Network detection demand processing method and device, storage medium and electronic device

By performing cluster analysis and feature comparison of the detection traffic log data, multi-dimensional evaluation parameters are determined, and target detection results are generated, the problems of low efficiency and poor accuracy of botnet detection in the existing technology are solved, and efficient and accurate abnormal events are achieved Test.

CN118921180APending Publication Date: 2024-11-08CHINA UNICOM DIGITAL TECNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410763454.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-13
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing botnet detection methods have problems such as low detection efficiency, poor accuracy, low timeliness and high false alarm rate, and have failed to effectively solve network security threats.

Method used

By obtaining the traffic log data to be detected corresponding to the preset network detection requirements, performing cluster analysis and feature comparison, determining multi-dimensional evaluation parameters, and generating object detection results to determine whether abnormal events have occurred in the computer network.

Benefits of technology

It improves the efficiency and accuracy of network detection, reduces the false alarm rate, realizes efficient detection of botnets, and enhances network security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921180A_ABST
    Figure CN118921180A_ABST
Patent Text Reader

Abstract

The invention discloses a network detection demand processing method and device, a storage medium and an electronic device. The method comprises the following steps: acquiring to-be-detected traffic log data corresponding to a preset network detection demand; performing clustering analysis on the to-be-detected traffic log data to obtain a first analysis result, and performing feature comparison analysis on the to-be-detected traffic log data and a preset rule base to obtain a second analysis result; determining a multi-dimensional evaluation parameter according to the first analysis result and the second analysis result; and generating a target detection result based on the to-be-detected traffic log data and the multi-dimensional evaluation parameters. According to the invention, the technical problems of low detection efficiency and poor accuracy of a network detection mode in related technologies are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer network technology, and in particular to a network detection demand processing method, device, storage medium and electronic device. Background Art

[0002] A botnet is a network consisting of a large number of computers infected with malware. Infected computers can be remotely controlled and used to conduct malicious activities, such as distributed denial of service attacks and spam, which pose a serious threat to network security. By detecting botnets, timely measures can be taken to remove infected computers, prevent them from causing damage to the network, and ensure network security. At the same time, detecting botnets also helps to gain a deeper understanding of the spread and behavioral characteristics of malware, so as to better develop network security protection and countermeasures. Botnet detection methods in related technologies mainly rely on key node identification, small sample analysis, etc. However, these detection methods are prone to problems such as low accuracy, low timeliness, low stability, and high false alarm rates.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] At least some embodiments of the present disclosure provide a network detection demand processing method, device, storage medium and electronic device to at least solve the technical problems of low detection efficiency and poor accuracy existing in the network detection method in the related art.

[0005] According to one embodiment of the present disclosure, a network detection demand processing method is provided, including: obtaining traffic log data to be detected corresponding to a preset network detection demand, wherein the preset network detection demand is used to set a detection demand for whether an abnormal event occurs in a computer network built within a target area, and the traffic log data to be detected is traffic log data collected from the computer network; performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result; determining a multidimensional evaluation parameter based on the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result is consistent with the second analysis result from multiple detection dimensions; generating a target detection result based on the traffic log data to be detected and the multidimensional evaluation parameter, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0006] According to one embodiment of the present disclosure, there is also provided a network detection demand processing device, including: an acquisition module, used to acquire traffic log data to be detected corresponding to a preset network detection demand, wherein the preset network detection demand is used to set the detection demand of whether an abnormal event occurs in a computer network constructed within a target area, and the traffic log data to be detected is traffic log data collected from the computer network; an analysis module, used to perform cluster analysis on the traffic log data to be detected to obtain a first analysis result, and perform feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result; a determination module, used to determine a multidimensional evaluation parameter based on the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result is consistent with the second analysis result from multiple detection dimensions; a processing module, used to generate a target detection result based on the traffic log data to be detected and the multidimensional evaluation parameter, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0007] According to one embodiment of the present disclosure, a computer-readable storage medium is further provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned network detection demand processing method in each embodiment of the present disclosure when running.

[0008] According to one embodiment of the present disclosure, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the above-mentioned network detection demand processing method in each embodiment of the present disclosure.

[0009] According to another aspect of an embodiment of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the network detection requirement processing method in each embodiment of the present disclosure is implemented.

[0010] According to another aspect of an embodiment of the present disclosure, a computer program product is also provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned network detection demand processing method in each embodiment of the present disclosure is implemented.

[0011] According to another aspect of the embodiments of the present disclosure, a computer program is also provided. When the computer program is executed by a processor, the network detection requirement processing method described above in each embodiment of the present disclosure is implemented.

[0012] In at least some embodiments of the present disclosure, by obtaining the traffic log data to be detected corresponding to the preset network detection requirements, and then performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result, then determining multidimensional evaluation parameters based on the first analysis result and the second analysis result, and finally generating a target detection result based on the traffic log data to be detected and the multidimensional evaluation parameters, the purpose of efficiently detecting abnormal events in computer networks is achieved, thereby achieving the technical effect of improving network detection efficiency and accuracy, and thus solving the technical problems of low detection efficiency and poor accuracy existing in the network detection method in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0014] Figure 1 It is a hardware structure block diagram of a mobile terminal of a network detection requirement processing method according to one embodiment of the present disclosure;

[0015] Figure 2 is a flow chart of a method for processing network detection requirements according to one embodiment of the present disclosure;

[0016] Figure 3 is a schematic diagram of a storage model of a multi-dimensional evaluation parameter according to one embodiment of the present disclosure;

