False alarm identification method and device, computer equipment and storage medium
By generating an eigenvalue array and calculating correlation coefficients, and accurately identifying false alarms, the problems of inaccurate and low efficiency of abnormal user behavior detection in the prior art are solved, the early warning false alarm rate is reduced, and the detection accuracy and efficiency are improved.
Patent Information
- Application Number
- CN202411095436.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art is prone to false alarms caused by accidental operational errors when detecting abnormal user behaviors, and the attack threat evades security protection by disguising as normal user behaviors, making detection inaccurate and inefficient, resulting in a high warning false alarm rate.
By obtaining behavior data, generating an array of eigenvalues, and determining the most relevant target preset behavior in the user behavior database, calculating the correlation coefficient if it is within a specific threshold range, it is determined that the alarm signal is an error alarm, thereby accurately identifying the error alarm. Improve detection accuracy and efficiency.
It effectively reduces the false alarm rate, improves the accuracy and efficiency of detecting abnormal behaviors of users, and reduces the occurrence of false alarms.
Smart Images

Figure CN119071034A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of network security technology, and in particular to a false alarm identification method, device, computer equipment and storage medium. Background Art
[0002] With the rapid development of communication technologies such as cloud computing and big data, and the emergence of various network services, the data in various network platforms and network software has increased massively. In order to ensure data security, it is usually necessary to monitor the user behaviors related to network platforms, network systems, computer rooms, servers, etc. in real time, and issue early warnings when user behaviors are abnormal, so that maintenance personnel can find the abnormal causes in time and solve the problems.
[0003] Normally, the judgment of abnormal user behavior relies on a preset threshold mechanism (e.g., traffic threshold, upper limit, specific operation count benchmark, etc.). Although this method can respond to abnormal user behavior immediately and trigger an early warning, it is easy to cause false alarms due to accidental operational errors. In addition, many current attack threats often evade traditional security protection measures by disguising themselves as normal user behavior, making the detection of abnormal user behavior inaccurate and inefficient, resulting in a high false alarm rate for early warnings. Summary of the invention
[0004] In view of this, the present invention provides a false alarm identification method, apparatus, computer equipment and storage medium to solve the problem of inaccurate and inefficient detection of abnormal user behavior, resulting in a high false alarm rate of early warnings.
[0005] In a first aspect, the present invention provides a method for identifying false alarms, the method comprising: when an alarm signal is received, obtaining behavior data of a series of behaviors, the behavior data including a behavior identifier corresponding to each behavior in the series of behaviors, the alarm signal being triggered when the monitoring system determines that the series of behaviors of the user as a whole are abnormal; searching for a feature value corresponding to each behavior identifier in a behavior mapping table, generating a feature value array for a series of behaviors, the behavior mapping table including at least one corresponding relationship, each corresponding relationship being a corresponding relationship between a behavior identifier and a feature value.
[0006] Based on the characteristic value array, a target preset series of behaviors that is most relevant to a series of behaviors is determined in the user behavior library, the target preset series of behaviors has a corresponding relationship with the target preset characteristic value array, the user behavior library includes at least one preset characteristic value array, each preset characteristic value array corresponds to a preset series of behaviors, and the preset series of behaviors are all normal behaviors; a target correlation coefficient between the characteristic value array and the target preset characteristic value array is determined, the target correlation coefficient is used to indicate the degree of correlation between a series of behaviors and the target preset series of behaviors; if the target correlation coefficient is greater than or equal to a first threshold and less than or equal to a second threshold, it is determined that the alarm signal triggered by the system is a false alarm, and the series of behaviors are all normal behaviors.
[0007] Based on the method of the first aspect above, when an alarm signal is received, behavioral data of a series of behaviors can be obtained, and the characteristic value corresponding to each behavior identifier can be searched in the behavior mapping table to generate a characteristic value array of a series of behaviors. Based on the characteristic value array, a target preset series of behaviors that is most relevant to the series of behaviors is determined in the user behavior library, and the target correlation coefficient between the characteristic value array and the target preset characteristic value array is determined. If the target correlation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the alarm signal triggered by the system is a false alarm, and the series of behaviors are all normal behaviors.
