Data detection method and device and electronic equipment

By combining operation behavior data and operation time data, combined with system priority information, a collection of abnormal operation behavior data is solved, and the problems of low detection accuracy and high false alarm rate in traditional detection methods are achieved, and more accurate abnormal behavior detection and Reduce false alarm rate.

CN119066453APending Publication Date: 2024-12-03CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER +1
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202411230848.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional abnormal behavior detection methods only consider user operation behavior or operation time information, resulting in low detection accuracy and high probability of false alarms. Especially when the system is of different importance, it is impossible to effectively distinguish abnormal behavior.

Method used

By obtaining the operation behavior data and operation time data of each system by the target object in each time window, combining the system's priority information, an abnormal operation behavior data collection is generated, and based on this, the detection rules are set, and the operation data to be tested is detected. , reduce false alarms.

Benefits of technology

It improves the accuracy of abnormal behavior detection, reduces the probability of false alarms, increases attention to important systems, reduces unnecessary risk alarms, and achieves more accurate detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066453A_ABST
    Figure CN119066453A_ABST
Patent Text Reader

Abstract

The invention provides a data detection method and device and electronic equipment, and relates to the technical field of information security. The method comprises the following steps: firstly, acquiring operation behavior data and operation time data of a target object in each time window for operating each system; splicing the operation behavior data in each time window with the identification information to obtain target operation behavior data corresponding to each time window; and finally, generating an abnormal operation behavior data set based on the target operation behavior data and the operation time data corresponding to each time window, and detecting the operation data to be detected based on an abnormal operation behavior detection rule set for the abnormal operation behavior data set. The behavior characteristics of the user can be comprehensively described by combining the priority of the system, the operation behavior of the user and the identification information of the operation time node of the user, the detection accuracy of the abnormal behavior of the user is improved, and the false alarm of risk alarm is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to a data detection method, device and electronic equipment. Background Art

[0002] Currently, there are many methods for detecting abnormal behaviors of target objects (such as users) applied in various systems of enterprises. Traditional abnormal behavior detection methods usually judge abnormal behaviors based on user operation behaviors or based on the time information of user operations. For example, a user used to operate the first system among various systems during working hours, but currently operates the first system during non-working hours; or the user usually logs into the first system for a long time during working hours, but currently logs in for a long time during non-working hours. At this time, the detector will determine the user's current behavior as abnormal behavior. However, in actual applications, because the importance of various systems is different, when the importance of the first system is low, it may not be necessary to determine the user's current operation of the first system during non-working hours as abnormal behavior.

[0003] In traditional abnormal behavior detection models, either only the impact of user operation behavior on abnormal behavior judgment is considered, or only the impact of user operation time information on abnormal behavior judgment is considered. However, the actual abnormal behavior judgment is related to the user's operation behavior, operation time, system importance, etc. Therefore, the detection information output by traditional abnormal behavior detection methods is less accurate and has a high probability of false alarms. Summary of the invention

[0004] The present invention application provides a data detection method, device and electronic device to improve the accuracy of identifying abnormal behavior and reduce the probability of false alarms. The specific technical solution is as follows:

[0005] In a first aspect, the present application provides a data detection method, comprising:

[0006] Obtaining the operation behavior data and operation time data of the target object operating each system within each time window, wherein the operation time data includes the operation duration and identification information of the operation time node, and the identification information is used to identify whether the operation time node belongs to the preset working time;

[0007] The operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window;

[0008] Based on the target operation behavior data and the operation time data corresponding to each time window, an abnormal operation behavior data set is generated, and the operation data to be tested is detected based on the abnormal operation behavior detection rule set for the abnormal operation behavior data set.

[0009] By comprehensively considering and splicing the target object's operation behavior data and operation time data for each system, it is possible to more accurately detect abnormal behaviors of the target object, improve detection accuracy, and reduce the probability of false alarms.

[0010] In a possible implementation, the operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window, including:

[0011] Based on the respective priorities of each system, encoding each system to obtain a respective encoding value corresponding to each system;

[0012] Concatenating the operation behavior data in each time window with the encoding value to obtain updated operation behavior data in each time window;

[0013] The update operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window.

[0014] Based on the above method, target operation behavior data including identification information of system priority and operation time node can be obtained, providing data support for subsequent detection of the operation data to be tested.

[0015] In a possible implementation, generating an abnormal operation behavior data set based on the target operation behavior data corresponding to each time window and the operation time data includes:

[0016] Clustering the target operation behavior data corresponding to each time window to obtain m operation behavior classes, and determining an abnormal operation behavior class from the m operation behavior classes;

[0017] Standardizing the operation time in the operation time data, and restoring the standardized operation time to obtain target operation time data corresponding to each time window;

[0018] Clustering the target operation time data corresponding to each of the time windows to obtain p operation time classes, and determining an abnormal operation time class from the p operation time classes;

[0019] Based on the abnormal operation behavior class and the abnormal operation time class, the abnormal operation behavior data set is generated.

