Knowledge graph retrieval method and system based on knowledge base representation

Abstract

The invention discloses a knowledge graph retrieval method and system based on knowledge base representation, and the method comprises the steps: crawling knowledge information stored in an existing website, analyzing and mapping the knowledge information, and obtaining a predefined legal field knowledge base model; obtaining a natural language sequence and obtaining a natural language question according to the natural language sequence; training the predefined legal domain knowledge base model to obtain entity representation and relation representation of the predefined legal domain knowledge base model; preprocessing the natural language question to generate a continuous representation of the natural language question, recording the continuous representation as QR, and obtaining a triple representation; and performing scoring calculation on the triple to obtain a scoring result, converting the scoring result into probability distribution, and optimizing the scoring result through a teacher model and a student model to obtain a final legal field knowledge base model.

Description

technical field [0001] The present invention relates to the field of knowledge base representation, in particular to a knowledge map retrieval method and system based on knowledge base representation. Background technique [0002] The existing knowledge base is a knowledge-based and intelligent system (or expert system). Not all intelligent programs have knowledge bases, only knowledge-based systems have knowledge bases. Many applications exploit knowledge, some to a very high level, but these applications may not be knowledge-based systems nor do they have knowledge bases. The difference between a general application program and a knowledge-based system is that a general application program implicitly encodes problem-solving knowledge in the program, while a knowledge-based system explicitly expresses the problem-solving knowledge of the application domain , and form a relatively independent program entity separately. The knowledge base often has the problem of missing li...

AI Technical Summary

Problems solved by technology

Many applications utilize knowledge, some to a very high level, but these applications may not be knowledge-based systems nor do they have knowledge bases

The difference between a general application program and a knowledge-based system is that a general application program implicitly encodes problem-solving knowledge in the program, while a knowledge-based system explicitly expresses the problem-solving knowledge of the application domain , and form a relatively independent program entity separately. The knowledge base often has the problem of missing links, which limits the application of knowledge graphs in related downstream tasks. To solve this problem, the knowledge graph completion task came into being.

Images