Completion method and related equipment for temporal knowledge graph based on graph neural network

Abstract

The present application provides a method and related equipment for completing a temporal knowledge graph based on a graph neural network. The method includes: obtaining temporal knowledge graphs of multiple historical moments and a temporal knowledge graph at the current moment, and preprocessing each of the temporal knowledge graphs respectively; inputting all the temporal knowledge graphs that have undergone the preprocessing into a pre-trained completion model to obtain the final representation vector of each node on the temporal knowledge graph at the current moment; selecting the candidate node with the greatest similarity to the node corresponding to the final representation vector from a pre-constructed candidate set through a similarity calculation model as a completion node, and completing the temporal knowledge graph at the current moment based on the completion node. The present application provides a method and related equipment for completing a temporal knowledge graph based on a graph neural network, which can conveniently and effectively complete a temporal knowledge graph.

Images