摘要
在电影素材数字化和大数据环境下能够快速准确地检索到目标电影素材,实现电影素材的自动关联,减少人工干预成为快速语义检索和智能推荐的研究重点。为了解决该问题,提出了一种基于Jena的电影素材领域本体推理模型。在电影领域专家的参与下抽取电影素材相关术语和概念,然后根据OWL语言规则,利用本体建模工具Protégé构建电影素材领域本体,并进行了语义公理和自定义规则的推理,描述了本体概念、属性相互之间的关系及本体构建和推理的细节。建立了一个基于Lucene影视素材的检索查询系统,进行了基于关键字查询和拓展查询。结果表明,该本体推理模型可以很好地对电影素材的知识进行表示,支持基于语义推理的智能查询,并且有较高的效率。
Under the environment of the digitization of movie material and the big data,it is the focus of research for fast semantic retriev- al and intelligent recommendation to quickly and accurately retrieve the target film material,and realize the automatic relevance of movie material and reduce the manual intervention. In order to solve the problem, a reasoning model of domain ontology for movie material based on Jena is proposed. The related terms and concepts of film material is extracted with the participation of experts in the field of cine- ma, then the movie material domain ontology is constructed with the ontology modeling tool Prot6g6 based on OWL rules. Then, it uses inference engine to perform reasoning for semantic axioms and user-defined rules, which describes the relationship of concept and attrib- utes of ontology with each other and the details of the construction and reasoning for the ontology. Search query system is constructed based on Lucene, supporting keyword-based query and expand query. The results show that the model can well represent the movie mate- rial knowledge, supporting intelligent recommendation based on the semantic reasoning with a high efficiency.
出处
《计算机技术与发展》
2016年第8期30-34,共5页
Computer Technology and Development
基金
上海市科学技术计划项目资助(14590500500)