评价目标前提的逻辑框架  

Logical Framework for Evaluation of Multiple-premise

作　　者：夏兰亭[1] 韩道军[1] 边芮[2] 李磊[1] 

机构地区：[1]中山大学软件研究所,广州510275 [2]广东商学院公共管理学院,广州510320

出　　处：《计算机科学》2012年第3期235-242,共8页Computer Science

基　　金：国家自然科学基金(60970042)资助

摘　　要：多前提决策问题是决策领域中重要的研究内容,其决策质量可反映决策理论研究的成果。在多前提决策中,目标会有多种实现方式,每种实现方式都有相应的实现难度。在多前提决策研究中,定义了目标的条件集,提出了将条件集分解到最简单形式的算法,并证明了算法的输出为目标的极小最简不完备条件集。然后,提出了条件集可信度的概念及其计算方式,利用可信度评估目标的所有极小最简不完备条件集的实现难度,并以此确定实现该目标的最优条件集。最后,给出了评价目标前提的逻辑框架O的形式定义,证明了框架O的可计算性和推理能力,并用逻辑程序Prolog实现了框架O的原型,通过对框架O的原理性实验和具体的工程应用验证了框架O的有效性。The multi-premise problem is an important research field of decision making and its optimal decision reflects the state of the art research of decision theory. Many methods can achieve it in multi-premise decision making, and each method has its own difficulties. This paper first introduced a new concept-premise set, proposed an algorithm to decom- pose premise set into the simplest form, and proved that the algorithm outputs minimal, non-complete premise sets for any given goal. Next the credibility of each premise was defined for measuring the difficulty of premise set, and the optimal premise set was recommended for the goal. Then this paper gave a formal description of the logical framework O for evaluation of multiple-premise, and proved its computability and reasoning faculty. Finally, a prototype of framework O was implemented in Prolog and its soundness was proved via experiments and application in software engineering.

关 键 词：多前提 最优条件集 可信度 实现难度 评价 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]