Traffic data anomaly detection method and device

Abstract

The invention discloses a traffic data anomaly detection method and device, electronic equipment and a storage medium, and the method comprises the steps: inputting preprocessed traffic data into an automatic coding network model, so as to carry out the automatic coding and decoding of the traffic data, and obtaining a reconstruction feature vector; inputting the reconstructed feature vector intoa recurrent neural network model to obtain internal feature information, wherein the internal feature information is used for representing the front-back correlation of the internal features of the flow data; and finally, classifying the internal feature information through a Sigmoid function to obtain a dichotomy result used for representing whether the flow data is abnormal or not, so that the anomaly detection accuracy can be improved.

Description

technical field [0001] The present invention relates to the technical field of neural networks, and more specifically, to a flow data abnormality detection method and device, electronic equipment, and a storage medium. Background technique [0002] Nowadays, with the promotion and development of WeChat, Alipay, and various credit cards, more and more people choose the convenient and fast way of online transaction payment, so transaction fraud in the financial field is gradually becoming more and more , such as obtaining a credit card from a card issuing bank through stolen identity information or through a forged credit card, and then binding this type of credit card for shopping, further cashing out, etc., which will not only bring economic losses to major financial institutions , It will also have a significant negative impact on their reputation and image, so how to effectively detect these highly likely transaction frauds has become the focus of major banking and financi...

AI Technical Summary

Problems solved by technology

Its shortcomings are: before the original data is brought into the algorithm training, there will be artificial data cleaning, data feature selection or data dimensionality reduction process; due to the existence of human subjective factors, in the process of feature selection, some of the original data Deep features may be filtered out or lost, which will affect the recognition and detection of subsequent models, resulting in inaccurate detection results

Images