摘要
对人工智能领域中人机对话系统的评测方法进行研究,针对不同对话系统的特征,分别提出了测试策略,对应策略开展某人机辩论系统测试验证,通过问题的解决,提高了被测软件的质量,验证了研究结果的可行性和有效性,为后续研究提供了基础。
The evaluation methods of human-computer dialogue system in the field of artificial intelligence are studied.According to the characteristics of different dialogue systems,test strategies are proposed respectively.Corresponding strategies are carried out to test and verify a human-computer debate system.Through the solution of problems,the quality of the tested software is improved,and the feasibility and effectiveness of the research results are verified,which provides a basis for subsequent research.
作者
林晓欲
Yuan Tommy
雷倩茹
Lin Xiaoyu;Yuan Tommy;Lei Qianru(Luoyang Opto-Electro Technology Development Center,Luoyang 471000,China;Department of Computer Science,University of York,York YO105GH,UK)
出处
《航空兵器》
CSCD
北大核心
2019年第5期87-94,共8页
Aero Weaponry
基金
国家留学基金委基金项目(201705270011)
关键词
人机对话系统
软件质量
软件测试
对话管理
场景分析
human-computer dialogue system
software quality
software testing
dialogue management
scene analysis