[0020] By clustering the target operation behavior data corresponding to each time window, the target operation behavior data contains the system priority information and the identification information of the operation time node, which can more comprehensively characterize the operation behavior of the target object.

[0021] In a possible implementation, generating the abnormal operation behavior data set based on the abnormal operation behavior class and the abnormal operation time class includes:

[0022] For each target operation behavior abnormal data in the operation behavior abnormal class, determine the operation time data corresponding to the target operation behavior abnormal data, and when it is determined that the operation time data is in the operation time abnormal class, splice the target operation behavior abnormal data with the operation time data, and add the splicing result to the first abnormal data set;

[0023] For each target operation time abnormal data in the operation time abnormal class, determining the operation behavior data corresponding to the target operation time abnormal data, and when determining that the operation behavior data is in the operation behavior abnormal class, splicing the target operation time abnormal data with the operation behavior data, and adding the splicing result to the second abnormal data set;

[0024] The abnormal operation behavior data set is obtained by taking the union of the first abnormal data set and the second abnormal data set.

[0025] Based on the above method, an abnormal operation behavior data set with abnormal operation behavior and abnormal operation time can be determined according to the abnormal operation behavior class and the abnormal operation time class.

[0026] In a possible implementation, the operation data to be tested includes operation behavior data to be tested and operation time data to be tested, and the detecting the operation data to be tested based on the abnormal operation behavior detection rule set for the abnormal operation behavior data set includes:

[0027] Determining whether the operation data to be tested belongs to the abnormal operation behavior data set;

[0028] If yes, determining that the operation behavior data to be tested is abnormal data;

[0029] If not, calculate the first similarity between the operation behavior data to be tested and each target operation behavior abnormal data in the operation behavior abnormal class, and calculate the second similarity between the operation time data to be tested and the operation time abnormal class, and determine whether the operation data to be tested is abnormal data based on the first similarity and the second similarity.

[0030] Based on the above method, the operation data to be tested can be detected based on the user's operation behavior, operation time and system priority. This can more comprehensively characterize the user's behavior characteristics, improve the accuracy of detecting the user's operation behavior on the system, and reduce false alarms.

[0031] In a possible implementation, the standardizing the operation duration in the operation time data and restoring the standardized operation duration to obtain the target operation time data corresponding to each time window includes:

[0032] Determine the working time and other time belonging to the preset working time from the operation time;

[0033] The working hours and other hours are standardized to obtain the target working hours and target other hours corresponding to each time window after standardization;

[0034] The target working time and target other time corresponding to each standardized time window are restored in the time series order of the operation time in each time window, and the identification information of the operation time node is spliced ​​to obtain the target operation time data corresponding to each time window.

[0035] By processing the working hours and other durations through the range standardization method, the numerical ranges of the working hours and other durations can satisfy 0≤X ′ ≤1, so that the operation duration and the identification information of the operation time node 0 or 1 can be clustered as a whole later.

[0036] In a second aspect, the present application provides a data detection device, comprising:

[0037] A data acquisition module, used to acquire the operation behavior data and operation time data of the target object operating each system within each time window, wherein the operation time data includes the operation duration and the identification information of the operation time node, and the identification information is used to identify whether the operation time node belongs to the preset working time;

[0038] A data splicing module, used to splice the operation behavior data and the identification information in each time window to obtain the target operation behavior data corresponding to each time window;

[0039] The data detection module is used to generate an abnormal operation behavior data set based on the target operation behavior data corresponding to each time window and the operation time data, and detect the operation data to be tested based on the abnormal operation behavior detection rules set for the abnormal operation behavior data set.

[0040] In a possible implementation, the data splicing module is specifically used to:

[0041] Based on the respective priorities of each system, encoding each system to obtain a respective encoding value corresponding to each system;

[0042] Concatenating the operation behavior data in each time window with the encoding value to obtain updated operation behavior data in each time window;

[0043] The update operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window.

[0044] In a possible implementation, the data detection module is specifically used to:

[0045] Clustering the target operation behavior data corresponding to each time window to obtain m operation behavior classes, and determining an abnormal operation behavior class from the m operation behavior classes;

[0046] Standardizing the operation time in the operation time data, and restoring the standardized operation time to obtain target operation time data corresponding to each time window;

[0047] Clustering the target operation time data corresponding to each of the time windows to obtain p operation time classes, and determining an abnormal operation time class from the p operation time classes;

[0048] Based on the abnormal operation behavior class and the abnormal operation time class, the abnormal operation behavior data set is generated.

[0049] In a possible implementation, the data detection module is specifically used to:

[0050] For each target operation behavior abnormal data in the operation behavior abnormal class, determine the operation time data corresponding to the target operation behavior abnormal data, and when it is determined that the operation time data is in the operation time abnormal class, splice the target operation behavior abnormal data with the operation time data, and add the splicing result to the first abnormal data set;

[0051] For each target operation time abnormal data in the operation time abnormal class, determining the operation behavior data corresponding to the target operation time abnormal data, and when determining that the operation behavior data is in the operation behavior abnormal class, splicing the target operation time abnormal data with the operation behavior data, and adding the splicing result to the second abnormal data set;

[0052] The abnormal operation behavior data set is obtained by taking the union of the first abnormal data set and the second abnormal data set.

