A clinical medical entity and an attribute extraction method thereof

An entity and attribute technology, applied in the field of auxiliary clinical medical decision-making, to achieve the effect of super high representation ability

Active Publication Date: 2019-05-24
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF7 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem of extracting clinical medical entities and their attributes, the present invention provides two joint learning methods for extracting clinical medical entities and their attributes

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
  • A clinical medical entity and an attribute extraction method thereof
  • A clinical medical entity and an attribute extraction method thereof
  • A clinical medical entity and an attribute extraction method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0140] The clinical medical entity and its attribute joint extraction method of the present invention are described in detail below in conjunction with the accompanying drawings:

[0141] Such as figure 1 As shown, the specific embodiment of the present invention is: the joint extraction of clinical medical entities and their attributes can adopt the "serial joint" method, and its neural network architecture includes the following three parts:

[0142] Sentence representation module: mainly solves the problem of vector representation of input sentences. This layer merges word vectors and part-of-speech vectors into the sentence representation module through step 1, and the output sentence representation vectors flow into the clinical medical "entity / attribute" recognition and clinical medical "entity-attribute" relationship extraction modules through step 2 and step 3 respectively;

[0143] Clinical medical "entity / attribute" identification: mainly complete the identification...

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 a clinical medical entity and an attribute extraction method thereof. The method comprises the following three modules: (1) preprocessing; (2) comprehensive expression of information of the sentences; and (3) joint learning of the clinical medical entity and attribute extraction thereof. The joint learning method mainly comprises two modes: (1) a serial joint mode; and (2)a parallel combination mode. The serial combination mode is divided into three sub-modules: (1) identification of'entities / attributes' of clinical medical treatment; (2) extracting an entity-attribute relation of clinical medical treatment; (3) joint learning. The parallel combination mode is that a sequence labeling method is adopted to carry out clinical medical entity and attribute combinationextraction. The method is of great significance to clinical medical aid decision making, clinical medical research and the like.

Description

technical field [0001] The invention relates to a clinical medical entity and an attribute extraction method thereof, which are mainly used in clinical medical knowledge mining of intelligent medical treatment, and assisting clinical medical decision-making. Background technique [0002] With the continuous development of medical and health services towards informatization and intelligence, a large amount of clinical medical data has been accumulated. These data contain a large amount of medical knowledge and patient health information, which can greatly promote the innovation and development of medical knowledge, evidence-based medical care, clinical assistance, and medical decision-making. Unstructured clinical medical data contains a large number of professional terms. Above all, information extraction becomes the first step in mining medical knowledge. The extraction of medical entities and their attributes is the key content. The extraction of medical entities and their...

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 Applications(China)
IPC IPC(8): G06F17/27G16H50/70
CPCY02A90/10
Inventor 汤步洲石雪陈清财王晓龙熊英蒋德焕
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap