基于SA-BP算法的本体概念语义相似度综合计算  

Comprehensive Calculation of Semantic Similarity of Ontology Concept Based on SA-BP

作　　者：许飞翔 叶霞 李琳琳 曹军博 王馨 XU Fei-xiang;YE Xia;LI Lin-lin;CAO Jun-bo;WANG Xin(Academy of Combat Support,Rocket Force University of Engineering,Xi’an 710025,China;Information Systems Department,University of Maryland,Baltimore,Maryland 21250,USA)

机构地区：[1]火箭军工程大学作战保障学院,西安710025 [2]马里兰大学信息系统学院,马里兰州巴尔的摩21250

出　　处：《计算机科学》2020年第1期199-204,共6页Computer Science

基　　金：国家自然科学基金(61702525)~~

摘　　要：不同作战部队在指挥信息系统测试评估中建立的指标存在异构问题,导致在信息交互和测试数据共享上存在较大困难。实现指标本体概念的映射和集成,建立一个统一的全局指标本体树可以有效地解决该问题,其中本体概念相似度计算的准确性至关重要。针对现有本体概念相似度计算模型中存在的精度不高的问题,提出了基于模拟退火改进BP(Back Propagation)神经网络(Simulated Annealing Back Propagation,SA-BP)算法的相似度综合计算模型。首先,对经典的基于语义距离、信息内容和概念属性的相似度计算模型进行改进,同时提出了基于概念子节点重合度的相似度计算模型;然后,采用SA-BP算法进行相似度综合计算,避免现有方法中人为确定权重的主观性和简单线性加权的不准确性问题;最后,从某作战部队不同单位建立的各异的指挥信息系统评估指标的本体概念中提取样本数据,对相似度综合计算模型进行训练测试。实验数据表明,相比于PSO-BP计算模型和主成分分析确定权值的线性加权计算模型,基于SA-BP算法的相似度综合计算模型的计算结果与专家评价结果的Pearson相关系数分别提升了0.0695和0.1351,达到了极强相关的一致性。实验数据充分说明,模拟退火算法改进的BP神经网络在训练后可以较好地收敛,在综合计算本体概念相似度时更加准确,从而有效地解决了本体概念集成的关键问题。There are heterogeneous problems in indicators that are established by different combat forces when evaluating and testing command information systems,which leads to great difficulties in information interaction and data sharing.In order to achieve mapping and integration of indicator’s ontology-concept,building a unified global indicator ontology tree is an effective solution.In this case,the accuracy of similarity calculation for ontology-concept becomes crucial.Aiming at the problem of low accuracy in the existing ontology-concept similarity calculation model,a comprehensive simi-larity calculation model based on BP neural network algorithm which is improved by Simulated Annealing(SA-BP),was proposed.This paper first improved the classical similarity calculation models based on semantic distance,information content and conceptual attribute.Besides,a similarity calculation model in view of concept’s sub-node coincidence was proposed in order to avoid the subjectivity of artificially determined weights and the inaccuracy of simple linear weighting in existing models.At last,a training test on the comprehensive similarity calculation model was performed,while the sample data were extracted from ontology-concept of variable evaluation indicators that come from command information systems established by different departments of combat forces.Experimental data show that compared with PSO-BP calculation model and principal-component linear weighted calculation model,the comprehensive similarity calculation model based on SA-BP algorithm achieves strong correlation,since its results and its Pearson correlation coefficient of the results evaluated by experts are increased by 0.0695 and 0.1351 respectively.The experimental results verify that,after training,SA-BP algorithm can converge better and achieve higher accurate when calculating ontology-concept similarity.Hence,key issues of integration for ontology-concept can be effectively solved.

关 键 词：本体集成 语义相似度计算 BP神经网络 模拟退火算法 子节点重合度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]