[0053] In a possible implementation, the data detection module is specifically used to:

[0054] Determining whether the operation data to be tested belongs to the abnormal operation behavior data set;

[0055] If yes, determining that the operation behavior data to be tested is abnormal data;

[0056] If not, calculate the first similarity between the operation behavior data to be tested and each target operation behavior abnormal data in the operation behavior abnormal class, and calculate the second similarity between the operation time data to be tested and the operation time abnormal class, and determine whether the operation data to be tested is abnormal data based on the first similarity and the second similarity.

[0057] In a possible implementation, the data detection module is specifically used to:

[0058] Determine the working time and other time belonging to the preset working time from the operation time;

[0059] The working hours and other hours are standardized to obtain target working hours and target other hours corresponding to each time window after standardization;

[0060] The target working time and target other time corresponding to each standardized time window are restored in the time series order of the operation time in each time window, and the identification information of the operation time node is spliced ​​to obtain the target operation time data corresponding to each time window.

[0061] In a third aspect, the present application provides an electronic device, including:

[0062] Memory, used to store computer programs;

[0063] The processor is used to implement the steps of the above-mentioned data detection method when executing the computer program stored in the memory.

[0064] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned data detection method are implemented.

[0065] For each aspect from the second to the fourth aspect and the technical effects that may be achieved by each aspect, please refer to the above description of the technical effects that can be achieved by the first aspect or various possible schemes in the first aspect, and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A flow chart of a data detection method provided in an embodiment of the present application;

[0067] Figure 2 A schematic diagram of the data detection system architecture provided in an embodiment of the present application;

[0068] Figure 3 A flowchart for obtaining target operation behavior data provided by an embodiment of the present application;

[0069] Figure 4 A flowchart of generating an abnormal operation behavior data set provided in an embodiment of the present application;

[0070] Figure 5 A schematic diagram of the structure of a data detection device provided in an embodiment of the present application;

[0071] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The specific operating methods in the method embodiments can also be applied to device embodiments or system embodiments. It should be noted that in the description of the present application, "multiple" is understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A is connected to B, which can represent: A is directly connected to B and A is connected to B through C. In addition, in the description of the present application, words such as "first" and "second" are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0073] The embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0074] At present, there are many methods for detecting abnormal behaviors of target objects (such as users) applied in various systems of enterprises. Traditional abnormal behavior detection methods usually judge abnormal behaviors based on user operation behaviors or based on the time information of user operations. For example, the user has not operated the first system among various systems before, but is currently operating the first system. At this time, the detector will determine the user's current behavior as abnormal behavior; for another example, the user used to operate the first system during working hours, but is currently operating the first system during non-working hours; or the user usually logs in to the first system for a long time during working hours, but is currently logging in for a long time during non-working hours. At this time, the detector will determine the user's current behavior as abnormal behavior. However, in actual applications, because the importance of various systems is different, when the importance of the first system is low, it may not be necessary to determine the operation behavior of users who have not operated the first system before and the behavior of users operating the first system during non-working hours as abnormal behavior.

[0075] In traditional abnormal behavior detection methods, either only the user's operation behavior is considered to affect the abnormal behavior judgment, or only the user's operation time information is considered to affect the abnormal behavior judgment. However, the actual user abnormal behavior judgment is related to the user's operation behavior, operation time, system importance, etc. Therefore, the detection information output by the traditional abnormal behavior detection method is less accurate and has a high probability of false alarms.

[0076] In view of this, in order to improve the accuracy of identifying abnormal behavior and reduce the probability of false alarms, the present application provides a data detection method, which specifically includes: first, obtaining the operation behavior data and operation time data of the target object in each time window operating each system; then, splicing the operation behavior data in each time window with the identification information to obtain the target operation behavior data corresponding to each time window; finally, based on the target operation behavior data and operation time data corresponding to each time window, generating an abnormal operation behavior data set, and detecting the operation data to be tested based on the abnormal operation behavior detection rules set for the abnormal operation behavior data set.

[0077] By comprehensively considering and splicing the system's importance information (system priority information) and operation time data in the operation behavior data, it is not only possible to discover abnormal behaviors based on the system's priority and increase the attention of operation and maintenance personnel to important systems; it is also possible to reduce unnecessary risk alarms, achieve risk noise reduction, and more accurately detect abnormal behaviors of target objects, improve detection accuracy, and reduce the probability of false alarms.

[0078] Reference Figure 1As shown, it is a flow chart of a data detection method provided in an embodiment of the present application, the method comprising:

[0079] S1, obtaining the operation behavior data and operation time data of the target object operating each system within each time window.

