Weighted hypergraph-based same user identification method

Abstract

The invention provides a weighted hypergraph-based same user identification method. The method comprises the following steps of step 1, constructing a weighted hypergraph model; step 2, calculating node topological structure similarity; step 3, further identifying the same user by utilizing cross matching; the method comprises the following specific steps: step 1.1, finding nodes and friend relations in a network topology, dividing the nodes into the same hyperedge, and endowing a weight p, if the nodes and the friend relations exist in the network topology, establishing a weighted hyperedge,reconstructing two social network topological structures by utilizing the weighted hyperedge, and describing the topological structure of an original network more accurately. The weighted hypergraph is used for representing the relation between the nodes in the network, the topological structure where the nodes are located is accurately represented, the accuracy of node similarity calculation is improved, and therefore the accuracy and the recall rate of the same user identification method are obviously improved.

Description

technical field [0001] The invention relates to a method for identifying the same user based on a weighted hypergraph, which belongs to the field of information security. Background technique [0002] Over the past decade, many types of social networking sites have emerged and contributed enormously to the vast amount of data on real-world social behavior. For example, Twitter, Sina Weibo, Facebook, WeChat, etc. have all played important roles, and hundreds of millions of users are using these social media networks every day. Due to the diversity of online social media networks (SMNs), people tend to use different SMNs to achieve different social experiences. Clearly, research across social media platforms can address many theoretical and applied questions. However, identifying the same user across social networks remains a challenge. While no solution can identify all the same anonymous SMN users, some SMN elements can be used to identify a subset of users across multipl...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that the accuracy of network node topology representation is insufficient, and the algorithm performance is low. In order to overcome the deficiencies of the prior art, a method for identifying the same user based on a weighted hypergraph is provided.

Images