High-order logic knowledge graph representation learning method based on structural features

Abstract

The invention belongs to the field of artificial intelligence research, and provides a high-order logic knowledge graph representation learning method based on structural features. The method comprises the following steps: firstly, performing high-order logic relation feature representation on data, extracting node neighborhood structure motif degree matrixes in a graph, and taking an entity motif degree matrix in each relation as a high-order logic relation feature; secondly, performing entity attribute feature and high-order logic relation feature representation on the graph convolutional network; and finally, carrying out feature polymerization by using three different polymerization methods of Hadamard product, summation and series connection. According to the method, two knowledge graph representation learning features are fused, sample data are learned from different angles and then are used for knowledge graph downstream tasks such as entity classification and link prediction, a high-order logic knowledge representation learning method with high precision is obtained, and meanwhile, the defect that an existing knowledge representation learning method is low in complexity is overcome. The method solves the problems of insufficient expression capability, large expression loss, high calculation cost, poor interpretability and the like of high-order logic relationships such as inverse relationships and composite relationships.

Description

technical field [0001] The present invention relates to the field of artificial intelligence research, in particular to a method for learning a high-order logical knowledge graph representation based on structural features. Background technique [0002] Knowledge graph is a branch of knowledge engineering and plays an important role in the field of artificial intelligence. The working logic behind the search engines we use every day and the intelligent recommendation of e-commerce platforms all use knowledge graphs. Knowledge graphs have been proven to be an effective application basis in various application scenarios such as recommendation systems, question answering systems, semantic analysis, and dialogue systems. Entities and relationships are two essential elements for storing and representing knowledge. Subject entities, relation entities and object entities are the basic representations of knowledge, and they are represented as triples. Knowledge graph representati...

AI Technical Summary

Problems solved by technology

[0006] Based on the existing knowledge graph representation learning methods, there are problems such as insufficient ability to express high-order logical relations such as inverse relations and composite relations common in knowledge graphs, large representation loss, high computational cost, and poor interpretability.

After learning sample data from different angles, it is used for downstream tasks of knowledge graphs such as entity classification and link prediction. Compared with existing knowledge graph representation learning methods, the accuracy of downstream tasks is higher and the calculation cost is lower.

Images