[0080] First of all, the method provided in this application can be applied to Figure 2 In the system architecture shown, the system architecture includes: a target object, a detector and a system (including a first system A1, a second system A2 and a third system A3), and the method provided in the present application can be executed in the detector.

[0081] The target object may be a staff member or other personnel related to the system business. The target object usually needs to perform corresponding operations on the system to complete the corresponding system business; the detector is used to detect whether the operating behavior of the target object is abnormal. When it is determined that the operating behavior of the target object is abnormal, the detector can send risk alarm information to the operation and maintenance personnel; the system can be a management system related to the enterprise's business, and this application does not impose specific restrictions on the number and type of systems.

[0082] In an embodiment of the present application, before the detector obtains the operation behavior data and operation time data of the target object operating each system within each time window, the detector may first obtain the operation behavior data of the target object operating each system within a set time period.

[0083] Specifically, the detector can monitor the target object's operation behavior on each system in real time, and record and store the operation behavior data of the target object on each system within a set time period. For example, if the enterprise includes q systems, the detector can record the operation behavior data of the target object on each system in the set time period, and the operation behavior data can be that when the user operates the first system among the q systems, the operation behavior data corresponding to the first system is set to 1; when the user does not operate the first system, the operation behavior data corresponding to the first system is set to 0.

[0084] It should be noted that the set time period can be 6 hours, 12 hours or a whole day, and this application does not impose any specific restrictions on this.

[0085] In the embodiment of the present application, when the detector obtains the operation behavior data of the target object operating each system within a set time period, it can also obtain and record the operation time data of the target object operating each system within the set time period.

[0086] Specifically, the operation time data includes the operation duration of the target object on each system and the identification information of the operation time node. In the specific implementation, if the target object operates the first system for 20 seconds, the detector can set the corresponding operation duration of the first system to 20; if the operation time node of the target object's operation on the first system is within the normal working time range of the target object, the detector can set the identification information of the operation time node to 1, otherwise it is set to 0.

[0087] In an embodiment of the present application, after obtaining the operation behavior data and operation time data of the target object operating on each system within a set time period, the detector can segment the operation behavior data and operation time data according to the set time window to obtain the operation behavior data and operation time data of the target object operating on each system within each time window. For example, the operation behavior data and operation time data of the target object operating on each system within 12 hours are segmented according to a time window of 1 hour, and the operation behavior data and operation time data of the target object operating on each system in each time window in 12 time windows are obtained.

[0088] In a possible implementation, if the target object needs to repeat the operation on q systems after operating q systems within a time window, the q systems can be arranged in a loop as follows, for example, A1, A2, A3, ... Aq, A1, A2, A3, ... Aq, and the operation behavior data corresponding to the time window can be (1, 0, ... 1, 0, 1, ... 0), indicating that only the second system A2 is operated in the second round; the operation time data corresponding to the time period is (t11, 0, ... t1q, 0, t1q+2, ... 0), where q is an integer greater than 3.

[0089] Through the above method, the operation behavior data and operation time data of the target object operating each system within each time window can be obtained, laying a data foundation for the subsequent detection of the operation data to be tested.

[0090] S2, concatenating the operation behavior data and identification information in each time window to obtain the target operation behavior data corresponding to each time window.

[0091] In the embodiment of the present application, after obtaining the operation behavior data in each time window and the identification information in the operation time data, the detector can splice the operation behavior data and the identification information in each time window to obtain the target operation behavior data corresponding to each time window. For details, please refer to the attached Figure 3 Steps S201-S203 in:

[0092] S201, encoding each system based on the priority of each system to obtain a coding value corresponding to each system;

[0093] S202, concatenating the operation behavior data and the encoding value in each time window to obtain updated operation behavior data in each time window;

[0094] S203, concatenating the update operation behavior data and the identification information in each time window to obtain the target operation behavior data corresponding to each time window.

[0095] Assume that we have A1, A2…A q In step S201, the detector can detect A1, A2, ... A according to the business importance of the system, the storage data status, and other dimensions. q The systems are divided into levels (i.e., the priority of each system is determined). For example, the system priorities can be divided into five levels, with system A1 being classified as the first priority and system A2 being classified as the second priority, and the present application does not impose any specific restrictions on the number of systems in each priority level; in addition, systems classified as the third priority level and above can be regarded as systems of important concern.

[0096] The detector can encode each system according to the priority of each system to obtain the corresponding encoding value of each system. In specific implementation, the detector can encode systems A1, A2...A q Perform one-hot encoding, for example, encode the systems from the first priority to the fifth priority as [00001, 00010, 00100, 01000, 10000] respectively.

[0097] In step S202, in order to include the priority of each system in the operation behavior data in each time window, the detector can concatenate the operation behavior data of the target object on each system in each time window with the respective coding value of each system to obtain the updated operation behavior data in each time window. For example, taking the first time window as an example. For the operation behavior data X1=[0, 1, ...1] in the first time window, add the respective coding value of the system priority after each operation behavior data to obtain the updated operation behavior data X1=[ 0 00001, 1 00010,… 1 10000].

