高可信众包群体构建方法  

An approach for developing a highly trustworthy crowd-sourced workforce

作　　者：冯洋 王祎 房春荣[1] 郭楠楠 陈振宇[1] Yang FENG;Yi WANG;Chunrong FANG;Nannan GUO;Zhenyu CHEN(State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210093,China;Department of Software Engineering,Rochester Institute of Technology,Rochester 14623,USA)

机构地区：[1]南京大学计算机软件新技术国家重点实验室,南京210093 [2]Department of Software Engineering,Rochester Institute of Technology,Rochester 14623,USA

出　　处：《中国科学：信息科学》2019年第11期1412-1427,共16页Scientia Sinica(Informationis)

基　　金：国家重点研发计划(批准号:2018YFB1403400);国家自然科学基金(批准号:61690201,61772014,61802171)资助项目

摘　　要：构建高可信众包群体是众包活动的一个重要挑战.目前,众包机制研究主要集中在激励众包个体,而忽略了能够反映微服务质量的高诚信众包群体的构建.本文根据通过融合委托–代理模型和信号博弈理论提出了一种新颖的高可信众包群体构建机制.该机制实现了众包工人和发包方的信息交换,并通过随机质量审查来为诚信/失信工人提供动态的经济激励/惩罚.本文通过大规模的仿真实验来对该机制进行验证.实验结果表明该机制具有良好的有效性和高效性,能够通过极小的代价让能力强但失信的工人在任务提交前改正行为做出诚信决策.In applying crowd-sourcing techniques,one of the most critical challenges is building a crowd workforce that is both capable and trustworthy.Previous studies proposed numerous strategies,methods,and mechanism to motivate individuals;however,although the results improved the effectiveness and efficiency of finishing crowd-sourcing tasks,few studies focused on improving the honesty of crowd-sourced workers and assisting requesters in obtaining the correct quality report.To address this,based on the principal-agent model and signaling game theory,we design a novel mechanism for building a capable and trustworthy crowd-sourced workforce.This mechanism enables information exchange between crowd-sourced workers and requesters,and leverages a random inspection strategy to assign financial incentives/punishments to honest/dishonest behaviors accordingly.To validate our mechanism,we conduct an extensive simulation.The results show this mechanism is effective and efficient to motivate workers to behave in a trustworthily manner and capable of changing the behavior of dishonest workers with minimal extra cost.

关 键 词：可信众包 众包机制 信号博弈理论 委托代理模型 

分 类 号：F27[经济管理—企业管理]