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

Electronic medical record named entity standardization method and system based on XLNet-BiGRU-CRF model

An electronic medical record and named entity technology, applied in the field of data processing, can solve the problems of mutual nesting of named entities, large character length, and many uncommon words, etc., to achieve the effect of ensuring speed

Pending Publication Date: 2022-06-03
INNER MONGOLIA UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are still some difficulties and challenges in the standardization of named entities in electronic medical records. Compared with general field texts, medical record named entities have (1) large character length; (2) many uncommon words; (3) nested named entities and so on
Therefore, named entity recognition of electronic medical records in the medical field has become a challenging task, and the performance of medical named entity recognition needs to be further improved

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
  • Electronic medical record named entity standardization method and system based on XLNet-BiGRU-CRF model
  • Electronic medical record named entity standardization method and system based on XLNet-BiGRU-CRF model
  • Electronic medical record named entity standardization method and system based on XLNet-BiGRU-CRF model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] First, as figure 1 As shown, the embodiment of the present invention provides an electronic medical record named entity standardization method based on the XLNet-BiGRU-CRF model, including:

[0069] S1. Acquire and preprocess the electronic medical record corpus to be identified;

[0070] S2, input the preprocessed electronic medical record corpus to be recognized into the XLNet sub-model, and obtain the first Embedding word vector, and the XLNet model includes an arrangement language model, a dual-stream attention mechanism and a Transformer-XL core component;

[0071] S3. Input the first Embedding word vector into the BiGRU-CRF sub-model, and obtain the entity recognition result corresponding to the electronic medical record corpus to be recognized;

[0072] S4, according to the entity recognition result, extract several relevant triples data with corresponding entities in the preset Neo4j database, and the triplet data is composed of the original entity, the entity ...

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 an electronic medical record named entity standardization method and system based on an XLNet-BiGRU-CRF model, a storage medium and electronic equipment, and relates to the technical field of data processing. The method comprises the following steps: respectively carrying out cosine similarity comparison on a first Embedding word vector and second Embedding word vectors corresponding to a plurality of related triple data, and taking a standard entity corresponding to a word with the highest similarity score as a target mapping entity result; and mapping the target mapping entity result to the reference table to obtain a final electronic medical record standard entity. Therefore, when the diagnosis of any doctor is retrieved, the incomplete data retrieval result caused by different habits can be avoided; therefore, the clinical input speed of a doctor is ensured, the doctor habits are met, and meanwhile, it is ensured that all different writing modes with the same medical characterization in data presentation and statistics can be identified as having the same medical meaning.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method, system, storage medium and electronic device for standardizing an electronic medical record named entity based on an XLNet-BiGRU-CRF model. Background technique [0002] Electronic medical records are medical records stored, managed and transmitted by computer information systems, including digital information about patients' medical history, clinical manifestations, and treatment methods recorded by medical staff in the process of diagnosis and treatment for patients. Because electronic medical records are mostly semi-structured and unstructured data, their analysis and data mining are severely restricted. Named entity recognition is the discovery and recognition of proper nouns and meaningful words in natural texts and classifying them into predefined categories, which is an important branch of natural language processing tasks. Using named entity recognition...

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): G16H10/60G06F40/295G06N3/04G06N3/08
CPCG16H10/60G06F40/295G06N3/08G06N3/047G06N3/048
Inventor 杨雨张培龙李华王显荣刘玉林
Owner INNER MONGOLIA UNIVERSITY
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