Statement extraction method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention relates to the technical field of natural language processing, and discloses a statement extraction method and device, electronic equipment and a computer readable storage medium. The statement extraction method comprises the steps that to-be-processed text information is acquired; wherein the to-be-processed text information comprises text information converted and generated according to acquired voice information; inputting the to-be-processed text information into a pre-trained statement partitioning model to obtain a plurality of candidate statements; filtering the plurality of candidate statements according to a preset filtering rule to obtain and output a target statement; wherein the target statement is the statement remaining after filtering in the candidate statements, the statement extraction method provided by the embodiment of the invention can scientifically, reasonably and accurately extract the core statement capable of representing the real intention of the user from the text information, so that high-quality service meeting the actual needs of the user is provided for the user.

Description

technical field [0001] The embodiments of the present application relate to the technical field of natural language processing, and in particular to a sentence extraction method, device, electronic equipment, and computer-readable storage medium. Background technique [0002] Natural Language Processing (Natural Language Processing, referred to as: NLP) is an important direction in the field of computer science and artificial intelligence. It is a technology that realizes effective communication between humans and computers through natural language. , computer science, and mathematics. The content of natural language processing research includes but is not limited to text classification, information extraction, automatic summarization, intelligent dialogue, topic recommendation, machine translation, keyword recognition, knowledge base construction, deep text representation, Named entity recognition, text generation, etc., and the rise of natural language processing technolog...

AI Technical Summary

Problems solved by technology

[0004] However, in actual use, due to the influence of factors such as external noise and Voice Activity Detect (Voice Activity Detect, referred to as: VAD) truncation, the text information received by the natural language understanding module is very messy and unsatisfactory, that is, the output of the speech recognition module Text information does not necessarily represent the user's real intention, which makes the natural language understanding module unable to accurately understand the user's real intention, and eventually causes the services provided by the smart device to fail to meet the actual needs of the user, which brings bad use to the user. to experience

Images