Loading…

Group task allocation approach for heterogeneous software crowdsourcing tasks

It is more common for multiple users to collaborate to develop a software application in a P2P collaborative working environment. In collaborative software development, the rational allocation of software development tasks is of great significance. However, heterogeneous of software development task...

Full description

Saved in:
Bibliographic Details
Published in:Peer-to-peer networking and applications 2021-05, Vol.14 (3), p.1736-1747
Main Authors: Yin, Xiaojing, Huang, Jiwei, He, Wei, Guo, Wei, Yu, Han, Cui, Lizhen
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is more common for multiple users to collaborate to develop a software application in a P2P collaborative working environment. In collaborative software development, the rational allocation of software development tasks is of great significance. However, heterogeneous of software development tasks, such as the value of the task, the skill required, the effort required and difficulty, increase the complexity of task allocation. This paper proposes an allocation approach of crowd intelligence software development task in which multiple individuals collaborate to complete software development tasks. The heterogeneous task allocation problem in the crowd intelligence software development system is formulated as an optimization problem. Then, the process of task allocation is modelled using the hidden Markov model. In our study, due to the insufficiency of data characteristics, we propose to construct a generator using Generative Adversarial Networks(GANs) to solve this problem. Then, the Baum-Welch algorithm is used for detailed analysis and calculation of model parameters. And on this basis, effective task allocation strategies for maximizing the total value of tasks obtained by the workers are explored through the Viterbi algorithm. Based on the Agile Manager (AM) dataset, which contains a large scale real human task allocation strategy, the model learns from human decision-making strategies that have achieved good outcomes. Based on the Agile Manager dataset, this approach is evaluated experimentally. The results show that it outperforms the artificial intelligence (AI) player in the AM game platform.
ISSN:1936-6442
1936-6450
DOI:10.1007/s12083-020-01000-6