticket order. Then, all the air ticket order data of each big data source are field mapped to ensure that the order information fields of the air ticket order data of different big data sources have the same meaning. Then, the historical air ticket order data of different big data sources are converted into a unified data format, such as using a standard data format, naming conventions, etc. Finally, all the air ticket order data are verified and checked to ensure the consistency, completeness and accuracy of the air ticket order data. The historical air ticket order data that has passed the verification and verification is merged into an integrated data set, namely, the air ticket order data domain, by using data integration tools or technologies. It should be noted that by integrating data sources, duplicate, contradictory or inconsistent air ticket order information can be eliminated to ensure the consistency and accuracy of the data, so as to reduce the impact of erroneous or abnormal air ticket order data on the overall data, and the air ticket order trusted domain can provide a more comprehensive perspective, better understand the overall situation of the air ticket order, and make abnormal patterns easier to be discovered.
[0059] In the above embodiment, the flight distance is used as the data dimension of the ticket order data domain to obtain the ticket order data space. It should be noted that by using the flight distance as the data dimension of the ticket order data domain, the data dimension of the ticket order data domain is increased, and the ticket order data domain after the data dimension is increased is used as the ticket order data space.
[0060] It should be noted that, in the present application, the extended pole of the air ticket order data space represents the average position of the air ticket order data space, and the extended range of the air ticket order data space represents the degree of data dispersion in the air ticket order data space.
[0061] Preferably, in some embodiments, reference Figure 2As shown, this figure is an exemplary flow chart of determining the extension pole and extension range of the air ticket order data space in some embodiments of the present application. In this embodiment, determining the extension pole and extension range of the air ticket order data space can be implemented by the following steps:
[0062] First, in step 1011, all data points in the air ticket order data space are obtained, and then the average value of all data points is used as the extension pole of the air ticket order data space;
[0063] Then, in step 1012, the total number of data and data dimensions of the air ticket order data space are obtained;
[0064] Finally, in step 1013, the extended range of the air ticket order data space is determined according to the total number of data and the data dimension of the air ticket order data space.
[0065] In the above embodiment, in specific implementation, the extended range of the air ticket order data space can be determined by the following formula:
[0066]
[0067] Among them, λ represents the extended range of the air ticket order data space, N G represents the total number of data in the air ticket order data space G, M G Represents the data dimension of the air ticket order data space G, It means rounding down. It should be noted that the data dimension of the air ticket order data space can be represented by the number of attributes of the air ticket order. For example, the attributes of the air ticket order have 4 attributes, so the data dimension of the air ticket order data space is 4.
[0068] In some embodiments, a flight distance extension domain is generated according to the extension poles and the extension range. In specific implementation, a multivariate normal distribution can be used to simulate and generate normally distributed random data points in a multidimensional space, and the normally distributed random data points are added to the extension poles, and then the set of all data points is used as the flight distance extension domain. The flight distance extension domain is a set of ticket order data with added flight distance information, which is used to extend and expand the ticket order data space to facilitate learning the nonlinear relationship between ticket anomalies and order distance. For example, international flights with longer distances often require customers to purchase tickets for a longer time, resulting in a longer order existence time and a higher probability of order loss. Customers who have changed their ticket orders for shorter distances multiple times are more likely to have duplicate orders, etc.
[0069] In some embodiments, the ticket order data space is extended according to the flight distance extension domain, and obtaining the order data extension space means merging the flight distance extension domain and the ticket order data space to obtain the data space as the order data extension space. It should be noted that in the present application, by merging the flight distance extension domain and the ticket order data space, the flight distance information can be merged into the ticket order data space, so that the data information and data dimension of the ticket order data space are extended, that is, the order data extension space is obtained.
[0070] In step 102, the secondary center distance matrix of the order data extension space is obtained, and the singular entropy corresponding to each air ticket order data in the order data extension space is determined by the secondary center distance matrix.
