Context-based operation and maintenance fault root cause location method, device, equipment and medium

Abstract

The present invention provides a method, device, computer equipment, and storage medium for locating the root cause of an operation and maintenance failure based on a situation. The method includes: obtaining the alarm information corresponding to this alarm; and inputting the alarm information into a pre-trained machine learning model to obtain the corresponding root cause of the fault; the process of determining the root cause of the fault by the machine learning model according to the alarm information includes: calculating the similarity between this alarm and multiple historical situations according to the alarm information ; According to the similarity between this alarm and multiple historical situations, determine the situation to find the root cause of the failure of this alarm; calculate the importance of each alarm source in the situation, and according to each alarm in the situation The importance of the source determines the root cause of the alarm. The present invention does not require high requirements for operation and maintenance personnel, saves time and effort, considers the cascading effect of faults, conducts global analysis on root cause location from a global perspective, and improves the accuracy of root cause location.

Description

technical field [0001] The present invention relates to the technical field of fault location, in particular to a situation-based root cause location method, device, computer equipment and storage medium for operation and maintenance faults. Background technique [0002] Various failures will occur during business operation, and experienced operation and maintenance personnel are often required to read a large number of system alarm information and use domain knowledge to analyze and infer the root cause of the failure. This solution requires the operation and maintenance personnel to It has high requirements and consumes a lot of manpower and material resources. At the same time, due to the limitation of the professional knowledge of operation and maintenance personnel, the location of the root cause of the fault will often lead to certain deviations. [0003] For this reason, relevant technical personnel have proposed a way to find the root cause of the fault through seque...

AI Technical Summary

Problems solved by technology

This method is mainly aimed at abnormal detection of a specific machine index. When there are multiple machines, different models need to be trained to detect at the same time. Many models will consume a lot of computing power; at the same time, many models will also generate a lot of errors. report, which brings a lot of manpower consumption to the operation and maintenance

In addition, the sequence analysis anomaly technology does not consider the cascading effect of faults, and the modeling of the correlation between multiple machines is not sufficient, and the correlation between anomalies cannot be detected, so it is impossible to conduct a global analysis of root cause location from a global perspective

Images