[0017] Figure 4 is a schematic diagram of a data format of traffic log data to be detected according to an embodiment of the present disclosure;

[0018] Figure 5 is a schematic diagram of a network detection requirement processing method according to one embodiment of the present disclosure;

[0019] Figure 6 is a structural block diagram of a network detection demand processing device according to one embodiment of the present disclosure;

[0020] Figure 7 is a schematic diagram of an electronic device according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0023] The above method embodiments involved in the present disclosure can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, the mobile terminal can be a smart phone, a tablet computer, a handheld computer, a mobile Internet device, a PAD, a game console and other terminal devices. Figure 1 1 is a hardware structure block diagram of a mobile terminal of a network detection requirement processing method according to an embodiment of the present disclosure. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 The processor 102 (only one is shown) may include, but is not limited to, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microprocessor (MCU), a field-programmable logic device (FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, etc.) and a memory 104 for storing data. In one embodiment of the present disclosure, it may also include: an input / output device 108 and a display device 110.

[0024] In some optional embodiments, the above-mentioned device can also provide a human-computer interaction interface with a touch-sensitive surface, which can sense finger contact and / or gestures to perform human-computer interaction with a graphical user interface (GUI). The human-computer interaction function may include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interface, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above-mentioned human-computer interaction functions are configured / stored in a computer program product executable by one or more processors or a readable storage medium.

[0025] Those skilled in the art will understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0026] According to one embodiment of the present disclosure, an embodiment of a network detection demand processing method 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 the 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.

[0027] Figure 2 is a flow chart of a method for processing network detection requirements according to one embodiment of the present disclosure, such as Figure 2 As shown, the method comprises the following steps:

[0028] Step S21, obtaining the traffic log data to be detected corresponding to the preset network detection requirement, wherein the preset network detection requirement is used to set the detection requirement of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network;

[0029] Step S22, performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result;

[0030] Step S23, determining a multi-dimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multi-dimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions;

[0031] Step S24, generating a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0032] The above-mentioned preset network detection requirements may be botnet detection requirements, which may be used to set detection requirements for whether botnet incidents occur in computer networks built within the target area. For example, detection requirements may be set for whether botnet incidents occur in computer networks built within District A of City A. Botnet detection requirements may be reported to the botnet detection platform through Internet access or proxy access to monitor and analyze malware and botnets. When accessing through the Internet, users may directly upload traffic log data to be detected to the botnet detection platform so that the platform can analyze and detect the data. When accessing through a proxy, users may forward traffic log data to be detected to the botnet detection platform through a proxy server to ensure the security of data transmission.

[0033] Optionally, the sparse matrix storage model in Formula 1 is used to store the preset network detection requirements:

[0034]

[0035] Wherein, each element in the matrix shown in Formula 1 represents a different preset network detection requirement.

[0036] The above-mentioned traffic log data to be detected is the traffic log data collected from the computer network, specifically including but not limited to the traffic log data monitored by the network traffic analysis tool (Netflow) or the domain name system (Domain Name System, DNS) traffic log data. By analyzing the traffic log data, we can understand the usage of network traffic, the source and destination of traffic, possible security issues, etc.

[0037] Exemplarily, the collected relevant traffic log data to be detected is sent to the Netflow and DNS traffic preprocessors through the Netflow and DNS traffic collectors, and analyzed and detected by the botnet detection platform. Information distributed collection can be realized through the data collection interface with big data aggregation capability, and the collected traffic log data to be detected is filtered, merged, standardized, deduplicated and other preprocessing operations. The data collection and analysis sources in the disclosed embodiments include but are not limited to: network-wide security data collection and abnormal traffic monitoring systems on the network side, distributed denial of service attacks (Distributed Denial of Service, DDoS), zombie Trojan worm detection systems, and deep packet inspection (Deep Packet Inspection, DPI) equipment. The data collection and analysis objects include but are not limited to: Netflow traffic, DPI data, DDoS attacks, cross-domain attack events and other network attack data, network topology data, Internet Protocol (Internet Protocoladdress, IP) address library and other information.

[0038] Furthermore, cluster analysis is performed on the traffic log data to be detected to obtain a first analysis result, and feature comparison analysis is performed on the traffic log data to be detected and a preset rule library to obtain a second analysis result. Specifically, a botnet feature cluster analysis is performed on the traffic log data to be detected through a multi-layer convolutional neural network model to obtain the first analysis result; feature comparison analysis is performed on the traffic log data to be detected and a feature and behavior rule library to obtain a second analysis result.

[0039] Next, a multi-dimensional evaluation parameter is determined based on the first analysis result and the second analysis result. The multi-dimensional evaluation parameter can evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions. For example, the multi-dimensional evaluation parameter may include but is not limited to: detection accuracy Detection false positive rate Detection timeliness Figure 3 is a schematic diagram of a storage model of a multi-dimensional evaluation parameter according to one embodiment of the present disclosure, such as Figure 3 As shown, a three-dimensional storage area is used to store the detection accuracy, detection timeliness, and detection false alarm rate. The detection accuracy, detection timeliness, and detection false alarm rate generated by each iteration need to be stored in Figure 3 In the three-dimensional space shown.

[0040] Based on the traffic log data to be detected and the multi-dimensional evaluation parameters, the target detection results are generated. After the target detection results are fed back to the demander, the target detection results can be used to determine whether a botnet incident occurs in the computer network.

