Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Medical dialogue system intention recognition and classification method based on deep learning

A dialogue system, recognition and classification technology, applied in the direction of character and pattern recognition, healthcare informatics, text database clustering/classification, etc., can solve the problems of limited and unstable classification ability, and achieve reasonable results in the medical direction

Active Publication Date: 2019-08-09
挂号网(杭州)科技有限公司
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Most of the existing classification methods for intent recognition are based on a single model, and the classification ability is limited and unstable

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
  • Medical dialogue system intention recognition and classification method based on deep learning
  • Medical dialogue system intention recognition and classification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The following describes the present invention in detail according to specific implementations, and the purpose and effects of the present invention will become more apparent.

[0026] like figure 1 Shown, the inventive method comprises the steps:

[0027] 1) According to the user's doctor-seeking habits and the capabilities of the medical dialogue system, the scope of intentions is clarified, and there are five intentions identified as finding a doctor, finding a hospital, finding a department, looking for content, and non-medical related. The relevant meanings of intentions are as follows:

[0028] Find a doctor: The user wants to find the corresponding doctor according to the relevant symptoms and diseases;

[0029] Find a hospital: The user wants to find the corresponding hospital according to the relevant symptoms and diseases;

[0030] Find a department: Users can identify the department to look for when they ask questions about the name of the disease, descripti...

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 medical dialogue system intention recognition and classification method based on deep learning. A large number of existing medical related information is utilized to learn the relation between words, questions in a large number of medical directions and non-related questions are collected, intention labeling is conducted on the questions through professionals, a recurrentneural network model based on an attention mechanism is trained, and a model result is fused to give an intention classification result. Direction support is provided for the medical dialogue systemin response to user requirements, and intention directions are provided for related intention ranges. When only a few functions in the intention range are needed, the corresponding most conforming intention can be identified. The medical dialogue system is more reasonable in the medical treatment direction and conforms to the user expectation.

Description

technical field [0001] The present invention relates to deep learning technology and natural language processing technology, in particular to a classification method for intent recognition in medical dialogue systems. Background technique [0002] In recent years, automated human-machine dialogue systems have gained considerable attention in both academia and industry. Since 2014, the release of dialogue products such as Microsoft Xiaobing and Baidu Dumi, as well as the establishment of a large number of artificial intelligence companies, the technologies behind these dialogue systems are constantly accumulating and deciphering. With the deepening of researchers' exploration, the dialogue system has gradually moved from science fiction movies to the possibility of real life. [0003] Products such as Microsoft Xiaobing are not sensitive to medical vocabulary and medical problems. Even if medical problems are recognized, the answers are relatively simple. The dialogue syste...

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): G06F16/332G06F16/35G06F16/36G16H80/00G06K9/62
CPCG06F16/3329G06F16/35G06F16/367G16H80/00G06F18/2411
Inventor 毛葛永孟海忠吴边尹伟东任宇翔柴鹏飞陈雪魁杨昭祥王蔚
Owner 挂号网(杭州)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com