Automatic question and answer generation method and system, terminal and readable storage medium

Abstract

The invention discloses an automatic question and answer generation method and system, a terminal and a readable storage medium, and overcomes the defect of insufficient coding capability of an incomplete knowledge graph in the prior art through a global normalized graph attention network, a coarse and fine granularity combined rich semantic text reading network and a problem and entity relationship deep interaction network, rich semantic text information is insufficient, and deep interaction between problems and entity relations is lacked. The accuracy of the question and answer result is improved; meanwhile, through a text content reading module combining coarse and fine granularities, on the basis of utilizing entities in the text and related information, relationship characteristics among the entities implied in the text can be further mined to complete the knowledge graph. And finally, a bidirectional attention network is utilized to carry out deep information interaction on the user question and the entity so as to find the entity more related to the user question.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, and relates to an automatic question and answer generation method, system, terminal and readable storage medium. Background technique [0002] Since Google proposed the concept of knowledge graph in 2012, a large number of knowledge graphs at home and abroad have been gradually developed and publicly released to provide auxiliary basis for big data analysis and reasoning, such as Freebase, Wikidata, Google Knowledge Graph, and OpenKG. These knowledge graphs play an important role in improving the interpretability of artificial intelligence algorithms, and also play an important role in the fields of automatic question answering, information retrieval, information extraction and human-computer dialogue based on knowledge graphs. However, since the construction of the knowledge graph requires a lot of manual annotation, and has strict specification requirements for the data format of the "...

AI Technical Summary

Problems solved by technology

Although the graph attention network has a better ability to encode graph structures, in the context of question answering based on knowledge graphs, the original graph attention network cannot distinguish the knowledge relations in the knowledge graph that are highly relevant to the user's question domain.

Therefore, the semantic information of related entities and relationships contained in the text information is further used to complete the entity relationship in the knowledge graph. However, the existing methods do not take into account the full capture of the hidden relationship information in the text, especially It does not take into account that the interaction between questions and relevant evidence in automatic question answering tasks has an extremely important impact on the quality of automatically generated answer results

Images