[0098] Through the above method, the operational behavior data within each time window can reflect the priority of each system, and abnormal user behavior can be discovered in combination with the system priority, which increases the attention of operation and maintenance personnel to important systems and reduces their workload.

[0099] In step S203, in order to make the operation behavior data in each time window also include the identification information of the operation time node, after obtaining the updated operation behavior data in each time window, the detector can also splice the updated operation behavior data in each time window with the identification information to obtain the target operation behavior data corresponding to each time window. As in the above example, the update operation behavior data in the first time window is spliced ​​with the identification information to obtain the target operation behavior data in the first time window. 0 00001 0 , 1 00010 0 , …, 1 10000 0 ].

[0100] Through the above method, the target operation behavior data within each time window can reflect whether the operation time node of the target object's operation on each system belongs to the preset working time; by effectively integrating the operation behavior data and identification information, the two are used as a whole to characterize the behavior of the target object, fully reflecting the target object's operation behavior on the system, which can improve the detection accuracy and reduce false alarms.

[0101] S3, generating an abnormal operation behavior data set based on the target operation behavior data and operation time data corresponding to each time window, and detecting the operation data to be tested based on the abnormal operation behavior detection rules set for the abnormal operation behavior data set.

[0102] In the embodiment of the present application, the detector obtains the target operation behavior data corresponding to each time window (eg, X = [X1, ..., X n ] T ) and operation time data (e.g., T = [T1,…,T n ] T ) After that, the abnormal operation behavior data set can be generated according to X and T. For details, please refer to the attached Figure 4 Steps S301-S304 in:

[0103] S301, clustering the target operation behavior data corresponding to each time window to obtain m operation behavior classes, and determining an abnormal operation behavior class from the m operation behavior classes;

[0104] S302, standardizing the operation time in the operation time data, and restoring the standardized operation time to obtain target operation time data corresponding to each time window;

[0105] S303, clustering the target operation time data corresponding to each time window to obtain p operation time classes, and determining an abnormal operation time class from the p operation time classes;

[0106] S304: Generate an abnormal operation behavior data set based on the abnormal operation behavior class and the abnormal operation time class.

[0107] In step S301, after obtaining the target operation behavior data corresponding to each time window, the detector can cluster the target operation behavior data corresponding to each time window to obtain m operation behavior classes. In order to facilitate the subsequent detection of the operation data to be tested, the detector can also determine the abnormal operation behavior class B from the m operation behavior classes, and in this application, the abnormal operation behavior class can be determined based on the data volume of the target operation behavior data in the m operation behavior classes. For example, the detector calculates the number of target operation behavior data in each operation behavior class, and when it is determined that the number of target operation behavior data in the current operation behavior class is less than the preset number, the current operation behavior class is defined as the abnormal operation behavior class.

[0108] By clustering the target operation behavior data corresponding to each time window, the target operation behavior data contains the system priority information and the identification information of the operation time node, which can more comprehensively characterize the operation behavior of the target object.

[0109] In step S302, in order to cluster the operation duration and the identification information 0 or 1 of the operation time node as a whole, the operation duration needs to be standardized to avoid affecting the role of the identification information of the operation time node in the clustering model. After obtaining the operation time data corresponding to each time window, the detector can first determine the operation duration in the operation time data, and determine the working time and other durations belonging to the preset working time from the operation duration. For example, for the operation duration t1 in each time window, ...t n , respectively extract the working time R1=[t1,…,t m ], other duration R2=[t m ,…,t n ].

[0110] The detector normalizes the working time and other time, and can obtain the target working time and target other time corresponding to each time window after normalization. In this application, the range normalization method can be used to normalize R1 and R2. For example, first determine the maximum value X of the indicator (working time) max and minimum value X min , and calculate X max With X minThen subtract X from the different index of the variable (X) min , divided by R, that is: each standardized working time or other time X ′ =(XX min ) / (X max -X min ).

[0111] By processing the working hours and other durations through the range standardization method, the numerical ranges of the working hours and other durations can satisfy 0≤X ′ ≤1.

[0112] After the detector has standardized the working time and other time, in order to ensure the consistency of the operation time of the target object on each system, it is necessary to restore the target working time and target other time corresponding to each time window after standardization according to the time series order of the operation time in each time window, and then concatenate the identification information of the corresponding operation time node with the restored target working time and target other time to obtain the target operation time data T = [Z1,…,Z n ] T , Z1=[(Z 11 ,0),(Z 12 ,0),(Z 1n ,0)].

[0113] By processing the working hours and other durations through the range standardization method, the numerical ranges of the working hours and other durations can satisfy 0≤X ′ ≤1, so that the operation duration and the identification information of the operation time node 0 or 1 can be clustered as a whole later.

[0114] In step S303, after obtaining the target operation time data corresponding to each time window, the detector can perform a n Clustering is performed to obtain p operation time classes, and an operation time abnormality class C is determined from the p operation time classes, where m and p are both integers greater than or equal to 1.