[0008] The method provided by the present aspect, when receiving an alarm signal, compares the series of behaviors of the user that triggered the alarm with the preset series of behaviors in the user behavior library, determines the target preset series of behaviors that are most relevant to the series of behaviors, and further determines the target correlation coefficient between the target preset feature value array and the feature value array based on the target preset feature value array of the target preset series of behaviors and the feature value array of the series of behaviors, and when the target correlation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, that is, when the target preset series of behaviors is the same or similar to the series of behaviors, since the target preset series of behaviors are all normal behaviors, it can be determined that a series of behaviors that are the same or similar to the target preset series of behaviors are also normal behaviors, and then it can be accurately determined that the alarm signal triggered by the system is a false alarm, thereby improving the accuracy and efficiency of detecting abnormal user behaviors and reducing the false alarm rate of early warnings.
[0009] In an optional embodiment, based on the feature value array, a target preset series of behaviors that are most relevant to a series of behaviors are determined in the user behavior library, including: based on the feature value array, using a correlation coefficient function expression, calculating the correlation coefficient between each preset feature value array and the feature value array in the user behavior library to obtain at least one correlation coefficient, the correlation coefficient is used to indicate the degree of difference between each preset feature value array and the feature value array, and the correlation coefficient function expression is determined based on the preset feature values in the preset feature value array, the average value of the preset feature values in the preset feature value array, the feature values in the feature value array, and the average value of the feature values in the feature value array.
[0010] Determine a maximum correlation coefficient among at least one correlation coefficient, and determine a preset eigenvalue array corresponding to the maximum correlation coefficient as a target preset eigenvalue array according to the maximum correlation coefficient and a first corresponding relationship, wherein the first corresponding relationship is a corresponding relationship between each correlation coefficient and each preset eigenvalue array;
[0011] According to the target preset characteristic value array and the second corresponding relationship, the preset series of behaviors corresponding to the target preset characteristic value array is determined as the target preset series of behaviors, and the second corresponding relationship is the corresponding relationship between each preset characteristic value array and each preset series of behaviors.
[0012] Based on the above method, the target preset series of behaviors that are most relevant to a series of behaviors can be determined by calculating the correlation coefficient between each preset feature value array and the feature value array in the user behavior library.
[0013] In an optional implementation, the correlation coefficient function expression is expressed by the following formula:
[0014]
[0015] r represents the correlation coefficient between each preset eigenvalue array and the eigenvalue array; X i represents the i-th eigenvalue in the preset eigenvalue array; Y i Represents the i-th preset eigenvalue in the eigenvalue array; represents the average value of the preset eigenvalues in the preset eigenvalue array, Represents the mean of the eigenvalues in the eigenvalue array.
[0016] Based on the above method, the correlation coefficient between each preset eigenvalue array and the eigenvalue array can be calculated through the correlation coefficient function expression.
[0017] In an optional implementation, determining a target correlation coefficient between the eigenvalue array and the target preset eigenvalue array includes: determining a maximum correlation coefficient as the target correlation coefficient between the eigenvalue array and the target preset eigenvalue array.
[0018] Based on the above method, the target correlation coefficient can be determined, so as to facilitate the subsequent determination of whether the alarm signal is a false alarm based on the target correlation coefficient.
[0019] In an optional embodiment, the method further includes: obtaining preset behavior data for at least one preset series of behaviors, the preset behavior data including a preset behavior identifier corresponding to each preset behavior in each preset series of behaviors; searching for a preset feature value corresponding to each preset behavior identifier in a behavior mapping table, and generating a preset feature value array for each preset series of behaviors; and generating a user behavior library based on at least one preset feature value array.
[0020] Based on the above method, a user behavior library including a preset feature value array of at least one preset series of behaviors can be generated, so as to facilitate the subsequent determination of the most relevant preset series of behaviors in the series of behaviors.
