Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Scientific research partner recommendation method based on multi-dimensional features under Research Gate platform

A scientific research collaborator, multi-dimensional feature technology, applied in the field of data mining and text mining, can solve the problem of occupying scientific research time of scientists

Active Publication Date: 2020-01-31
HOHAI UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, finding scientific researchers with the same or similar research interests as one's own to have a useful dialogue is a difficult task, which will take up a lot of research time of scientists

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
  • Scientific research partner recommendation method based on multi-dimensional features under Research Gate platform
  • Scientific research partner recommendation method based on multi-dimensional features under Research Gate platform
  • Scientific research partner recommendation method based on multi-dimensional features under Research Gate platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] combine figure 1The technical details of the present invention are described. ResearchGate is a platform for sharing scientific research and academic achievements based on social networks. Scientific researchers can share their latest research results on this platform, and they can also pay attention to other scientific researchers who are interested in them and conduct academic exchanges with them. The present invention is a personalized recommendation method for scientific research collaborators based on multi-dimensional features under the ResearchGate platform. The method mainly includes the following six steps: First, collect the published papers, social associations and self-influence related data of scientific research workers under the ResearchGate platform Carry out preprocessing operations; the second is to use the Doc2Vec text depth representation model to calculate the text similarity of papers between scientific researchers; the third is to establish a rel...

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 scientific research partner recommendation method based on multi-dimensional features under a Research Gate platform. According to the method, association relationships between scientific researchers and other scientific researchers are measured from three dimensions of text similarity of papers published by the scientific researchGate platform, social association degreesamong the scientific researchers and influences of the scientific researchers; and a scientific research partner recommendation model is constructed by using a linear combination method to perform Top-N recommendation, so that personalized scientific research partner recommendation services are provided for scientific research workers. Wherein text similarity calculation is carried out by utilizing a Doc2Vec text depth representation model, and weight parameters are adjusted through a stochastic gradient descent and back propagation algorithm, so that the model is optimal; the social correlation degree is calculated based on the common proportion of friends, and the higher the proportion is, the more similar the two are. Personalized scientific research partner recommendation services canbe provided for scientific research workers, and therefore the problem that scientific research partners are difficult to find is solved.

Description

technical field [0001] The invention relates to a method for recommending scientific research collaborators based on multidimensional features under the ResearchGate platform, and belongs to the technical fields of software engineering recommendation systems, data mining and text mining. Background technique [0002] Today, many scientific research projects are conducted collaboratively, and exchanges between scientists often lead to new ideas. Scientific cooperation can not only improve the creativity of scientific workers through the sharing of ideas and technologies, but also motivate scientific workers to keep moving forward and relieve the boring sense of academic work. However, finding scientific researchers with the same or similar research interests as one's own to have a useful dialogue is a difficult task, which will take up a lot of research time of scientists. Therefore, a major problem in enabling scientific collaborations is to identify scientific collaborator...

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): G06F16/9535G06F16/9536G06Q50/20G06N3/04
CPCG06F16/9535G06F16/9536G06Q50/205G06N3/045
Inventor 张鹏程邵孟巧金惠颖张雅玲于佳男
Owner HOHAI 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
Eureka Blog
Learn More
PatSnap group products