A network fault location method, system, storage medium and electronic device

Abstract

This application discloses a network fault location method, system, storage medium, and electronic device. It uses a network traffic model to monitor network devices and obtain monitoring results. If the monitoring result indicates an abnormal state, the network fault characteristics corresponding to that result are determined. A preset probability algorithm is used to estimate the probability of the network fault characteristics and preset network fault features, resulting in a network fault with a preset probability. Based on the fault node location information, the network fault location result of the network device is determined. Based on the above, the acquired abnormal network traffic data is used as a machine learning sample feature set to construct a network traffic model. This model is used to perform real-time network status judgment and monitoring of network devices, improving the efficiency and accuracy of network fault detection. Furthermore, the network fault location results assist maintenance personnel in quickly and accurately locating and maintaining network faults, ensuring the long-term stable operation of the network.

Description

Technical Field

[0001] The present application relates to the technical field of network fault processing, and more specifically, to a network fault locating method, system, storage medium and electronic device. Background Art

[0002] Network failure refers to the state where the network cannot provide normal services or the service quality is reduced due to hardware problems, software vulnerabilities, virus intrusion, etc. In order to solve the network failure, it is necessary to locate the network failure.

[0003] Most of the existing network fault location methods use active detection, that is, setting up detectors at each node to analyze network faults and obtain faulty node information. This method requires the deployment of a large number of detection devices. Deploying a large number of detection devices will bring additional configuration overhead and traffic load to the network, thereby reducing the accuracy of network fault location.

[0004] Therefore, the accuracy of existing network fault location methods is low. Summary of the invention

[0005] In view of this, the present application discloses a network fault location method, system, storage medium and electronic device, aiming to improve the detection efficiency and accuracy of network faults. In addition, the network fault location results are used to assist maintenance personnel in quickly and accurately locating and maintaining network faults, thereby ensuring the long-term stable operation of the network.

[0006] In order to achieve the above purpose, the disclosed technical solution is as follows:

[0007] The first aspect of the present application discloses a network fault location method, the method comprising:

[0008] Performing fault monitoring on the network device to be processed by using a pre-built network traffic model to obtain a monitoring result; the monitoring result is used to indicate the network status of the network device to be processed;

[0009] If the monitoring result is a monitoring result in an abnormal state, determining a network fault feature corresponding to the monitoring result in the abnormal state;

[0010] By using a preset probability algorithm, the network fault feature and the preset network fault feature in the pre-built network fault event database are probability estimated to obtain a network fault with a preset probability; the preset probability is used to represent the maximum probability in the network fault event database;

[0011] Based on the fault node position information of the network fault with the preset probability, a network fault locating result of the network device is determined.

[0012] Preferably, the performing fault monitoring on the network device to be processed by using the pre-built network traffic model to obtain the monitoring result includes:

[0013] Matching device events of the network devices to be processed through preset fault events in the pre-built network traffic model;

[0014] If the preset fault event matches the device event of the network device to be processed, determining that the monitoring result is a monitoring result in an abnormal state;

[0015] If the preset fault event does not match the device event of the network device to be processed, the monitoring result is determined to be a monitoring result in a normal state.

[0016] Preferably, the determining of the network fault location result of the network device based on the fault node location information of the network fault with a preset probability includes:

[0017] Determine the fault node location information of the network fault of the preset probability in the network fault event database;

[0018] Based on the fault node location information, a network fault locating result of the network device is determined.

[0019] Preferably, the process of building a network traffic model includes:

[0020] Performing data flow monitoring on the network device to be processed to obtain network flow information corresponding to the network device to be processed;

[0021] De-noising the network traffic information by using a de-noising algorithm to obtain de-noised network traffic information;

[0022] Extracting abnormal network traffic information from the denoised network traffic information;

[0023] A network traffic model is constructed based on the abnormal network traffic information.

