Service data anomaly detection method based on time sequence classification

Abstract

The invention discloses a service data anomaly detection method based on time sequence classification, which comprises the following steps: s1, extracting offline service data, classifying the offlineservice data according to a time sequence, and generating a sample library comprising different types of time sequences; s2, associating different types of time sequences in the sample library with different time sequence anomaly detection algorithms; s3, acquiring online service data, and classifying the online service data according to the time sequence based on the classification of the time sequence in the sample library; and S4, carrying out anomaly detection on the classified online time series according to an association relationship between time series classification and a time seriesanomaly detection algorithm. The method automatically classifies and identifies different types of time sequences, automatically selects parameters or algorithms to perform time sequence anomaly detection, automatically identifies the types of the time sequences when processing large-scale time sequence anomaly detection, reduces false alarms and missing alarms of alarms, and effectively saves the labor cost.

Description

technical field [0001] The invention relates to an anomaly detection method, in particular to a business data anomaly detection method based on time series classification. Background technique [0002] Anomaly detection of time series indicators is the core link for problem discovery. Traditional static threshold detection is the main method. If the threshold is too high, there will be many missed alarms, making it difficult to find potential quality risks. If the threshold is too low, too many alarms will cause an alarm storm and interfere with business operations. The judgment of the maintenance personnel. For different types of time series, it is necessary to manually select what kind of anomaly detection algorithm to use. When the number of time series is small, it can be selected manually. When anomaly detection of large-scale time series is required, manual processing will have great limitations. Therefore, there is a need for a method for classifying large-scale time...

AI Technical Summary

Problems solved by technology

[0002] Anomaly detection of time series indicators is the core link to discover problems. Traditional static threshold detection is the main method. If the threshold is too high, there will be many missed alarms, which will make it difficult to find hidden quality risks. If the threshold is too low, too many alarms will cause alarm storms and interfere with business operations. The judgment of the maintenance personnel

For different types of time series, it is necessary to manually select what kind of anomaly detection algorithm to use. When the number of time series is small, it can be manually selected. When anomaly detection of large-scale time series is required, manual processing will have great limitations.

Images