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

Crowd-sourcing software task recommendation method based on developer characteristics

A recommendation method and developer's technology, applied in the field of recommendation, can solve the problems of complex software development tasks, different modeling methods, and inapplicability, so as to reduce the time for selecting tasks, increase enthusiasm, and improve accuracy.

Pending Publication Date: 2020-04-24
SOUTHEAST UNIV
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the one hand, these recommended methods are mainly aimed at some small tasks, that is, non-software development tasks. Such tasks are usually relatively simple and can be completed without professional knowledge, and the completion time is relatively short, but software development tasks are usually more complicated. People with professional knowledge are required to complete and the cycle is long. The mo

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
  • Crowd-sourcing software task recommendation method based on developer characteristics
  • Crowd-sourcing software task recommendation method based on developer characteristics
  • Crowd-sourcing software task recommendation method based on developer characteristics

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0025] Example: see Figure 1-Figure 5 , a kind of group intelligence software task recommendation method based on developer characteristic, described method comprises the following steps:

[0026] (1) Analyze historical data of swarm intelligence software developers, perform feature extraction for the historical tasks that developers participated in, and obtain two types of features, which are developer's preference information and competitiveness information;

[0027] (2) For the developer's historical task preference information, divide it according to time to obtain multiple historical task preference sequences, and use the long-short-term memory neural network based on the attention mechanism for training to predict the developer's current preference;

[0028] (3) Compare the developer's preference with all tasks to be recommended by using the distance formula to filter out the top N tasks of interest, where N mainly depends on the average number of tasks registered by al...

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

Crowd-sourced software development is a novel software development mode which utilizes developer resources around the world to complete complex development tasks based on a competition or cooperationmode. However, the current software development mode has the problems that information is overloaded, tasks are difficult to select and complex, and the quality is difficult to guarantee. In order toeffectively solve the problem, tasks suitable for being completed are recommended to a crowd-sourcing software developer on the basis of characteristics of the crowd-sourcing software developer, so that the software development efficiency and quality are improved. Developer characteristics are mainly measured from two aspects, namely dynamic preferences of developers and competitiveness of the developers. The method comprises the steps that firstly, a long-term and short-term memory neural network based on an attention mechanism is used for obtaining dynamic change preferences of developers and screening out first N tasks meeting the preferences of the developers; and then, for the competitiveness of the developer, the score of the developer on the to-be-recommended task is predicted by adopting an improved XGBoost model based on a differential evolution algorithm; finally the Top-K task is recommended to the developer according to the predicted score.

Description

technical field [0001] The invention relates to a technique for recommending group-intelligent software tasks to developers by using the dynamic preferences and competitiveness of developers, and belongs to the technical field of recommendation. Background technique [0002] In recent years, crowd-intelligent software development has received widespread attention from academia and industry. As a new software development method, crowd intelligence software development makes full use of the idea of ​​"crowd intelligence". Compared with traditional software development, swarm intelligence software development can maximize the use of the resources of developers distributed all over the world, and use group competition or collaboration to complete complex development tasks, which can effectively reduce development costs and improve development efficiency. At present, there are already many crowd-intelligent platforms on the Internet, for the demand side to issue tasks and the p...

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): G06F16/9535G06N3/12G06N20/20G06Q10/06
CPCG06F16/9535G06N3/126G06N20/20G06Q10/06311G06Q10/063112
Inventor 王红兵严嘉
Owner SOUTHEAST 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