[0024] Preferably, the process of building a network fault event database includes:

[0025] A network fault event database is constructed by presetting the fault characteristics of the faulty nodes.

[0026] A second aspect of the present application discloses a network fault location system, the system comprising:

[0027] A monitoring unit, used to perform fault monitoring on the network device to be processed by using a pre-built network traffic model to obtain a monitoring result; the monitoring result is used to indicate the network status of the network device to be processed;

[0028] A first determining unit, configured to determine, if the monitoring result is a monitoring result in an abnormal state, a network fault feature corresponding to the monitoring result in the abnormal state;

[0029] An estimation unit, configured to perform probability estimation on the network fault feature and a preset network fault feature in a pre-built network fault event database by using a preset probability algorithm to obtain a network fault with a preset probability; the preset probability is used to represent the maximum probability in the network fault event database;

[0030] The second determining unit is used to determine the network fault locating result of the network device based on the fault node location information of the network fault with the preset probability.

[0031] Preferably, the monitoring unit further includes:

[0032] A matching module, used for matching device events of the network device to be processed with preset fault events in a pre-built network traffic model;

[0033] A first determination module, configured to determine that the monitoring result is a monitoring result in an abnormal state if the preset fault event matches the device event of the network device to be processed;

[0034] The second determination module is used to determine that the monitoring result is a monitoring result in a normal state if the preset fault event does not match the device event of the network device to be processed.

[0035] Preferably, the second determining unit includes:

[0036] A third determination module is used to determine the fault node location information of the network fault with a preset probability in the network fault event database;

[0037] The fourth determination module is used to determine the network fault location result of the network device based on the fault node location information.

[0038] A third aspect of the present application discloses a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the network fault locating method as described in any one of the first aspects.

[0039] The fourth aspect of the present application discloses an electronic device, comprising a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the network fault locating method as described in any one of the first aspects.

[0040] Through the above technical scheme, it can be known that the present application discloses a network fault location method, system, storage medium and electronic device, which monitors the network equipment to be processed through a pre-constructed network traffic model to obtain a monitoring result, which is used to indicate the network status of the network equipment to be processed. If the monitoring result is a monitoring result in an abnormal state, the network fault feature corresponding to the monitoring result in the abnormal state is determined, and the network fault feature and the preset network fault feature in the pre-constructed network fault event database are estimated by a preset probability algorithm to obtain a network fault with a preset probability; the preset probability is used to characterize the maximum probability in the network fault event database, and the network fault location result of the network equipment is determined based on the fault node location information of the network fault with the preset probability. Based on the above, the obtained abnormal network traffic data is used as a machine learning sample feature set to construct a network traffic model, and the network equipment is judged and monitored in real time through the network traffic model, which is conducive to improving the detection efficiency and accuracy of network faults. In addition, the network fault location result assists maintenance personnel in quickly and accurately locating and maintaining network faults to ensure the long-term stable operation of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 A flowchart of a network fault location method disclosed in an embodiment of the present application;

[0043] Figure 2 A schematic diagram of a process of performing fault monitoring on a network device to be processed by using a pre-built network traffic model and obtaining a monitoring result according to an embodiment of the present application;

[0044] Figure 3 A schematic diagram of a process for determining a network fault location result of a network device disclosed in an embodiment of the present application;

[0045] Figure 4 A schematic diagram of the structure of a network fault location system disclosed in an embodiment of the present application;

[0046] Figure 5 A schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0049] As can be seen from the background technology, the accuracy of existing network fault location methods is low.

[0050] In order to solve the above problems, the embodiments of the present application disclose a network fault location method, system, storage medium and electronic device, which constructs a network traffic model by using the acquired abnormal network traffic data as a machine learning sample feature set, and performs real-time network status judgment and monitoring of network devices through the network traffic model, which is conducive to improving the detection efficiency and accuracy of network faults. In addition, it can assist maintenance personnel to quickly and accurately locate and maintain network faults, and ensure the long-term stable operation of the network. The specific implementation method is illustrated by the following embodiments.

