组合测试研究进展  

Research Advances in Interaction Testing

作　　者：陈翔[1] 顾庆[1] 王新平[1] 陈道蓄[1] 

机构地区：[1]南京大学计算机科学与技术系计算机软件新技术国家重点实验室,南京210093

出　　处：《计算机科学》2010年第3期1-5,共5页Computer Science

基　　金：国家重点基金项目(2006AA01Z177);国家自然科学基金(60873027);江苏自然科学基金基础研究项目(BK2006115)资助

摘　　要：组合测试(Interaction Testing)是一种有效的测试用例生成技术,它假设被测系统中的缺陷往往由少数参数间的交互触发,所以可以使用较小规模的测试用例集(Test Suite)完成高质量的软件测试。对目前组合测试的已有工作予以研究,首先通过介绍常见的组合覆盖标准引入组合测试问题;然后总结目前常见的4种组合对象;之后依据生成策略的特征对现有的组合测试技术予以分类并简要介绍其中的典型方法;接着给出一套评价标准并对各个方法予以综合比较;最后总结并提出下一步的研究方向。Interaction testing is an effective test suite generation technique and becoming a challenging problem. It is concerned with the interaction among several parameters of system under test （SUT） and can test the SUT effectively with smaller test suite. We described the interaction testing problem based on the interaction coverage criteria, explained four well-known combinatorial objects,classified several well-known interaction testing approaches by their characteris- tic and gave a brief interpretation of some classical approaches. We also gave a set of evaluation criteria and made a comparison among all the approaches. At last we gave a conclusion and discussed some issues to be further studied.

关 键 词：组合测试 组合对象 代数构造 贪婪法 元启发式搜索技术 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]