[0041] Based on the above steps S21 to S24, by obtaining the traffic log data to be detected corresponding to the preset network detection requirements, and then performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and the preset rule library to obtain a second analysis result, then determining multidimensional evaluation parameters based on the first analysis result and the second analysis result, and finally generating target detection results based on the traffic log data to be detected and the multidimensional evaluation parameters, the purpose of efficiently detecting abnormal events in computer networks is achieved, thereby realizing the technical effect of improving network detection efficiency and accuracy, and thus solving the technical problems of low detection efficiency and poor accuracy existing in the network detection method in the related technology.

[0042] The following is a further introduction to the network detection requirement processing method in the embodiment of the present disclosure.

[0043] Optionally, in step S22, cluster analysis is performed on the traffic log data to be detected, and the first analysis result obtained includes:

[0044] Step S221, extracting multiple fields from the traffic log data to be detected;

[0045] Step S222: Perform network feature clustering analysis on the field data of multiple fields to obtain a first analysis result.

[0046] Specifically, Figure 4 is a schematic diagram of a data format of traffic log data to be detected according to an embodiment of the present disclosure, such as Figure 4 As shown, the traffic log data to be detected includes: access start time, access end time, duration, protocol type, source address, source port, destination address, destination port, Transmission Control Protocol (TCP) flag, service type, number of incoming packets, number of incoming bytes, number of packets per second, number of bits per second, number of bytes per packet, network flow (Flow number), next hop IP address, router IP address, inbound interface, outbound interface, source end mask, destination end mask, enterprise unique identification code, etc. Extracting multiple fields from the traffic log data to be detected may specifically include: source IP address, destination IP address, destination port, source port, duration, number of bits per second, and then performing network feature clustering analysis on the field data of the multiple fields, and autonomously learning the botnet features through a multi-layer convolutional neural network model to obtain a first analysis result.

[0047] Botnets are characterized by having one or more control nodes, also known as command and control servers, which are used to remotely control infected computers. Infected computers can be remotely controlled to perform various malicious activities. Botnets can launch DDoS attacks, spread malware, steal information, and other malicious activities, and they are somewhat concealed and periodic.

[0048] Specifically, when performing network feature clustering analysis on field data of multiple fields, before the first iteration occurs, the input of the multi-layer convolutional neural network model is the botnet detection requirements and real-time Netflow and DNS traffic data. in, Include Figure 4 After the first iteration, the input of the multi-layer convolutional neural network model is Netflow, DNS traffic data, and the detection accuracy of the kth iteration. Detection false positive rate Detection timeliness wait.

[0049] Based on the above optional embodiments, multiple fields are extracted from the traffic log data to be detected, and then network feature clustering analysis is performed on the field data of the multiple fields to obtain a first analysis result. By performing clustering analysis on the multiple fields extracted from the traffic log data to be detected, it can help identify and analyze relevant features in the network traffic, and then discover abnormal behaviors and potential threats in the network, thereby further improving the detection efficiency of network detection.

[0050] Optionally, the multiple fields include: source Internet Protocol address, destination Internet Protocol address, source port, destination port, duration and bits per second. In step S222, network feature clustering analysis is performed on field data of the multiple fields, and the first analysis result includes:

[0051] Step S2221, composing the field data of the source Internet Protocol address, the field data of the destination Internet Protocol address, the field data of the source port, the field data of the target port, the field data of the duration, and the field data of the bits per second into a cluster analysis six-tuple;

[0052] Step S2222, using a multi-layer convolutional neural network model to perform network feature clustering analysis on the cluster analysis six-tuple to obtain a first analysis result.

[0053] Specifically, the source IP address in each real-time Netflow and DNS traffic data Destination IP address Destination Port Source Port Duration Bits per second Six fields of data form a cluster analysis six-tuple Then, a multi-layer convolutional neural network model is used to perform network feature cluster analysis on the cluster analysis six-tuple to obtain the first analysis result, and then determine whether a botnet event occurs in the computer network. The convolution function calculation process involved in the cluster analysis process is shown in Formula 2:

[0054]

[0055]

[0056] Among them, i, j, and t are Figure 3 The three-dimensional coordinates in the three-dimensional storage space shown are as follows, k is the number of iterations, x and w represent different convolution functions, and y is an approximately infinite value.

[0057] Based on the above optional embodiment, the field data of the source Internet Protocol address, the field data of the destination Internet Protocol address, the field data of the source port, the field data of the target port, the field data of the duration and the field data of the bits per second are formed into a cluster analysis six-tuple, and then a multi-layer convolutional neural network model is used to perform network feature clustering analysis on the cluster analysis six-tuple to obtain a first analysis result, thereby achieving effective classification and analysis of network traffic data, thereby improving the detection efficiency of network detection.

[0058] Optionally, in step S22, feature comparison analysis is performed on the traffic log data to be detected and a preset rule base, and a second analysis result is obtained, including:

[0059] Step S223, according to the feature length of a single feature to be compared in the preset rule base, the traffic log data to be detected is decomposed into a data byte stream to obtain multiple data attribute byte streams;

[0060] Step S224, performing feature comparison analysis on the multiple data attribute byte streams and the multiple features to be compared to obtain a second analysis result.

[0061] The above-mentioned features to be compared are associated word substrings. According to the feature length of a single feature to be compared in the preset rule library, the data byte stream of the traffic log data to be detected is decomposed to obtain multiple data attribute byte streams. For example, assuming that the feature length of a single feature to be compared in the feature and behavior rule library is 8 bytes, the data byte stream of the traffic log data to be detected is decomposed according to 8 bytes for easy comparison. It should be noted that the feature length of a single feature to be compared can be determined according to demand. The embodiment of the present disclosure only gives an example, but does not constitute a specific limitation.