[0051] refer to Figure 1 FIG. 1 is a flow chart of a network fault location method disclosed in an embodiment of the present application. The network fault location method mainly includes the following steps:

[0052] S101: Perform fault monitoring on the network device to be processed through a pre-built network traffic model to obtain a monitoring result; the monitoring result is used to indicate the network status of the network device to be processed. If the monitoring result is a monitoring result in an abnormal state, execute S102; if the monitoring result is a monitoring result in a normal state, execute S105.

[0053] In S101, the network devices include hubs, switches, bridges, routers, gateways and other devices.

[0054] The construction process of the network traffic model is as follows:

[0055] First, data traffic of the network device to be processed is monitored to obtain network traffic information corresponding to the network device to be processed.

[0056] The network management system monitors the data flow of the network device to be processed, and obtains the network flow information of the network device when running the application in real time.

[0057] Data that conforms to the network traffic model is a normal data packet. By filtering out normal data packets, abnormal network traffic information can be obtained.

[0058] For example, fault monitoring is performed on the network devices in the entire network traffic model. For example, among the 10 network devices in the network traffic model, the monitoring results of the first 9 devices are normal (i.e., the monitoring results are in a normal state), and the monitoring result of the tenth device is abnormal (i.e., the monitoring result is in an abnormal state). The monitoring result in an abnormal state may be an abnormal fault such as packet loss fault, no network response fault, delay fault, distortion fault, or the like.

[0059] Secondly, the network traffic information is denoised using a denoising algorithm to obtain denoised network traffic information.

[0060] Among them, the network traffic information is denoised by a denoising algorithm to improve the accuracy of the network traffic information.

[0061] The denoising algorithm can be a wavelet transform, which can be replaced by a neighborhood averaging method, a median filter, a low-pass filter, etc. The specific denoising algorithm is determined by the technicians according to the actual situation, and this application does not make any specific limitations.

[0062] Then, the abnormal network traffic information is extracted from the denoised network traffic information.

[0063] Among them, abnormal network traffic information includes abnormal traffic information caused by network viruses and abnormal traffic information caused by faults.

[0064] Finally, a network traffic model is constructed based on abnormal network traffic information.

[0065] Among them, the abnormal network traffic data is obtained as a machine learning sample feature set to build a network traffic model.

[0066] Using network traffic models to conduct real-time network status judgment and monitoring can help improve the efficiency and accuracy of network fault detection, and lay the foundation for subsequent network fault location.

[0067] Specifically, the process of performing fault monitoring on the network device to be processed by using the pre-built network traffic model and obtaining the monitoring result is shown in A1-A3.

[0068] A1: Match the device events of the network devices to be processed through the preset fault events in the pre-built network traffic model.

[0069] Among them, the fault nodes constructed by the network traffic model are common fault nodes, and the network fault event database is constructed through the fault symptoms of common fault nodes. The network fault event database stores the characteristic information of the fault, wherein the characteristic information of the fault includes gateway fault events, hub fault events, switch fault events, bridge fault events, router fault events, etc.

[0070] The device events of the network devices to be processed include gateway failure events, gateway normal events, hub failure events, hub normal events, switch failure events, switch normal events, bridge failure events, bridge normal events, router failure events, router normal events, etc.

[0071] Preset fault events have been pre-set in the network traffic model, and the preset fault events include preset gateway fault events, preset hub fault events, preset switch fault events, preset bridge fault events, preset router fault events, etc.

[0072] A2: If the preset fault event matches the device event of the network device to be processed, the monitoring result is determined to be a monitoring result in an abnormal state.

[0073] For example, if the device event of the network device to be processed is a gateway failure event, it is consistent with the preset gateway failure event in the network traffic model, and a monitoring result of the gateway failure is obtained.