[0071] It should be noted that in the present application, the quadratic center distance matrix is a matrix used to describe the degree of diffusion of air ticket order data in different dimensions in the order data extension space. In specific implementation, the quadratic cross terms of each pair of data attributes in the order data extension space, that is, the quadratic center distance, can be calculated, and all the quadratic cross terms can be combined into a matrix, that is, the quadratic center distance matrix of the order data extension space.
[0072] Preferably, in some embodiments, the singular entropy corresponding to each air ticket order data in the order data extension space is determined by the secondary center distance matrix in the following manner, namely:
[0073] Determine the data location core of the order data extension space;
[0074] The singular entropy corresponding to each air ticket order data in the order data extension space is determined by the data position central kernel and the quadratic center distance matrix.
[0075] It should be noted that in the present application, the data position central core is a vector used to describe the central position of the order data extension space. The data position central core shows the average level of the air ticket order data in a given dimension. In specific implementation, the data mean vector of the order data extension space is calculated, and the data mean vector can be used as the data position central core of the order data extension space. The singular entropy is a quantitative value of the fluctuation degree of the air ticket order data in the order data extension space. The larger the singular entropy, the higher the fluctuation degree of the air ticket order data.
[0076] In the above embodiment, the singular entropy corresponding to each air ticket order data in the order data extension space is determined by the data position central core and the secondary center distance matrix. In specific implementation, the singular entropy can be determined according to the following formula:
[0077]
[0078] Among them, γi Represents the flight order data x i The corresponding singular entropy, x i represents the i-th air ticket order data in the order data extension space, μ g Represents the data location core of the order data extension space g, SeM g Represents the quadratic center distance matrix of the order data extension space g, and T represents the transpose operation.
[0079] It should be noted that, through the calculation of singular entropy, it is possible to find out the air ticket order data with abnormal characteristics or unusual patterns in the order data extension space, so that the air ticket order processing system can more accurately identify and handle abnormal situations and reduce the false alarm rate.
[0080] In step 103, an extension core of the order data extension space is obtained, and a data drift amount corresponding to each air ticket order data in the order data extension space is determined by using the extension core.
[0081] It should be noted that in the present application, the extension core represents the overall average level of the order data extension space. In specific implementation, the extension core of the order data extension space is obtained. The extension core can be determined according to the position center of the order data extension space. For example, assuming that the average value of all air ticket order data in the order data extension space, that is, the position center is H, then the extension core value can be H.
[0082] In some embodiments, the data drift amount corresponding to each air ticket order data in the order data extension space is determined by the extension core in the following manner, namely:
[0083] For each air ticket order data in the order data extension space, obtaining the singular entropy corresponding to the air ticket order data;
[0084] The data drift amount corresponding to the air ticket order data is determined by the singular entropy and the extension kernel, and then the data drift amount corresponding to each air ticket order data in the order data extension space is obtained.
[0085] It should be noted that in the present application, the data drift is a quantitative value of the degree of deviation of the ticket order data relative to the overall order data extension space. The larger the data drift, the higher the degree of deviation. In specific implementation, first, all singular entropies are sorted in ascending order according to the size of the singular entropy values. Then, for each ticket order data in the order data extension space, the singular entropy corresponding to the ticket order data is obtained, and the absolute value of the difference between the singular entropy corresponding to the ticket order data and the extension kernel is used as the data drift corresponding to the ticket order data, and then the data drift corresponding to each ticket order data can be obtained.
[0086] In step 104, according to the data drift and singular entropy corresponding to each air ticket order data, the abnormal order feature quantity is determined, and the order data extension space is spatially clustered based on the abnormal order feature quantity to obtain an abnormal order feature set.
[0087] Preferably, in some embodiments, reference Figure 3 As shown, this figure is an exemplary flow chart for determining the characteristic amount of abnormal orders in some embodiments of the present application. In this embodiment, determining the characteristic amount of abnormal orders can be implemented by the following steps:
[0088] First, in step 1041, a maximum data drift amount among all data drift amounts is determined, and then a sequence position corresponding to the maximum data drift amount among all data drift amounts is obtained;
[0089] Next, in step 1042, the maximum singular entropy among all the singular entropies is determined; and then the sequence position corresponding to the maximum singular entropy among all the singular entropies is obtained;
[0090] Finally, in step 1043, the abnormal order feature is determined by the maximum data drift, the sequence position corresponding to the maximum data drift, the maximum singular entropy, and the sequence position corresponding to the maximum singular entropy.