[0062] Furthermore, the data attribute byte stream to be identified is used as input, the main feature and behavior rule library is queried, and feature comparison analysis is performed on multiple data attribute byte streams and multiple features to be compared to obtain a second analysis result to determine whether the network to which the data attribute byte stream belongs is a botnet.

[0063] Based on the above optional embodiments, the traffic log data to be detected is decomposed into data byte streams according to the feature length of a single feature to be compared in the preset rule base to obtain multiple data attribute byte streams, and then feature comparison analysis is performed on the multiple data attribute byte streams and the multiple features to be compared to obtain a second analysis result, thereby further improving the accuracy and efficiency of network detection.

[0064] Optionally, in step S224, feature comparison analysis is performed on multiple data attribute byte streams and multiple features to be compared, and the second analysis result obtained includes:

[0065] Step S2241, performing feature comparison analysis on multiple data attribute byte streams and multiple features to be compared one by one;

[0066] Step S2242, in response to determining through feature comparison analysis that the current data attribute byte stream matches any of the multiple features to be compared, stopping rule matching; in response to determining through feature comparison analysis that the current data attribute byte stream does not match any of the multiple features to be compared, continuing to perform feature comparison analysis on the next data attribute byte stream adjacent to the current data attribute byte stream and the multiple features to be compared one by one, until all the comparison and analysis of the multiple data attribute byte streams are completed, and obtaining a second analysis result.

[0067] Specifically, the multiple features to be compared contained in the feature and behavior rule library include: 1) the attacking IP address has a scanning behavior on a company's assets; 2) a group of computers or other terminals infected with malware remotely control the infected computers or other terminals through a control server, and the control server sends instructions to coordinate the behavior of the computers or other terminals; 3) excessive network delay, abnormal traffic size and flow rate, abnormal port traffic, abnormal host behavior, periodic abnormal behavior, and abnormal IP distribution.

[0068] In the feature comparison and analysis process, the data attribute byte stream to be identified is used as input to query the main feature and behavior rule library to determine whether the network to which the data attribute byte stream belongs is a botnet. Specifically, each feature to be compared is sequentially compared with multiple data attribute bytes to be identified from the feature and behavior rule library. If the feature comparison and analysis determines that the current data attribute byte stream matches any of the multiple features to be compared, the rule matching is stopped; if the feature comparison and analysis determines that the current data attribute byte stream does not match any of the multiple features to be compared, the feature comparison and analysis of the next data attribute byte stream adjacent to the current data attribute byte stream is continued with the multiple features to be compared one by one, until all the multiple data attribute byte streams are compared and analyzed, and the second analysis result is obtained.

[0069] For example, the associated word substring R[M], where M is the sequence identifier of the feature and behavior rule, and the data attribute byte stream S[U], where U is the sequence identifier of the data attribute byte stream to be determined. If the data attribute byte stream satisfies the conditions of Formula 3 and Formula 4 in the feature comparison analysis, then the data attribute byte stream is determined to be a botnet-type byte stream, otherwise it is a normal byte stream.

[0070]

[0071]

[0072] Based on the above optional embodiments, it is possible to quickly and accurately determine whether the data attribute byte stream matches the feature to be compared. At the same time, by stopping the rule matching, the efficiency of the comparison analysis can be improved, unnecessary calculation time can be reduced, and the network detection efficiency can be further improved.

[0073] Optionally, in step S23, determining the multi-dimensional evaluation parameters according to the first analysis result and the second analysis result includes:

[0074] Step S231, determining whether the first analysis result is consistent with the second analysis result, and obtaining a determination result;

[0075] Step S232, respectively calculating the detection accuracy, detection false alarm rate and detection timeliness of the computer network association according to the determination result to obtain multi-dimensional evaluation parameters.

[0076] Specifically, the first analysis result is obtained through cluster analysis, and the second analysis result is obtained through feature comparison analysis. The two analysis processes can be processed in parallel. Among them, the cluster analysis has a faster judgment speed, and the feature comparison has a higher accuracy. Both cluster analysis and feature comparison can output judgment results about the botnet respectively. The detection accuracy of each iteration can be calculated by checking whether the judgment results of the two are consistent. Detection false positive rate Detection timeliness After multiple iterations, such as 50 iterations, the final iteration result is used as the basis for determining whether a botnet event occurs in the computer network.

[0077] Based on the above optional embodiments, a determination result is obtained by determining whether the first analysis result is consistent with the second analysis result, and then the detection accuracy, detection false alarm rate and detection timeliness associated with the computer network are calculated according to the determination result to obtain multi-dimensional evaluation parameters, which are then used to improve the accuracy of the network detection results.

[0078] Optionally, in step S24, generating a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters includes:

[0079] Step S241, calculating the multidimensional evaluation parameters to be used in the next iteration round based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak values;

[0080] Step S242, repeatedly iterate based on the traffic log data to be detected and the multi-dimensional evaluation parameters to be used until a preset number of iterations is met, and a target detection result is generated.

[0081] The above historical evaluation peaks include the historical minimum botnet detection false alarm rate, the historical maximum botnet detection accuracy, and the historical maximum botnet detection timeliness. The multidimensional evaluation parameters to be used in the k+1th round are calculated based on the multidimensional evaluation parameters obtained in the kth round and the historical evaluation peaks, and repeated iterations are performed based on the traffic log data to be detected and the multidimensional evaluation parameters to be used until the preset number of iterations, such as 50 times, is met, thereby generating the target detection result.

