Open source software project hatching state prediction method based on multiple features

A technology of open source software and forecasting methods, applied in forecasting, computer components, data processing applications, etc., can solve problems such as the inability to realize open source software incubation status prediction, and achieve the effect of solving industry needs

Active Publication Date: 2018-01-30
ZHEJIANG UNIV OF TECH
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiency that the existing technology cannot realize the prediction of the incubation state of open source software (OSS) projects, the present invention provides a method for predicting the incubation state of open source software projects based on multi-features, which not only combines the initial attribute characteristics of the project, but also extracts network Features are used together for training and prediction. By extracting the network features and related attribute features of open source software projects in the early stage, machine learning algorithms are used to predict the future development results of the project (project incubation success or failure)

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 software project hatching state prediction method based on multiple features
  • Open source software project hatching state prediction method based on multiple features
  • Open source software project hatching state prediction method based on multiple features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0053] refer to figure 1 and figure 2, a multi-feature based open source software project hatching state prediction method, the present invention carries out instance analysis on the Apache data set, and the original data includes information such as the number of participants of the project, the project ID, the number of files submitted. In this patent, we extract the programmer ID, the number of emails for the project, and the number of file submissions.

[0054] The present invention is specifically divided into the following four steps:

[0055] Step 1: Collect historical data on Apache project file submissions and email exchanges;

[0056] Step 2: According to the historical data of the pre-set time period (5 months) of the project, build a social network for project members;

[0057] Step 3: Extract the attrib...

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 provides an open source software project hatching state prediction method based on multiple features. The method comprises the steps that 1 historical data of file submission and mail exchange about the Apache project are collected; 2 according to the historical data of the first 5 months of the project, the directed network of the project member is constructed; 3 feature data including the network feature of a mail network and the related attribute feature are extracted and are used as training test data; and 4 the data are trained by the method of Support Vector Machine, and amulti-feature open source software project hatching state prediction model is built. According to the invention, the attribute feature and the network feature are combined to predict and classify the state of the project; the final hatching state of the project can be reasonably and efficiently predicted; and the industry demand of open source software project management is met.

Description

technical field [0001] The invention relates to data mining, complex network and machine learning technology, in particular to a method for predicting the hatching state of an open source software project based on multi-features. Background technique [0002] In the open source software community (Open source software, OSS), developers usually voluntarily make code or idea contributions to the project, and do not ask for remuneration. Secondly, members of the open source software project team are often located all over the world, and their usual project communication activities tend to be more online and spontaneous. Therefore, compared with traditional commercial software projects, the development process and results of open source software projects are affected by many potential, related and uncertain factors. The Apache Software Foundation (ASF) provides platform support for its managed projects, which can reflect the development direction and status of the project team ...

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): G06Q10/04G06K9/62
Inventor 宣琦李永苗周鸣鸣傅晨波
Owner ZHEJIANG UNIV OF TECH
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