Automatic question-answering system

Abstract

The embodiment of the invention discloses an automatic question-answering system. According to the automatic question-answering system, a user interaction unit receives a question input by a user, a question analysis unit extracts keywords from the question input by the user and expands the keywords, then an information retrieval unit searches a frequently asked question bank for answers to the question according to the expanded keywords and returns the answers to related documents, and finally, according to answer extraction rules corresponding to the question type, an answer extraction unit extracts an answer according with the rules from the related documents returned by the information retrieval unit, and sends the extracted answer to the user interaction unit to be fed back to the user. Compared with an automatic question-answering system in the prior art, the automatic question-answering system can automatically expand the keywords and divide the types of the input questions, different types of questions correspond to different types, further answer search is carried out in the types, and the accuracy and diversity of answers are improved.

Description

technical field [0001] The invention relates to the technical field of computer software, in particular to an automatic question answering system. Background technique [0002] Since the 1990s, the Internet has developed rapidly all over the world, and there are more and more information on the Internet, which provides people with rich information resources. On the other hand, more and more information on the Internet has greatly promoted the development of natural language processing technology, and at the same time put forward higher requirements for natural language processing technology: people hope to quickly and accurately obtain the information you want. Although there are many search engines on the Internet that can help people search for the information they want, the current search engines still have many shortcomings and cannot satisfy people's needs for obtaining information conveniently, quickly and accurately. It is manifested in the following three aspects: ...

AI Technical Summary

Problems solved by technology

Traditional search engines return too many relevant web pages, and it is difficult for users to locate the required information quickly and accurately

For example, if a user enters a few keywords on Google, it may return thousands of web pages, and the user will waste a lot of time looking for the information he needs in these web pages

The second is to express the retrieval needs with the logical combination of keywords, because people's retrieval needs are often very complex and special, and cannot be expressed with a simple combination of several keywords, so that users do not express their own retrieval intentions Obviously, the search engine will naturally have no way to find out the answer that satisfies the user.

The third is the indexing and matching algorithm based on keywords. Although the algorithm is simple and easy to implement, after all, it stays at the surface of the language without touching the semantics, so it is difficult to further improve the retrieval effect

[0007] Second, the Internet-based automatic question answering system, the retrieved information is too redundant, and may belong to multiple subject information, the answer extraction process will be more complicated and the accuracy of the answer cannot be guaranteed

[0008] Third, the keyword matching and semantic expansion problems in retrieval, but due to the flexible expression in Chinese, the position of keywords in sentences with the same semantics is also uncertain, and the sequential matching of keywords often cannot meet the retrieval requirements. A large number of synonyms, completely different keywords in the question and answer may have the same semantics, if the semantic expansion is not carried out, the retrieval will fail, but the semantic expansion improves the recall rate of the retrieval but may reduce the accuracy of the retrieval. Intelligently classify the types of questions asked, which can improve the accuracy rate

[0009] Fourth, most of the above methods retrieve the questions in the FAQ library by inputting questions, and return the answers to the most similar questions in the FAQ library. For some open questions, the answers are often limited to a certain field, although they can be obtained. One or more common answers are often unable to provide users with diverse answers for reference

Images