[0082] Based on the above optional embodiment, the multidimensional evaluation parameters to be used in the next iteration round are calculated based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value, and then repeated iterations are performed based on the traffic log data to be detected and the multidimensional evaluation parameters to be used until the preset number of iterations is met, and the target detection result is generated, thereby further improving the accuracy of network detection and retrieval efficiency.

[0083] Optionally, in step S241, the multidimensional evaluation parameters to be used in the next iteration round are calculated based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value, including:

[0084] Step S2411, calculating the target factor based on the multi-dimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value;

[0085] Step S2412, based on the multidimensional evaluation parameters, target factors and preset coefficients obtained in the current iteration round, the multidimensional evaluation parameters to be used in the next iteration round are calculated.

[0086] Specifically, taking the current iteration round as the kth round as an example, the artificial intelligence (AI) supervised deep learning factor corresponding to the kth iteration cycle is calculated based on the multi-dimensional evaluation parameters obtained in the kth round and the historical evaluation peak value as shown in Formula 5:

[0087]

[0088] Among them, C Gmin is the historical minimum false alarm rate of botnet detection, W Gmax is the highest botnet detection accuracy in history, F Gmax Detect timeliness for the largest botnet in history.

[0089] Based on the multidimensional evaluation parameters, target factors and preset coefficients obtained in the kth round, the multidimensional evaluation parameters to be used in the k+1th round are calculated using Formula 6:

[0090]

[0091]

[0092] in, Mainly include: Three aspects of information vector.

[0093] Based on the above optional embodiment, through comprehensive analysis of current and historical evaluation parameters, and calculation of target factors and preset coefficients, accurate prediction and adjustment of multi-dimensional evaluation parameters to be used in the next iteration round are achieved. This method can better guide the work of the next iteration and improve the accuracy and efficiency of network detection.

[0094] Figure 5 is a schematic diagram of a network detection requirement processing method according to one embodiment of the present disclosure, such as Figure 5As shown, the network detection demand processing method can be implemented based on a multi-level AI adaptive botnet detection platform. First, the traffic log data to be detected corresponding to the preset network detection demand is obtained, wherein the preset network detection demand is used to set the detection demand of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network. The preset network detection demand can be reported to the multi-level AI adaptive botnet detection platform through Internet access or proxy access, so as to monitor and analyze malware and botnets. In a multi-level AI adaptive botnet detection platform, cluster analysis is performed on the traffic log data to be detected to obtain a first analysis result, and feature comparison analysis is performed between the traffic log data to be detected and a preset rule library to obtain a second analysis result; multi-dimensional evaluation parameters are determined based on the first analysis result and the second analysis result, wherein the multi-dimensional evaluation parameters are used to evaluate whether the first analysis result is consistent with the second analysis result from multiple detection dimensions; based on the traffic log data to be detected and the multi-dimensional evaluation parameters, a target detection result is generated, wherein the target detection result is used to determine whether an abnormal event occurs in a computer network, thereby enabling analysis based on a multi-level AI adaptive botnet detection algorithm to achieve a detection effect with high accuracy, high timeliness, high stability, and low false alarm rate.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0096] In this embodiment, a network detection demand processing 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.

[0097] Figure 6 is a structural block diagram of a network detection demand processing device according to one embodiment of the present disclosure, such as Figure 6 As shown, the device comprises:

[0098] The acquisition module 601 is used to acquire the traffic log data to be detected corresponding to the preset network detection requirement, wherein the preset network detection requirement is used to set the detection requirement of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network;

[0099] The analysis module 602 is used to perform cluster analysis on the traffic log data to be detected to obtain a first analysis result, and to perform feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result;

[0100] A determination module 603 is used to determine a multi-dimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multi-dimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions;

[0101] The processing module 604 is used to generate a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0102] Optionally, the analysis module 602 is further used to: extract multiple fields from the traffic log data to be detected; perform network feature clustering analysis on the field data of the multiple fields to obtain a first analysis result.

[0103] Optionally, the analysis module 602 is also used to: combine the field data of the source Internet Protocol address, the field data of the destination Internet Protocol address, the field data of the source port, the field data of the target port, the field data of the duration, and the field data of the number of bits per second into a cluster analysis sextuple; and use a multi-layer convolutional neural network model to perform network feature clustering analysis on the cluster analysis sextuple to obtain a first analysis result.

[0104] Optionally, the analysis module 602 is also used to: decompose the data byte stream of the traffic log data to be detected according to the feature length of a single feature to be compared in a preset rule base to obtain multiple data attribute byte streams; perform feature comparison analysis on the multiple data attribute byte streams and the multiple features to be compared to obtain a second analysis result.

[0105] Optionally, the analysis module 602 is also used to: perform feature comparison analysis on multiple data attribute byte streams and multiple features to be compared one by one; in response to the feature comparison analysis determining that the current data attribute byte stream matches any of the multiple features to be compared, stop rule matching; in response to the feature comparison analysis determining that the current data attribute byte stream does not match any of the multiple features to be compared, continue to perform feature comparison analysis on the next data attribute byte stream adjacent to the current data attribute byte stream and the multiple features to be compared one by one, until all the comparison and analysis of the multiple data attribute byte streams are completed, and obtain a second analysis result.

[0106] Optionally, the determination module 603 is also used to: determine whether the first analysis result is consistent with the second analysis result to obtain a determination result; calculate the detection accuracy, detection false alarm rate and detection timeliness of computer network associations according to the determination result to obtain multi-dimensional evaluation parameters.

