Link prediction method based on network structure and text information

Abstract

The invention relates to the technical field of computer networks, and discloses a link prediction method based on a network structure and text information, and the method comprises the steps: S1, obtaining a structure embedding vector of a node based on a random walk node in the network structure; s2, constructing a convolutional neural network to process the text information of the nodes to obtain text information embedding vectors of the nodes; s3, performing joint embedding on the structure embedding vector and the text information embedding vector of the node; s4, generating a training set and a test set; s5, constructing a neural network for binary classification learning; s6, training a neural network; and S7, result prediction: the link prediction method based on the network structure and the text information is simple in calculation process, small in error and high in prediction accuracy.

Description

technical field [0001] The invention relates to the technical field of computer networks, in particular to a link prediction method based on network structure and text information. Background technique [0002] Link prediction methods refer to, for a complex system composed of interacting elements, inferring new relationships or still unknown interactions between entity pairs based on their attributes and currently observed links. In a complex network, a node interacting with different nodes can express different aspects and produce different results. For example, in a social networking site, a user has different topics and interests with different friends. In academic work, research topics vary among different researchers. The existing link prediction methods are generally divided into methods based on similarity, methods based on likelihood probability statistics, and methods based on machine learning. The first approach tends to form connections with other similar node...

AI Technical Summary

Problems solved by technology

The first approach tends to form connections with other similar nodes, but is often inefficient, computationally complex, and difficult to scale to large networks

The second method needs to create the system information of the entire network, and the computational complexity is also high

However, these network embedding methods simply use the word embedding method to obtain the static low-dimensional vector of the node, and do not consider the context information well, and accurately consider the semantic relationship between nodes

Images