A concept connection method for medical diagnosis texts

A connection method and medical diagnosis technology, applied in the field of concept connection, can solve the problem of low recall rate and achieve the effect of easy transplantation and realization

Active Publication Date: 2017-02-15
广东速创数据技术有限公司
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The commonly used shortcut concept connection method is to directly extract the matching string from the synonym database. The advantage of this is that the precision rate is relatively high, but the disadvantage is that the recall rate is low

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 concept connection method for medical diagnosis texts
  • A concept connection method for medical diagnosis texts
  • A concept connection method for medical diagnosis texts

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be described in detail below in conjunction with specific embodiments.

[0020] A concept linking method for medical diagnostic texts that utilizes recurrent neural networks (RNNs) to tackle the concept linking problem, with a particular focus on summarizing unseen concepts at test time with vectorized concept symbols, sharing their characteristics, and then Multiple layers predict the entire traversal, allowing the model to satisfactorily achieve good concatenation. The method includes the following steps, such as figure 2 as shown,

[0021] The first step 201 is to construct a recurrent neural network system (RNNs), such as figure 1 As shown, the components include:

[0022] A span encoder 101, which is a 2-layer 256-unit long-short-term memory encoder. The input span is represented by a word vector (pretrained by GloVe), and a 256-dimensional element embedding es is generated. The output corresponds to the previous time step hidden sta...

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 concept connection method for medical diagnosis texts. The method employs a recurrent neural network model and simulates a series of complicated morphological and syntactic conversions employed by a rule-based system, summarizes and arranges invisible concepts during testing by using vector type concept symbols, shares the features thereof and predicts the whole traversal along multiple layers of a graph to perform concept connection. The method comprises the steps of firstly, establishing a recurrent neural network system (RNNs) which includes a span encoder, a concept encoder and a decoder; secondly, training the model, wherein the basic data source of the model is from the systematized nomenclature of medicine-clinical terms (SNOMED-CT) in a knowledge graph and input-output values; thirdly, employing a rule-based algorithm, applying a series of complicated morphological and syntactic conversions, identifying the spans of medical records accurately, and adding tags to form a big data set of correlated concepts; fourthly, performing concept connection on the results of the last step. The method has higher accuracy and a higher recall rate.

Description

technical field [0001] The invention relates to a concept connection method, in particular to a concept connection method for medical diagnosis texts. Background technique [0002] The knowledge graph (KG) organizes and stores a large amount of knowledge in a symbolic manner, which is easy to calculate and infer. However, it also has birth defects. Since the knowledge graph is handcrafted by many people, its symbolic nature makes it relatively difficult to handle. You must know that using encoded knowledge is not an easy task. In general, there are several challenges in using knowledge graphs: some concepts are either too specialized or too broad; concepts of the same attribute appear inconsistently in different parts of the graph; some concepts are ambiguous. In addition, knowledge graphs generally can only be expanded by adding new concepts and relationships, so the reconstruction cost is also quite expensive. [0003] Terminology and vocabularies are especially heavily...

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): G06F17/30G06F17/27G06F17/24G06F17/22G06N3/08G06F19/00
CPCG06F16/367G06F19/324G06F40/151G06F40/169G06F40/211G06F40/268G06F40/279G06N3/084
Inventor 朱佳武兴成肖菁
Owner 广东速创数据技术有限公司
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