Abnormality detection method, electronic equipment and storage medium

Abstract

The invention provides an anomaly detection method, electronic equipment and a storage medium. The method comprises the following steps: receiving an exception detection instruction; obtaining a sample to be detected, determining whether the to-be-detected sample has periodicity; when the to-be-detected sample has periodicity, detecting the to-be-detected sample; determining a point in time to bedetected, all data are not detected; detection efficiency is improved, determining an acquisition value corresponding to the to-be-detected time point from the to-be-detected sample, calling a pre-trained anomaly detection model; obtaining an expected value corresponding to the acquisition value from the anomaly detection model, calculating a residual value between the acquisition value and the expected value; and determining whether the to-be-detected sample is abnormal based on the anomaly detection model and the residual value, intelligent operation and maintenance are achieved, and due tothe fact that the anomaly detection model is a multi-model established based on S-H-ESD, anomaly detection has the characteristic of high precision, and then automatic detection of various anomalies is achieved.

Description

technical field [0001] The invention relates to the technical field of intelligent operation and maintenance, in particular to an abnormality detection method, electronic equipment and a storage medium. Background technique [0002] In intelligent operation and maintenance monitoring and management, anomaly detection is an important part of the whole process. Since it is difficult to provide a large number of abnormal labels for monitoring index sequences, the existing detection methods are mainly based on unsupervised learning algorithms or statistical algorithms, and also include deep learning algorithms. [0003] Anomaly detection has the following two requirements for the algorithm: [0004] (1) The lightweight of the algorithm ensures that the algorithm can be deployed in a million-level indicator monitoring environment. [0005] (2) The high precision of the algorithm (including precision and recall). [0006] In the existing technical solutions, if high precision i...

AI Technical Summary

Problems solved by technology

[0006] In the existing technical solutions, if high precision is to be ensured, all the collected data must be analyzed and processed. Due to the huge amount of data, it will not be able to meet the lightweight requirements, and to meet the lightweight requirements, the processing must be reduced. The amount of data, which in turn will lead to the inability to meet the high-precision requirements, therefore, the existing technology is still unable to meet both lightweight and high-precision requirements

Images