[0021] In an optional embodiment, if the target correlation coefficient is less than the first threshold and greater than or equal to the third threshold, the alarm signal triggered by the marking system is a suspected false alarm, and an early warning message is sent, which is used to instruct management personnel to manually analyze a series of behaviors.
[0022] Based on the above method, if the target correlation coefficient is less than the first threshold and greater than or equal to the third threshold, that is, the correlation between the target preset series of behaviors and the series of behaviors is general, it is impossible to determine whether a series of behaviors are similar to the target preset series of behaviors and are all normal behaviors. Therefore, it is necessary to mark the alarm signal triggered by the system as a suspected false alarm, and further notify the management personnel to manually analyze the series of behaviors.
[0023] In an optional embodiment, the method further includes: if the target correlation coefficient is greater than or equal to a fourth threshold and less than the third threshold, determining that the alarm signal triggered by the system is a normal alarm and that abnormal behavior exists in a series of behaviors.
[0024] Based on the above method, if the target correlation coefficient is greater than or equal to the fourth threshold and less than the third threshold, that is, the correlation between the target preset series of behaviors and the series of behaviors is poor, it is determined that a series of behaviors is significantly different from the target preset series of behaviors. Therefore, it is determined that there are abnormal behaviors in the series of behaviors, and the alarm signal triggered by the system is a normal alarm.
[0025] In a second aspect, the present invention provides a false alarm identification device, which includes: an acquisition module, which is used to acquire behavior data of a series of behaviors when an alarm signal is received, the behavior data including a behavior identifier corresponding to each behavior in the series of behaviors, and the alarm signal is triggered when the monitoring system determines that the series of behaviors of the user are abnormal as a whole; a processing module, which is used to search for a characteristic value corresponding to each behavior identifier in a behavior mapping table, and generate a characteristic value array for a series of behaviors, the behavior mapping table including at least one corresponding relationship, each corresponding relationship being a corresponding relationship between a behavior identifier and a characteristic value.
[0026] The processing module is also used to determine, based on the characteristic value array, a target preset series of behaviors that is most relevant to a series of behaviors in the user behavior library, the target preset series of behaviors has a corresponding relationship with the target preset characteristic value array, the user behavior library includes at least one preset characteristic value array, each preset characteristic value array corresponds to a preset series of behaviors, and the preset series of behaviors are all normal behaviors; the processing module is also used to determine a target correlation coefficient between the characteristic value array and the target preset characteristic value array, the target correlation coefficient is used to indicate the degree of correlation between a series of behaviors and the target preset series of behaviors; the processing module is also used to determine that the alarm signal triggered by the system is a false alarm, and the series of behaviors are all normal behaviors if the target correlation coefficient is greater than or equal to a first threshold and less than or equal to a second threshold.
[0027] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the false alarm identification method of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.
[0028] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to execute the false alarm identification method of the first aspect or any corresponding embodiment thereof.
[0029] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the false alarm identification method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0031] Figure 1 is a flow chart of a method for identifying a false alarm according to an embodiment of the present invention;
[0032] Figure 2 is a flow chart of another method for identifying false alarms according to an embodiment of the present invention;
[0033] Figure 3 is a structural block diagram of a false alarm identification device according to an embodiment of the present invention;
[0034] Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0036] As described in the background technology, the detection method of abnormal user behavior based on a preset threshold mechanism can respond to abnormal user behavior immediately and trigger an early warning, but it is easy to cause false alarms due to accidental operational errors of personnel. In addition, many attack threats now often evade traditional security protection measures by disguising themselves as normal user behaviors, making the detection of abnormal user behaviors inaccurate and inefficient, resulting in a high false alarm rate for early warnings.
[0037] In order to solve the above technical problems, an embodiment of the present invention provides a method for identifying false alarms, which can solve the problem that the detection of abnormal user behavior is inaccurate and inefficient, resulting in a high false alarm rate of early warnings.
