Finding Data Tractable Description Logics for Computing a Minimum Cost Diagnosis Based on ABox Decomposition  

作　　者：杜剑峰 漆桂林 Jeff Z.Pan 

机构地区：[1]Guangdong University of Foreign Studies [2]State Key Laboratory of Computer Science,Institute of Software, Chinese Academy of Sciences [3]School of Computer Science and Engineering, Southeast University [4]Department of Computing Science, the University of Aberdeen

出　　处：《Tsinghua Science and Technology》2010年第6期623-632,共10页清华大学学报（自然科学版（英文版）

基　　金：Supported by the National Natural Science Foundation of China(Nos.61005043 and 60970045)

摘　　要：Ontology diagnosis, a well-known approach for handling inconsistencies in a description logic （DL） based ontology, computes a diagnosis of the ontology, i.e., a minimal subset of axioms in the ontology whose removal restores consistency. However, ontology diagnosis is computationally hard, especially computing a minimum cost diagnosis （MCD） which is a diagnosis such that the sum of the removal costs attached to its axioms is minimized. This paper addresses this problem by finding data tractable DLs for computing an MCD which allow computing an MCD in time polynomial in the size of the ABox of a given ontology. ABox decomposition is used to find a sufficient and necessary condition to identify data tractable DLs for computing an MCD under the unique name assumption （UNA） among all fragments of that are at least as expressive as without inverse roles. The most expressive, data tractable DL identified is without inverse roles or qualified existential restrictions.Ontology diagnosis, a well-known approach for handling inconsistencies in a description logic （DL） based ontology, computes a diagnosis of the ontology, i.e., a minimal subset of axioms in the ontology whose removal restores consistency. However, ontology diagnosis is computationally hard, especially computing a minimum cost diagnosis （MCD） which is a diagnosis such that the sum of the removal costs attached to its axioms is minimized. This paper addresses this problem by finding data tractable DLs for computing an MCD which allow computing an MCD in time polynomial in the size of the ABox of a given ontology. ABox decomposition is used to find a sufficient and necessary condition to identify data tractable DLs for computing an MCD under the unique name assumption （UNA） among all fragments of that are at least as expressive as without inverse roles. The most expressive, data tractable DL identified is without inverse roles or qualified existential restrictions.

关 键 词：ontology diagnosis minimum cost diagnosis description logics data tractability 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]