一个基于枸杞病虫害领域本体的语义检索模型  

A Semantic Retrieval Model with Domain Ontology Based on Wolfberry Disease and Pests

作　　者：李贯峰[1] 李卫军[2] 

机构地区：[1]宁夏大学信息工程学院,宁夏银川750021 [2]北方民族大学网络信息技术中心,宁夏银川750021

出　　处：《计算机技术与发展》2017年第9期48-52,共5页Computer Technology and Development

基　　金：宁夏自治区高校科研基金资助项目(NGY2014009)

摘　　要：由于缺少信息在语义上的处理和表示,传统的以关键字和主题词为检索途径的信息检索方法会导致检索结果不全面和不准确,无法完全满足用户的检索要求。为了提升检索系统的检索质量,将本体引入至语义检索过程中,提出了一种基于枸杞病虫害领域本体的语义检索模型,并对模型涉及的一些关键技术进行了研究。该模型构建了枸杞病虫害领域本体,并修复了本体不一致问题,确保领域知识能准确的组织和表示,利用本体固有的树形结构,结合语义距离、上下位概念重合度及概念节点层次深度等影响语义相似度计算的因素,提出了一个概念相似度算法,结合所建立的语义推理规则,构建了基于枸杞病虫害领域本体的查询与检索模型。实验结果表明,该语义检索模型能较好地弥补传统检索方式的不足,提高信息检索的查全率和查准率。The traditional information retrieval methods based on keywords and subject are lack of processing and presentation on the se- mantic level and thus lead to incomplete and inaccurate retrieval results, which cannot meet the user＇ s retrieval needs totally. In order to improve the quality of retrieval system, a model of semantic retrieval based on ontology for wolfberry disease and pests domain has been presented and its key technologies have been investigated in the processing of the introduction of ontology into semantic retrieving. It con- structs the domain ontology of wolfberry diseases and pests, and modifies its inconsistent problem to ensure consistency and accuracy of wolfberry diseases and pests knowledge. Under the guidance of hierarchical tree structure of the domain ontology, a concept similarity method considering semantic distance, superior concepts coincidence degree and depth of concept nodes is proposed. Combined with the semantic inference rules a semantic retrieval model based on domain ontology of wolfberry disease and pests is realized. The experimental results demonstrate that the semantic retrieval model has well overcome the deficiency of the traditional retrieval method and effectively improved the recall and precision of information retrieval.

关 键 词：本体 枸杞病虫害 不一致性检测 语义相似度 语义检索 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]