基于强化学习的Web服务众测任务分派方法  

Web Service Crowdtesting Task Assignment Approach Based on Reinforcement Learning

作　　者：唐文君 张佳丽 陈荣[1] 郭世凯[1] TANG Wen-jun;ZHANG Jia-li;CHEN Rong;GUO Shi-kai(College of Information Science and Technology,Dalian Maritime University,Dalian,Liaoning 116026,China)

机构地区：[1]大连海事大学信息科学技术学院

出　　处：《计算机科学》2020年第3期54-60,共7页Computer Science

基　　金：国家自然科学基金(61672122,61902050,61602077);中央高校基本科研业务费专项基金(3132019355);赛尔创新项目(NGII20190627)~~

摘　　要：如何将众包测试任务分派给合适的众测工人,以较低的成本获得更好的测试结果,是一个重要问题。文中将CWS众测任务分派问题建模为一个基于马尔可夫决策过程的问题,且使用Deep Q Network进行学习和实时在线测试任务分派。该基于强化学习的方法被命名为WTA-C。此外,文中根据众测工人执行任务的历史时间,通过统计条件概率计算测试工人在任务期限内完成任务的概率,将其作为工人信誉值来反映工人质量,并在每次分派完成后对工人信誉值进行更新。实验结果显示,WTA-C在控制测试任务的“质量-成本”权衡和保证工人可靠度方面优于其他基于启发式策略的实时分派方法,并在分派效果上高于各启发式策略18%以上,从而证明了其可以更好地适应CWS的结构和众测环境的特点。How to assign tasks to appropriate workers to get better testing results at a lower cost is an important problem.This paper modeled the CWS testing task assignment as a Markov decision process-based problem,and used Deep Q Network to learn and perform real-time online testing task assignment.The proposed approach based on reinforcement learning is named WTA-C.In addition,this paper calculated the probability of the testing worker completing the task within the duration through statistical conditional probability in accordance with the time of the worker’s historical execution of tasks,and used it as the workers’reputation value to reflect their quality.The worker’s reputation is updated after each assignment.The experimental results show that WTA-C is superior to other real-time assignment methods based on heuristic strategies in controlling the“quality-cost”trade-off of testing tasks and ensuring worker quality,and its assignment effect is more than 18%higher than that of each heuristic strategy,which demonstrates that WTA-C can better adapt to the structure of the CWS and the characteristics of Crowdsourcing environment.

关 键 词：众包测试 组合Web服务测试 WEB服务测试 强化学习 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]