[0091] In the above embodiment, in specific implementation, the abnormal order feature quantity can be determined according to the following formula:
[0092]
[0093] Among them, σ represents the abnormal order feature, n represents the total number of air ticket order data, γ max represents the maximum singular entropy, a represents the maximum singular entropy γ max The corresponding sequence position, κ max represents the maximum singular entropy, and b represents the maximum singular entropy κ max Corresponding sequence position, it should be noted that, in this application, the abnormal order feature quantity is the number of abnormal order features used for anomaly identification. For air ticket order data, the larger the singular entropy and data drift, the more abnormal the air ticket order data is, the more complex the intrinsic structure and spatial distribution of the abnormal features that need to be learned, and the larger the abnormal order feature quantity.
[0094] It should be noted that based on data drift and singular entropy, the air ticket order data with significant offset and distortion can be screened out more accurately. After obtaining the abnormal order feature quantity, the air ticket order processing system can more accurately select the air ticket order data that needs to be focused on, reduce the processing of ordinary air ticket order data, and improve the processing efficiency of the air ticket order processing system.
[0095] In some embodiments, spatial clustering is performed on the order data extension space based on the abnormal order feature quantity to obtain the abnormal order feature set in the following manner, namely:
[0096] Determining the number of spatial clustering centers by using the abnormal order feature quantity;
[0097] The order data extension space is spatially clustered based on the number of spatial clustering centers to obtain a set of abnormal order features.
[0098] In the specific implementation, first, the abnormal order feature quantity determines the number of spatial clustering centers. For example, if the value of the abnormal order feature quantity is 10, the number of spatial clustering centers can be determined to be 10. Then, based on the number of spatial clustering centers, the order data extension space is spatially clustered to obtain the abnormal order feature set. The mean clustering algorithm can be used for spatial clustering to obtain multiple abnormal order data clusters, and the set of cluster centers of all abnormal order data clusters is used as the abnormal order feature set.
[0099] In step 105, anomaly detection is performed on the ticket order to be detected according to the abnormal order feature set.
[0100] In the specific implementation, first, all the ticket orders to be detected are obtained, and the distance between each ticket order to be detected and the mean of the abnormal order feature set is determined. The distance is used as the singular value of the ticket order to be detected. The singular value is used to measure the abnormal degree of the ticket order to be detected. Then, the singular threshold is determined by the abnormal order feature quantity. It should be noted that the singular value obeys the chi-square distribution with the degree of freedom being the abnormal order feature quantity σ value, that is, χ 2 (σ), usually the confidence interval is assumed to be 97.5%, then the singular threshold can be obtained as When the ticket order is pending i The corresponding singular value is higher than the singular threshold, that is, Then determine the ticket order y to be tested i For abnormal air ticket order data, it should be noted that according to the judgment condition that the singular value is greater than the singular threshold, the abnormal air ticket order data can be quickly located and identified, which improves the speed and efficiency of abnormal identification.