[0038] In an embodiment of the present invention, the above-mentioned false alarm identification method can be performed by a false alarm identification device. The false alarm identification device can be any device with communication function and computing function. For example, the false alarm identification device can be a computer, a server or a cloud server.
[0039] According to an embodiment of the present invention, an embodiment of a method for identifying false alarms is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0040] In this embodiment, a false alarm identification method is provided, which can be used in the above-mentioned false alarm identification device. Figure 1 is a flow chart of a method for identifying false alarms according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:
[0041] S101: When an alarm signal is received, behavior data of a series of behaviors are obtained.
[0042] The behavior data includes the behavior identifier corresponding to each behavior in a series of behaviors. The series of behaviors can be behaviors required by the user to perform business, or behaviors caused by user's erroneous operation. For example, the behavior data includes the identifier corresponding to logging into the business system, the identifier corresponding to accessing the project page, and the identifier corresponding to downloading the file.
[0043] In the embodiment of the present invention, the alarm signal is triggered when the monitoring system determines that a series of user behaviors are abnormal as a whole.
[0044] It can be understood that if a series of behaviors are judged as abnormal as a whole, it means that at least one behavior in the series of behaviors is abnormal, and the monitoring system can judge the series of behaviors as abnormal as a whole.
[0045] S102: Searching for a feature value corresponding to each behavior identifier in the behavior mapping table to generate a feature value array of a series of behaviors.
[0046] The behavior mapping table includes at least one corresponding relationship, and each corresponding relationship is a corresponding relationship between a behavior identifier and a characteristic value.
[0047] Exemplarily, a behavior mapping table includes the correspondence between the identifier corresponding to logging into the business system and the characteristic value a1, the correspondence between the identifier corresponding to accessing the project page and the characteristic value b1, and the correspondence between the identifier corresponding to downloading the file and the characteristic value c1; a series of behaviors include user logging into the business system, accessing the project page and downloading the file as an example, the false alarm identification device searches the behavior mapping table for the characteristic value of the identifier corresponding to logging into the business system, which is a1, the characteristic value of the identifier corresponding to accessing the project page is b1, and the characteristic value of the identifier corresponding to downloading the file is c1, and generates a characteristic value array of [a1, b1, c1] for a series of behaviors.
[0048] S103: Based on the feature value array, determine a target preset series of behaviors that are most relevant to the series of behaviors in the user behavior library.
[0049] Among them, a series of target preset behaviors have a corresponding relationship with the target preset characteristic value array.
[0050] In the embodiment of the present invention, the user behavior library includes at least one preset feature value array. Each preset feature value array corresponds to a preset series of behaviors. The preset series of behaviors are all normal behaviors.
[0051] In some optional embodiments, the false alarm identification device is based on the characteristic value array, and uses the correlation coefficient function expression to calculate the correlation coefficient between each preset characteristic value array and the characteristic value array in the user behavior library to obtain at least one correlation coefficient; determine the maximum correlation coefficient among the at least one correlation coefficient, and determine the preset characteristic value array corresponding to the maximum correlation coefficient as the target preset characteristic value array based on the maximum correlation coefficient and the first corresponding relationship; determine the preset series of behaviors corresponding to the target preset characteristic value array as the target preset series of behaviors based on the target preset characteristic value array and the second corresponding relationship.
[0052] The correlation coefficient is used to indicate the degree of difference between each preset eigenvalue array and the eigenvalue array.
[0053] In the embodiment of the present invention, the first corresponding relationship is the corresponding relationship between each correlation coefficient and each preset characteristic value array. The second corresponding relationship is the corresponding relationship between each preset characteristic value array and each preset series of behaviors.
[0054] In an embodiment of the present invention, the correlation coefficient function expression is determined based on preset eigenvalues in a preset eigenvalue array, an average value of preset eigenvalues in a preset eigenvalue array, eigenvalues in an eigenvalue array, and an average value of eigenvalues in an eigenvalue array.
