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

Medical team composition method based on community discovery

A technology of community discovery and composition methods, applied in the field of machine learning, can solve problems such as non-conformity with application requirements and scattered points, and achieve the effects of promoting communication and learning, improving medical level, and optimizing medical resource allocation

Inactive Publication Date: 2018-09-07
DALIAN UNIV OF TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, only using modularity as the termination condition is not only prone to scatter problems, but also does not meet many practical application requirements.

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
  • Medical team composition method based on community discovery
  • Medical team composition method based on community discovery
  • Medical team composition method based on community discovery

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Such as figure 1 Shown the flow process of the inventive method, comprises the steps:

[0029] 1. Data collection and preprocessing

[0030] 1.1 Distributed web crawler

[0031] The distributed web crawler system is improved from the traditional centralized web crawler. Its working principle is similar to that of the centralized web crawler. The distributed web crawler system is regarded as several centralized web crawlers with certain communication and organization methods. Systems that are wired together to coordinate web crawling. Through the web crawler, two datasets are initially captured:

[0032] (1) Data set A is information about doctor’s cooperative papers (Paper_Doctor_CoAuthor.txt) captured from Wanfang Medical Network, mainly including doctor id, collaborator id and number of cooperative papers;

[0033] (2) Data set B is the team information (source.xls) of traditional Chinese medicine doctors in top three hospitals nationwide collected from the regist...

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 medical team composition method based on community discovery. The medical team composition method based on community discovery comprises the following steps that informationabout doctor cooperation papers is captured through web crawlers, information of nationwide top-three hospital doctor teams is acquired from a registration network, ID sets of doctors are used, checked, re-divided and merged to construct a relational graph; any one of SC, GN, FN and WalkTrap methods is selected to discover the community structures in the data and divide communities. On the premisethat each divided community meets the five-degree segmentation theory, results making iterated and divided communities more stable are selected for each time iteration, and finally the final resultsare visualized by using Gephi. The medical team composition method is completed by using computer software analysis, has the beneficial scientific guiding role on the construction of medical teams, isconducive to solving of the current domestic problems such as difficulty in seeking medical treatment, medical resource allocation is optimized, and the efficiency of seeking medical treatment and diagnosis and treatment are improved.

Description

technical field [0001] The present invention relates to machine learning; artificial intelligence; community discovery; data mining; social network, and more specifically relates to a medical team composition based on community discovery. Background technique [0002] FN (FastNewman) is one of the most widely used community discovery algorithms. FN can solve the subgraph partition problem of relational network. Its basic idea is to divide communities based on modularity so that there are as many connections within the same community as possible, and as few connections as possible between different communities. In this way, based on the maximum modularity, the overall best subgraph division effect can be obtained. But this feature is also easy to cause too much emphasis on modularity and ignore the separate division of nodes, resulting in many scattered points. Obviously, this result is not a representative ideal result for the division of relational network subgraphs. How...

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
IPC IPC(8): G16H50/70G06F17/30
CPCG16H50/70
Inventor 毛璐金博
Owner DALIAN UNIV OF TECH
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