Data anomaly detection algorithm determination method and device and computer equipment

Abstract

The invention discloses a data anomaly detection algorithm determination method and device and computer equipment. The method comprises the steps of obtaining to-be-detected data; performing feature extraction on the to-be-detected data according to a preset feature extraction tool to obtain fingerprint information of the to-be-detected data; and performing feature matching according to the fingerprint information of the to-be-detected data and fingerprint information in a preset algorithm selection model, and determining an anomaly detection algorithm of the to-be-detected data according to an anomaly detection algorithm corresponding to the fingerprint information most similar to the fingerprint information of the to-be-detected data. According to the invention, the feature extraction is performed on the to-be-detected data, the feature matching is performed on the fingerprint information of the plurality of data in the preset algorithm selection model, and the anomaly detection algorithm of the to-be-detected data is determined according to the anomaly detection algorithm corresponding to the fingerprint information with the highest matching degree, so that according to the data feature change, an anomaly detection algorithm most suitable for the to-be-detected data is selected in real time, the scene adaptability is high, and the universality is good.

Description

technical field [0001] The present invention relates to the technical field of data anomaly detection, in particular to a method, device and computer equipment for determining a data anomaly detection algorithm. Background technique [0002] With the development of IoT technology, streaming data will be collected rapidly. In the real-time scenario of flow data collection, there are various abnormal flow data, and accurate and timely capture of these abnormal flow data is very important for specific application systems. At present, Anomaly Detection Algorithms (ADA) have been widely used in many operation and maintenance monitoring platforms. However, there are a wide variety of anomaly detection algorithms that can be applied to these streaming data, and each anomaly detection algorithm has its own application scenarios. [0003] In related technologies, when performing anomaly detection on streaming data, a specific anomaly detection model is usually established for a spe...

AI Technical Summary

Problems solved by technology

[0004] Therefore, the technical problem to be solved by the present invention is to overcome the establishment of a specific anomaly detection model for a specific scene or data in the prior art, and the anomaly detection method for data cannot be switched flexibly as the scene changes or the data characteristics change, and the versatility is low defects, thereby providing a data anomaly detection algorithm determination method, device and computer equipment

Images