重庆文理学院学报:自然科学版
重慶文理學院學報:自然科學版
중경문이학원학보:자연과학판
Journal of Chongqing University of Arts and Sciences
2012年
4期
18-22
,共5页
绩效评估%档案网站%语言变量%LWAA算子%信息熵%相离度
績效評估%檔案網站%語言變量%LWAA算子%信息熵%相離度
적효평고%당안망참%어언변량%LWAA산자%신식적%상리도
performance evaluation%archives websites%linguistic variables%Lin.guistic Weighted Arithmetic Averaging (LWAA) Operator%entropy%deviation degree
研究基于语言信息的档案网站绩效评估问题.首先引入语言变量的运算法则,给出语言变量间距离的概念.针对属性权重完全未知的情形,利用待评档案网站的综合属性值之间的相离度和属性权系数的随机性,给出一种语言变量多属性决策方法.该方法利用优化方法建立数学模型,以待评档案网站的综合属性值之间的相离度和权系数信息熵最大化为优化目标,用拉格朗日乘子法给出模型的最优解,得到属性的权系数.该方法能够结合决策者的主观意志和客观事实,精确确定各属性的权系数.然后利用语言加权算术平均(LWAA)算子,对语言决策信息进行加权集成,继而对档案网站进行排序和择优.最后进行实例分析.
研究基于語言信息的檔案網站績效評估問題.首先引入語言變量的運算法則,給齣語言變量間距離的概唸.針對屬性權重完全未知的情形,利用待評檔案網站的綜閤屬性值之間的相離度和屬性權繫數的隨機性,給齣一種語言變量多屬性決策方法.該方法利用優化方法建立數學模型,以待評檔案網站的綜閤屬性值之間的相離度和權繫數信息熵最大化為優化目標,用拉格朗日乘子法給齣模型的最優解,得到屬性的權繫數.該方法能夠結閤決策者的主觀意誌和客觀事實,精確確定各屬性的權繫數.然後利用語言加權算術平均(LWAA)算子,對語言決策信息進行加權集成,繼而對檔案網站進行排序和擇優.最後進行實例分析.
연구기우어언신식적당안망참적효평고문제.수선인입어언변량적운산법칙,급출어언변량간거리적개념.침대속성권중완전미지적정형,이용대평당안망참적종합속성치지간적상리도화속성권계수적수궤성,급출일충어언변량다속성결책방법.해방법이용우화방법건립수학모형,이대평당안망참적종합속성치지간적상리도화권계수신식적최대화위우화목표,용랍격랑일승자법급출모형적최우해,득도속성적권계수.해방법능구결합결책자적주관의지화객관사실,정학학정각속성적권계수.연후이용어언가권산술평균(LWAA)산자,대어언결책신식진행가권집성,계이대당안망참진행배서화택우.최후진행실례분석.
In this paper, the model of archives websites' performance evaluation was investigated with lin- guistic information. Firstly, the operational laws of linguistic variables and the concept of deviation degree between linguistic variables are introduced. Then, applying the deviation degree of decision projects and the randomicity of attribute weight coefficients, a new mathematical programming model is established. The ob- jective is to maximize the deviation degree of decision projects and to maximize the entropy of weights of each attribute. The optimal solution is the best attribute weight coefficients, which is solved, by the Lagrange mul- tiple method. And the exact and reliable decision results combining the subjectivity and the facts are ob- tained. Then the linguistic weightihg arithmetic average (LWAA) operator is utilized to aggregate the lin- guistic variables corresponding to each archives website. A method for ranking the archives websites and se- lecting the most desirable one (s) is presented. Finally, an illustrative example is shown to highlight the pro- cedure of the proposed algorithm at the end of this paper.