求解QBF问题的启发式调查传播算法  

Heuristic Survey Propagation Algorithm for Solving QBF Problem

作　　者：殷明浩[1,2] 周俊萍[1,3] 孙吉贵[3,2] 谷文祥[1] 

机构地区：[1]东北师范大学计算机学院,吉林长春130117 [2]吉林大学教育部符号计算与知识工程重点实验室,吉林长春130012 [3]吉林大学计算机科学与技术学院,吉林长春130012

出　　处：《软件学报》2011年第7期1538-1550,共13页Journal of Software

基　　金：国家自然科学基金(60773097;60803102)

摘　　要：提出了一种启发式调查传播算法,并基于该算法设计了一种QBF(quantified Boolean formulae)求解器——HSPQBF(heuristic survey propagation algorithm for solving QBF)系统.它将Survey Propagation信息传递方法应用到QBF求解问题中.利用Survey Propagation作为启发式引导DPLL(Davis,Putnam,Logemann and Loveland)算法,选择合适的变量进行分支,从而可以减小搜索空间,并减少算法回退的次数.在分支处理过程中,HSPQBF系统结合了单元传播、冲突学习和满足蕴涵学习等一些优秀的QBF求解技术,从而能够提高QBF问题的求解效率.实验结果表明,HSPQBF无论在随机问题上还是在QBF标准测试问题上都有很好的表现,验证了调查传播技术在QBF问题求解中的实际价值.This paper presents a heuristic survey propagation algorithm for solving Quantified Boolean Formulae （QBF） problem. A QBF solver based on the algorithm is designed, namely HSPQBF （heuristic survey propagation algorithm for solving QBF）. This solver is a QBF reasoning engine that incorporates Survey Propagation method for problem solving. Using the information obtained from the survey propagation procedure, HSPQBF can select a branch accurately. Furthermore, when handling the branches, HSPQBF uses efficient technology to solve QBF problems, such as unit propagation, conflict driven learning, and satisfiability directed at implication and learning. The experimental results also show that HSPQBF can solve both random and QBF benchmark problems efficiently, which validates the effect of using survey propagation in a QBF solving process.

关 键 词：人工智能 QBF问题 QBF问题求解器 因子图 调查传播 冲突学习 满足蕴涵学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]