计算机应用 ›› 2010, Vol. 30 ›› Issue (4): 982-984.

• 人工智能 • 上一篇    下一篇

基于论据系统的带权定性概率推理机

廖士中1,李翔坤2,高培涣1   

  1. 1.
    2. 大连东软信息学院
  • 收稿日期:2009-10-15 修回日期:2009-12-16 发布日期:2010-04-15 出版日期:2010-04-01
  • 通讯作者: 廖士中

Weighted qualitative probabilistic reasoner based on argument system

  • Received:2009-10-15 Revised:2009-12-16 Online:2010-04-15 Published:2010-04-01

摘要: 定性概率推理是不确定性推理领域的一种重要方法。将定性概率推理的论据系统方法和抽象系统方法二者合而为一,在定性概率推理机(QPR)的基础上提出基于论据系统的带权定性概率推理机(WQPR)。首先扩展了带权定性概率网的定义,讨论了带权定性影响的对称性;其次将带权定性概率推理融入到论据系统中,提出WQPR推理系统,相比QPR能够在更精确的尺度进行不确定性推理,并证明了系统的正确性与完备性。

关键词: 定性概率推理, 论据系统, 带权定性概率推理机, 不确定性推理

Abstract: Qualitative Probabilistic Reasoner (QPR) is an important approach for reasoning under uncertainty. Two methods of qualitative probabilistic reasoning of systems of argumentation and systems of abstraction were united into one system and a Weighted Qualitative Probabilistic Reasoner (WQPR) based on argumentation system and QPR was presented. Firstly give a patch to the weighted qualitative probabilistic network and discuss the symmetry property of weighted qualitative influences; secondly integrate the inference with qualitative probabilistic influence into the argumentation system, present a WQPR inference system with a high inference accuracy compared to QPR, and also give the proof of soundness and completeness for the WQPR system.

Key words: Qualitative Probabilistic Reasoner (QPR), argument system, Weighted Qualitative Probabilistic Reasoner (WQPR), reasoning under uncertainty