Intention recognition method and device under dialogue framework

Abstract

The invention provides an intention recognition method and an intention recognition device under a dialogue framework. The method comprises the steps: obtaining the matching degree of a to-be-recognized corpus and rule monomers in a preset rule template, wherein the preset rule template comprises a plurality of rule monomers, and each rule monomer corresponds to one label; judging whether a matching degree greater than a preset threshold exists or not; if so, taking the label of the rule monomer corresponding to the maximum matching degree as an intention recognition result; if not, inputtingthe corpus to be recognized into a pre-trained intention recognition model. Moreover, the output of the pre-trained intention recognition model is used as an intention recognition result. When the rule template cannot effectively recognize the user intention, the machine learning model is used for recognizing the user intention. The user intention can be accurately recognized. The requirement forthe number of training samples is low. The development of artificial intelligence equipment such as a question-answering system and a dialogue robot is promoted.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an intention recognition method and device under a dialogue framework. Background technique [0002] With the development of search engine technology, what modern search engines, question answering systems and dialogue robots need is no longer simple correlation information retrieval, but a deep understanding of users' information needs in order to accurately provide users with the services they need. Correctly identifying user intent is a critical step in achieving this goal. [0003] At present, machine learning models are mainly used to identify user intentions. Generally, hundreds of thousands of labeled samples are required to train a machine model with good recognition effect. For the early construction of question answering systems or dialogue robots, it is impossible to collect large-scale and satisfying dialogues. The corpus of the scene, so it i...

AI Technical Summary

Problems solved by technology

[0003] At present, machine learning models are mainly used to identify user intentions. Generally, hundreds of thousands of labeled samples are required to train a machine model with good recognition effect. For the early construction of question answering systems or dialogue robots, it is impossible to collect large-scale and satisfying dialogues. The corpus of the scene, so it is impossible to train a machine learning model with a good recognition effect, resulting in the inability to accurately recognize user intent; in addition, for dialog-based intent recognition, since the user input in the dialog is usually very short, it can be accurately recognized under the dialog framework. User intent is more difficult, which seriously restricts the development of artificial intelligence equipment such as question answering systems and dialogue robots

Images