Medical named entity identification method and system

A technology named entity recognition and entity, which is applied in the field of entity recognition to achieve the effect of improving recognition accuracy and enriching semantic features

Active Publication Date: 2021-09-03
SHANDONG NORMAL UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the difference between Chinese expression and English expression, there is a problem of word segmentation in Chinese, so most of the syntactic analysis at this stage is concentrated on English

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 named entity identification method and system
  • Medical named entity identification method and system
  • Medical named entity identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Embodiment 1 of the present disclosure provides a medical named entity recognition method, including the following process:

[0050] First, the XLnet pre-training model is used to generate an embedding vector, which integrates contextual features and has rich semantic information.

[0051] Second, a graph convolutional neural network is used to model the local dependencies of nodes in the syntactic analysis results to generate embedding vectors, which provide richer semantic features for named entity recognition tasks,

[0052] Finally, the dynamic stacking network is used to superimpose the network according to the number of layers of entity nesting, and the nested entities in the sentence are dynamically stacked to identify, and the characteristics of the embedded entities are used to help the identification of external entities, thereby solving entity nesting The problem.

[0053] Such as figure 1 As shown, the network architecture is composed of embedded modules and...

Embodiment 2

[0150] Embodiment 2 of the present disclosure provides a medical named entity recognition system, including:

[0151] The data acquisition module is configured to: acquire medical text data to be identified;

[0152] The word embedding vector acquisition module is configured to: obtain the word embedding vector in at least one sentence according to the medical text data obtained;

[0153] The feature vector extraction module is configured to: carry out the grammatical role labeling of the phrases in the sentence, combine the dependency relationship between the phrases, obtain the relationship diagram between the phrases, and obtain the feature vector according to the preset graph convolutional neural network;

[0154] The vector splicing module is configured to: splice the obtained word embedding vector and feature vector to obtain the spliced ​​input vector;

[0155] The entity recognition module is configured to obtain a medical named entity recognition result according to ...

Embodiment 3

[0158] Embodiment 3 of the present disclosure provides a computer-readable storage medium on which a program is stored, and when the program is executed by a processor, the steps in the medical named entity recognition method as described in Embodiment 1 of the present disclosure are implemented.

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 provides a medical named entity identification method and system. The method comprises the following steps: acquiring to-be-identified medical text data; obtaining a word embedding vector in at least one sentence according to the obtained medical text data; carrying out grammatical role marking of phrases in the sentences, obtaining a relation graph between the phrases in combination with the dependency relation between the phrases, and obtaining feature vectors in a convolutional neural network according to a preset graph; splicing the obtained word embedding vector and the feature vector to obtain a spliced input vector; and obtaining a medical named entity recognition result according to the spliced input vector and a preset dynamic stacking network. The reason of adopting the dynamic stacking network is to solve the problem of entity nesting, and the recognition precision of the medical named entities is greatly improved.

Description

technical field [0001] The present disclosure relates to the technical field of entity recognition, in particular to a medical named entity recognition method and system. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] Currently, with the emergence of a large amount of electronic medical record data, the availability of health information in electronic format is a strategic choice for improving the quality and reducing the cost of healthcare across the medical field. In recent years, the healthcare system has made a major breakthrough in electronic medical records. Substantial benefits that can be realized through the use of electronic health records include improvements in quality, safety and efficiency, as well as increased capacity for education and research. Nonetheless, there are still many hurdles to overcome in the process of dat...

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): G06F40/295G06F40/205G06F40/253G06N3/04G16H10/60
CPCG06F40/295G06F40/205G06F40/253G16H10/60G06N3/045Y02D10/00
Inventor 王红韩书李威庄鲁贺张慧余盛朋王正军杨杰杨雪滑美芳于晓梅
Owner SHANDONG NORMAL UNIV
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