[0074] A3: If the preset fault event does not match the device event of the network device to be processed, the monitoring result is determined to be a monitoring result in a normal state.

[0075] For example, if the device event of the network device to be processed is a normal hub event, it is inconsistent with the preset fault event in the network traffic model, and a normal hub monitoring result is obtained.

[0076] S102: Determine a network fault feature corresponding to the monitoring result in an abnormal state.

[0077] Among them, network fault characteristics include packet loss fault characteristics, no network response fault characteristics, delay fault characteristics, etc.

[0078] To help you understand the network fault characteristics corresponding to the abnormal monitoring results, an example is given here:

[0079] For example, if the monitoring result of the abnormal state is a gateway failure event, it is determined that the network failure corresponding to the detection result of the gateway failure event is a no network response failure feature.

[0080] S103: Probability estimation is performed on the network fault feature and the preset network fault feature in the pre-built network fault event database by using a preset probability algorithm to obtain a network fault with a preset probability; the preset probability is used to represent the maximum probability in the network fault event database.

[0081] In S103, the preset probability algorithm may be Bayesian law, Monte Carlo algorithm, etc. The specific preset probability algorithm is set by the technicians according to the actual situation, and this application does not make any specific limitation. The preset probability algorithm of this application is preferably Bayesian law.

[0082] The network fault features and the preset network fault features in the pre-built network fault event database are probability estimated by using Bayes' theorem, and the network fault event with the highest probability in the network fault event database is selected.

[0083] A network fault event database is constructed by presetting the fault characteristics of the faulty nodes.

[0084] Among them, a network fault event database is constructed according to the fault characteristics of each fault node in the network traffic model.

[0085] After the network fault event database is built, the relevant information of the faulty node is stored. The relevant information of the faulty node includes location information, model parameter information, purchase time and warranty period information, which is helpful for assisting network maintenance personnel to quickly locate and maintain the fault, and thus helps to ensure the long-term stable operation of the network.

[0086] S104: Determine a network fault location result of the network device based on the fault node location information of the network fault with a preset probability.

[0087] Specifically, based on the fault node location information of the network fault with a preset probability, the process of determining the network fault location result of the network device is as follows:

[0088] First, the fault node location information of the network fault with a preset probability in the network fault event database is determined.

[0089] Then, based on the fault node location information, a network fault location result of the network device is determined.

[0090] The network fault of the network device is located by using the fault node position information of the network fault corresponding to the preset probability (maximum probability), and the network fault location result of the network device is obtained.

[0091] The network fault location results are sent to network maintenance personnel, who will isolate, repair or replace faulty components based on the network fault location results to ensure normal network operation.

[0092] S105: Do not perform the network fault location operation.

[0093] In the embodiment of the present application, the acquired abnormal network traffic data is used as a machine learning sample feature set to construct a network traffic model, and the network status of network devices is judged and monitored in real time through the network traffic model, which is conducive to improving the efficiency and accuracy of network fault detection. In addition, the network fault location results are used to assist maintenance personnel in fast and accurate network fault location and maintenance, ensuring the long-term stable operation of the network.

[0094] refer to Figure 2 As shown in the figure, the process of performing fault monitoring on the network device to be processed by using the pre-built network traffic model in the above S101 to obtain the monitoring result mainly includes the following steps:

[0095] S201: Match the device event of the network device to be processed with the preset fault event in the pre-built network traffic model. If the preset fault event matches the device event of the network device to be processed, execute S202; if the preset fault event does not match the device event of the network device to be processed, execute S203.

[0096] S202: Determine that the monitoring result is a monitoring result in an abnormal state.

[0097] S203: Determine that the monitoring result is a normal monitoring result.

[0098] The execution process and execution principle of S201-S203 are consistent with the execution process and execution principle of the above-mentioned S101, which can be used as a reference and will not be repeated here.

