Network fault detection method, device and equipment and readable storage medium

Abstract

This invention relates to the field of network operation and maintenance technology. It provides a network fault detection method, apparatus, device, and readable storage medium. The method includes: acquiring the anomaly type and comparison index of network anomaly data to be detected; sorting multiple pieces of network anomaly data to be detected based on the anomaly type and the comparison index; determining the anomaly information of a fault node based on the associated service information of the target network anomaly data, wherein the target network anomaly data is the network anomaly data to be detected determined based on the sorting result; and determining the fault information of the root cause node and the corresponding repair strategy based on the anomaly information, wherein the root cause node is determined based on the fault node. This invention, by comprehensively considering multiple variables of a complex network, performs in-depth analysis of the network anomaly data to be detected, enabling accurate detection of network faults.

Description

Technical Field

[0001] This invention relates to the field of network operation and maintenance technology, and in particular to a network fault detection method, apparatus, device, and readable storage medium. Background Technology

[0002] Current network operation and maintenance solutions based on machine learning and deep learning mostly rely on traditional statistical algorithms. Anomaly detection algorithms and root cause diagnosis algorithms also depend on labeled data and expert experience, which are difficult to compile into the model. In terms of access maintenance, when encountering new customers, private domain knowledge, business experience, and data changes, traditional network operation and maintenance methods usually have to retrain. Since unknown network faults have not been trained on, traditional network operation and maintenance methods cannot achieve accurate fault detection. Summary of the Invention

[0003] This invention provides a network fault detection method, apparatus, device, and readable storage medium to solve the technical problem that existing network operation and maintenance solutions cannot achieve accurate detection of network faults.

[0004] This invention provides a network fault detection method, comprising:

[0005] Obtain the anomaly types and comparison indicators of the network anomaly data to be detected;

[0006] Based on the anomaly type and the comparison index, the multiple network anomaly data to be detected are sorted.

[0007] Based on the associated service information of the target network anomaly data, the anomaly information of the faulty node is determined. The target network anomaly data is the network anomaly data to be detected determined based on the sorting results.

[0008] Based on the anomaly information, the fault information of the root cause node is determined, as well as the corresponding repair strategy. The root cause node is determined based on the fault node.

[0009] According to a network fault detection method provided by the present invention, the step of sorting multiple network anomaly data to be detected based on the anomaly type and the comparison index includes:

[0010] Based on the anomaly type and the comparison index, a priority index is determined for each of the network anomaly data to be detected;

[0011] The multiple network anomaly data to be detected are sorted according to the priority index of each of the network anomaly data to be detected.

[0012] According to a network fault detection method provided by the present invention, determining the priority index of each network anomaly data to be detected based on the anomaly type and the comparison index includes:

[0013] When there are multiple exception types, determine the order in which the multiple exception types exist;

[0014] Based on the order of events and the comparison index of the network anomaly data to be detected for each anomaly type, a priority index for each network anomaly data to be detected is determined.

[0015] According to a network fault detection method provided by the present invention, the anomaly types include network device faults, port connection anomalies, and performance degradation; the method for determining the priority index of each network anomaly data to be detected based on the order of occurrence and the comparison index of the network anomaly data to be detected for each anomaly type includes:

[0016] Given that the order of priority is network device failure, port connection anomaly, and performance degradation, the priority index of the network anomaly data to be detected for network device failure is determined to be greater than the priority index of the network anomaly data to be detected for port connection anomaly, and the priority index of the network anomaly data to be detected for port connection anomaly is greater than the priority index of the network anomaly data to be detected for performance degradation.

[0017] Among the multiple network anomaly data to be detected due to network device failure, or among the multiple network anomaly data to be detected due to port connection anomaly, or among the multiple network anomaly data to be detected due to performance index degradation, a priority index for the multiple network anomaly data to be detected due to network device failure is determined based on a comparison index for each of the network anomaly data to be detected.

[0018] According to a network fault detection method provided by the present invention, the network fault detection method further includes:

[0019] When there are multiple fault nodes, obtain the abnormal indicator data and abnormal information of each fault node;

[0020] Based on the abnormal indicator data and the abnormal information, the root cause node among the multiple fault nodes is determined.

[0021] According to a network fault detection method provided by the present invention, determining the fault information of the root cause node based on the anomaly information includes:

[0022] Obtain the node information of the root cause node;

[0023] Based on the node information and the degree of anomaly, the fault information of the root cause node is determined, wherein the degree of anomaly is determined based on the anomaly index data of the root cause node.

