Malicious user detection method based on feature learning and graph reasoning

Abstract

The invention discloses a malicious user detection method based on feature learning and graph reasoning. Firstly, the suspicion degree of a product is evaluated according to a user sequence, then the suspicion degree of each user is indirectly evaluated according to the suspicion degree of the product, and then, from the product suspiciousness degree, related new features are provided, and the screened malicious users suitable for the new features are combined; and, on the other hand, the same composition hypothesis is provided, the user-user graph is constructed, feature learning of the graph neural network and a paired Markov label propagation method are fused, a unified objective function is established for iterative optimization, feature learning of graph nodes and node label reasoning are carried out, and then malicious user detection is completed.

Description

technical field [0001] The invention relates to the technical field of malicious user detection, and mainly relates to a malicious user detection method based on feature learning and graph reasoning. Background technique [0002] In recent years, a new type of malicious users has emerged on the Internet. They bypass the existing malicious user detection system through cooperation. Different from traditional malicious users, these malicious users are obviously more "smart". Specifically, , they not only comment on the target movie and TV, but also occasionally comment on the target product, which makes it look like a normal person's behavior, thereby circumventing the existing detection system of malicious users who affect consumers' behavior Decision-making, how to detect these new types of malicious users, there are usually two research ideas, one is to treat it as a single malicious user detection, and the other is to treat it as a malicious user group detection. If you r...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: Aiming at the problems existing in the above-mentioned background technology, the present invention provides a malicious user detection method based on feature learning and graph reasoning, which solves the problem that existing malicious user detection schemes are difficult to detect that malicious users use cooperation to designate target commodities. Questions to comment on

Images