Question recommending method and system

Abstract

The invention relates to a question recommendation method and a system. The method which is applied in an interactive QA system and is used to recommend questions to answering users comprises the following steps: ascertaining the degree of correlation between the questions to be answered and the question history of the answering users or the questions which have been answered a moment ago according to a plurality of questions to be answered put forward by questioning users and stored in the system; recommending and displaying the questions to be answered with the degree of correlation over a preset threshold to the answering users. The method provided by the invention not only can rapidly recommend the most correlated questions to be answered to the answering users for answering but also can keep equalization of the questions, thereby ensuring that the questions are not beyond the answering capability of the answering users, preventing the questions from missing the chance of being answered by other answering users due to accumulation in an answering user. Furthermore, with one answering user continuously answering questions, the ability value of the answering user is updated in different periods of time, thereby regulating the number of the acceptable recommended questions in next period of time.

Description

technical field [0001] The invention relates to an interactive question answering system, in particular to a question recommendation method and system. Background technique [0002] With the rapid development of information technology, users can obtain more and more information through channels such as networks and databases. However, in the existing retrieval method of only inputting retrieval terms through a search engine, since it retrieves too much irrelevant content, the workload of the user's screening is relatively large, and the retrieval hit rate is low. Therefore, new information acquisition methods such as interactive question-and-answer systems have emerged. Users can directly ask questions in free text form, and the system undertakes the work of classifying and searching in the huge answer database, or other online users answer. That is, users who log in to the interactive question-and-answer system achieve the purpose of learning and solving doubts by asking a...

AI Technical Summary

Problems solved by technology

However, the existing method of searching only by inputting search terms through a search engine has too much irrelevant content retrieved, the user has a large screening workload, and the retrieval hit rate is low.

Images