Data index exception monitoring method and system, storage medium and electronic equipment

Abstract

The invention discloses a data index exception monitoring method and system, a storage medium and electronic equipment. The data index exception monitoring method comprises the following steps that: obtaining a data index which needs to be monitored and the historical data of an associated data index corresponding to the data index which needs to be monitored; according to the data index which needs to be monitored and the historical data of the associated data index, generating a scatter diagram; according to the data index which needs to be monitored, the historical data of the associated data index and the scatter diagram, through a quantile regression algorithm, selecting an upper tail, a lower tail and a median, and taking the upper tail, the lower tail and the median as parameters togenerate a learnt monitoring sample model through machine learning; and comparing a data difference between the data index which is obtained in real time and needs to be monitored and the monitoringsample data, and carrying out exception detection on the data index which needs to be monitored, wherein the exception detection on the data index which needs to be monitored comprises exceptional fluctuation point detection and exceptional fluctuation tendency detection.

Description

technical field [0001] The invention relates to a monitoring method for abnormal data indicators, a system thereof, a storage medium, and electronic equipment. Background technique [0002] Various data indicators need to be monitored during system operation and maintenance. At present, most of the existing methods for monitoring data indicators in various system operation and maintenance processes adopt the method of setting various thresholds. This method mainly has the following problems: [0003] 1. The accuracy of the threshold is not high. Generally, it is a one-size-fits-all value, or it is compared according to the historical time series year-on-year, etc., which cannot adapt to the fluctuation and dispersion of data indicators; [0004] 2. It is difficult to find out that there is no large fluctuation anomaly in a short period of time, but there is an abnormal mid-to-long-term trend; [0005] 3. A large number of thresholds need to be set, and a large amount of w...

AI Technical Summary

Problems solved by technology

[0003] 1. The accuracy of the threshold value is not high. Generally, it is a one-size-fits-all value, or it is compared according to the historical time series year-on-year and quarter-on-quarter, which cannot adapt to the fluctuation and dispersion of data indicators;

[0004] 2. It is difficult to find out that there is no large fluctuation abnormality in a short period of time, but there is an abnormal mid-to-long-term trend;

[0005] 3. A large number of thresholds need to be set, and a large amount of work is required to set and adjust the initial settings;

[0006] 4. With the change of the environment (increasing business or changing business, etc.), the maintainability of adding or updating the threshold to adapt to the latest data indicators is poor, requiring a lot of manpower, and monitoring is often reduced to decoration

Images