摘要
1 引言
用户需求一般用自然语言描述,是非形式化的,因而在生成确定的、形式化的需求规格时不可避免地会牺牲用户的部分需求.采取何种方法能尽量减少信息损失和不一致,从而使需求规格更接近于用户需求是软件开发中必须解决的重要问题.
There are at least two challenges with requirements engineering- First ,requirements are usually vague and imprecise in nature; Second ,requirements often conflict with each other and many conflicts are difficult to identify. This paper discusses inconsistency and imprecision on requirement respectively. Then,it points out that comprehensive method should be adopted to face with natural attribution in requirement engineering. The difficulties of this kind of methods are how to limit solving domain and induce solving model by contextual knowledge.
出处
《计算机科学》
CSCD
北大核心
2001年第2期48-51,共4页
Computer Science
基金
国家教委博士点基金(98069923)
关键词
软件工程
需求工程
不确定性
模糊逻辑
人工智能
Requirement engineering, Inconsistency, Imprecision, Generalized fuzzy logic, Revising default theory, Evolution, Context