[0115] In the present application, the operation time anomaly class can also be determined based on the amount of data of the target operation duration in p operation time classes. For example, the detector calculates the number of target operation times in each operation time class, and when it is determined that the number of target operation times in the current operation time class is less than a preset number, the current operation time class is defined as an operation time anomaly class.

[0116] In step S304, after determining the abnormal operation behavior class and the abnormal operation time class, the detector may generate an abnormal operation behavior data set based on the abnormal operation behavior class and the abnormal operation time class.

[0117] Specifically, for each target operation behavior abnormal data in the operation behavior abnormal class B, the detector can determine the operation time data corresponding to the target operation behavior abnormal data. When it is determined that the operation time data corresponding to the target operation behavior abnormal data is in the operation time abnormal class C, the target operation behavior abnormal data is spliced ​​with the operation time data corresponding to the target operation behavior abnormal data, and the splicing result is added to the first abnormal data set E1; for each target operation time abnormal data in the operation time abnormal class C, the detector can determine the operation behavior data corresponding to the target operation time abnormal data. When it is determined that the operation behavior data corresponding to the target operation time abnormal data is in the operation behavior abnormal class B, the target operation time abnormal data is spliced ​​with the operation behavior data corresponding to the target operation time abnormal data, and the splicing result is added to the second abnormal data set E2; the detector takes the union of the first abnormal data set and the second abnormal data set to obtain the abnormal operation behavior data set D=E1∪E2.

[0118] By clustering the operation duration and the identification information of the operation time node as a whole when calculating the abnormal operation behavior data set, the identification information of the operation time node is considered when calculating the abnormal operation behavior class and the abnormal operation time class, increasing the weight of the identification information in the abnormal behavior identification, and effectively integrating the operation behavior data and the operation time data. The two are taken as a whole to fully characterize the target object's operation behavior on the system, which can improve the accuracy of detection and reduce false alarms.

[0119] In the embodiment of the present application, after generating the abnormal operation behavior data set, the detector can detect the operation data to be detected based on the abnormal operation behavior detection rules set for the abnormal operation behavior data set. The specific detection method is as follows:

[0120] The detector obtains the operation data to be tested within the time window to be tested, wherein the operation data to be tested includes the operation behavior data to be tested and the operation time data to be tested. Assume that the operation behavior data to be tested is X j (including system priority information and identification information of operation time node), the operation time data to be tested is T j , for the operation time data to be tested T j The operation time data to be tested is standardized in the same manner as the operation time in the above operation time data to obtain the standardized operation time data Z j ; The detector first determines the operation data to be tested [X j ,T j ] belongs to the abnormal operation behavior data set. If the operation data to be tested [X j ,T j] belongs to the abnormal operation behavior data set. The detector can determine that the operation behavior data to be tested is abnormal data and output the corresponding abnormal detection results to the operation and maintenance personnel.

[0121] If the operation data to be tested [X j ,T j ] does not belong to the abnormal operation behavior data set, the detector can calculate the operation behavior data to be tested X j The first similarity between each target operation behavior abnormal data in the operation behavior abnormality class. For example, assuming that there are w target operation behavior abnormal data in B, for k=1,2,…,w,calculate X j With b K The first similarity of X j With b K The cosine similarity of , which is not specifically limited in this application.

[0122] The calculation of the first similarity can refer to the following formula:

[0123]

[0124] The detector can also calculate the second similarity h between the operation time data to be tested and the class center of the operation time anomaly class based on the above formula, and the repeated parts will not be repeated here.

[0125] The detector can determine whether the operation data to be tested is abnormal data according to the first similarity and the second similarity. Specifically, the detector can sum the first similarity and the second similarity to obtain the target similarity Y K =ρ k +h, if min(Y K ) is greater than 1, the operation data to be tested is determined to be abnormal data, and the corresponding abnormal detection result is output to the operation and maintenance personnel; otherwise, the operation data to be tested is determined to be normal data.

[0126] To sum up, the method provided in this application comprehensively characterizes the user's behavior characteristics by combining the system priority, the user's operation behavior and the identification information of the user's operation time node, which can improve the detection accuracy of abnormal user behavior, reduce the false alarm of risk alarms, and effectively reduce the workload of operation and maintenance personnel.

[0127] Based on the method provided in the above embodiment, the embodiment of the present application also provides a data detection device, such as Figure 5 The figure is a schematic diagram of the structure of a data detection device in an embodiment of the present application, the device comprising:

[0128] The data acquisition module 501 is used to acquire the operation behavior data and operation time data of the target object operating each system within each time window, wherein the operation time data includes the operation duration and the identification information of the operation time node, and the identification information is used to identify whether the operation time node belongs to the preset working time;

[0129] A data splicing module 502 is used to splice the operation behavior data and the identification information in each time window to obtain the target operation behavior data corresponding to each time window;

[0130] The data detection module 503 is used to generate an abnormal operation behavior data set based on the target operation behavior data corresponding to each time window and the operation time data, and detect the operation data to be tested based on the abnormal operation behavior detection rules set for the abnormal operation behavior data set.

