基于改进的证据推理方法的企业R&D成果验收评估  

Assessment of R&D productions based on an improved evidential reasoning approach

作　　者：周谧[1] 刘心报[1] 杨剑波[1,2] 

机构地区：[1]合肥工业大学管理学院,安徽合肥230009 [2]英国曼彻斯特大学商学院

出　　处：《合肥工业大学学报（自然科学版）》2009年第8期1183-1188,共6页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(7063100370772029);国家863资助项目(2006AA04Z134)

摘　　要：文章从成果质量、过程控制、项目附加值3个方面,建立了企业研发(R&D)成果评估的指标体系;介绍了证据推理(ER)算法的发展过程,论述了未改进的证据推理方法的不合理性。经过改进后的证据推理算法可以使得若干个确定性的证据在经过证据融合后的总信度也是确定性的,从而能够较好地保留专家原始评价信息的特性。最后,通过改进的证据推理算法对某大型企业的若干项R&D成果进行验收评估和排序,并利用智能决策系统(IDS)软件对此评估过程进行了模拟分析,取得了良好的效果。Quality of productions, process control and project added value are considered in constructing the assessment system of R＆D productions Of enterprises. The development process of the evidential reasoning（ER） algorithm is illustrated, and the irrationality of the original ER approach is disussed. With an improved ER algorithm, the combined reliable degree of several certain evidences is still certain, thus the characteristics of the original assessment information provided by experts are preserved. The improved ER algorithm is applied to the assessment and ranking of several R＆D productions of an enterprise. The Intelligent Decision System（IDS） software is used to simulate and analyze the whole assessment process and the effect is satisfying.

关 键 词：R&D成果 Dempster合成法则 证据推理算法 不确定性 智能决策系统 

分 类 号：C934[经济管理—管理学]