Unlock instant, AI-driven research and patent intelligence for your innovation.

Session intention recognition method and device based on prompt learning and electronic equipment

An intent and new conversation technology, applied in the field of computer-readable media, can solve the problem of low accuracy of intent recognition, and achieve the effect of improving the accuracy.

Pending Publication Date: 2022-04-12
北海淇诚信息科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims to solve the problem that the accuracy of intent recognition is not high due to the existing conversation recognition method based solely on the pre-training model of the conversation text

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Session intention recognition method and device based on prompt learning and electronic equipment
  • Session intention recognition method and device based on prompt learning and electronic equipment
  • Session intention recognition method and device based on prompt learning and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings, and although the exemplary embodiments may be embodied in many specific forms, these should not be construed as limited to the embodiments set forth herein. On the contrary, these exemplary embodiments are provided in order to make the content of the present invention more complete and more convenient to fully convey the inventive concept to those skilled in the art.

[0031] On the premise of complying with the technical concept of the present invention, the structure, performance, effect or other features described in a specific embodiment can be combined in any suitable way into one or more other embodiments.

[0032] During the introduction of specific embodiments, detailed descriptions of structures, performances, effects or other features are intended to enable those skilled in the art to fully understand the embodiments. However, it does no...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a prompt learning-based session intention recognition method and device, electronic equipment and a computer readable medium. The method comprises the following steps: performing voice recognition and audio hidden feature extraction on session voice to obtain a session text and audio hidden features corresponding to the session voice; establishing a prompt according to the relevance between the session text and the audio hidden feature; and training a machine learning model by using the session text, the audio hidden feature, the prompt and the corresponding intention of the historical session voice, and processing the session text, the audio hidden feature and the prompt of the new session voice by using the machine learning model to identify the session intention of the new session voice. Due to the fact that prompt learning and self-supervised training based on the pre-training model are adopted, and the audio hidden features of the session voice are introduced into intention recognition, the intention recognition accuracy can be improved.

Description

technical field [0001] The present invention relates to the field of natural language understanding, in particular to a method, device, electronic device and computer-readable medium for recognizing conversational intentions based on prompt learning. Background technique [0002] With the emergence of word2vec, GPT, BERT and other models, the research and application of NLP (Natural Language Processing) technology is increasingly centered on pre-trained language models. In the prior art, it has been proposed to realize the intention recognition of type conversation by establishing a pre-training model. When the pre-training model is used for intent recognition, the conversational text is usually input into the pre-training model to generate text latent features, and then the text latent features are input into the intent recognition model to obtain the conversational intent. [0003] figure 1 is a flowchart of an existing intent recognition method. Such as figure 1 As sh...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F40/35G06K9/62G06N3/04G06N3/08G10L15/26
Inventor 马达标张常睿张依桐李蒙叶峰
Owner 北海淇诚信息科技有限公司