[0055] Among them, the correlation coefficient function expression is expressed by the following formula:
[0056] Among them, r represents the correlation coefficient between each preset eigenvalue array and the eigenvalue array; represents the i-th eigenvalue in the preset eigenvalue array; represents the i-th preset eigenvalue in the eigenvalue array; represents the average value of the preset eigenvalues in the preset eigenvalue array, and represents the average value of the eigenvalues in the eigenvalue array.
[0057] Optionally, the false alarm identification device obtains preset behavior data of at least one preset series of behaviors; searches for a preset feature value corresponding to each preset behavior identifier in a behavior mapping table, and generates a preset feature value array for each preset series of behaviors; and generates a user behavior library based on at least one preset feature value array.
[0058] The preset behavior data includes a preset behavior identifier corresponding to each preset behavior in each preset series of behaviors. The preset behavior can be for different permissions (for example, permissions to access a page), positions (for example, the preset position of finance allows access to a specified page or the preset position limits the number of times a specified page is accessed), and scenarios (in a preset scenario, the execution order of a series of behaviors is different).
[0059] For example, the preset behavior can be local login to the business system, remote login to the business system, normal access to the project page (the traffic required to access the project web page is less than the preset traffic), normal download / upload of files, normal program startup (the resources occupied by the startup program are less than the preset resources), and changing settings.
[0060] Correspondingly, the preset characteristic value of the identifier corresponding to the local login business system is a1, the preset characteristic value of the identifier corresponding to the remote login business system is a2, the preset characteristic value of the identifier corresponding to the normal access to the project page is b1, the preset characteristic value of the identifier corresponding to the normal file download is c1, the preset characteristic value of the identifier corresponding to the normal file upload is c2, the preset characteristic value of the identifier corresponding to the normal program startup is d1, and the preset characteristic value of the identifier corresponding to the setting change is e1.
[0061] It can be understood that the user behavior library may include [a1, b1, c1], [a2, b1, c1], [a2, b1, c2], [a1, b1, d1], [a2, b1, c1, d1], [a1, c1, b1], etc.
[0062] S104: Determine a target correlation coefficient between the eigenvalue array and a target preset eigenvalue array.
[0063] Among them, the target correlation coefficient is used to indicate the degree of difference between a series of behaviors and the target preset series of behaviors.
[0064] In some optional implementations, the false alarm identification device determines the maximum correlation coefficient as a target correlation coefficient between the eigenvalue array and the target preset eigenvalue array.
[0065] S105: If the target correlation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the alarm signal triggered by the system is a false alarm and the series of behaviors are normal behaviors.
[0066] The target correlation coefficient may range from -1 to 1.
[0067] In the embodiment of the present invention, the first threshold value may be set according to actual needs without limitation. For example, the first threshold value may be 0.8.
[0068] In the embodiment of the present invention, the second threshold value may be set according to actual needs without limitation. For example, the second threshold value may be 1.
[0069] In one example, when a series of behaviors are all normal behaviors, the false alarm identification device incorporates the feature value array of the series of behaviors into the user behavior library.
[0070] It is understandable that, since a series of behaviors are normal behaviors, the false alarm identification device incorporates the feature value array of a series of behaviors into the user behavior library, which can improve the user behavior library to make subsequent identification of false alarms more accurate.
[0071] Based on the above-mentioned S101-S105 methods, the false alarm identification device can obtain the behavior data of a series of behaviors when receiving an alarm signal, and search the characteristic value corresponding to each behavior identifier in the behavior mapping table to generate a characteristic value array of a series of behaviors. Based on the characteristic value array, a target preset series of behaviors that is most relevant to the series of behaviors is determined in the user behavior library, and the target correlation coefficient between the characteristic value array and the target preset characteristic value array is determined. If the target correlation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the alarm signal triggered by the system is a false alarm, and the series of behaviors are all normal behaviors.
