Natural language understanding method and travel question-answering system based on same

Abstract

The invention discloses a natural language understanding method and a travel question-answering system based on the same. The natural language understanding method is characterized in that questions are matched with questions in a syntax database, answers are extracted from a knowledge database according to functions and parameters corresponding to the questions, the syntax database contains most questions in the domain, questions out of the domain are provided through non-domain knowledge databases, the acquired answers are allowed to conform to the context when a user asks the questions by reading the related data of historical questions in a cache, and the accurate answers and related answers are provided. When the method is used for the travel question-answering system, more than 99% pf questions in the travel domain can be covered, the answers out of the travel domain can be extracted, the related answers can be provided, and tests show that accuracy can reach more than 95%.

Description

technical field [0001] The invention relates to a language understanding processing method, in particular to a natural language understanding method and a tourism question answering system based on the method. Background technique [0002] A question answering system based on natural language understanding methods can understand questions raised by users in natural language and give corresponding answers. This type of system is different from an information retrieval system. Its answer is not a list of possible answers but accurate and humanized, and the machine has a high degree of intelligence. According to the scope of the field that the question answering system deals with, it can be divided into question answering systems in the open field and question answering systems in the professional field. The open domain question answering system is a question answering system based on unstructured Internet resources; the professional field question answering system is an exper...

AI Technical Summary

Problems solved by technology

[0004] The problems existing in the existing question and answer processing based on natural language understanding are: first, the answer is obtained completely according to the semantic matching result of the question and the answer, such as patent 201310190366.5 "A Semantic Analysis Method and Device for Natural Language", if the question analysis Mistakes will inevitably affect the accuracy of the results, and the results given are irrelevant

Second, the question answering system in the professional field only provides the knowledge base within the scope of the field, for example, the patent 200810233734.9 "Answer Extraction Method for Tourism Question Answering System Based on Ontology Reasoning" only provides the tourism ontology knowledge base, and cannot answer questions beyond the scope, or It is impossible to get an answer when the question is not clear, and the user experience is poor

Third, the answer mode is one question and one answer. Generally, the content of the user's historical questions is not considered, that is, it can only answer the questions raised by the question itself, so the answers obtained are sometimes not the results expected by the users.

Images