[0024] According to a network fault detection method provided by the present invention, the types of anomalies in acquiring the network anomaly data to be detected include:

[0025] Obtain abnormal indicator data from the abnormal data of the network to be detected;

[0026] Based on the abnormal indicator data, the abnormal type of the network abnormal data to be detected is determined.

[0027] The present invention also provides a network fault detection device, comprising:

[0028] The acquisition module is used to acquire the anomaly type and comparison indicators of the network anomaly data to be detected;

[0029] The data sorting module is used to sort multiple network anomaly data to be detected based on the anomaly type and the comparison index.

[0030] The anomaly information determination module is used to determine the anomaly information of the faulty node based on the associated service information of the target network anomaly data, wherein the target network anomaly data is the network anomaly data to be detected determined based on the sorting results.

[0031] The repair strategy determination module is used to determine the fault information of the root cause node and the repair strategy corresponding to the fault information based on the anomaly information, wherein the root cause node is determined based on the fault node.

[0032] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the network fault detection method as described above.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the network fault detection method as described above.

[0034] The network fault detection method, apparatus, device, and readable storage medium provided by this invention sorts multiple network anomaly data sets by acquiring anomaly types and comparison indicators. Based on the sorting results, it identifies target network anomaly data sets among the multiple sets. Then, it determines the anomaly information of faulty nodes based on the associated service information of the target network anomaly data sets. Finally, it determines the fault information of the root cause node among the faulty nodes and its corresponding repair strategy based on the anomaly information. By comprehensively considering multiple variables of a complex network and performing in-depth analysis of the network anomaly data sets, it can accurately detect network faults. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 This is one of the flowcharts of the network fault detection method provided by the present invention;

[0037] Figure 2 This is the second flowchart of the network fault detection method provided by the present invention;

[0038] Figure 3 This is a schematic diagram of the network fault detection device provided by the present invention;

[0039] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0041] Please refer to Figure 1 This invention provides a network fault detection method, comprising:

[0042] Step 100: Obtain the anomaly type and comparison index of the network anomaly data to be detected;

[0043] The network fault detection method provided in this application embodiment may further include:

[0044] Step 110: Obtain abnormal indicator data from the abnormal data of the network to be detected;

[0045] Step 120: Based on the abnormal indicator data, determine the abnormal type of the network abnormal data to be detected.

[0046] Specifically, the implementation process of the network fault detection method provided in this embodiment first involves identifying the type of abnormal network data (including network device failures, port connection anomalies, and performance degradation, etc.). When abnormal network data occurs, the abnormal data is detected to obtain the anomaly detection result and determine the type of abnormal data.

[0047] Step 200: Sort the multiple network anomaly data to be detected based on the anomaly type and the comparison index;

[0048] Specifically, combining (network) industry standards and customer perception standards, the network anomaly data to be detected is ranked according to two comparative indicators: importance and priority. For example, multiple network anomaly data to be detected are first classified by anomaly type and ranked by anomaly type, then multiple network anomaly data to be detected for each type are ranked, finally obtaining the ranking result of all network anomaly data to be detected.

[0049] For example, the abnormal network data to be detected can be divided into three types: A, B, and C. The sorting result of the three types is ABC. The network data to be detected of type A includes A1, A2, A3, and A4, and the sorting result of the network data to be detected of type A is A1, A2, A3, A4; the network data to be detected of type B includes B1, B2, B3, and B4, and the sorting result of the network data to be detected of type B is B1, B2, B3, B4; the network data to be detected of type C includes C1, C2, C3, and C4, and the sorting result of the network data to be detected of type C is C1, C2, C3, C4. Then the sorting result of all the network data to be detected is: A1, A2, A3, A4, B1, B2, B3, B4, C1, C2, C3, C4.

[0050] Step 300: Based on the associated service information of the target network anomaly data, determine the anomaly information of the faulty node. The target network anomaly data is the network anomaly data to be detected determined based on the sorting results.

[0051] Specifically, the network fault detection method provided in this embodiment is applied to a network fault detection device, which includes a network model decision scheduler, an operation and maintenance knowledge base, a network detection model, a root cause localization model, a network knowledge graph, a problem classification model, a problem analysis model, and operation and maintenance tools. The network model decision scheduler receives anomaly notifications (including sorted network anomaly data to be detected). After receiving the anomaly notification, the network model decision scheduler obtains the associated services and impact scope of the network anomaly data to be detected (i.e., associated service information in this embodiment) through the operation and maintenance knowledge base, and initiates, organizes, and schedules the collaborative work of the network detection model, root cause localization model, problem classification model, and problem analysis model. Upon receiving an anomaly detection task, the network detection model detects the top-ranked network anomaly data to be detected (i.e., the target network anomaly data in this embodiment), identifies multiple (potentially) fault nodes associated with the target network anomaly data, and detects the anomaly information of the fault nodes, including anomaly indicators, anomaly occurrence time, and anomaly severity.