[0101] In the present application, firstly, the historical air ticket order data obtained from different big data sources are extended to obtain the order data extension space, which can make the data space composed of the historical air ticket order data from different big data sources more complete and robust, and the data redundancy in the order data extension space is less, and the focus can be focused on the most recent and more valuable reference air ticket order data, so as to more accurately identify the current possible abnormal air ticket order situation, and then, the quadratic center distance matrix of the order data extension space is obtained, and the singular entropy corresponding to each air ticket order data in the order data extension space is determined by the quadratic center distance matrix. According to the singular entropy, the intrinsic characteristics of the air ticket order data can be represented and the historical air ticket order data with abnormal characteristics in the order data extension space can be found, so that the air ticket order processing system can more accurately identify and handle abnormal situations. Secondly, an extension kernel of the order data extension space is obtained, and the data drift corresponding to each air ticket order data in the order data extension space is determined by the extension kernel, so as to measure the degree of deviation and distribution characteristics of each air ticket order data from the data center in the order data extension space. Then, according to the data drift and singular entropy corresponding to each air ticket order data, the abnormal order feature quantity is determined to obtain accurate abnormal order feature quantity, which is used to increase the completeness of the order abnormal feature set. Finally, the order data extension space is spatially clustered based on the abnormal order feature quantity to obtain the abnormal order feature set. According to the abnormal order feature set, anomaly detection is performed on the air ticket order to be detected. In the data processing process of the air ticket order, accurate abnormal order feature quantity can be obtained for air ticket order anomaly identification, thereby improving the accuracy of air ticket anomaly identification.
[0102] In addition, in another aspect of the present application, in some embodiments, the present application provides a ticket order processing system based on big data, the system includes a ticket order processing unit, reference Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a ticket order processing unit according to some embodiments of the present application, the ticket order processing unit 400 includes: an extension module 401, a processing module 402 and an anomaly detection module 403, which are described as follows:
[0103] Extension module 401, in this application, extension module 401 is mainly used to perform data extension on the historical air ticket order data obtained from different big data sources to obtain an order data extension space;
[0104] Processing module 402, in this application, processing module 402 is mainly used to obtain the secondary center distance matrix of the order data extension space, and determine the singular entropy corresponding to each air ticket order data in the order data extension space by the secondary center distance matrix;
[0105] The processing module 402 is further configured to obtain an extension core of the order data extension space, and determine a data drift amount corresponding to each air ticket order data in the order data extension space through the extension core;
[0106] The processing module 402 is further used to determine the abnormal order feature quantity according to the data drift and singular entropy corresponding to each air ticket order data, and perform spatial clustering on the order data extension space based on the abnormal order feature quantity to obtain an abnormal order feature set;
[0107] Anomaly detection module 403, in the present application, anomaly detection module 403 is mainly used to perform anomaly detection on the air ticket order to be detected according to the abnormal order feature set.
[0108] The above describes in detail the examples of the ticket order processing method and system based on big data provided by the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.
[0109] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data-based air ticket order processing method.
[0110] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional, and the figure is a schematic diagram of the structure of a computer device according to a method for processing air ticket orders based on big data provided in an embodiment of the present application. The above-mentioned method for processing air ticket orders based on big data in the above-mentioned embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 can be a terminal device, a server or a chip.
[0111] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).
[0112] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.
[0113] For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.
[0114] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and the data can be stored at the same storage address as the program 504, or the data can be stored at a different storage address from the program 504.
[0115] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.
[0116] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or a software-based instruction in the processor 501. The processor 501 can be a central processing unit, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.
[0117] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0118] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are executed on a computer, the computer implements the above-mentioned big data-based air ticket order processing method.
[0119] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0120] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A method for processing air ticket orders based on big data, characterized in that: The steps include: Perform data extension on the historical air ticket order data obtained from different big data sources to obtain the order data extension space; Obtaining a secondary center distance matrix of the order data extension space, and determining a singular entropy corresponding to each air ticket order data in the order data extension space according to the secondary center distance matrix; Acquire an extension core of the order data extension space, and determine the data drift amount corresponding to each air ticket order data in the order data extension space through the extension core; Determine the abnormal order feature quantity according to the data drift and singular entropy corresponding to each air ticket order data, and perform spatial clustering on the order data extension space based on the abnormal order feature quantity to obtain an abnormal order feature set; Performing anomaly detection on the ticket order to be detected according to the abnormal order feature set; Among them, the historical air ticket order data obtained from different big data sources are extended, and the order data extension space obtained specifically includes: Integrate the historical air ticket order data obtained from different big data sources to obtain the air ticket order data domain; Taking the flight distance as the data dimension of the air ticket order data domain, obtaining the air ticket order data space; Determine the extended extreme point and extended range of the air ticket order data space; Generate a flight distance extension domain according to the extension pole and the extension range, wherein the flight distance extension domain is a set of ticket order data with added flight distance information; Extending the air ticket order data space according to the flight distance extension domain to obtain an order data extension space; Wherein, determining the extension extreme point and extension range of the air ticket order data space specifically includes: Obtaining all data points in the air ticket order data space, and then taking the average value of all data points as the extension point of the air ticket order data space; Obtain the total number of data and data dimensions of the air ticket order data space; The extended range of the air ticket order data space is determined by the total number of data and the data dimension of the air ticket order data space.
