[目的/意义] 情境建模是解决信息泛滥、信息过载、实现信息按需服务的重要手段，目前已有的知识库构建和知识融合方法普遍忽略了情境信息，阻碍了知识库的实际应用，降低了知识服务的效率和效果。[方法/过程] 综合考虑环境情境、个人情境和领域本体三个方面，提出一种情境本体驱动的多源知识融合框架，并以此框架融合生成基于情境的药物不良反应知识库ConADR Ontology。在本框架的指导下，以药物不良反应的知识库构建为例，半自动实现情境本体模式层的构建和数据层的扩充；并以情境本体作为中介本体，实现情境本体，药物不良反应领域本体ADReCS和人类疾病领域本体Disease Ontology间的融合；最终在此基础上实现基于SPARQL的案例查询。[结果/结论] 实例验证表明，本框架具有一定的可行性，对知识库的建设和应用具有理论性指导和参考价值。
[Purpose/significance] Context-awareness modeling is an important method to solve information overflow, information overload, and to realize information on demand, however, it always being ignored in the construction of knowledge base, which hinders the practical application of knowledge base as well as reduces the efficiency and effectiveness of knowledge service.[Method/process] This paper proposed an ontology-based context driven multi-source knowledge fusion framework taking the context, personal profiles and domain ontology into consideration. Under the guidance of this framework, this paper constructed an Adverse Drug Reactions (ADR) knowledge base with respect to the contextual relevance naming ConADR Ontology. Firstly, we constructed a situation ontology which can semi-automatically update schema and extend ontology instance, and then successfully fuse it with existed domain ontology ADReCS and Disease Ontology using Jena and Protégé. Finally, we developed a case query application based on SPARQL.[Result/conclusion] The example shows that the framework has a certain feasibility and theoretical reference value for the merger and construction of knowledge base.
[1] 蒋勋, 徐绪堪, 苏新宁, 等. 知识服务驱动的知识库框架系统内的逻辑架构[J]. 情报理论与实践, 2014,37(10):125-129.
[2] 李枫林, 李娜. 基于情景的医药信息服务本体建模及规则推理研究[J]. 情报理论与实践, 2016,39(5):120-124.
[3] 周莉, 潘旭伟, 谢玉开. 情境感知的电子商务个性化商品信息服务[J]. 图书情报工作, 2011,55(10):130-134.
[4] 潘旭伟, 李娜, 周莉, 等. 情境感知的自适应个性化信息服务体系框架研究[J]. 情报学报, 2011,30(5):514-521.
[5] CANTADOR I, CASTELLS P. Semantic contextualisation in a news recommender system[EB/OL].[2018-01-10]. https://www.mendeley.com/research-papers/semantic-contextualisation-news-recommender-system/.
[6] REICHLE R, WAGNER M, KHAN M U, et al. A comprehensive context modeling framework for pervasive computing systems[C]//MEIER R, TERZIS S. Ifip wg 6.1 international conference on distributed applications and interoperable systems. Berlin:Springer-verlag, 2008:281-295.
[7] SOHN M, JEONG S, LEE H J. Case-based context ontology construction using fuzzy set theory for personalized service in a smart home environment[M]. Berlin:Springer-verlag, 2014:1715-1728.
[8] WANG X H, ZHANG D Q, GU T, et al. Ontology based context modeling and reasoning using OWL[C]//IEEE annual conference on pervasive computing and communications workshops. Piscataway:IEEE, 2004:18-22.
[9] ALOUI N, GARGOURI F. A generic context ontology for a learning through context-aware annotations memory[C]//JARRAH O A, QUWAIDER M. Omar Al Jarrah and Muhannad Quwaider. Proceedings of the 3rd international conference on information and communication systems. New York:ACM, 2012:1-7.
[10] 王丽伟, 王伟, 高玉堂, 等. 领域本体映射的语义互联方法研究——以药物本体为例[J]. 图书情报工作, 2013,57(17):21-25.
[11] 刘晓娟, 李广建, 化柏林. 知识融合:概念辨析与界说[J]. 图书情报工作, 2016,60(13):13-19.
[12] SMIRNOV A, LEVASHOVA T, SHILOV N. Patterns for context-based knowledge fusion in decision support systems[J]. Information fusion, 2015, 21(1):114-129.
[13] 周宇,欧石燕. 面向关联数据的高校机构知识库构建方法研究[J]. 图书情报工作, 2016,60(1):105-113.
[14] PREECE A, HUI K, GRAY A, et al. The KRAFT architecture for knowledge fusion and transformation[J]. Knowledge-based systems, 2000, 13(2/3):113-120.
[15] 庄严,李国良,冯建华. 知识库实体对齐技术综述[J]. 计算机研究与发展, 2016,53(1):165-192.
[16] 刘峤,李杨,段宏,等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016, 53(3):582-600.
[17] 王海栋,郑骁庆,张红俊. 基于置信度理论的网络知识融合系统和应用[J]. 计算机系统应用, 2011, 20(1):1-6.
[18] NIKFARJAM A, SARKER A, O'CONNOR K, et al. Pharmacovigilance from social media:mining adverse drug reaction mentions using sequence labeling with word embedding cluster features[J]. Journal of the American Medical Informatics Association, 2015,22(3):671-681.
[19] BEAN D M, WU H, IQBAL E, et al. Knowledge graph prediction of unknown adverse drug reactions and validation in electronic health records[J]. Scientific reports, 2017,7(1):16416.
[20] 姜兵. 药物不良反应及其监测工作现状[J]. 中国医药科学, 2012,2(24):175-176.
[21] XIE G, XIONG R, CHURCH I. Comparison of kinetics, neural network and fuzzy logic in modelling texture changes of dry peas in long time cooking[J]. LWT-food science and technology, 1998,31(7/8):639-647.
[22] HEBELER J, FISHER M, BLACE R, et al. Web 3.0与Semantic Web编程[M]. 唐富年,唐荣年,译.北京:清华大学出版社, 2010.
