Abnormity recognition method and device based on semi-supervised deep learning and storage medium

Abstract

The invention relates to the field of machine learning, and provides an anomaly recognition method and device based on semi-supervised deep learning, and a storage medium, and the method comprises thesteps: S110, obtaining sample data; s120, acquiring positive sample data enhancement, negative sample data enhancement and data noise; s130, forming a corresponding annotation data positive sample, an annotation data negative sample and an annotation data noise sample; s140, forming three corresponding initial prediction models; s150, respectively inputting the unlabeled sample data into the three trained initial prediction models for data prediction; s160, labeling the unlabeled sample data to form new labeled sample data; s170, adding new labeled sample data into the initial labeled sampledata, and circularly executing the steps S120 to S170 to form a final prediction model; and S180, inputting to-be-identified data into the final prediction model to perform anomaly identification. According to the method, the requirement for data is low, a large amount of marking data is not needed, and meanwhile the data exception recognition accuracy can be improved.

Description

technical field [0001] The present invention relates to the technical field of anomaly detection, in particular to an anomaly identification method, device and computer-readable storage medium based on semi-supervised deep learning. Background technique [0002] Anomaly detection is the detection of data and behaviors that do not meet expectations. In practical applications, it includes denoising, network intrusion detection, fraud detection, equipment failure detection, opportunity identification, risk identification, special group identification, disease diagnosis, video monitoring, etc. Anomaly detection detects abnormal states by analyzing input data. Input data types include: continuous type, binary type, category type, graph, spatio-temporal data, image, audio, etc., and output abnormal events or abnormal probability. When choosing an anomaly detection method, it is necessary to consider not only the problem to be solved, but also the state of the data, such as data t...

AI Technical Summary

Problems solved by technology

[0005]Currently, semi-supervised learning is used to identify abnormalities, usually by using normal sample points for modeling. If a sample point does not belong to the modeling category, it is an abnormal point. This method Calculation-intensive and low-precision, it is not applicable when the normal sample category data is sparse

Images