[0131] In a possible implementation, the data splicing module 502 is specifically used for:

[0132] Based on the respective priorities of each system, encoding each system to obtain a respective encoding value corresponding to each system;

[0133] Concatenating the operation behavior data in each time window with the encoding value to obtain updated operation behavior data in each time window;

[0134] The update operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window.

[0135] In a possible implementation, the data detection module 503 is specifically used to:

[0136] Clustering the target operation behavior data corresponding to each time window to obtain m operation behavior classes, and determining an abnormal operation behavior class from the m operation behavior classes;

[0137] Standardizing the operation time in the operation time data, and restoring the standardized operation time to obtain target operation time data corresponding to each time window;

[0138] Clustering the target operation time data corresponding to each of the time windows to obtain p operation time classes, and determining an abnormal operation time class from the p operation time classes;

[0139] Based on the abnormal operation behavior class and the abnormal operation time class, the abnormal operation behavior data set is generated.

[0140] In a possible implementation, the data detection module 503 is specifically used to:

[0141] For each target operation behavior abnormal data in the operation behavior abnormal class, determine the operation time data corresponding to the target operation behavior abnormal data, and when it is determined that the operation time data is in the operation time abnormal class, splice the target operation behavior abnormal data with the operation time data, and add the splicing result to the first abnormal data set;

[0142] For each target operation time abnormal data in the operation time abnormal class, determining the operation behavior data corresponding to the target operation time abnormal data, and when determining that the operation behavior data is in the operation behavior abnormal class, splicing the target operation time abnormal data with the operation behavior data, and adding the splicing result to the second abnormal data set;

[0143] The abnormal operation behavior data set is obtained by taking the union of the first abnormal data set and the second abnormal data set.

[0144] In a possible implementation, the data detection module 503 is specifically used to:

[0145] Determining whether the operation data to be tested belongs to the abnormal operation behavior data set;

[0146] If yes, determining that the operation behavior data to be tested is abnormal data;

[0147] If not, calculate the first similarity between the operation behavior data to be tested and each target operation behavior abnormal data in the operation behavior abnormal class, and calculate the second similarity between the operation time data to be tested and the operation time abnormal class, and determine whether the operation data to be tested is abnormal data based on the first similarity and the second similarity.

[0148] In a possible implementation, the data detection module 503 is specifically used to:

[0149] Determine the working time and other time belonging to the preset working time from the operation time;

[0150] The working hours and other hours are standardized to obtain target working hours and target other hours corresponding to each time window after standardization;

[0151] The target working time and target other time corresponding to each standardized time window are restored in the time series order of the operation time in each time window, and the identification information of the operation time node is spliced ​​to obtain the target operation time data corresponding to each time window.

[0152] Based on the same inventive concept, an electronic device is also provided in the embodiment of the present application, and the electronic device can realize the function of the aforementioned data detection device, referring to Figure 6 , the electronic device comprises:

[0153] At least one processor 601, and a memory 602 connected to the at least one processor 601. The specific connection medium between the processor 601 and the memory 602 is not limited in the embodiment of the present application. Figure 6 In the example, the processor 601 and the memory 602 are connected via a bus 600. Figure 6 The connection between other components is shown by bold lines, and is not intended to be limiting. The bus 600 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 601 can also be called a controller, and there is no limitation on the name.

[0154] In the embodiment of the present application, the memory 602 stores instructions that can be executed by at least one processor 601. The at least one processor 601 can execute the data detection method discussed above by executing the instructions stored in the memory 602. The processor 601 can implement Figure 5 The functions of each module in the device shown.

[0155] Among them, the processor 601 is the control center of the device, and can use various interfaces and lines to connect the various parts of the entire control device. By running or executing instructions stored in the memory 602 and calling the data stored in the memory 602, the various functions of the device and processing data, the device can be monitored as a whole.

[0156] In one possible design, the processor 601 may include one or more processing units, and the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 601. In some embodiments, the processor 601 and the memory 602 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on separate chips.

[0157] Processor 601 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the data detection method disclosed in the embodiments of the present application can be directly embodied as a hardware processor to be executed, or a combination of hardware and software modules in the processor can be executed.

[0158] The memory 602 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 602 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 602 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 602 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0159] By designing and programming the processor 601, the code corresponding to the data detection method described in the above embodiment can be fixed into the chip, so that the chip can execute the code when running. Figure 1 The steps of the data detection method in the embodiment shown are as follows: How to design and program the processor 601 is a technique well known to those skilled in the art and will not be described in detail here.

[0160] Based on the same inventive concept, an embodiment of the present application further provides a storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer executes the data detection method discussed above.

[0161] In some possible implementations, various aspects of the data detection method provided by the present application may also be implemented in the form of a program product, which includes a program code. When the program product is run on an apparatus, the program code is used to enable the control device to execute the steps of the data detection method according to various exemplary implementations of the present application described above in this specification.

[0162] 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.

