Supercharge Your Innovation With Domain-Expert AI Agents!

Open source community-oriented cross-project issue participant recommendation framework

A participant and cross-project technology, applied in other database retrieval, semantic analysis, instruments, etc., can solve problems such as difficult to achieve good results, dimensionality disaster, etc., to enhance accuracy and interpretability, and improve recommendation ability Effect

Pending Publication Date: 2022-02-18
NANJING UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, without restricting the scope of developers, if the text classification method is still used, it will face the disaster of dimensionality and it will be difficult to achieve good results.

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
  • Open source community-oriented cross-project issue participant recommendation framework
  • Open source community-oriented cross-project issue participant recommendation framework
  • Open source community-oriented cross-project issue participant recommendation framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention is described in further detail now in conjunction with accompanying drawing.

[0044] Such as figure 1 As shown, an open source community-oriented cross-project issue participant recommendation framework proposed by the present invention mainly includes a data collection and text preprocessing module, an associated text semantic embedding module, an open source community entity structure embedding module and a recommendation result sorting module, figure 1 The structure diagram of the entire recommendation framework is shown, and the specific processing procedures of each module are as follows:

[0045] (1) Data acquisition and text preprocessing module

[0046] 1.1) Obtain the required open source warehouse collection R through the GitHub API, and for each warehouse r in R, obtain all its issues through the API to form a collection I r , each issue contains all the texts of the title, description and comments, and the issues of all warehouses fo...

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

Aiming at the problem that issue participant recommendation in an open source community is limited in a project, the invention provides an open source community-oriented cross-project issue participant recommendation framework, which comprises a data acquisition and text preprocessing module, an associated text semantic embedding module, an open source community entity structure embedding module and a recommendation result sorting module. According to the method, the scene characteristics of the open source community are combined, the participation of developers except for projects is expanded by utilizing the reference relationship of issue, and the accuracy and interpretability of recommendation are enhanced by utilizing the structural relationship of the open source community, so that the defects of the traditional bug shunting technology in the open source community are overcome, and the cross-project issue recommendation capability is improved. In addition, coupling of all parts of the framework is low, and an associated text semantic embedding module can be expanded into a general associated text vector embedding algorithm.

Description

technical field [0001] The invention belongs to the application field of computer software engineering, and in particular relates to an open source community-oriented cross-project issue participant recommendation framework. Background technique [0002] With the vigorous development of open source software, more and more software repositories are maintained in the open source community (such as GitHub). Everyone can submit issues in the public software repositories. Issues can help developers find software vulnerabilities, but due to the large number of Maintainers often fail to check these issues in a timely manner. Additionally, manually reviewing issues and picking the right contributors is difficult and tedious, and this situation is made worse in larger repositories. [0003] A similar problem arises in bug tracking systems (another type of open source community that typically maintains a single repository, such as Mozilla), where bug triage techniques treat this issu...

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): G06F16/9035G06F40/30G06F40/216G06K9/62G06F16/901
CPCG06F16/9035G06F40/30G06F40/216G06F16/9024G06F18/22
Inventor 汪亮江会煜陶先平
Owner NANJING UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More