System abnormality detection method, device, equipment and storage medium

Abstract

The invention relates to artificial intelligence and provides a system abnormality detection method, device, equipment and storage medium. The method comprises: respectively inputting the marked log, unmarked log and extended log of the system to be detected into three identical training models in the training model set for training, and outputting the probability distribution of each abnormal level of the three; and then calculating the output of the training model The cross-entropy loss and consistency loss; then predict the abnormal level of the unmarked log and the extended log according to the consistency loss, and iterate the training model set according to the cross-entropy loss until the training model set converges to obtain the log anomaly detection model; finally Detect abnormal logs during system operation through the log anomaly detection model. In addition, the present invention also relates to block chain technology, and its marked log, unmarked log and extended log can be stored in the block chain. By optimizing the model training method, it prevents the model from overfitting and reduces the difficulty of the detection model in detecting abnormal points in the system.

Description

technical field [0001] The present invention relates to artificial intelligence decision-making, and in particular, to a system abnormality detection method, device, equipment and storage medium. Background technique [0002] As the scale of the system increases, the complexity increases, and the monitoring coverage improves, the amount of monitoring data becomes larger and larger, and the operation and maintenance personnel cannot find quality problems from the massive monitoring data. Intelligent anomaly detection is to automatically, real-time, and accurately discover anomalies from monitoring data through AI algorithms, providing a basis for subsequent diagnosis and self-healing. Anomaly detection is a very basic but very important function in the AIOps (Algorithmic IT Operations) system. It mainly uses algorithms and models to automatically discover abnormal behaviors in KPI time series data for subsequent alarms. Automatic stop loss, root cause analysis, etc. provide ...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to solve the problem that the abnormality detection of the intelligent operation system is difficult

Images