基于AHP-BP神经网络的政府信息资源配置评价研究  被引量:4

Research on Evaluation of Government Information Resources Allocation Based on AHP-BP Neural Network

在线阅读下载全文

作  者:毛太田[1] 王诗玉[1] MAO Tai-tian;WANG Shi-yu(School of Public Administration,Xiangtan University,Xiangtan 411105)

机构地区:[1]湘潭大学公共管理学院

出  处:《科技情报研究》2020年第1期66-73,共8页Scientific Information Research

基  金:国家社会科学基金项目“大数据环境下政务信息资源优化配置与服务模式创新研究”(编号:15BTQ051)

摘  要:[目的/意义]从信息设备投入、信息技术水平、信息人员素质、信息利用效率4个方面出发,对政府信息资源配置进行评价研究。针对AHP、BP神经网络评价方法的特性,提出基于AHP-BP神经网络的评价模型。[方法/过程]首先,利用AHP计算评价指标体系的综合权重,根据权值,通过重要指标筛选法选出主要因素;其次,构建BP神经网络模型,以筛选出的主要因素指标数据为训练样本,输入神经网络模型中,对其进行训练、测试;最后,将BP神经网络和AHP-BP神经网络的评价结果进行对比。[结果/结论]文章将AHP与BP神经网络相结合对政府信息资源配置进行评价,在充分考虑主观因素对评价结果影响的基础上,提高计算精度,简化神经网络模型,通过实际运用验证模型的有效性和优越性。[Purpose/significance]From the aspects of information equipment investment,information technology level,information personnel quality and information utilization efficiency,the evaluation of government information resource allocation is studied.Aiming at the characteristics of AHP and BP neural network evaluation methods,an evaluation model based on AHP-BP neural network is proposed.[Method/process]Firstly,the comprehensive weight of the evaluation index system is calculated by AHP.According to the weight,the main factors are selected by the important index screening method.Secondly,the BP neural network model is constructed,and the main factor index data is selected as the sample and input into the neural network model.It is trained and tested.Finally,the evaluation results of BP neural network and AHPBP neural network are compared.[Result/conclusion]This paper combines AHP and BP neural network to evaluate the allocation of government information resources.On the basis of fully considering the influence of subjective factors on the evaluation results,the calculation accuracy is improved,the neural network model is simplified,and the validity and superiority of the model are verified through practical application.

关 键 词:政府信息资源 AHP 重要指标筛选法 BP神经网络 

分 类 号:C931[经济管理—管理学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象