任务驱动的领域本体搜索方法研究与应用  

Research and Application on Domain Ontology Search Driven by Task

作　　者：周建慧 彭炜[1] 高云 张旭龙 郭艳萍[1] ZHOU Jian-hui;PENG Wei;GAO Yun;ZHANG Xu-long;GUO Yan-ping(School of Computer and Network Engineering,Shanxi Datong University,Datong Shanxi,037009)

机构地区：[1]山西大同大学计算机与网络工程学院,山西大同037009

出　　处：《山西大同大学学报（自然科学版）》2021年第5期33-38,共6页Journal of Shanxi Datong University(Natural Science Edition)

基　　金：大同市科技局应用基础研究计划项目[2019165]。

摘　　要：由于领域本体中蕴含了大量语义信息,而传统的本体搜索工具仅采用文本特征进行索引,在面向业务需求时未能发现最相关的领域本体。针对这种情况,提出任务驱动的领域本体搜索方法。首先对领域本体中的语义信息进行索引建模,然后对用户提出的任务进行解析,查询索引文件获得匹配结果,最后利用索引中领域本体的语义信息计算每个领域本体的排序得分,获得搜索的最终结果。实验结果表明,在不同的领域本体中,术语的相关度权重有所不同,进而能够有效地对领域本体的搜索结果进行排序,并且与传统的本体搜索工具相比,搜索的准确率和召回率均有所提升。Because domain ontology contains large amount of semantic information,and traditional method of ontology searching only used text features to index,it is difficult to find the most relevant domain ontology who matched business requirements.In view of this,a domain ontology search method driven by task is proposed.Semantic information in domain ontology was indexed first,and then task proposed by user was analyzed,based on which matching results were obtained.Finally,ranking scores of domain ontology were calculated by using semantic information in index to obtain final search results.Experimental results show that domain terms had different weights in different domain ontologies,which effectively sorted the search results,and accuracy rate and recall rate of domain ontology search were improved compared with other traditional ontology search tools.

关 键 词：本体搜索 领域本体 知识管理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]