Abnormal data detection method and device, computer equipment and storage medium

Abstract

The invention relates to an abnormal data detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring to-be-detected data acquired by sensing equipment in the Internet of Things; inputting the feature vector corresponding to the to-be-detected data into a strategy selection model, and determining a target model identifier through the strategy selection model; determining a target detection model corresponding to the target model identifier from detection models deployed at multiple levels of the Internet of Things. wherein the hierarchy where the target detection model is located is matched with the hierarchy characteristics represented by the feature vectors of the to-be-detected data; transmitting the to-be-detected data to a detection device in the hierarchy where the target detection model is located, so that the target detection model deployed in the detection device processes the feature vector; and outputting a detection result corresponding to the to-be-detected data, wherein the detection result includes a detection result representing normal and a detection result representing abnormal. By adopting the method, the anomaly detection efficiency can be greatly improved.

Description

technical field [0001] The present application relates to the technical field of the Internet of Things, and in particular to a detection method, device, computer equipment and storage medium for abnormal data. Background technique [0002] In the Internet of Things, sensor devices can convert specific physical phenomena into abstract signal data, and transmit these data to the cloud platform for richer processing and analysis. However, due to possible failures of sensor equipment and noise in actual signals, abnormalities and even errors often occur in the collected data, which affects subsequent processing and analysis. At the same time, these abnormalities are usually accompanied by some important events, such as equipment failures, sudden changes in the environment, and security attacks, etc. Therefore, it is necessary to detect abnormal data generated by these sensor devices. [0003] In the traditional way, an abnormality detection model deployed on a cloud server is...

AI Technical Summary

Problems solved by technology

However, the traditional method of transferring all the data to the cloud server will cause high communication delay in the network, resulting in low detection efficiency

Images