| 141 | 3 | 80 |
| 下载次数 | 被引频次 | 阅读次数 |
为了解决在未知工人效用情况下提高任务完成质量的问题,提出带有效用的最高分数匹配模型。该模型包含两个阶段:阶段一利用多臂老虎机模型计算工人效用值;阶段二利用更改了加分规则后的带有效用的基本方法(U-Basic)、带有效用的最小位置熵方法(U-LLEP)、带有效用的近距离优先方法(U-CDP)进行分配。在MovieLens和Gowalla真实世界数据集上的实验结果表明,所提方法与未使用效用的CDP和LLEP方法相比,一些评价指标有较大提升。
Abstract：In order to improve the quality of task completion in the absence of worker utilities, a two-stage maximum score assignment model with utility was proposed. Stage 1, the worker utility values were calculated using a multi-armed bandit model. Stage 2, they were distributed by using basic method with utility(U-Basic), minimum position entropy method with utility(U-LLEP) and proximity priority method with utility(U-CDP) with changed scoring rules. The experimental results on MovieLens and Gowalla real world data sets showed that some evaluation indexes were improved greatly compared with CDP and LLEP methods without utility.
[1] LI G L,WANG J N,ZHENG Y D,et al.Crowdsourced data management:a survey[J].IEEE transactions on knowledge and data engineering,2016,28(9):2296-2319.
[2] SHAHABI C.Spatial crowdsourcing[M]//International Encyclopedia of Geography:People,the Earth,Environment and Technology.New York:John Wiley & Sons,Ltd,2017:1-14.
[3] XIAO M J,MA K,LIU A,et al.SRA:secure reverse auction for task assignment in spatial crowdsourcing[J].IEEE transactions on knowledge and data engineering,2020,32(4):782-796.
[4] GUMMIDI S R B,XIE X K,PEDERSEN T B.A survey of spatial crowdsourcing[J].ACM transactions on database systems,2019,44(2):1-46.
[5] HO C J,VAUGHAN J W.Online task assignment in crowdsourcing markets[C]//Proceedings of the 26th AAAI Conference on Artificial Intelligence.Palo Alto:AAAI Press,2012:45-51.
[6] DWORK C.Differential privacy[M]//Automata,Languages and Programming.Berlin:Springer,2006:1-12.
[7] TO H,SHAHABI C,KAZEMI L.A server-assigned spatial crowdsourcing framework[J].ACM transactions on spatial algorithms and systems,2015,1(1):1-28.
[8] HADJI M,ZEGHLACHE D.Minimum cost maximum flow algorithm for dynamic resource allocation in clouds[C]//Proceedings of the IEEE 5th International Conference on Cloud Computing.Piscataway:IEEE Press,2012:876-882.
[9] DAI P,MAUSAM M,WELD D.Artificial intelligence for artificial artificial intelligence[C]//Proceedings of the 25th AAAI Conference on Artificial Intelligence.Palo Alto:AAAI Press,2011:1153-1159.
[10] ROBBINS H.Some aspects of the sequential design of experiments[J].Bulletin of the American mathematical society,1952,58(5):527-536.
[11] AGRAWAL R.Sample mean based index policies by O(log n) regret for the multi-armed bandit problem[J].Advances in applied probability,1995,27(4):1054-1078.
[12] AUER P,CESA-BIANCHI N,FISCHER P.Finite-time analysis of the multiarmed bandit problem[J].Machine learning,2002,47(2/3):235-256.
[13] LI S,KARATZOGLOU A,GENTILE C.Collaborative filtering bandits[C] //Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York:ACM Press,2016:539-548.
[14] GENTILE C,LI S,ZAPPELLA G.Online clustering of bandits[C]//Proceedings of the 31st International Conference on Machine Learning.New York:ACM Press,2014:757-765.
基本信息:
DOI：10.13705/j.issn.1671-6841.2020371
中图分类号:TP393.09
引用信息:
[1]王亦敬,陈荣,郭世凯,等.用于空间众包任务匹配的未知工人效用估计方法[J].郑州大学学报(理学版),2021,53(03):65-71.DOI:10.13705/j.issn.1671-6841.2020371.
基金信息:
国家自然科学基金项目(61672122,61902050,61906027); 中央高校基本科研业务基金项目(3132020211); 中国博士后科学基金项目(2019M661080,2020M670736); 大连海事大学优秀科技创新团队培育计划项目(3132019355)
2021-02-09
2021-02-09
2021-02-09