2. The method according to claim 1, characterized in that Extending the air ticket order data space according to the flight distance extension domain to obtain the order data extension space means merging the flight distance extension domain and the air ticket order data space to obtain a data space as the order data extension space.
3. The method according to claim 1, characterized in that Determining the data drift amount corresponding to each air ticket order data in the order data extension space by the extension core specifically includes: For each air ticket order data in the order data extension space, obtaining the singular entropy corresponding to the air ticket order data; The data drift amount corresponding to the air ticket order data is determined by the singular entropy and the extension kernel, and then the data drift amount corresponding to each air ticket order data in the order data extension space is obtained.
4. The method according to claim 1, characterized in that According to the data drift and singular entropy corresponding to each air ticket order data, the abnormal order feature quantity is determined to include: Determine a maximum data drift amount among all data drift amounts, and then obtain a sequence position corresponding to the maximum data drift amount among all data drift amounts; Determine the maximum singular entropy among all singular entropies; and then obtain the sequence position corresponding to the maximum singular entropy among all singular entropies; The abnormal order feature quantity is determined by the maximum data drift, the sequence position corresponding to the maximum data drift, the maximum singular entropy, and the sequence position corresponding to the maximum singular entropy.
5. The method according to claim 1, characterized in that Based on the abnormal order feature quantity, the order data extension space is spatially clustered to obtain the abnormal order feature set, which specifically includes: Determining the number of spatial clustering centers by using the abnormal order feature quantity; The order data extension space is spatially clustered based on the number of spatial clustering centers to obtain a set of abnormal order features.
6. A ticket order processing system based on big data, which uses the method described in any one of claims 1 to 5 to process ticket orders, characterized in that: The ticket order processing system based on big data includes a ticket order processing unit, and the ticket order processing unit includes: The extension module is used to extend the historical air ticket order data obtained from different big data sources to obtain the order data extension space; A processing module, used for obtaining a secondary center distance matrix of the order data extension space, and determining the singular entropy corresponding to each air ticket order data in the order data extension space according to the secondary center distance matrix; The processing module is further used to obtain an extension core of the order data extension space, and determine the data drift amount corresponding to each air ticket order data in the order data extension space through the extension core; The processing module is further used to determine the abnormal order feature quantity according to the data drift amount and singular entropy corresponding to each air ticket order data, and perform spatial clustering on the order data extension space based on the abnormal order feature quantity to obtain the abnormal order feature set; The anomaly detection module is used to perform anomaly detection on the air ticket order to be detected according to the abnormal order feature set.
7. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the big data-based air ticket order processing method described in any one of claims 1 to 5.
8. A computer-readable storage medium, wherein instructions or codes are stored in the computer-readable storage medium. When the instructions or codes are executed on a computer, the computer implements the big data-based air ticket order processing method as described in any one of claims 1 to 5.
Citation Information
Patent Citations
A moving object detection method oriented to radar signal data
CN109447163A
Gravity and magnetic potential field analytic continuation method based on spatial domain
CN110389391A
Power distribution network fault identification method and system based on intelligent data fusion analysis
CN111965486A
Spectral clustering algorithm parallelization method in abnormal data detection and system
CN112988693A
Abnormal behavior detection method, device and system and computer readable storage medium
CN114238952A
