Automated Modelling and Solving in Constraint Programming
Automated Modelling and Solving in Constraint Programming
复制标题
约束规划中的自动建模和求解
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
B. O’Sullivan
中科院分区：
文献类型：
--
作者：
B. O’Sullivan
约束规划可以非常粗略地分为建模和求解。建模根据可以采用不同值的变量来定义问题，并受到允许变量组合的限制（约束）。求解会找到同时满足所有约束的所有变量的值。然而，约束编程的影响因缺乏“用户友好性”而受到限制。约束编程有一个主要的“声明性”方面，即问题模型可以转交给各种标准求解方法来解决。这些方法嵌入在算法、库或专门的约束编程语言中。然而，为了充分利用这种声明性机会，我们必须在建模过程以及特定于应用程序的问题求解器的设计中提供更多帮助和自动化。约束中的自动化建模和求解人工智能，特别是机器学习，是探索将更多约束编程负担从用户转移到机器的一个自然领域。本文提出了约束模型获取、制定和重新制定、全局约束过滤算法的综合以及自动求解等领域的技术挑战。
Constraint programming can be divided very crudely into modeling and solving. Modeling defines the problem, in terms of variables that can take on different values, subject to restrictions (constraints) on which combinations of variables are allowed. Solving finds values for all the variables that simultaneously satisfy all the constraints. However, the impact of constraint programming has been constrained by a lack of "user-friendliness'. Constraint programming has a major "declarative" aspect, in that a problem model can be handed off for solution to a variety of standard solving methods. These methods are embedded in algorithms, libraries, or specialized constraint programming languages. To fully exploit this declarative opportunity however, we must provide more assistance and automation in the modeling process, as well as in the design of application-specific problem solvers. Automated modelling and solving in constraint programming presents a major challenge for the artificial intelligence community. Artificial intelligence, and in particular machine learning, is a natural field in which to explore opportunities for moving more of the burden of constraint programming from the user to the machine. This paper presents technical challenges in the areas of constraint model acquisition, formulation and reformulation, synthesis of filtering algorithms for global constraints, and automated solving. We also present the metrics by which success and progress can be measured.