[0163] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0164] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0165] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0166] 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 application. 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 data detection method, characterized in that: include: Obtaining the operation behavior data and operation time data of the target object operating each system within each time window, wherein the operation time data includes the operation duration and identification information of the operation time node, and the identification information is used to identify whether the operation time node belongs to the preset working time; The operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window; Based on the target operation behavior data and the operation time data corresponding to each time window, an abnormal operation behavior data set is generated, and the operation data to be tested is detected based on the abnormal operation behavior detection rule set for the abnormal operation behavior data set.

2. The method according to claim 1, characterized in that The step of concatenating the operation behavior data in each time window with the identification information to obtain target operation behavior data corresponding to each time window includes: Based on the respective priorities of each system, encoding each system to obtain a respective encoding value corresponding to each system; Concatenating the operation behavior data in each time window with the encoding value to obtain updated operation behavior data in each time window; The update operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window.

3. The method according to claim 1, characterized in that The generating of the abnormal operation behavior data set based on the target operation behavior data corresponding to each time window and the operation time data includes: Clustering the target operation behavior data corresponding to each time window to obtain m operation behavior classes, and determining an abnormal operation behavior class from the m operation behavior classes; Standardizing the operation time in the operation time data, and restoring the standardized operation time to obtain target operation time data corresponding to each time window; Clustering the target operation time data corresponding to each of the time windows to obtain p operation time classes, and determining an abnormal operation time class from the p operation time classes; Based on the abnormal operation behavior class and the abnormal operation time class, the abnormal operation behavior data set is generated.

4. The method according to claim 3, characterized in that The generating the abnormal operation behavior data set based on the abnormal operation behavior class and the abnormal operation time class includes: For each target operation behavior abnormal data in the operation behavior abnormal class, determine the operation time data corresponding to the target operation behavior abnormal data, and when it is determined that the operation time data is in the operation time abnormal class, splice the target operation behavior abnormal data with the operation time data, and add the splicing result to the first abnormal data set; For each target operation time abnormal data in the operation time abnormal class, determining the operation behavior data corresponding to the target operation time abnormal data, and when determining that the operation behavior data is in the operation behavior abnormal class, splicing the target operation time abnormal data with the operation behavior data, and adding the splicing result to the second abnormal data set; The abnormal operation behavior data set is obtained by taking the union of the first abnormal data set and the second abnormal data set.

5. The method according to claim 3, characterized in that The operation data to be tested includes operation behavior data to be tested and operation time data to be tested, and the abnormal operation behavior detection rule set for the abnormal operation behavior data set is used to detect the operation data to be tested, including: Determining whether the operation data to be tested belongs to the abnormal operation behavior data set; If yes, determining that the operation behavior data to be tested is abnormal data; If not, calculate the first similarity between the operation behavior data to be tested and each target operation behavior abnormal data in the operation behavior abnormal class, and calculate the second similarity between the operation time data to be tested and the operation time abnormal class, and determine whether the operation data to be tested is abnormal data based on the first similarity and the second similarity.

6. The method according to claim 3, characterized in that The standardizing the operation time in the operation time data and restoring the standardized operation time to obtain the target operation time data corresponding to each time window includes: Determine the working time and other time belonging to the preset working time from the operation time; The working hours and other hours are standardized to obtain target working hours and target other hours corresponding to each time window after standardization; The target working time and target other time corresponding to each standardized time window are restored in the time series order of the operation time in each time window, and the identification information of the operation time node is spliced ​​to obtain the target operation time data corresponding to each time window.

7. A data detection device, characterized in that: include: A data acquisition module, used to acquire the operation behavior data and operation time data of the target object operating each system within each time window, wherein the operation time data includes the operation duration and the identification information of the operation time node, and the identification information is used to identify whether the operation time node belongs to the preset working time; A data splicing module, used to splice the operation behavior data and the identification information in each time window to obtain the target operation behavior data corresponding to each time window; The data detection module is used to generate an abnormal operation behavior data set based on the target operation behavior data corresponding to each time window and the operation time data, and detect the operation data to be tested based on the abnormal operation behavior detection rules set for the abnormal operation behavior data set.

8. The device according to claim 7, characterized in that The data splicing module is specifically used for: Based on the respective priorities of each system, encoding each system to obtain a respective encoding value corresponding to each system; Concatenating the operation behavior data in each time window with the encoding value to obtain updated operation behavior data in each time window; The update operation behavior data in each time window is concatenated with the identification information to obtain the target operation behavior data corresponding to each time window.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to implement the method steps of any one of claims 1 to 6 when executing the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Method for detecting user abnormal behavior based on behavior similarity

    CN104731914A

  • Baseline construction and unknown abnormal behavior detection method oriented to system log

    CN107528832A

  • Abnormal-user detection method based on session feature similarity fuzzy-clustering

    CN108595655A

  • Internal threat intelligent detection method and system based on spatial-temporal feature fusion

    CN113919239A

  • Internal threat detection method and system based on multiple modes

    CN115034292A