Intention classification method and device, intelligent terminal and storage medium

Abstract

The invention discloses an intention classification method and device, an intelligent terminal and a storage medium, and the method comprises the steps: obtaining a target text; performing named entity recognition based on the target text to obtain a named entity recognition result; based on the named entity recognition result, normalizing the target text to obtain a normalized text sentence pattern as a normalized processing result; performing intention classification based on the target text and the normalization processing result; and outputting a result of the intention classification. According to the scheme, intention analysis does not need to be performed based on a template, and intention classification performance can be enhanced by combining sentence pattern features of the text;therefore, intention classification does not depend on a template and is not affected by data scale and data quality, the problem that text features are forgotten during classification can be relieved, and the accuracy of intention classification can be improved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to an intention classification method, device, intelligent terminal and storage medium. Background technique [0002] With the rapid development of artificial intelligence technology, various application products based on dialogue systems are gradually increasing, and the demand for voice interaction is also increasing. A dialogue system is a human-computer interaction system based on natural language. Through the dialogue system, users can use natural language to interact with the computer in multiple rounds to complete specific tasks. At present, dialogue systems are widely used in different fields, such as search, intelligent question answering, sentiment analysis, etc. Among them, natural language understanding is the core module of dialogue systems. The goal of natural language understanding is to convert the text information of natural language in...

AI Technical Summary

Problems solved by technology

[0005] In the prior art, template-based intent classification relies heavily on template coverage, and is easily affected by data scale and data quality; when combining text context information for intent classification, it is easy to forget some text features, which affects the accuracy of intent classification results Technical problem, the present invention provides an intention classification method, device, intelligent terminal and storage medium, which can obtain the target text; perform named entity recognition based on the above target text, and obtain the named entity recognition result; based on the above named entity recognition result, the above-mentioned Perform normalization processing on the target text, obtain the normalized text sentence pattern as the result of the normalization processing; perform intent classification based on the above target text and the above normalization processing results; output the above result of the intent classification

Images