基于排序学习的软件众包任务推荐算法

Software Crowdsourcing Task Recommendation Algorithm Based on Learning to Rank

为了更有效地实现软件众包任务推荐,提升软件开发质量,为工人推荐合适的任务,降低工人利益受损风险,以达到工人和众包平台双赢的效果,设计了一种基于排序学习的软件众包任务推荐方法。首先,基于改进的隐语义模型提取工人-任务间的隐含特征;然后,结合隐式信息对排序学习模型进行改进,并将提取的隐含特征进行排序学习训练,获得最优排序模型;最终通过排序模型对测试集任务进行排序得到任务推荐列表,从而为工人进行众包任务推荐,并采用NDCG,MAP,Recall推荐评价指标对推荐结果进行检验。实验表明,所设计的方法能有效提高软件众包任务推荐的精度,其推荐评价指标的NDCG,MAP,Recall值分别达到0.722,0.326,0.169。与基于用户的协同过滤算法相比,推荐精度提升了18.6%;与仅基于RankNet的排序学习算法相比,精度提升了10.2%,因此能够有效指导软件众包任务推荐。

In order to realize software crowdsourcing task recommendation more effectively,improve the quality of software development,recommend suitable tasks for workers,reduce the risk of workers’interests being damaged,and achieve a win-win result for workers and crowdsourcing platforms,a software crowdsourcing task recommendation method based on learning to rank is designed.First,the hidden features between workers and tasks are extracted based on the improved latent factor model.Then,the model of learning to rank is improved by combining implicit information,and the extracted hidden features are ranked and trained to obtain the optimal ranking model.The ranking model sorts the test set tasks to get a task recommendation list to perform crowdsourcing task recommendation for workers,and uses relevant evaluation indicators to verify the recommendation results.Experiments show that the proposed method can effectively improve the software crowdsourcing task recommendation accuracy.The NDCG,MAP,and Recall values of the recommended evaluation indicators reach 0.722,0.326,0.169,respectively.Compared with the user-based collaborative filtering algorithm,the recommendation accuracy is improved by 18.6%.Compared with rank learning algorithm based on RankNet only,the accuracy is improved by 10.2%,which can effectively guide software crowdsourcing task recommendation.