Supercharge Your Innovation With Domain-Expert AI Agents!

Electronic medical record data set analysis method and system based on ernie model

A technology of electronic medical records and analysis methods, which is applied in the fields of patient-specific data, medical data mining, text database query, etc. It can solve problems such as reducing analysis costs, repeated update of extraction rules, and inability to analyze text without keywords, so as to reduce the analysis time. Cost, saving time for running-in and updating rules, and universal effects

Active Publication Date: 2020-06-26
山东浪潮智慧医疗科技有限公司
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] The technical task of the present invention is to provide an electronic medical record data set analysis method and system based on the ernie model, to solve how to overcome the dependence of the electronic medical record data set extraction process on keywords and rules, resulting in repeated update of extraction rules and inability to analyze unresolved problems. Keyword text, effectively reducing the problem of parsing costs

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 data set analysis method and system based on ernie model
  • Electronic medical record data set analysis method and system based on ernie model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] as attached figure 1 As shown, the electronic medical record data group analysis method based on the ernie model of the present invention, the method is to distinguish the data group according to the meaning of each sentence in the electronic medical record, and overcome the dependence on keywords and rules in the electronic medical record analysis process; the details are as follows :

[0080] S1. Determine different types of text data groups: According to "Electronic Medical Record Data Groups and Data Elements", a data group (Data Group) is a composite data structure formed by gathering related information items. Different types of electronic medical record texts contain different data groups; electronic medical record texts from different manufacturers and hospitals have slightly different content in the data groups; therefore, the details of data determination are as follows:

[0081] S101. Determine and extract data groups according to different types of electron...

Embodiment 2

[0113] The electronic medical record data group parsing system based on the ernie model of the present invention, the system includes,

[0114] The data group determining unit is used to determine and extract data groups according to different types of electronic medical records, and then perform data group mapping or fine-tuning according to the situation of electronic medical record texts of different manufacturers;

[0115] The data group sample extraction and marking unit is used to collect and label samples to construct a sample set after determining the electronic medical record data groups to be extracted from different types of documents; the data group sample extraction and marking unit includes,

[0116] The text random extraction module is used to randomly extract N texts from various samples to be parsed respectively;

[0117] The text block module is used to select a reasonable delimiter (usually a period or a carriage return, or multiple delimiters can be used in...

Embodiment 3

[0130] In the storage medium of the present invention, a plurality of instructions are stored therein, and the instructions are loaded by the processor to execute the steps of the method for parsing electronic medical record data sets based on the ernie model in Embodiment 1.

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 an electronic medical record data set analysis method and system based on an ernie model, and belongs to the field of natural language processing. The technical problem to be solved by the invention is how to overcome repeated update of an extraction rule caused by dependence of an electronic medical record data set extraction process on keywords and rules, and a keyword-free text cannot be analyzed. According to the method, data set discrimination is carried out according to the meaning of each sentence in the electronic medical record, and dependence on keywords and rules in the electronic medical record analysis process is overcome; the method specifically comprises the following steps: S1, determining different types of text data sets: determining an extractiondata set according to different types of electronic medical records; S2, extracting and marking data set samples, wherein after electronic medical record data sets to be extracted of different types of documents are determined, the samples are collected and marked to construct a sample set; S3, retraining a text classification model based on an ernie pre-training model; and S4, extracting the content of the data set: extracting the content of the corresponding data set by using the model trained in the step S3.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to an electronic medical record data set analysis method and system based on an ernie model. Background technique [0002] Electronic medical records are complete and detailed clinical information resources generated and recorded during a person's previous visits to a medical institution, and are the main component of current medical data. However, at present, electronic medical records are mainly in the form of text, which cannot be directly used for analysis and research. Therefore, how to accurately and effectively analyze electronic medical records and extract the content of data groups for analysis and research is an urgent problem to be solved in medical data governance. [0003] At present, the commonly used method of data group analysis is the method of keyword extraction and regular expression matching. The method is as follows: [0004] First, according to the ...

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): G16H10/60G16H50/70G06F16/33G06F16/35G06F40/30
CPCG16H10/60G16H50/70G06F16/3344G06F16/35Y02P90/30
Inventor 刘文丽
Owner 山东浪潮智慧医疗科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com