[0052] Step 400: Determine the fault information of the root cause node and the corresponding repair strategy based on the abnormal information. The root cause node is determined based on the fault node.

[0053] Specifically, the root cause localization model, based on the detailed detection results output by the network detection model and combined with network knowledge graph analysis, identifies the root cause node (among multiple faulty nodes). The problem classification model determines the specific fault type and location of the network anomaly based on the node information of the root cause node and the degree of anomaly (described by anomaly indicators). The problem analysis model provides a detailed analysis report for the fault based on the problem object and problem type determined by the problem classification model. The detailed analysis report includes the radius of the fault's impact and fault repair suggestions. Based on the analysis report provided by the problem analysis model, it suggests calling network operation and maintenance tools to perform network anomaly repair actions. If the analysis report indicates that the current solution lacks relevant information or cannot resolve the network anomaly problem, it provides suggestions for further network diagnosis.

[0054] This embodiment sorts multiple network anomaly data sets by acquiring anomaly types and comparison indicators. Based on the sorting results, it identifies target network anomaly data among these sets. Then, it determines the anomaly information of faulty nodes based on the associated service information of the target network anomaly data. Finally, it determines the fault information of the root cause node among the faulty nodes and its corresponding repair strategy based on the anomaly information. By comprehensively considering multiple variables of a complex network and performing in-depth analysis of the network anomaly data, it can accurately detect network faults.

[0055] Please refer to Figure 2In one embodiment, the network fault detection method provided in this application may further include:

[0056] Step 210: Based on the anomaly type and the comparison index, determine the priority index of each of the network anomaly data to be detected;

[0057] Step 220: Sort the multiple network anomaly data to be detected according to the priority index of each network anomaly data to be detected.

[0058] The network fault detection method provided in this application embodiment may further include:

[0059] Step 211: If there are multiple exception types, determine the order of the multiple exception types;

[0060] Step 212: Based on the order of events and the comparison index of the network anomaly data to be detected for each anomaly type, determine the priority index of each network anomaly data to be detected.

[0061] The anomaly types include network device failures, port connection anomalies, and performance degradation; the network fault detection method provided in this application embodiment may further include:

[0062] Step 212-1: In the case that the order of network device failure, port connection abnormality and performance index degradation is network device failure, the priority index of the network abnormality data to be detected is determined to be greater than the priority index of the network abnormality data to be detected for port connection abnormality, and the priority index of the network abnormality data to be detected for port connection abnormality is greater than the priority index of the network abnormality data to be detected for performance index degradation.

[0063] Step 212-2: Among the multiple network anomaly data to be detected due to network device failure, or among the multiple network anomaly data to be detected due to port connection anomaly, or among the multiple network anomaly data to be detected due to performance index degradation, determine the priority index of the multiple network anomaly data to be detected based on the comparison index of each of the network anomaly data to be detected.

[0064] Specifically, the types of network anomalies mentioned above include network device failures, port connection anomalies, and performance degradation. Based on the anomaly type of each network anomaly data to be detected and the comparison index of each network anomaly data to be detected, a priority index is determined for each network anomaly data to be detected. The priority index obtained here is the basis for sorting the network anomaly data to be detected. For example, the network anomaly data to be detected are sorted in descending order of priority index.

[0065] Before sorting the initial multiple network anomaly data sets to be detected, the anomaly types are first sorted. The sorting results for anomaly types could be: network device failure, port connection anomalies, and performance degradation. Then, the multiple network anomaly data sets for each anomaly type are sorted, and finally, the overall sorting result for all network anomaly data sets is obtained.

[0066] When the anomaly type ranking results are network device failure, port connection failure, and performance degradation, the priority index of the network anomaly data to be detected belonging to network device failure is determined to be > the priority index of the network anomaly data to be detected belonging to port connection failure > the priority index of the network anomaly data to be detected belonging to performance degradation.

[0067] Taking network device failure types as an example, among multiple network anomaly data points to be detected for network device failures, a priority index is determined based on the comparison indicators for each data point. When the comparison indicators include importance and priority, the data can be divided into four regions using the horizontal and vertical axes respectively for ranking. Importance has a greater impact on the ranking than priority. Alternatively, the ranking result for each type of network anomaly data point can be determined based on the weighted sum of each comparison indicator; for example, data with a larger weighted sum is ranked higher.

