User query intention understanding method and system based on knowledge base and deep learning

Abstract

The invention discloses a user query intention understanding method based on a knowledge base and deep learning. The invention further discloses a user query intention understanding system based on the knowledge base and deep learning. The method has the beneficial effects that only a small number of seed query statements need to be labeled, so that manual labeling of a large number of sample datais avoided. The method comprises the following steps: crawling all concepts related to an intention field by utilizing the most comprehensive semi-structured knowledge base-Wikipedia at present, andtaking the concept sets as tools for intention representation to ensure that concept features in query statements are covered to the greatest extent; performing similarity matching of query statementsand Wikipedia concepts by using a deep learning model, extracting semantic vectors of texts by using a convolutional neural network (CNN) and a long short-term memory (LSTM) network. Compared with aword of bag method, the semantic vectors extracted by the method have the characteristic of low latitude and have stronger semantic feature expression ability.

Description

technical field [0001] The invention belongs to the technical field of user query intent understanding methods and systems, and in particular relates to a user query intent understanding method based on a knowledge base and deep learning, and also relates to a user query intent understanding system based on a knowledge base and deep learning. Background technique [0002] The understanding of user query intent has always been the core issue in search engine technology, and solving this problem can greatly improve user experience. At the same time, with the rise of artificial intelligence, human-computer dialogue technology has become a hot topic, and this technology also needs to rely on accurate understanding of user query intentions. Therefore, the difficult problem of how to accurately understand user query intent has attracted the attention of both academia and industry. [0003] At present, the mainstream method of query intent understanding is the machine learning met...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a user query intent understanding method and system based on knowledge base and deep learning to solve the problem that the traditional method proposed in the above background technology is usually based on the bag of words model, which has high latitude and high sparseness. The problem, the feature expression ability is very weak, and the context relationship is ignored, and the abstract semantic information cannot be extracted

Images