[0107] Optionally, the processing module 604 is also used to: calculate the multidimensional evaluation parameters to be used in the next iteration round based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value; perform repeated iterations based on the traffic log data to be detected and the multidimensional evaluation parameters to be used until the preset number of iterations is met, and generate a target detection result.

[0108] Optionally, the processing module 604 is also used to: calculate the target factor based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value; calculate the multidimensional evaluation parameters to be used in the next iteration round based on the multidimensional evaluation parameters obtained in the current iteration round, the target factor and the preset coefficient.

[0109] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0110] An embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0111] Optionally, in this embodiment, the above-mentioned computer-readable storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0112] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the mobile terminals in a mobile terminal group.

[0113] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0114] S1, obtaining the traffic log data to be detected corresponding to the preset network detection requirement, wherein the preset network detection requirement is used to set the detection requirement of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network;

[0115] S2, performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result;

[0116] S3, determining a multidimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions;

[0117] S4, generating a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0118] Optionally, the computer-readable storage medium is further configured to store program codes for executing the following steps: extracting multiple fields from the traffic log data to be detected; performing network feature clustering analysis on the field data of the multiple fields to obtain a first analysis result.

[0119] Optionally, the computer-readable storage medium is also configured to store program code for executing the following steps: combining field data of the source Internet Protocol address, field data of the destination Internet Protocol address, field data of the source port, field data of the target port, field data of the duration, and field data of bits per second into a cluster analysis sextuple; performing network feature clustering analysis on the cluster analysis sextuple using a multi-layer convolutional neural network model to obtain a first analysis result.

[0120] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: decomposing the traffic log data to be detected into a data byte stream according to the feature length of a single feature to be compared in a preset rule base to obtain multiple data attribute byte streams; performing feature comparison analysis on the multiple data attribute byte streams and the multiple features to be compared to obtain a second analysis result.

[0121] Optionally, the computer-readable storage medium is further configured to store program codes for executing the following steps: performing feature comparison analysis on multiple data attribute byte streams and multiple features to be compared one by one; in response to determining through feature comparison analysis that the current data attribute byte stream matches any of the multiple features to be compared, stopping rule matching; in response to determining through feature comparison analysis that the current data attribute byte stream does not match any of the multiple features to be compared, continuing to perform feature comparison analysis on the next data attribute byte stream adjacent to the current data attribute byte stream and the multiple features to be compared one by one, until all comparisons and analyses of the multiple data attribute byte streams are completed, thereby obtaining a second analysis result.

[0122] Optionally, the above-mentioned computer-readable storage medium is also configured to store program codes for executing the following steps: determining whether the first analysis result is consistent with the second analysis result to obtain a determination result; and calculating the detection accuracy, detection false alarm rate and detection timeliness associated with the computer network based on the determination result to obtain multi-dimensional evaluation parameters.

[0123] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: obtaining the multidimensional evaluation parameters to be used in the next iteration round based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak values; performing repeated iterations based on the traffic log data to be detected and the multidimensional evaluation parameters to be used until a preset number of iterations is met, thereby generating a target detection result.

[0124] Optionally, the computer-readable storage medium is also configured to store program codes for executing the following steps: calculating a target factor based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value; calculating the multidimensional evaluation parameters to be used in the next iteration round based on the multidimensional evaluation parameters obtained in the current iteration round, the target factor and preset coefficients.

[0125] In the computer-readable storage medium of this embodiment, by obtaining the traffic log data to be detected corresponding to the preset network detection requirements, and then performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule library to obtain a second analysis result, then determining multidimensional evaluation parameters based on the first analysis result and the second analysis result, and finally generating a target detection result based on the traffic log data to be detected and the multidimensional evaluation parameters, the purpose of efficiently detecting abnormal events in computer networks is achieved, thereby realizing the technical effect of improving network detection efficiency and accuracy, and thus solving the technical problems of low detection efficiency and poor accuracy existing in the network detection method in the related technology.

[0126] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0127] In an exemplary embodiment of the present disclosure, a program product capable of implementing the above method of the present embodiment is stored on a computer-readable storage medium. In some possible implementations, various aspects of the embodiments of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of the present embodiment.

[0128] According to the program product for implementing the above method in the embodiment of the present disclosure, it can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the embodiment of the present disclosure is not limited to this. In the embodiment of the present disclosure, the computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0129] The program product may be in any combination of one or more computer-readable media. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive) of computer-readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0130] It should be noted that the program code contained in the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0131] An embodiment of the present disclosure further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0132] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0133] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0134] S1, obtaining the traffic log data to be detected corresponding to the preset network detection requirement, wherein the preset network detection requirement is used to set the detection requirement of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network;

[0135] S2, performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result;

[0136] S3, determining a multidimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions;

[0137] S4, generating a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0138] Optionally, the processor may also be configured to execute the following steps through a computer program: extract multiple fields from the traffic log data to be detected; perform network feature clustering analysis on the field data of the multiple fields to obtain a first analysis result.

[0139] Optionally, the processor can also be configured to perform the following steps through a computer program: combining field data of the source Internet Protocol address, field data of the destination Internet Protocol address, field data of the source port, field data of the target port, field data of the duration, and field data of bits per second into a cluster analysis sextuple; performing network feature cluster analysis on the cluster analysis sextuple using a multi-layer convolutional neural network model to obtain a first analysis result.

