Internet-of-Things time series data anomaly detection method and system

Abstract

The invention discloses an Internet-of-Things time series data anomaly detection method and system. The method comprises the steps of obtaining to-be-tested Internet-of-Things time series data; dividing to-be-tested Internet-of-Things time series data to obtain a to-be-tested time series data segment set; and inputting the to-be-tested time sequence data segment set into the trained semi-supervised self-encoding model to obtain a detection result, wherein the trained semi-supervised self-encoding model is obtained by training the semi-supervised self-encoding model based on the LSTM and the attention mechanism by taking the to-be-trained Internet-of-Things time series data of the unmarked Internet-of-Things time series data and the marked Internet-of-Things time series data as input, taking the corresponding class label as output and taking the minimum loss function as a target. According to the invention, the accuracy of time series data anomaly detection can be improved, and the costis reduced.

Description

technical field [0001] The invention relates to the field of time series data detection, in particular to a method and system for detecting anomalies in time series data of the Internet of Things. Background technique [0002] With the popularization of digitization in various fields, many devices equipped with sensors generate a large amount of time data, forming a time series. Such time series are widely generated and have applications in many application domains, such as finance, biology, transportation, and healthcare. Anomaly detection in time series is required in many real-world applications in various fields, such as predictive maintenance, intrusion detection, fraud prevention, cloud platform monitoring and management, etc. [0003] The study of anomaly detection in time series has a long history. However, due to the diversity of time series in real environments and the high cost of time series labeling, traditional algorithms cannot achieve satisfactory effective...

AI Technical Summary

Problems solved by technology

There are currently a lot of research on unsupervised time series data anomaly detection methods, but unsupervised algorithms are usually unsatisfactory in terms of indicators, and there is a problem of unbalanced accuracy and recall

Although supervised algorithms can obtain better performance indicators, they require a large amount of labeled data, and the cost is too high in the context of big data, and their applicability is not high in practical applications.

Images