Network fault diagnosis method and device

Abstract

The embodiment of the invention provides a network fault diagnosis method and device. Automatic locating of network faults can be realized without manual intervention; furthermore, fault root causes can be determined; and thus, automatic fault diagnosis is realized. The method comprises the steps of: acquiring log, alarm, configuration and KPI data of network elements, network management equipment and monitoring equipment, and detecting an abnormal network element and abnormal information according to the acquired data; according to the abnormal information and the pre-stored corresponding relationship, determining a first fault event; according to the first fault event and a pre-stored fault rule library, determining a first fault rule; and, acquiring the real-time data of the abnormal network element, confirming the suspected fault event in the first fault event and a second fault event, performing logic calculation according to the suspected fault event and second fault event confirmation result and the fault rule, and determining root causes causing faults of a network system. The network fault diagnosis method and device provided by the invention are applied to the technical field of computers.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a network fault diagnosis method and device. Background technique [0002] With the rapid development of information technology, the scale and complexity of network systems continue to expand, which makes the traditional diagnostic method of manually checking system logs to locate network faults no longer applicable. [0003] At present, for the diagnosis of network faults, big data technology can be used to extract relevant features from massive log records, and then machine learning algorithms can be used to perform statistical analysis on these features to quickly detect faults. Since the machine learning algorithm is a probabilistic algorithm, the detected fault is only a suspected fault, and manual analysis of logs is required to confirm the fault. In addition, limited by the length, the information that can be recorded in a single log is limited. For example, events that...

AI Technical Summary

Problems solved by technology

In addition, limited by the length, the information that can be recorded in a single log is limited. For example, events that occur in a certain service are usually recorded, but more detailed information, such as real-time status information of network elements, etc., are often not recorded.

And the lack of these fine-grained information may make it impossible to find the root cause of the network failure

In other words, manual analysis of logs can only confirm faults, but cannot guarantee that the root cause of network faults can be found

[0004] To sum up, the existing network fault diagnosis methods need manual intervention to confirm the fault, and can only confirm the fault but cannot find the root cause of the fault

Images