Data exception detection method and device thereof, electronic equipment and storage medium

Abstract

The invention relates to a data processing technology, and discloses a data exception detection method, which comprises the following steps of: obtaining a standard training data set containing missing data and an exception detection model framework containing a variational lower limit function; adjusting the variational lower limit function by utilizing the missing data to obtain an optimized variational lower limit function; training an anomaly detection model framework by utilizing the standard training data set to obtain an anomaly detection model; detecting the to-be-detected data set byusing the anomaly detection model and obtaining a reconstruction probability of the to-be-detected data; and if the target to-be-detected data of which the reconstruction probability is greater than or equal to the reconstruction threshold exists, determining that the target to-be-detected data is abnormal data. The invention further provides the data exception detection device, electronic equipment and a computer readable storage medium. In addition, the invention also relates to a blockchain technology, and the standard training data set can be obtained from the nodes of the blockchain. According to the invention, the efficiency and accuracy of KPI anomaly detection can be improved.

Description

technical field [0001] The present invention relates to artificial intelligence technology, in particular to a data anomaly detection method, device, electronic equipment and computer-readable storage medium. Background technique [0002] KPI (Key Performance Indicator) anomaly detection is a very important part in the field of intelligent operation and maintenance. In order to ensure uninterrupted business, it is usually necessary to detect whether there are abnormalities in various KPIs (such as KPIs of application programs, KPIs of operating systems, etc.), so as to determine whether there is a fault in the software or hardware of the system, and perform troubleshooting in a timely manner. [0003] In the KPI anomaly detection method in the prior art, due to the low robustness and low model stability of the anomaly detection model after training, the detection results are not accurate enough; at the same time, the detection method in the prior art will generate A large n...

AI Technical Summary

Problems solved by technology

[0003] In the KPI anomaly detection method in the prior art, due to the low robustness and low model stability of the anomaly detection model after training, the detection results are not accurate enough; at the same time, the detection method in the prior art will generate A large number of tags occupy computer resources and reduce detection efficiency

Images