Currently, knowledge-based sharing and service system has been a hot issue and knowledge fusion, especially for implicit knowledge discovery, becomes the core of knowledge processing and optimization in the system. In...Currently, knowledge-based sharing and service system has been a hot issue and knowledge fusion, especially for implicit knowledge discovery, becomes the core of knowledge processing and optimization in the system. In the research, a knowledge fusion framework based on agricultural ontology and fusion rules was pro- posed, including knowledge extraction, clearing and annotation modules based on a- gricultural ontology, fusion rule construction, choosing and evaluation modules based on agricultural ontology and knowledge fusion module for users＇ demands. Finally, the significance of the framework to system of agricultural knowledge services was proved with the help of a case.展开更多
Inconsistencies or conflicts appearing in the integration of ontologies and general rules are handled by applying prioritizing and updating. First, a prioritized knowledge base is obtained by weighting information wei...Inconsistencies or conflicts appearing in the integration of ontologies and general rules are handled by applying prioritizing and updating. First, a prioritized knowledge base is obtained by weighting information weight. Then, based on the idea ＂abandoning the old for the new＂, the weight of each rule is greater than that of the information in ontologies. If ontologies conflict with general rules, then a new knowledge-base without any inconsistency or conflict is obtained by using rules with big weight updating information in ontologies with small weight. Thus, current logic programming solvers and description logic reasoners are employed to implement the reasoning services, such as querying etc. Updating based on prioritizing is more suitable for handling inconsistencies than other approaches to introducing non-standard semantics if knowledge bases are dynamically evolving. Moreover, a consistent knowledge base can be always maintained in the dynamical environment by updating outdated information with new information based on weighting. Finally, this approach to dealing with inconsistencies is feasibly exemplified.展开更多
The minimal unsatisfiability-preserving sub-TBoxes（MUPS）of an unsatisfiable class C identified by two equivalent transformations,axiom splitting and ontology reduction,and three discrimination rules comprise minimal...The minimal unsatisfiability-preserving sub-TBoxes（MUPS）of an unsatisfiable class C identified by two equivalent transformations,axiom splitting and ontology reduction,and three discrimination rules comprise minimal sets of axioms which support the unsatisfiability.Discrimination rules classify all MUPS into three types based on the transitivity of unsatisfiability,fully dependent on C（MUPSf）,transitively dependent on C（MUPSt）and uncertainly dependent on C（MUPSu）.The results show that the number of MUPSt is frequently a large fraction of the total number of all MUPS,but only MUPSf catches the root error of C.Modelers and domain experts conduct iterative repair work effectively,considering only MUPSf in each iteration.The classification shows the significance for the evaluation of the quality of ontologies from the perspective of maintenance and for repair work.展开更多
基金Supported by Specialized Funds of CASIndividual Service System of Agricultural Information in Tibet(2012-J-08)+1 种基金Science and Technology Funds of CASMultimedia Information Service in Rural Area based on 3G Information Terminal(201219)~~
文摘Currently, knowledge-based sharing and service system has been a hot issue and knowledge fusion, especially for implicit knowledge discovery, becomes the core of knowledge processing and optimization in the system. In the research, a knowledge fusion framework based on agricultural ontology and fusion rules was pro- posed, including knowledge extraction, clearing and annotation modules based on a- gricultural ontology, fusion rule construction, choosing and evaluation modules based on agricultural ontology and knowledge fusion module for users＇ demands. Finally, the significance of the framework to system of agricultural knowledge services was proved with the help of a case.
基金The National Natural Science Foundation of China (No60973003)
文摘Inconsistencies or conflicts appearing in the integration of ontologies and general rules are handled by applying prioritizing and updating. First, a prioritized knowledge base is obtained by weighting information weight. Then, based on the idea ＂abandoning the old for the new＂, the weight of each rule is greater than that of the information in ontologies. If ontologies conflict with general rules, then a new knowledge-base without any inconsistency or conflict is obtained by using rules with big weight updating information in ontologies with small weight. Thus, current logic programming solvers and description logic reasoners are employed to implement the reasoning services, such as querying etc. Updating based on prioritizing is more suitable for handling inconsistencies than other approaches to introducing non-standard semantics if knowledge bases are dynamically evolving. Moreover, a consistent knowledge base can be always maintained in the dynamical environment by updating outdated information with new information based on weighting. Finally, this approach to dealing with inconsistencies is feasibly exemplified.
基金The Science and Technology Development Program of Tianjin(No.06YFGZGX05900)
文摘The minimal unsatisfiability-preserving sub-TBoxes（MUPS）of an unsatisfiable class C identified by two equivalent transformations,axiom splitting and ontology reduction,and three discrimination rules comprise minimal sets of axioms which support the unsatisfiability.Discrimination rules classify all MUPS into three types based on the transitivity of unsatisfiability,fully dependent on C（MUPSf）,transitively dependent on C（MUPSt）and uncertainly dependent on C（MUPSu）.The results show that the number of MUPSt is frequently a large fraction of the total number of all MUPS,but only MUPSf catches the root error of C.Modelers and domain experts conduct iterative repair work effectively,considering only MUPSf in each iteration.The classification shows the significance for the evaluation of the quality of ontologies from the perspective of maintenance and for repair work.