[0068] This embodiment comprehensively determines the ranking of abnormal data in the network to be detected by comparing the anomaly type and comparison indicators of each abnormal data, thus determining the order for subsequent anomaly detection.

[0069] Please refer to Figure 2 In one embodiment, the network fault detection method provided in this application may further include:

[0070] Step 500: If there are multiple fault nodes, obtain the abnormal indicator data and abnormal information for each fault node.

[0071] Step 600: Based on the abnormal indicator data and the abnormal information, determine the root cause node among the multiple fault nodes.

[0072] Specifically, as described above, there may be multiple faulty nodes, therefore it is necessary to filter out the root cause node from among them. The root cause localization model uses the detailed detection results output by the network detection model (including abnormal indicator data and abnormal information for each faulty node) and combines them with network knowledge graph analysis to identify the root cause node among the multiple faulty nodes.

[0073] This embodiment filters root cause nodes from faulty nodes using abnormal indicator data and abnormal information.

[0074] In one embodiment, the network fault detection method provided in this application may further include:

[0075] Step 410: Obtain the node information of the root cause node;

[0076] Step 420: Based on the node information and the degree of anomaly, determine the fault information of the root cause node, wherein the degree of anomaly is determined based on the anomaly index data of the root cause node.

[0077] Specifically, after identifying the root cause node, its node information is obtained. These nodes can be physical layer devices or virtual layer devices. The root cause node localization method is as follows: Based on real-time alarm streams and topology data aggregation of fault-related events, time series algorithms, unsupervised methods, Bayesian networks, and interpretable methods are used to quickly identify faults and accurately locate their root causes. The degree of anomaly is determined based on the abnormal indicator data of the root cause node. Based on the node information and the degree of anomaly, the fault information of the root cause node is then determined.

[0078] This embodiment determines the fault information of the root cause node by analyzing the node information and the degree of anomaly of the root cause node.

[0079] The network fault detection device provided by the present invention is described below. The network fault detection device described below can be referred to in correspondence with the network fault detection method described above.

[0080] Please refer to Figure 3 The present invention also provides a network fault detection device, comprising:

[0081] The acquisition module 301 is used to acquire the anomaly type and comparison index of the network anomaly data to be detected;

[0082] Data sorting module 302 is used to sort multiple network anomaly data to be detected based on the anomaly type and the comparison index;

[0083] The anomaly information determination module 303 is used to determine the anomaly information of the faulty node based on the associated service information of the target network anomaly data, wherein the target network anomaly data is the network anomaly data to be detected determined based on the sorting result;

[0084] The repair strategy determination module 304 is used to determine the fault information of the root cause node and the repair strategy corresponding to the fault information based on the abnormal information, wherein the root cause node is determined based on the fault node.

[0085] Optionally, the data sorting module includes:

[0086] The priority index determination unit is used to determine the priority index of each of the network anomaly data to be detected based on the anomaly type and the comparison index.

[0087] The data sorting unit is used to sort multiple network anomaly data according to the priority index of each network anomaly data to be detected.

[0088] Optionally, the priority index determination unit includes:

[0089] The sequence determination unit is used to determine the sequence order of the multiple exception types when there are multiple exception types.

[0090] The priority index calculation unit is used to determine the priority index of each network anomaly data to be detected based on the order of events and the comparison index of each anomaly type.

[0091] Optionally, the anomaly types include network device failures, port connection anomalies, and performance index degradation; the priority index calculation unit includes:

[0092] The first index determination unit is used to determine, in the case that the order of network device failure, port connection abnormality and performance index degradation is network device failure, the priority index of the network abnormal data to be detected is greater than the priority index of the network abnormal data to be detected for port connection abnormality, and the priority index of the network abnormal data to be detected for port connection abnormality is greater than the priority index of the network abnormal data to be detected for performance index degradation.

[0093] The second index determination unit is used to determine the priority index of the multiple network anomaly data to be detected for network device failure, or the multiple network anomaly data to be detected for port connection anomaly, or the multiple network anomaly data to be detected for performance index degradation, based on the comparison index of each of the network anomaly data to be detected.

[0094] Optionally, the network fault detection device further includes:

[0095] The information acquisition module is used to acquire abnormal indicator data and abnormal information for each of the multiple fault nodes.

[0096] The root cause node determination module is used to determine the root cause node among the multiple fault nodes based on the abnormal indicator data and the abnormal information.

[0097] Optionally, the repair strategy determination module includes:

[0098] A node information acquisition unit is used to acquire the node information of the root cause node;

[0099] The fault information determination unit is used to determine the fault information of the root cause node based on the node information and the degree of abnormality, wherein the degree of abnormality is determined based on the abnormal indicator data of the root cause node.

