Query Intent Recognition Based on Multi-Class Features

In order to enhance the user search experience of the search engine, an intent recognition search based on natural language input is proposed. By using reality mining technology to obtain the potential consciousness information from the query expression, search engines can better predict the query results that meet users’ requirements. With the development of conventional machine learning and deep learning, it is possible to further improve the accuracy of prediction results. This paper adopts a similarity calculation method based on long short-term memory (LSTM) and a traditional machine learning method based on multi-feature extraction. It is found that entity features can significantly improve the accuracy of intention classification. Second, the accuracy of intention classification based on the feature sequence constructed by key entities is up to 94.16% in the field of manual labeling by using the BiLSTM classification model.