A neural network-based recommendation method for crowdsourced software developers

A software developer, neural network technology, applied in the field of crowdsourcing software developer recommendation based on neural network, can solve problems such as difficult to accurately model, lack of historical data for users, and insufficient historical data for crowdsourcing tasks.

Active Publication Date: 2018-12-18
BEIHANG UNIV
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem of recommendation by crowdsourcing software developers, the present invention proposes a neural network-based recommendation method for crowdsourcing software developers, thereby ensuring software quality and development efficiency
The present invention solves three problems in crowdsourcing software developer recommendation: (1) the amount of historical data of crowdsourcing tasks is insufficient, and it is difficult to model accurately; The problem of limited recommendation range; (3) The cold start problem caused by the lack of historical data of users

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 neural network-based recommendation method for crowdsourced software developers
  • A neural network-based recommendation method for crowdsourced software developers
  • A neural network-based recommendation method for crowdsourced software developers

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0014] The present invention proposes a neural network-based crowdsourcing software developer recommendation method, such as figure 1 As shown, when recommending, the method contains three main components: a registration behavior predictor, a submission behavior predictor, and a winning behavior predictor. These three can respectively predict the corresponding behavior of the user. The submissi...

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

A neural network-based recommendation method for crowdsourced software developers is provided. The model in the method generally consists of three main components, a registration behavior predictor, asubmission behavior predictor and a winning behavior predictor, the submission behavior predictor performs prediction based on the situation after the user has registered, the winning behavior predictor predicts based on the situation that the user has submitted, the registrant predictor predicts that there is no prerequisite. In the learning of the task data set by the registration behavior predictor, if the output registration probability is not before top R, the user wins by 0, and the instance prediction is terminated; otherwise, the output detection is continued by using the submission behavior predictor. In the commit behavior predictor, if the output commit probability is not before top S, the user's winning probability is 0, and the instance prediction is terminated; otherwise, the user enters the winning behavior predictor; Finally, the winning probability is obtained by the user winning behavior predictor, and the list of the first K users is recommended according to the winning probability.

Description

technical field [0001] The invention relates to the field of intelligent recommenders, in particular to a neural network-based crowdsourcing software developer recommendation method. Background technique [0002] Crowdsourcing software development is the application of crowdsourcing technology in the field of software development. The software demander divides complex software into modules according to functions or characteristics, and then outsources all or part of the software modules in the form of crowdsourcing development tasks, allowing the public developers to complete these tasks. Now there are many crowdsourcing software development platforms in the industry, such as Topcoder, Kaggle, etc., among which the largest platform is Topcoder. The Topcoder platform has been leading the trend of crowdsourcing software development for more than 10 years and has more than 1 million users. A typical crowdsourcing software development process includes: the software demander re...

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): G06F8/35G06N3/04
CPCG06F8/35G06N3/04
Inventor 孙海龙王旭张振羽刘旭东
Owner BEIHANG 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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap