基于灰度关联和神经网络的装备价格第三方服务机构评价模型  

Evaluation model of third-party service organization of equipment price based on gray correlation and neural network

作　　者：杨黎峰 孙胜祥 姚轶智 YANG Lifeng;SUN Shengxiang;YAO Yizhi(Department of Management Engineering and Equipment Economics,Naval University of Engineering,Wuhan 430033,China;Science and Technology on Scramjet Laboratory,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]海军工程大学管理工程与装备经济系,湖北武汉430033 [2]国防科技大学高超声速冲压发动机技术重点实验室,湖南长沙410073

出　　处：《国防科技大学学报》2023年第2期131-137,共7页Journal of National University of Defense Technology

基　　金：民技军用定价机制研究基金资助项目(18BGL287)。

摘　　要：为了科学合理选择装备价格第三方服务机构,研究以灰度关联分析和神经网络方法构建评价模型。研究数据采用问卷调研形式获取,针对样本数据采用灰度关联法分析评价指标与综合评分之间的关联性,发现服务态度和制度建设情况两个评价指标与综合评分关联度达0.74以上,较为重要。采用有效二级指标和综合评分作为输入和输出数据,构建基于神经网络的装备价格第三方服务机构评价模型。通过实际数据验证分析,发现神经网络模型预测精准的概率为75%,预测满足要求的概率为25%,满足实际应用需求,能够为主管部门遴选机构建言献策。In order to scientifically and reasonably select the third-party service organizations of equipment price,the evaluation model was constructed by gray correlation analysis and neural network.The research data was obtained in the form of questionnaire survey.The gray correlation method was used to analyze the correlation between the evaluation index and the comprehensive score.It is found that the two primary evaluation indicators of service attitude and system construction are more important,with a correlation degree of more than 0.74.Using effective secondary indicators and comprehensive scores as input and output data,the evaluation model based on neural network was built.Finally,through the verification and analysis of the rationality of the method,it is found that the prediction accuracy probability of the neural network model is 75%and the probability of meeting the requirements is 25%,which meets the actual user needs and can provide suggestions for the competent departments to select third-party institutions.

关 键 词：灰度关联 神经网络 第三方服务机构 评估模型 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]