Method and device for identifying abnormal data of monitoring index data

Abstract

The invention discloses a method and a device for identifying abnormal data of monitoring index data. The method comprises the steps of: obtaining index data at a current moment, determining the prediction interval of the index data according to the historical index data in a preset period, and determining the fluctuation value of the index data according to the prediction interval and the index data at the current moment; when the fluctuation value does not accord with a fluctuation threshold, determining that the index data is problem data, the fluctuation threshold being obtained by comparing the index data with historical index data in a first time period before the current moment; and if the index data at the current moment is stable, determining the problem data as abnormal data. Theindex data at the current moment is identified according to the historical index data, and the alarm accuracy is improved; and the problem data is determined as abnormal data according to the stability of the index data at the current moment, so that the accuracy of identifying the abnormal data is improved, and false alarms caused by data increment or data cutting are reduced.

Description

technical field [0001] The invention relates to the field of operation and maintenance, in particular to a method and device for identifying abnormal data of monitoring index data. Background technique [0002] In the existing technology, the scale of operation and maintenance data is large, explosive growth, and the types of monitoring indicators increase, such as: system indicators (such as memory usage overload, etc.), business indicators, but the indicator features are many and complicated, and the content included in the indicator features is becoming more and more abundant , such as: stable trend, periodic changes, large fluctuations, etc. [0003] In terms of technology for monitoring indicators, the existing technology is to set thresholds through traditional manual experience to monitor indicator data, and to notify users by generating alarms when thresholds are exceeded. [0004] However, the verification period of the above method is long, the maintenance cost is...

AI Technical Summary

Problems solved by technology

[0004] However, the verification period of the above method is long, the maintenance cost is high, and it leads to a large number of alarms and false alarms, which makes the accuracy and coverage of monitoring and early warning low, and it is impossible to find and solve faults in time, and it is easy to generate complaints. Therefore, there is an urgent need for a A method for identifying abnormal data of monitoring index data, which improves the accuracy of alarms and reduces the amount of alarms

Images