An automatic question answering method and system

Abstract

The invention discloses an automatic questioning and answering method and an automatic questioning and answering system, comprising the following steps: 1) a question analyzing step: separating the words of a natural question sentence and then identifying the words obtained after the words are separated by a question point / premise point identifying model so as to identify the question point and premise point of the question sentence; 2) an information retrieving step: querying an information resource library via the identified question point and premise point and extracting the query result. The information resource library is a structural information resource library. In the step 2), the question point in the question point / premise point data structure is used as a field for SQL query, and the premise point is used as a premise for SQL query. The automatic questioning and answering method and the automatic questioning and answering system enable people to understand the question better and provide correct answers by querying the structural information resource library via logic relationship of the question point and the premise point.

Description

technical field [0001] The invention relates to computer natural language processing technology, in particular to an automatic question answering method and system based on a resource library. Background technique [0002] With the popularization of the Internet, the information on the Internet is becoming more and more abundant, and now people can easily obtain all kinds of information they want through search engines. The more famous search engines are Google, Baidu and so on. Regardless of the content, these search engines can help people quickly find relevant web pages. Users only need to enter some keywords, and they will immediately search out relevant web pages. But there are many deficiencies in these traditional search engines. First, there are too many relevant information, and a large number of relevant web pages are returned, so it is difficult for users to quickly and accurately locate the required information. The second is to express the retrieval needs wit...

AI Technical Summary

Problems solved by technology

However, these traditional search engines have many deficiencies. First, there are too many relevant information, and a large number of relevant web pages are returned. It is difficult for users to locate the required information quickly and accurately.

The second is to express the retrieval needs with the combination of keywords. Since people’s retrieval needs are often very complex and special, they cannot be expressed with a simple combination of several keywords. In this way, users do not express their retrieval intentions clearly. Naturally, there is no way for search engines to find answers that satisfy users, so it is difficult to further improve the retrieval effect.

The automatic question answering method based on a fixed document library has poor scalability; while the automatic question answering method based on the Internet, the information retrieved is too redundant and may belong to multiple subject information, which affects the accuracy of the answer

[0005] A problem existing in the existing automatic question answering technology is that in the process of question analysis, only keywords are extracted to judge the type of question. low accuracy

Images