Imaging diagnosis report named entity identification method based on multi-feature fusion

A named entity recognition and multi-feature fusion technology, applied in medical reports, instruments, biological neural network models, etc., can solve problems such as manual intervention

Pending Publication Date: 2020-10-27
KUNMING UNIV OF SCI & TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is vulnerable to manual intervention and has a strong dependence on dictionaries

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
  • Imaging diagnosis report named entity identification method based on multi-feature fusion
  • Imaging diagnosis report named entity identification method based on multi-feature fusion
  • Imaging diagnosis report named entity identification method based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Embodiment 1: as Figure 1-4 As shown, the named entity recognition method for image diagnosis report based on multi-feature fusion, the specific steps of the method are as follows:

[0039] Step1. First, copy the chest X-ray image report from the hospital information management system as the experimental corpus, and preprocess the corpus;

[0040] Step2. Then the preprocessed diagnostic report text data is input into the BI-LSTM network, and the optimal word segmentation result is output;

[0041] Step3. Obtain the feature vector of the optimal word segmentation result, and then send the feature vector to the CRF model to perform named entity recognition on the diagnosis report text, and train to obtain the image diagnosis report named entity recognition model based on multi-feature fusion; after obtaining the optimal acne When the feature vector of the result is obtained, the feature selection can be performed first, and then the feature calculation can be performed ...

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 imaging diagnosis report named entity recognition method based on multi-feature fusion, and belongs to the technical field of natural language processing. The method comprises the steps of firstly copying a chest X-ray film image report from a hospital information management system to serve as an experimental corpus, and preprocessing the corpus; inputting the preprocessed diagnosis report text data into a BI-LSTM network, and outputting an optimal word segmentation result; obtaining a feature vector of the optimal word segmentation result, then sending the featurevector to a CRF model to carry out named entity identification on the diagnosis report text, and training to obtain an image diagnosis report named entity identification model based on multi-feature fusion; and evaluating the obtained image diagnosis report named entity identification model, selecting an optimal model according to a test result, and performing image diagnosis report named entity identification according to the model. The named entity in the image report is effectively identified, and the final total F1 value reaches 88.03%.

Description

technical field [0001] The invention relates to a named entity recognition method of an image diagnosis report based on multi-feature fusion, and belongs to the technical field of natural language processing. Background technique [0002] The task of named entity recognition (NER) is very important, and it is of great significance for question answering systems, structured database construction, retrieval and other work. The commonly used methods of named entity recognition in the past are: using manually established rules and dictionaries as standards, and realizing the recognition of named entities through string matching. This approach is vulnerable to human intervention and has a strong dependency on dictionaries. The strategy of using machine learning is currently the mainstream method to deal with this type of problem, mainly including the maximum entropy model, the most widely used conditional random field, the support vector machine model, and the more common hidden...

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): G06F40/295G06F40/205G06F40/242G16H15/00G06N3/04
CPCG06F40/295G06F40/205G06F40/242G16H15/00G06N3/049
Inventor 黄青松唐志豪尤诚诚刘利军冯旭鹏
Owner KUNMING UNIV OF SCI & TECH
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