Knowledge-based deep medical problem routing method and system

A problem and knowledge technology, applied in the field of knowledge-based in-depth medical problem routing methods and systems, can solve problems such as misdiagnosis

Active Publication Date: 2019-10-11
SHANDONG UNIV
View PDF10 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even minor misunderstandings can lead to misdiagnosis

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
  • Knowledge-based deep medical problem routing method and system
  • Knowledge-based deep medical problem routing method and system
  • Knowledge-based deep medical problem routing method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] The purpose of this embodiment is to seek a knowledge matching method between questions and doctors based on deep learning and knowledge maps. The name is Deep Medical Question Routing (referred to as DMQR). The overall structure of the model is as follows image 3 shown.

[0036] In order to achieve the above purpose, this embodiment discloses a knowledge-based in-depth medical problem routing method, such as figure 1 shown, including the following steps:

[0037] Step 1: Receive training data, which includes paired training medical questions and corresponding doctor data;

[0038] Step 2: Low-dimensional vector representation of all medical problems in the training data;

[0039] Step 3: Take the low-dimensional vector representation of the training medical problem as input, and the corresponding doctor problem as output, train the deep neural network, and obtain the deep medical problem routing model;

[0040] Step 4: Receive test medical questions and perform low...

Embodiment 2

[0098] The purpose of this embodiment is to provide a knowledge-based in-depth medical problem routing system.

[0099] In order to achieve the above purpose, this embodiment provides a knowledge-based in-depth medical problem routing system, including:

[0100] The model training module receives training data, which includes paired training medical problems and corresponding doctor data; calls the feature representation module to perform low-dimensional vector representation of all medical problems in the training data; the low-dimensional vector representation of the training medical problems Dimensional vector representation as input, corresponding doctor questions as output, training deep neural network, and obtaining deep medical problem routing model;

[0101] The model application module receives the test medical question, calls the feature representation module to perform low-dimensional vector representation; inputs the low-dimensional vector representation of the tes...

Embodiment 3

[0110] The purpose of this embodiment is to provide an electronic device.

[0111] In order to achieve the above object, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the program, it realizes:

[0112] Step 1: Receive training data, which includes paired training medical questions and corresponding doctor data;

[0113] Step 2: Low-dimensional vector representation of all medical problems in the training data;

[0114] Step 3: Take the low-dimensional vector representation of the training medical problem as input, and the corresponding doctor problem as output, train the deep neural network, and obtain the deep medical problem routing model;

[0115] Step 4: Receive test medical questions and perform low-dimensional vector representation;

[0116] Step 5: Input the low-dimensional vector representation of the test medical question into the ...

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 a knowledge-based deep medical problem routing method and system, and the method comprises the steps: receiving training data which comprises paired training medical problems and corresponding doctor data; performing feature representation on all medical problems in the training data; training a deep neural network by taking the low-dimensional vector representation of thetraining medical problem as input and the corresponding doctor problem as output to obtain a deep medical problem routing model, wherein the deep medical problem routing model is used for matching doctors for medical problems, and the step of carrying out feature representation on the medical problem comprises the sub-steps of respectively carrying out word segmentation and medical entity extraction on the medical problem to obtain text channel representation and knowledge channel representation; and splicing the text channel representation and the knowledge channel representation to obtain afinal representation of the medical problem. According to the method, the medical problems are described based on texts and knowledge, the matching relationship between the problems and doctors is constructed, and the method is more persuasive and credible.

Description

technical field [0001] The invention relates to the technical field of medical data processing, in particular to a knowledge-based deep medical problem routing method and system. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] The purpose of question routing is to find suitable answerers to answer newly posted questions in the Q&A community. From the perspective of questioners, question routing technology can help them find suitable answers in a short period of time, so as to reduce the waiting time for answers; from the perspective of answerers, question routing technology can pre-screen for them Questions about their professional abilities; from the perspective of a question-and-answer website, question routing technology can increase the participation of questioners and answerers at the same time, and the efficiency of website operati...

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): G16H50/20G06N3/04G06N3/08
CPCG06N3/049G06N3/08G16H50/20
Inventor 陈竹敏孙文超任鹏杰马军任昭春
Owner SHANDONG 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