[0100] Optionally, the acquisition module includes:

[0101] The abnormal indicator data acquisition unit is used to acquire abnormal indicator data from the abnormal data of the network to be detected.

[0102] An anomaly type determination unit is used to determine the anomaly type of the network anomaly data to be detected based on the anomaly index data.

[0103] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440. The processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions from the memory 430 to execute a network fault detection method.

[0104] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0105] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the network fault detection methods provided by the methods described above.

[0106] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0107] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A network fault detection method, characterized by, The method comprises: obtaining an abnormal type and a comparison index of network abnormal data to be detected; sorting a plurality of the network abnormal data to be detected based on the abnormal type and the comparison index; determining a fault node and abnormal information of the fault node based on associated service information of target network abnormal data, the target network abnormal data being determined based on the sorting result; determining fault information of a root cause node and a repair strategy corresponding to the fault information based on the abnormal information, the root cause node being determined based on the fault node; the sorting a plurality of the network abnormal data to be detected based on the abnormal type and the comparison index comprises: determining a priority index of each of the network abnormal data to be detected based on the abnormal type and the comparison index; sorting a plurality of the network abnormal data to be detected according to the priority index of each of the network abnormal data to be detected; the determining a priority index of each of the network abnormal data to be detected based on the abnormal type and the comparison index comprises: determining an order of a plurality of the abnormal types when the abnormal type has a plurality of abnormal types; determining a priority index of each of the network abnormal data to be detected based on the order and the comparison index of each of the abnormal types.

2. The network fault detection method of claim 1, wherein, The abnormal type comprises network device failure, port connection abnormality and performance index attenuation; the determining a priority index of each of the network abnormal data to be detected based on the order and the comparison index of each of the abnormal types comprises: when the order is network device failure, port connection abnormality and performance index attenuation, determining that the priority index of the network abnormal data to be detected of the network device failure is greater than the priority index of the network abnormal data to be detected of the port connection abnormality, and the priority index of the network abnormal data to be detected of the port connection abnormality is greater than the priority index of the network abnormal data to be detected of the performance index attenuation; determining a priority index of a plurality of the network abnormal data to be detected based on the comparison index of each of the network abnormal data to be detected in the plurality of the network abnormal data to be detected of the network device failure, or in the plurality of the network abnormal data to be detected of the port connection abnormality, or in the plurality of the network abnormal data to be detected of the performance index attenuation.

3. The network fault detection method of claim 1, wherein, The network fault detection method further comprises: obtaining abnormal index data and abnormal information of each of the fault nodes when the fault node has a plurality of fault nodes; determining a root cause node in the plurality of the fault nodes based on the abnormal index data and the abnormal information.

4. The network fault detection method of claim 3, wherein, The determining fault information of the root cause node based on the abnormal information comprises: obtaining node information of the root cause node; determining fault information of the root cause node based on the node information and an abnormal degree, the abnormal degree being determined based on abnormal index data of the root cause node.

5. The network fault detection method of claim 1, wherein, The obtaining an abnormal type of network abnormal data to be detected comprises: obtaining abnormal index data in the network abnormal data to be detected; Determine an abnormal type of the network abnormal data to be detected based on the abnormal index data.

6. A network fault detection apparatus characterized by comprising: Comprise: An acquisition module, configured to acquire an abnormal type of network abnormal data to be detected and a comparison index; A data sorting module, configured to sort a plurality of the network abnormal data to be detected based on the abnormal type and the comparison index; An abnormal information determination module, configured to determine a fault node and abnormal information thereof based on associated business information of target network abnormal data, the target network abnormal data being determined based on a sorting result of the network abnormal data to be detected; A repair strategy determination module, configured to determine fault information of a root cause node and a repair strategy corresponding to the fault information based on the abnormal information, the root cause node being determined based on the fault node; The data sorting module specifically comprises: A priority index determination unit, configured to determine a priority index of each of the network abnormal data to be detected based on the abnormal type and the comparison index; An abnormal data sorting unit, configured to sort a plurality of the network abnormal data to be detected according to the priority index of each of the network abnormal data to be detected; The priority index determination unit is specifically configured to: Determine an order of a plurality of the abnormal types in a case where there are a plurality of the abnormal types; Determine the priority index of each of the network abnormal data to be detected based on the order and the comparison index of the network abnormal data to be detected of each of the abnormal types.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the network fault detection method of any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the network fault detection method of any one of claims 1 to 5.

Images