[0140] Optionally, the processor can also be configured to perform the following steps through a computer program: decomposing the traffic log data to be detected into a data byte stream according to the feature length of a single feature to be compared in a preset rule base to obtain multiple data attribute byte streams; performing feature comparison analysis on the multiple data attribute byte streams and the multiple features to be compared to obtain a second analysis result.

[0141] Optionally, the processor may also be configured to perform the following steps through a computer program: performing feature comparison analysis on multiple data attribute byte streams and multiple features to be compared one by one; in response to determining through feature comparison analysis that the current data attribute byte stream matches any of the multiple features to be compared, stopping rule matching; in response to determining through feature comparison analysis that the current data attribute byte stream does not match any of the multiple features to be compared, continuing to perform feature comparison analysis on the next data attribute byte stream adjacent to the current data attribute byte stream and the multiple features to be compared one by one, until all comparisons and analyses of the multiple data attribute byte streams are completed, thereby obtaining a second analysis result.

[0142] Optionally, the processor can also be configured to perform the following steps through a computer program: determine whether the first analysis result is consistent with the second analysis result to obtain a determination result; calculate the detection accuracy, detection false alarm rate and detection timeliness of the computer network association according to the determination result to obtain multi-dimensional evaluation parameters.

[0143] Optionally, the processor can also be configured to perform the following steps through a computer program: obtaining the multidimensional evaluation parameters to be used in the next iteration round based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak values; performing repeated iterations based on the traffic log data to be detected and the multidimensional evaluation parameters to be used until the preset number of iterations is met, thereby generating a target detection result.

[0144] Optionally, the processor can also be configured to perform the following steps through a computer program: calculating a target factor based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value; calculating the multidimensional evaluation parameters to be used in the next iteration round based on the multidimensional evaluation parameters, the target factor and the preset coefficients obtained in the current iteration round.

[0145] In the electronic device of this embodiment, by obtaining the traffic log data to be detected corresponding to the preset network detection requirements, and then performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule library to obtain a second analysis result, then determining multidimensional evaluation parameters based on the first analysis result and the second analysis result, and finally generating a target detection result based on the traffic log data to be detected and the multidimensional evaluation parameters, the purpose of efficiently detecting abnormal events in computer networks is achieved, thereby realizing the technical effect of improving network detection efficiency and accuracy, and thus solving the technical problems of low detection efficiency and poor accuracy existing in the network detection method in the related technology.

[0146] Figure 7 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. Figure 7 As shown, the electronic device 700 is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0147] like Figure 7 As shown, the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 may include but are not limited to: at least one processor 710, at least one memory 720, a bus 730 connecting different system components (including the memory 720 and the processor 710), and a display 740.

[0148] The memory 720 stores program codes, which can be executed by the processor 710, so that the processor 710 executes the steps described in the method part of the embodiment of the present disclosure according to various exemplary embodiments of the present disclosure.

[0149] The memory 720 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 7201 and / or a cache memory unit 7202, and may further include a read-only memory unit (ROM) 7203, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0150] In some examples, the memory 720 may also include a program / utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include the implementation of a network environment. The memory 720 may further include a memory remotely disposed relative to the processor 710, and these remote memories may be connected to the electronic device 700 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.

[0151] Bus 730 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a local bus of processor 710, or any of a variety of bus architectures.

[0152] The display 740 may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 700 .

[0153] Optionally, the electronic device 700 may also communicate with one or more external devices 800 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 700, and / or any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 750. Furthermore, the electronic device 700 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 760. Figure 7 As shown, the network adapter 760 communicates with other modules of the electronic device 700 via the bus 730. It should be understood that although Figure 7 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0154] The electronic device 700 may further include: a keyboard, a cursor control device (such as a mouse), an input / output interface (I / O interface), a network interface, a power supply and / or a camera.

[0155] It can be understood by those skilled in the art that Figure 7 The structure shown is for illustration only and does not limit the structure of the above electronic device. Figure 7 More or fewer components as shown, or with Figure 1 The memory 720 may be used to store computer programs and corresponding data, such as the computer programs and corresponding data corresponding to the network detection demand processing method in the embodiment of the present disclosure. The processor 710 executes various functional applications and data processing by running the computer programs stored in the memory 720, that is, implementing the above-mentioned network detection demand processing method.

[0156] The embodiment of the present disclosure further provides a computer program product. Optionally, in this embodiment, the computer program product may include a computer program, and the computer program implements the method provided in the embodiment when executed by a processor.

[0157] Optionally, the computer program included in the above-mentioned computer program product is executed by a processor to perform the following steps:

[0158] S1, obtaining the traffic log data to be detected corresponding to the preset network detection requirement, wherein the preset network detection requirement is used to set the detection requirement of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network;

[0159] S2, performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result;

[0160] S3, determining a multidimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions;

[0161] S4, generating a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0162] The embodiments of the present disclosure also provide a computer program product. Optionally, the computer program product may include a non-volatile computer-readable storage medium, which may be used to store a computer program, and when the computer program is executed by a processor, the method provided in the embodiments is implemented.

[0163] Optionally, the computer program stored in the non-volatile computer-readable storage medium is used by the processor to execute the following steps:

[0164] S1, obtaining the traffic log data to be detected corresponding to the preset network detection requirement, wherein the preset network detection requirement is used to set the detection requirement of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network;

[0165] S2, performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result;

[0166] S3, determining a multidimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions;

[0167] S4, generating a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0168] The embodiment of the present disclosure further provides a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, the method provided in the above embodiment is implemented.

