D3L(ccy)的属性及分布式Tableaux推理算法的研究

Properties and Distributed Tableaux Reasoning Algorithm for D3L_(ccy)

分步式动态描述逻辑(distributed dynamic description logics,D3L)很好地实现了在多个自治本体之间导入和重用知识的思想.在多个动态描述逻辑(dynamic description logics,DDL)本体之间桥规则构成链的情况下,知识并不总是按预期的方式正确传播.借鉴了基于包的描述逻辑(P-DL)的思想,引入了组合一致性语义对D3L进行了扩展从而很好地解决了上述问题.系统地研究了扩展得到的描述逻辑D3L(ccy)的属性及分布式推理理论.证明了该描述逻辑的单调性(D3L(ccy)是一种单调逻辑)、有向性(桥规则的影响具有方向性)及冲突局部性(局部本体的冲突不会传播到整个分布式系统);通过对原有Tableaux推理算法的扩展,为D3L(ccy)提出了分布式Tableaux推理算法并研究了算法的性质,证明了该算法是可终止的、可靠的和完备的.与传统的D3L相比,扩展后的D3L可以为信息集成系统、语义Web等分布式、动态的系统提供更为合理的逻辑基础.

As the distributed extension of traditional dynamic description logics（DDL）, distributed dynamic description logics （D3L） enables reasoning with multiple heterogeneous DDL ontologies interconnected by directional semantic mapping. D3L captures the idea of importing and reusing knowledge between several ontologies. This idea combines well with the basic assumption of the distributed and dynamic systems such as the semantic Web and the heterogeneous information integration system. We find in the case when more than two ontologies are involved and bridge rules form chains, knowledge does not always propagate along chains of bridge rules even if we would expect it. Inspired by package-based description logics, we propose D3L（ccy） by imposing so called compositional consistency condition on domain relations in D3L interpretations. Under this semantics knowledge propagates along chains of bridge rules correctly. We research the properties and distributed Tableaux reasoning algorithm for D3L（ccy） systematically. We prove that D3L（ccy） satisfies the monotonicity property（D3L（ccy） is a monotonic logic）, the directionality property（the effect of bridge rules is directional） and the restrained inconsistency propagation property（if some of the local ontologies is inconsistent, it does not necessarily pollute the whole distributed system）. Furthermore we provide a distributed Tableaux reasoning algorithm which is sound and complete for deciding satisfiability of concepts in D3L（ccy）. Compared with original one, the extended D3L provides more reasonable logic foundation for distributed and dynamic systems such as the Semantic Web and the information integration system.