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

A personalized recommendation method for software projects for open source communities

A technology for software projects and recommended methods, applied in software maintenance/management, instrumentation, demand analysis, etc., can solve problems such as low accuracy, aggravate waste of human resources, and developer distrust, and achieve the goal of lowering the threshold and improving efficiency. Effect

Active Publication Date: 2020-08-21
YANGZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, if a developer is good at one development direction, it is also likely to be able to speak multiple languages ​​in this development direction.
This kind of coarse-grained recommendation is not only not accurate, but also leaves an impression of distrust to developers, further aggravating the waste of human resources

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 personalized recommendation method for software projects for open source communities
  • A personalized recommendation method for software projects for open source communities
  • A personalized recommendation method for software projects for open source communities

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Technical thinking of the present invention is:

[0030] The TF-IDF feature extraction is performed on the project content, combined with the user's evaluation of known projects, and similar projects that combine the user's personality and project needs are recommended to the user. When recommending related items, on the one hand, according to user personality, the candidate recommendation results are calculated through ALS collaborative filtering. On the other hand, each item feature is calculated using word frequency-inverse text frequency, and candidate recommendation results are calculated according to the similarity of item features. Then linearly combine the two recommendation results, perform filtering and ranking, and generate recommendation results. Finally, the word frequency-inverse text frequency is used as a label to make a reasonable explanation for the recommendation results. Such as figure 1 shown.

[0031]Term Frequency-Inverse Document Frequency (T...

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 open source community-oriented software item personalized recommendation method. The present invention performs TF-IDF feature extraction on item content, combines user evaluation of known items, recommends similar items combined with user personality and item requirements, and calculates candidate recommendation results through ALS collaborative filtering for user personality, using word frequency-inverse text Calculate the feature of each item by frequency, calculate the candidate recommendation result according to its similarity, linearly combine the two recommendation results, perform filtering and ranking, and generate the recommendation result. The invention overcomes the defects that the past recommendation technology cannot fully reflect the item characteristics, the granularity is not fine, and the accuracy rate is not high. The present invention recommends similar items aimed at the user's personality and item content from the perspective of the user's rating of known items and item content, accurately recommends item content similar to the item developed by the user, and realizes the personalized recommendation function. Reference or reuse is facilitated, increasing the efficiency of developers searching for projects.

Description

technical field [0001] The invention belongs to the field of software maintenance recommendation, in particular to a software project personalized recommendation method for open source communities. Background technique [0002] Due to the large number of software projects, according to the statistics of Github, the largest open source software community at present, as of 2016, Github has more than 14 million registered users and 35 million code warehouses. As of 2014, there are 68 warehouses on Github with more than 10,000 stars, 10 warehouses with more than 8,000 forks, and 944,872 warehouses with more than 1 forks. It can be seen that the distributed development of software has become a trend. Developers have different personalities and have different needs for projects. If there is no good recommendation mechanism, there will be serious problems such as waste of human resources. The recommendation task of recommending similar items based on user personality and item need...

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 Patents(China)
IPC IPC(8): G06F8/10G06F8/70G06F40/216G06F16/9535
CPCG06F8/10G06F8/70
Inventor 孙小兵徐文远李斌李云
Owner YANGZHOU UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com