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

An online medical text symptom recognition method based on part-of-speech incremental iteration

A technology of incremental iteration and recognition method, which is applied in the field of online medical text symptom recognition, can solve problems such as unsatisfactory recognition effect, and achieve the effect of improving method performance, reducing burden, and reducing human work

Active Publication Date: 2022-07-22
KUNMING UNIV OF SCI & TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These traditional symptom recognition methods cannot solve the difficulty of symptom recognition in medical questions and answers, and the recognition effect is not ideal

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
  • An online medical text symptom recognition method based on part-of-speech incremental iteration
  • An online medical text symptom recognition method based on part-of-speech incremental iteration
  • An online medical text symptom recognition method based on part-of-speech incremental iteration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Example 1: as Figure 1-4 As shown, an online medical text symptom recognition method based on part-of-speech incremental iteration, the specific steps of the method are as follows:

[0037] Step1. Use the crawler program to crawl all the questions from November 20, 2018 to November 25, 2018 from the orthopaedic consultation section of six health websites such as "39 ​​Ask a Doctor" and "Haowenkang.com", and The texts of unknown diseases in orthopaedics are obtained by manual classification as experimental corpus, and then the corpus is preprocessed, and a word vector model is generated;

[0038] Step 2. Determine the location of the symptom entity; after the preprocessing operation in Step 1, the location of the symptom entity is determined by identifying the basic symptom words, and the recognition of the basic symptoms is regarded as a classification problem with words as a unit rather than a sequence labeling problem;

[0039] Step 3. Determine the boundary of symp...

Embodiment 2

[0059] Example 2: as Figure 1-4 As shown, an online medical text symptom recognition method based on part-of-speech incremental iteration, the specific steps of the method are as follows:

[0060] Step1. Use the crawler program to crawl all the questions from November 20, 2018 to November 25, 2018 from the orthopaedic consultation section of six health websites such as "39 ​​Ask a Doctor" and "Haowenkang.com", and The texts of unknown diseases in orthopaedics are obtained by manual classification as experimental corpus, and then the corpus is preprocessed, and a word vector model is generated;

[0061] Further, the specific steps of the step Step1 are as follows:

[0062] Step1.1. Use the crawler program to crawl all the questions from November 20, 2018 to November 25, 2018 from the orthopaedic consultation section of six health websites such as "39 ​​Ask a Doctor" and "Haowen Kang.com" ,;

[0063]Step1.2. Filter and deduplicate the crawled questions to obtain non-repetiti...

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 relates to an online medical text symptom recognition method based on part-of-speech incremental iteration, and belongs to the technical field of computer natural language processing. The present invention includes steps: firstly, basic symptom identification is completed through a feature fusion-based classification model to determine the location of symptom entities; then, according to the composition pattern of symptom entities, the basic symptom words are used as the center to perform incremental iterations before and after using corresponding parts of speech to determine symptoms The boundary of the entity is used to complete the symptom entity recognition; finally, the symptom recognition result is obtained by merging all the symptom entities. The method effectively recognizes complex and long symptoms in online medical texts, and its accuracy is about 5.4% higher than that of traditional medical named entity recognition methods.

Description

technical field [0001] The invention relates to an online medical text symptom recognition method based on part-of-speech incremental iteration, and belongs to the technical field of computer natural language processing. Background technique [0002] Symptom entity recognition in medical question and answer is a difficult problem for two reasons: First, compared with the extraction of medical entities such as diseases and examinations, there is no standard symptom database available for the extraction of symptom entities, and the construction of medical question and answer is more time-consuming. It is laborious; second, when patients describe symptoms, due to individual differences, the expressions of symptoms are often rich and varied, and the oral language is serious. Therefore, the general symptom entity recognition methods often have inaccurate identification boundaries in medical question answering, resulting in the inability to completely identify complex and long sym...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/295G06F40/242G06F16/35G06F16/951G06N3/04G16H80/00G16H50/20
CPCG06F16/355G06F16/951G16H80/00G16H50/20G06F40/242G06F40/295G06N3/044G06N3/045
Inventor 黄青松尤诚诚余慧刘利军冯旭鹏
Owner KUNMING UNIV OF SCI & TECH
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