Knowledge reasoning method and device for knowledge graph, equipment and storage medium

Abstract

The embodiment of the invention discloses a knowledge reasoning method for a knowledge graph, which comprises the following steps: acquiring an initial knowledge graph, and generating an alternative rule according to the initial knowledge graph; judging the alternative rules, and determining qualified rules of which the confidence coefficients are greater than a set threshold value; and reasoning and complementing the initial knowledge graph according to a qualification rule, obtaining a new node and a corresponding relation, and adding the new node and the corresponding relation into a graph knowledge set. According to the knowledge reasoning method of the knowledge graph provided by the embodiment of the invention, a rule reasoning method and a graph neural network reasoning method are combined, so that a hybrid reasoning framework based on a generative adversarial model is formed, and the hybrid reasoning framework is designed to realize hybrid reasoning; the nodes and the relations are predicted by utilizing a link prediction method based on a hierarchical structure, and the advantages of different reasoning methods are combined, so that the generalization ability and the calculation efficiency of knowledge reasoning are improved, and the accuracy and the interpretability of a reasoning result are also ensured.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a knowledge reasoning method, device, equipment and storage medium of a knowledge map. Background technique [0002] Knowledge reasoning refers to the process of inferring unknown facts or knowledge based on known facts or knowledge. The task of knowledge graph reasoning is to infer new knowledge or identify wrong knowledge based on the existing knowledge in the knowledge graph. Knowledge reasoning, as the main method for solving human problems, has always attracted much attention. Generally speaking, knowledge reasoning includes two main methods: one is the rule-based traditional knowledge reasoning mode; the other is the reasoning method based on graph neural network. [0003] Traditional rule-based reasoning has a good accuracy rate, but usually requires a lot of expert costs to construct business rules, and the constructed business rules are usually only appl...

AI Technical Summary

Problems solved by technology

[0003] Traditional rule-based reasoning has a good accuracy rate, but usually requires a lot of expert costs to construct business rules, and the constructed business rules are usually only applicable to specific scenarios, and the generalization ability is weak; and in large-scale multi-mode In the dynamic knowledge graph scenario, its efficiency can easily become a bottleneck

The single-step reasoning based on neural network tries to use the powerful learning ability of neural network to model knowledge map fact tuples, and obtain good reasoning ability and generalization ability, but the accuracy and rationality are difficult to guarantee, and the inherent interpretability of neural network Problems still exist in the application of knowledge graphs, how to properly explain the reasoning ability of neural networks is a big problem

Images