[0099] In the embodiment of the present application, the device events of the network device to be processed are matched by preset fault events in the pre-constructed network traffic model to achieve the purpose of determining whether the monitoring result is a monitoring result in an abnormal state or a monitoring result in a normal state.

[0100] refer to Figure 3 As shown, the process of determining the network fault location result of the network device based on the fault node location information of the network fault based on the preset probability involved in the above S104 mainly includes the following steps:

[0101] S301: Determine fault node location information of a network fault with a preset probability in a network fault event database.

[0102] S302: Determine a network fault location result of the network device based on the fault node location information.

[0103] The execution process and execution principle of S301-S302 are consistent with the execution process and execution principle of the above-mentioned S104, which can be used as a reference and will not be repeated here.

[0104] In an embodiment of the present application, the fault node location information of a network fault with a preset probability is determined in a network fault event database, and based on the fault node location information, the network fault location result of the network device is determined. The network fault location result can assist maintenance personnel in performing fast and accurate network fault location and maintenance, thereby ensuring the long-term stable operation of the network.

[0105] Based on the above embodiments Figure 1 A network fault location method is disclosed, and the embodiment of the present application also discloses a network fault location system, such as Figure 4 As shown, the network fault location system includes a monitoring unit 401 , a first determining unit 402 , an estimating unit 403 and a second determining unit 404 .

[0106] The monitoring unit 401 is used to perform fault monitoring on the network device to be processed by using a pre-built network traffic model to obtain a monitoring result; the monitoring result is used to indicate the network status of the network device to be processed.

[0107] The first determining unit 402 is configured to determine a network fault feature corresponding to the monitoring result in the abnormal state if the monitoring result is a monitoring result in the abnormal state.

[0108] The estimation unit 403 is used to perform probability estimation on the network fault feature and the preset network fault feature in the pre-built network fault event database through a preset probability algorithm to obtain a network fault with a preset probability; the preset probability is used to represent the maximum probability in the network fault event database.

[0109] The second determining unit 404 is configured to determine a network fault locating result of the network device based on the fault node location information of the network fault with a preset probability.

[0110] Furthermore, the monitoring unit 401 includes a matching module, a first determining module and a second determining module.

[0111] The matching module is used to match the fault events of the network device to be processed through the preset fault events in the pre-built network traffic model.

[0112] The first determination module is used to determine that the monitoring result is a monitoring result in an abnormal state if the preset fault event is consistent with the fault event of the network device to be processed.

[0113] The second determination module is used to determine that the monitoring result is a monitoring result in a normal state if the preset fault event is inconsistent with the fault event of the network device to be processed.

[0114] Further, the second determining unit 404 includes a third determining module and a fourth determining module.

[0115] The third determination module is used to determine the fault node location information of the network fault with a preset probability in the network fault event database.

[0116] The fourth determination module is used to determine the network fault location result of the network device based on the fault node location information.

[0117] Furthermore, the monitoring unit 401 of the process of constructing the network traffic model includes a monitoring module, a processing module, an extraction module and a construction module.

[0118] The monitoring module is used to monitor the data flow of the network device to be processed and obtain the network flow information corresponding to the network device to be processed.

[0119] The processing module is used to perform denoising on the network traffic information through a denoising algorithm to obtain denoised network traffic information.

[0120] The extraction module is used to extract abnormal network traffic information from the denoised network traffic information.

[0121] A building module is used to build a network traffic model through abnormal network traffic information.

[0122] Furthermore, the estimation unit 403 of the process of constructing the network fault event database is specifically configured to construct the network fault event database by presetting the fault characteristics of the fault node.

[0123] In the embodiment of the present application, the acquired abnormal network traffic data is used as a machine learning sample feature set to construct a network traffic model, and the network status of network devices is judged and monitored in real time through the network traffic model, which is conducive to improving the efficiency and accuracy of network fault detection. In addition, the network fault location results are used to assist maintenance personnel in fast and accurate network fault location and maintenance, ensuring the long-term stable operation of the network.

