Sentence analysis method, device, computer equipment and readable medium

Abstract

The present invention provides a sentence parsing method, device, computer equipment and readable medium, by obtaining the characteristic information of the heuristic understanding corresponding to the target sentence to be parsed; according to the characteristic information of the heuristic understanding corresponding to the target sentence, the A variety of candidate analysis results and the corresponding confidence levels of various candidate analysis results; each candidate analysis result includes candidate intentions and candidate slots; according to each candidate analysis result and the corresponding confidence level, the target understanding corresponding to the target sentence is obtained. The sentence parsing scheme of the present invention can obtain the characteristic information of the heuristic understanding corresponding to the target sentence even in the cold start stage when the training data resources are insufficient, so as to realize accurate understanding of the target sentence. Moreover, it is possible to avoid the use of fixed-format templates for sentence recognition, avoid the technical defect of poor sentence comprehension accuracy caused by weak template generalization capabilities, and effectively improve the accuracy and efficiency of sentence analysis.

Description

【Technical field】 [0001] The present invention relates to the field of computer application technology, in particular to a sentence analysis method, device, computer equipment and readable medium. 【Background technique】 [0002] Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. [0003] With the rapid development of intelligent interactive products, query statement understanding technology has received more and more attention. The goal of query statement understanding is to parse the user...

AI Technical Summary

Problems solved by technology

[0005] However, when the labeled training data resources are insufficient, the machine learning model is not suitable for cold start, and can only use manually marked templates to understand query statements, and the number of existing templates is limited, and the template format is fixed and the generalization ability is very weak, resulting in The accuracy of the existing Query statement understanding is poor

Images