[0072] After receiving the alarm signal, the characteristic value array of the series of behaviors of the user that triggered the alarm can be compared with the preset series of behaviors in the user behavior library to determine the target preset series of behaviors that are most relevant to the series of behaviors. Therefore, if the target correlation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, that is, the correlation between the target preset series of behaviors and the series of behaviors is very large, since the target preset series of behaviors are all normal behaviors, the possibility that the series of behaviors are all normal behaviors is high, and thus the alarm signal triggered by the system can be accurately determined to be a false alarm, thereby improving the accuracy and efficiency of detecting abnormal user behaviors and reducing the false alarm rate of early warnings.
[0073] Optional, such as Figure 2 As shown, Figure 2 This is another false alarm identification method of the embodiment of the present invention. The target correlation coefficient is different, and the false alarm identification device can also perform different steps;
[0074] S106: If the target correlation coefficient is less than the first threshold and greater than or equal to the third threshold, the false alarm identification device marks the alarm signal triggered by the system as a suspected false alarm and sends a warning message.
[0075] Among them, the early warning information is used to instruct managers to conduct manual analysis of a series of behaviors.
[0076] In a possible design, the third threshold value can be set according to actual needs without limitation. For example, the third threshold value can be -0.8.
[0077] S107: If the target correlation coefficient is greater than or equal to the fourth threshold and less than the third threshold, the false alarm identification device determines that the alarm signal triggered by the system is a normal alarm and that there is an abnormal behavior in the series of behaviors.
[0078] In a possible design, the fourth threshold value can be set according to actual needs without limitation. For example, the fourth threshold value can be -1.
[0079] In this embodiment, a false alarm identification device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0080] This embodiment provides a false alarm identification device, such as Figure 3 As shown, Figure 3 1 is a structural block diagram of a false alarm identification device according to an embodiment of the present invention; the device comprises:
[0081] The acquisition module 301 is used to acquire behavior data of a series of behaviors when receiving an alarm signal, wherein the behavior data includes a behavior identifier corresponding to each behavior in the series of behaviors, and the alarm signal is triggered when the monitoring system determines that the user's series of behaviors are abnormal as a whole;
[0082] Processing module 302, used to search for a characteristic value corresponding to each behavior identifier in a behavior mapping table, and generate a characteristic value array of a series of behaviors, wherein the behavior mapping table includes at least one corresponding relationship, and each corresponding relationship is a corresponding relationship between a behavior identifier and a characteristic value;
[0083] The processing module 302 is further used to determine, based on the feature value array, a target preset series of behaviors that is most relevant to a series of behaviors in the user behavior library, the target preset series of behaviors having a corresponding relationship with the target preset feature value array, the user behavior library including at least one preset feature value array, each preset feature value array corresponding to a preset series of behaviors, and the preset series of behaviors are all normal behaviors;
[0084] The processing module 302 is further used to determine a target correlation coefficient between the feature value array and the target preset feature value array, where the target correlation coefficient is used to indicate the degree of correlation between a series of behaviors and a target preset series of behaviors;
[0085] The processing module 302 is further configured to determine that the alarm signal triggered by the system is a false alarm and that the series of behaviors are normal behaviors if the target correlation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold.
[0086] In some optional embodiments, the processing module 302 is specifically used to calculate the correlation coefficient between each preset feature value array and the feature value array in the user behavior library based on the feature value array and using the correlation coefficient function expression to obtain at least one correlation coefficient, and the correlation coefficient is used to indicate the degree of difference between each preset feature value array and the feature value array, and the correlation coefficient function expression is determined based on the preset feature values in the preset feature value array, the average value of the preset feature values in the preset feature value array, the feature values in the feature value array, and the average value of the feature values in the feature value array.
[0087] The processing module 302 is specifically used to determine the maximum correlation coefficient among at least one correlation coefficient, and determine the preset eigenvalue array corresponding to the maximum correlation coefficient as the target preset eigenvalue array based on the maximum correlation coefficient and the first corresponding relationship, and the first corresponding relationship is the corresponding relationship between each correlation coefficient and each preset eigenvalue array.
