Question answering method and device based on knowledge graph, storage medium and question answering robot

Abstract

The invention provides a question answering method and device based on a knowledge graph, a storage medium and a question answering robot. According to the method, the entities, the first-level attributes and the first-level constraint information contained in the question can be recognized for the input question, the object type attributes in the first-level attributes can serve as the second-level entities, the attributes of the second-level entities in the question are recognized, and the multi-hop attributes are obtained; the method comprises the steps of obtaining a question, identifying constraint information of a multi-hop attribute in the question to obtain a multi-hop constraint, generating a query graph containing an entity of the question, a first-level attribute, first-level constraint information, the multi-hop attribute and the multi-hop constraint, and generating a multi-constraint multi-hop query graph corresponding to the complex question aiming at the complex question with constraints and a multi-hop relationship. Through the multi-constraint multi-hop query graph, the accurate reply information corresponding to the complex question can be queried, the dialogue ability of processing complex questions with constraints and multi-hop relationships is achieved, and the reply accuracy of the complex questions with constraints and multi-hop relationships is improved.

Description

technical field [0001] The present application relates to artificial intelligence technology, and in particular to a question-answering method, device, storage medium and question-answering robot based on a knowledge map. Background technique [0002] With the development of artificial intelligence, intelligent dialogue products such as intelligent customer service Q&A robots have dialogue capabilities such as task-based Q&A, Frequently Asked Questions (FAQ for short), and Q&A based on knowledge pictures, which can replace manual Q&A to a certain extent. service, which can reduce the labor cost of the question-and-answer service and improve the efficiency of the question-and-answer service. [0003] At present, the query graph of the question answering system design based on the knowledge map defines the entity, the attribute of the entity, and the constraint, and the attribute of the entity is used to describe the entity. For complex problems with constraints and multi-hop...

AI Technical Summary

Problems solved by technology

For complex problems with constraints and multi-hop relationships, which contain a large number of attributes and constraints and complex multi-hop relationships, the multi-hop relationships that appear in the problem and the constraint attributes of constraints are easy to identify errors, resulting in query graphs In the case of multi-hop relationship errors and constraint mounting errors, the question and answer results are wrong, and the intelligent dialogue ability is insufficient. It is only suitable for single-relationship problems with constraints or multi-hop relationship problems, but it is not capable of dealing with problems with For complex questions with constraints and multi-hop relationships, the answer to complex questions with constraints and multi-hop relationships is not accurate enough

Images