[0169] Optionally, the computer program is executed by a processor to perform the following steps:

[0170] S1, obtaining the traffic log data to be detected corresponding to the preset network detection requirement, wherein the preset network detection requirement is used to set the detection requirement of whether an abnormal event occurs in the computer network built within the target area, and the traffic log data to be detected is the traffic log data collected from the computer network;

[0171] S2, performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result;

[0172] S3, determining a multidimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions;

[0173] S4, generating a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether an abnormal event occurs in the computer network.

[0174] The serial numbers of the above-mentioned embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0175] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0176] In the several embodiments provided in the present disclosure, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0177] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0178] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0179] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0180] The above is only a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present disclosure. These improvements and modifications should also be regarded as the scope of protection of the present disclosure.

Claims

1. A network detection requirement processing method, characterized in that: include: Obtaining traffic log data to be detected corresponding to a preset network detection requirement, wherein the preset network detection requirement is used to set a detection requirement for whether an abnormal event occurs in a computer network built within a target area, and the traffic log data to be detected is traffic log data collected from the computer network; Performing cluster analysis on the traffic log data to be detected to obtain a first analysis result, and performing feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result; Determining a multidimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions; Based on the traffic log data to be detected and the multi-dimensional evaluation parameters, a target detection result is generated, wherein the target detection result is used to determine whether the abnormal event occurs in the computer network.

2. The network detection requirement processing method according to claim 1, characterized in that: The first analysis result obtained by clustering the traffic log data to be detected includes: Extracting multiple fields from the traffic log data to be detected; Performing network feature clustering analysis on the field data of the multiple fields to obtain the first analysis result.

3. The network detection demand processing method according to claim 2, characterized in that: The multiple fields include: source Internet Protocol address, destination Internet Protocol address, source port, destination port, duration and bits per second. Network feature clustering analysis is performed on field data of the multiple fields to obtain the first analysis result including: Combining the field data of the source Internet Protocol address, the field data of the destination Internet Protocol address, the field data of the source port, the field data of the target port, the field data of the duration, and the field data of the bits per second into a cluster analysis six-tuple; A multi-layer convolutional neural network model is used to perform network feature clustering analysis on the cluster analysis six-tuple to obtain the first analysis result.

4. The network detection requirement processing method according to claim 1, characterized in that: Performing feature comparison analysis on the traffic log data to be detected and the preset rule base to obtain the second analysis result includes: Decomposing the traffic log data to be detected into a data byte stream according to the feature length of a single feature to be compared in the preset rule base to obtain a plurality of data attribute byte streams; Perform feature comparison analysis on the multiple data attribute byte streams and the multiple features to be compared to obtain the second analysis result.

5. The network detection requirement processing method according to claim 4, characterized in that: Performing feature comparison analysis on the multiple data attribute byte streams and the multiple features to be compared, and obtaining the second analysis result includes: Perform feature comparison analysis on the multiple data attribute byte streams and the multiple features to be compared one by one; In response to determining through feature comparison analysis that the current data attribute byte stream matches any of the multiple features to be compared, stopping rule matching; in response to determining through feature comparison analysis that the current data attribute byte stream does not match any of the multiple features to be compared, continuing to perform feature comparison analysis on the next data attribute byte stream adjacent to the current data attribute byte stream and the multiple features to be compared one by one until all the multiple data attribute byte streams are compared and analyzed, thereby obtaining the second analysis result.

6. The network detection requirement processing method according to claim 1, characterized in that: Determining the multidimensional evaluation parameter according to the first analysis result and the second analysis result includes: Determine whether the first analysis result is consistent with the second analysis result, and obtain a determination result; The detection accuracy, detection false alarm rate and detection timeliness of the computer network association are calculated respectively according to the determination results to obtain the multi-dimensional evaluation parameters.

7. The network detection requirement processing method according to claim 1, characterized in that: Generating the target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters includes: The multidimensional evaluation parameters to be used in the next iteration round are calculated based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak values; Repeated iteration is performed based on the traffic log data to be detected and the multi-dimensional evaluation parameters to be used until a preset number of iterations is met to generate the target detection result.

8. The network detection demand processing method according to claim 7, characterized in that: The multidimensional evaluation parameters to be used in the next iteration round are calculated based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value, including: Calculate the target factor based on the multidimensional evaluation parameters obtained in the current iteration round and the historical evaluation peak value; The multidimensional evaluation parameters to be used in the next iteration round are calculated based on the multidimensional evaluation parameters obtained in the current iteration round, the target factor and the preset coefficient.

9. A network detection demand processing device, characterized in that: include: An acquisition module, used to acquire traffic log data to be detected corresponding to a preset network detection requirement, wherein the preset network detection requirement is used to set a detection requirement for whether an abnormal event occurs in a computer network built within a target area, and the traffic log data to be detected is traffic log data collected from the computer network; An analysis module, configured to perform cluster analysis on the traffic log data to be detected to obtain a first analysis result, and to perform feature comparison analysis on the traffic log data to be detected and a preset rule base to obtain a second analysis result; a determination module, configured to determine a multidimensional evaluation parameter according to the first analysis result and the second analysis result, wherein the multidimensional evaluation parameter is used to evaluate whether the first analysis result and the second analysis result are consistent from multiple detection dimensions; A processing module is used to generate a target detection result based on the traffic log data to be detected and the multi-dimensional evaluation parameters, wherein the target detection result is used to determine whether the abnormal event occurs in the computer network.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the network detection requirement processing method described in any one of claims 1 to 8 when executed by a processor.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the network detection requirement processing method described in any one of claims 1 to 8.

12. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the network detection demand processing method described in any one of claims 1 to 8.