[0088] The processing module 302 is specifically used to determine the preset series of behaviors corresponding to the target preset feature value array as the target preset series of behaviors according to the target preset feature value array and the second corresponding relationship, wherein the second corresponding relationship is the corresponding relationship between each preset feature value array and each preset series of behaviors.
[0089] In some optional implementations, the correlation coefficient function expression is expressed by the following formula:
[0090]
[0091] r represents the correlation coefficient between each preset eigenvalue array and the eigenvalue array; represents the i-th eigenvalue in the preset eigenvalue array; represents the i-th preset eigenvalue in the eigenvalue array; represents the average value of the preset eigenvalues in the preset eigenvalue array, and represents the average value of the eigenvalues in the eigenvalue array.
[0092] In some optional implementations, the processing module 302 is further specifically configured to determine the maximum correlation coefficient as a target correlation coefficient between the eigenvalue array and the target preset eigenvalue array.
[0093] In some optional embodiments, the acquisition module 301 is also used to obtain preset behavior data of at least one preset series of behaviors, and the preset behavior data includes a preset behavior identifier corresponding to each preset behavior in each preset series of behaviors; the processing module 302 is also used to search the preset feature value corresponding to each preset behavior identifier in the behavior mapping table, and generate a preset feature value array for each preset series of behaviors; the processing module 302 is also used to generate a user behavior library based on at least one preset feature value array.
[0094] In some optional embodiments, the processing module 302 is also used to mark the alarm signal triggered by the system as a suspected false alarm if the target correlation coefficient is less than the first threshold and greater than or equal to the third threshold, and send a warning message, which is used to instruct the management personnel to manually analyze a series of behaviors.
[0095] In some optional implementations, the processing module 302 is further configured to determine that the alarm signal triggered by the system is a normal alarm and that abnormal behavior exists in a series of behaviors if the target correlation coefficient is greater than or equal to a fourth threshold and less than a third threshold.
[0096] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.
[0097] The false alarm identification device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.
[0098] The embodiment of the present invention also provides a computer device having the above Figure 3 The false alarm identification device is shown.
[0099] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.
[0100] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware integrated circuit. The hardware integrated circuit may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable logic gate array, a general purpose array logic or any combination thereof.
[0101] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.
[0102] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0103] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
[0104] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.
[0105] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
[0106] Part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes but is not limited to source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.
[0107] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. A method for identifying false alarms, characterized in that: The method comprises: When an alarm signal is received, behavioral data of a series of behaviors is obtained, wherein the behavioral data includes a behavior identifier corresponding to each behavior in the series of behaviors, and the alarm signal is triggered when the monitoring system determines that the series of behaviors of the user as a whole are abnormal; Searching for a feature value corresponding to each behavior identifier in a behavior mapping table to generate a feature value array of the series of behaviors, wherein the behavior mapping table includes at least one corresponding relationship, and each corresponding relationship is a corresponding relationship between a behavior identifier and a feature value; Based on the feature value array, determining a target preset series of behaviors that is most relevant to the series of behaviors in the user behavior library, the target preset series of behaviors having a corresponding relationship with the target preset feature value array, the user behavior library including at least one preset feature value array, each of the preset feature value arrays corresponding to one of the preset series of behaviors, and the preset series of behaviors are all normal behaviors; Determining a target correlation coefficient between the feature value array and the target preset feature value array, the target correlation coefficient being used to indicate a correlation degree between the series of behaviors and the target preset series of behaviors; If the target correlation coefficient is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the alarm signal triggered by the system is a false alarm and the series of behaviors are all normal behaviors.
