Knowledge graph-based question and answer intention identification method

Abstract

The invention discloses a knowledge graph-based question and answer intention recognition method. The method comprises the steps of constructing a domain topic dictionary; constructing a template; performing part-of-speech analysis and syntactic dependency analysis on the retrieval statement; calculating the similarity between the search text and the template sample by utilizing the word vector and an LDA algorithm; on the basis of a known word vector, carrying out wider intention recognition on the basis of TextCNN to serve as a result of open information; extracting keywords from the domainmap. According to the method, intention recognition is achieved by integrating multiple methods, comprehensive retrieval of accurate answers and related information is achieved in combination with theknowledge graph of the field, and various requirements of users are met.

Description

technical field [0001] The invention relates to the technical fields of natural language processing and deep learning, and in particular, to a question-and-answer intent recognition method based on a knowledge graph. Background technique [0002] With the explosive growth of contemporary information and the rapid development of science and technology, people are no longer satisfied with the function of search engines and are no longer satisfied with the traditional mode of returning a large number of web pages or links containing relevant keywords after entering keywords in search engines. In this case, the user also needs to manually distinguish and browse in the returned results, and the redundant results often need to waste a lot of time of the user to eliminate, and the accuracy is not high. More easy-to-use search engines allow users to obtain more directional answers or related knowledge after inputting colloquial description information, which requires programs to ana...

AI Technical Summary

Problems solved by technology

[0003] Traditional intent recognition mainly uses syntax and semantic analysis, syntax dependency analysis, and template matching methods. This method requires a large number of rules to support, and the recognition accuracy is high within the specified range, but the scalability is poor. Once the rules change Reconfiguration is required, which is labor-intensive

[0004] After the large-scale development of machine learning, algorithms for classification problems such as SVM, Bayesian algorithm, and KNN have also been widely used in the field of intent recognition. In the application scenario, the text entered by the user is not a single intent, and a sentence may contain two or more intents

Images