[0124] An embodiment of the present application further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned network fault locating method.

[0125] The present application also provides an electronic device, whose structural diagram is as follows: Figure 5As shown, it specifically includes a memory 501 and one or more instructions 502, wherein the one or more instructions 502 are stored in the memory 501 and are configured to be executed by one or more processors 503 to execute the one or more instructions 502 to perform the above-mentioned network fault location method.

[0126] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0127] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0128] The steps in the methods of the embodiments of the present application can be adjusted in order, combined, and deleted according to actual needs.

[0129] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0130] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0131] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A network fault location method, characterized in that: The method comprises: Performing fault monitoring on the network device to be processed by using a pre-built network traffic model to obtain a monitoring result; the monitoring result is used to indicate the network status of the network device to be processed; If the monitoring result is a monitoring result in an abnormal state, determining a network fault feature corresponding to the monitoring result in an abnormal state; the network fault feature includes at least a packet loss fault feature, a no network response fault feature, and a delay fault feature; By using a preset probability algorithm, the network fault feature and the preset network fault feature in the pre-built network fault event database are probability estimated to obtain a network fault with a preset probability; the preset probability is used to represent the maximum probability in the network fault event database; Determine the fault node location information of the network fault of the preset probability in the network fault event database; Based on the fault node location information, a network fault locating result of the network device is determined.

2. The method according to claim 1, characterized in that The fault monitoring of the network device to be processed is performed by using the pre-built network traffic model to obtain the monitoring result, including: Matching device events of the network devices to be processed through preset fault events in the pre-built network traffic model; If the preset fault event matches the device event of the network device to be processed, determining that the monitoring result is a monitoring result in an abnormal state; If the preset fault event does not match the device event of the network device to be processed, the monitoring result is determined to be a monitoring result in a normal state.

3. The method according to claim 1, characterized in that: The process of building a network traffic model includes: Performing data flow monitoring on the network device to be processed to obtain network flow information corresponding to the network device to be processed; De-noising the network traffic information by using a de-noising algorithm to obtain de-noised network traffic information; Extracting abnormal network traffic information from the denoised network traffic information; A network traffic model is constructed based on the abnormal network traffic information.

4. The method according to claim 1, characterized in that: The process of building a network fault event database includes: A network fault event database is constructed by presetting the fault characteristics of the faulty nodes.

5. A network fault location system, characterized in that: The system comprises: A monitoring unit, used to perform fault monitoring on the network device to be processed by using a pre-built network traffic model to obtain a monitoring result; the monitoring result is used to indicate the network status of the network device to be processed; A first determining unit is used to determine, if the monitoring result is a monitoring result in an abnormal state, a network fault feature corresponding to the monitoring result in the abnormal state; the network fault feature at least includes a packet loss fault feature, a no network response fault feature, and a delay fault feature; An estimation unit, configured to perform probability estimation on the network fault feature and a preset network fault feature in a pre-built network fault event database by using a preset probability algorithm to obtain a network fault with a preset probability; the preset probability is used to represent the maximum probability in the network fault event database; The second determining unit includes: a third determining module and a fourth determining module; The third determination module is used to determine the fault node location information of the network fault with the preset probability in the network fault event database; The fourth determination module is used to determine the network fault location result of the network device based on the fault node location information.

6. The system according to claim 5, characterized in that The monitoring unit further includes: A matching module, used for matching device events of the network device to be processed with preset fault events in a pre-built network traffic model; A first determination module, configured to determine that the monitoring result is a monitoring result in an abnormal state if the preset fault event matches the device event of the network device to be processed; The second determination module is used to determine that the monitoring result is a monitoring result in a normal state if the preset fault event does not match the device event of the network device to be processed.

7. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the network fault locating method according to any one of claims 1 to 4.

8. An electronic device, characterized in that: The system comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the network fault locating method according to any one of claims 1 to 4.

Images