2. The method according to claim 1, characterized in that The step of determining a series of target preset behaviors that are most relevant to the series of behaviors in the user behavior library based on the feature value array includes: Based on the feature value array, using a correlation coefficient function expression, calculating the correlation coefficient between each of the preset feature value arrays in the user behavior library and the feature value array, to obtain at least one correlation coefficient, wherein the correlation coefficient is used to indicate the degree of difference between each of the preset feature value arrays and the feature value array, and the correlation coefficient function expression is determined based on the preset feature values in the preset feature value array, the average value of the preset feature values in the preset feature value array, the feature values in the feature value array, and the average value of the feature values in the feature value array; Determining a maximum correlation coefficient among the at least one correlation coefficient, and determining a preset eigenvalue array corresponding to the maximum correlation coefficient as the target preset eigenvalue array according to the maximum correlation coefficient and a first corresponding relationship, wherein the first corresponding relationship is a corresponding relationship between each of the correlation coefficients and each of the preset eigenvalue arrays; According to the target preset characteristic value array and the second corresponding relationship, the preset series of behaviors corresponding to the target preset characteristic value array is determined as the target preset series of behaviors, and the second corresponding relationship is the corresponding relationship between each of the preset characteristic value arrays and each of the preset series of behaviors.
3. The method according to claim 2, characterized in that The correlation coefficient function expression is expressed by the following formula: r represents the correlation coefficient between each of the preset eigenvalue arrays and the eigenvalue array; X i represents the i-th preset eigenvalue in the preset eigenvalue array; Y i represents the i-th eigenvalue in the eigenvalue array; represents the average value of the preset eigenvalues in the preset eigenvalue array, Represents the average of the eigenvalues in the eigenvalue array.
4. The method according to claim 3, characterized in that The determining of the target correlation coefficient between the eigenvalue array and the target preset eigenvalue array includes: The maximum correlation coefficient is determined as the target correlation coefficient between the eigenvalue array and the target preset eigenvalue array.
5. The method according to claim 1, characterized in that: The method further comprises: Acquire preset behavior data of at least one of the preset series of behaviors, wherein the preset behavior data includes a preset behavior identifier corresponding to each preset behavior in each of the preset series of behaviors; Searching the preset characteristic value corresponding to each preset behavior identifier in the behavior mapping table, and generating a preset characteristic value array for each preset series of behaviors; The user behavior library is generated based on at least one of the preset feature value arrays.
6. The method according to claim 1, characterized in that The method further comprises: If the target correlation coefficient is less than the first threshold and greater than or equal to the third threshold, the alarm signal triggered by the system is marked as a suspected false alarm, and an early warning message is sent, wherein the early warning message is used to instruct the management personnel to manually analyze the series of behaviors.
7. The method according to claim 6, characterized in that The method further comprises: If the target correlation coefficient is greater than or equal to the fourth threshold and less than the third threshold, it is determined that the alarm signal triggered by the system is a normal alarm and that abnormal behavior exists in the series of behaviors.
8. A false alarm identification device, characterized in that: The device comprises: an acquisition module, configured to acquire behavior data of a series of behaviors when receiving an alarm signal, wherein the behavior data includes a behavior identifier corresponding to each behavior in the series of behaviors, and the alarm signal is triggered when the monitoring system determines that the series of behaviors of the user are abnormal as a whole; A processing module, used for searching a characteristic value corresponding to each behavior identifier in a behavior mapping table to generate a characteristic value array of the series of behaviors, wherein the behavior mapping table includes at least one corresponding relationship, and each corresponding relationship is a corresponding relationship between a behavior identifier and a characteristic value; The processing module is further used to determine, based on the feature value array, a target preset series of behaviors that is most relevant to the series of behaviors in the user behavior library, the target preset series of behaviors having a corresponding relationship with the target preset feature value array, the user behavior library including at least one preset feature value array, each of the preset feature value arrays corresponding to one of the preset series of behaviors, and the preset series of behaviors are all normal behaviors; The processing module is further used to determine a target correlation coefficient between the feature value array and the target preset feature value array, wherein the target correlation coefficient is used to indicate a correlation degree between the series of behaviors and the target preset series of behaviors; The processing module is further configured to determine that the alarm signal triggered by the system is a false alarm and that the series of behaviors are all normal behaviors if the target correlation coefficient is greater than or equal to a first threshold and less than or equal to a second threshold.
9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the false alarm identification method according to any one of claims 1 to 7 by executing the computer instructions.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the false alarm identification method according to any one of claims 1 to 7.
