[论文解读] Conjunctive Query Containment and Answering under Description Logics Constraints
本文提出了一种在描述逻辑约束下对合取查询包含与回答进行可判定性处理的方法,通过归约到查询包含问题。该方法在联合复杂度下达到 EXPTIME 完全性,在数据复杂度下为单指数时间,同时证明了当右端查询中允许使用不等式时,问题变为不可判定。
Query containment and query answering are two important computational tasks in databases. While query answering amounts to compute the result of a query over a database, query containment is the problem of checking whether for every database, the result of one query is a subset of the result of another query. In this paper, we deal with unions of conjunctive queries, and we address query containment and query answering under Description Logic constraints. Every such constraint is essentially an inclusion dependencies between concepts and relations, and their expressive power is due to the possibility of using complex expressions, e.g., intersection and difference of relations, special forms of quantification, regular expressions over binary relations, in the specification of the dependencies. These types of constraints capture a great variety of data models, including the relational, the entity-relationship, and the object-oriented model, all extended with various forms of constraints, and also the basic features of the ontology languages used in the context of the Semantic Web. We present the following results on both query containment and query answering. We provide a method for query containment under Description Logic constraints, thus showing that the problem is decidable, and analyze its computational complexity. We prove that query containment is undecidable in the case where we allow inequalities in the right-hand side query, even for very simple constraints and queries. We show that query answering under Description Logic constraints can be reduced to query containment, and illustrate how such a reduction provides upper bound results with respect to both combined and data complexity.
研究动机与目标
- 解决在丰富的完整性约束(以描述逻辑表达)存在下,合取查询包含与回答的问题。
- 为基于描述逻辑的模式约束在不完整数据库上的推理提供正式框架。
- 建立在这些约束下查询包含与查询回答的可判定性及复杂度界限。
- 研究不等式约束对可判定性的影响,证明在某些情况下问题变为不可判定。
提出的方法
- 通过从不完整数据库和目标元组构造布尔查询,将查询回答归约为查询包含问题。
- 将查询之间的包含定义为在描述逻辑约束模式下的蕴含关系。
- 采用模型论方法,将特定答案刻画为在所有模式与数据库模型中均满足包含关系的那些答案。
- 利用已有 Datalog 与查询包含结果分析复杂度,尤其关注合取查询的并集。
- 应用复杂度分析推导出查询回答在联合复杂度与数据复杂度下的上界。
- 通过查询包含证明不完整数据库的可满足性,将其归约为布尔查询的包含问题。
实验结果
研究问题
- RQ1在描述逻辑约束下,合取查询包含是否可判定?
- RQ2在描述逻辑约束下,查询包含与查询回答的计算复杂度为何?
- RQ3在何种条件下查询包含会变为不可判定,特别是当涉及不等式时?
- RQ4在描述逻辑约束下,查询回答能否归约为查询包含?
- RQ5在此设定下,联合复杂度与数据复杂度的界限是什么?
主要发现
- 在描述逻辑约束下,查询包含是可判定的,联合复杂度位于 EXPTIME。
- 在描述逻辑约束下,查询回答可归约为查询包含,从而可通过包含检查进行复杂度分析。
- 决定特定答案的复杂度在数据库常量数量上为单指数时间,因此数据复杂度为单指数时间。
- 当右端查询中允许使用不等式时,证明了查询包含的不可判定性,即使在简单约束下亦然。
- 相对于模式,不完整数据库的可满足性可在模式与数据库大小的指数时间内判定。
- 结果可推广至 TBox+ABox 可满足性问题,其复杂度为 EXPTIME,且可进一步推广至 ABox 的析取形式。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。