首页|单边区间集模糊半概念的知识表示及提取方法

单边区间集模糊半概念的知识表示及提取方法

扫码查看
原文链接
  • 万方数据
  • 维普
为了使"区间"形式加以表述的不确定信息的提取具有侧重性,需提取出对象(属性)集对应的属性(对象)区间集.本文在模糊形式背景中,通过引入2个阈值,将单边区间集与经典半概念结合,提取出属性(对象)集对应的对象(属性)区间集,从而提出区间集外延-集合内涵(集合外延-区间集内涵)(interval set extent-set intent(set extent-interval set intent),ISE-SI(SE-ISI))型单边区间集模糊半概念.全体ISE-SI(SE-ISI)型单边区间集模糊半概念构成格,并给出基于格搜寻全体ISE-SI(SE-ISI)型单边区间集模糊半概念的算法.通过与已有成果对比,显示出这2种知识表示形式的多方优势.本文所得结果在知识表示及提取方法上具有适用范围广、实际应用强等优点.
Knowledge representation and extraction method of partially-known fuzzy semiconcepts
To ensure that the extraction of uncertain information expressed in the form of"intervals"is focused,it is ne-cessary to extract the corresponding attribute(object)interval set for the object(attribute)set.By introducing two thresholds from the fuzzy context,the unilateral interval set is combined with the classical semiconcept to extract the corresponding object(attribute)interval set for the attribute(object)set,and thereby the interval set extent-set intent(set extent-interval set intent)(ISE-SI(SE-ISI))type partially-known fuzzy semiconcept is proposed.All ISE-SI(SE-ISI)type partially-known fuzzy semiconcepts form a lattice,and the algorithm based on lattice search for all ISE-SI(SE-ISI)type partially-known fuzzy semiconcepts is given.The multiple advantages of these two knowledge representation forms are demonstrated by comparing them with existing achievements.The results obtained in this paper have the advantages of broad applicability and strong practical application in knowledge representation and extraction methods.

fuzzy formal contextsemiconceptinterval setinterval-set conceptpartially-known formal conceptfuzzy conceptpartially-known fuzzy semiconceptknowledge representation and extraction

毛华、胥德华、刘川、郑博雅、王刚、张植明

展开 >

河北大学 数学与信息科学学院,河北 保定 071002

河北大学 河北省机器学习与计算机智能重点实验室,河北 保定 071002

河北大学 生命科学学院,河北 保定 071002

模糊形式背景 半概念 区间集 区间集概念 单边区间集概念 模糊概念 单边区间集模糊半概念 知识表示和提取

国家自然科学基金项目河北省高等学校人文社会科学研究项目

61572011SZ2023135

2024

10.11992/tis.202304057

智能系统学报
中国人工智能学会　哈尔滨工程大学

智能系统学报

CSTPCD北大核心
影响因子：0.672
ISSN：1673-4785
年,卷(期)：2024.19(4)
  • 13