摘要
为客观、准确地比较地区生产总值(GDP)万亿元级城市的创新能力,确定城市创新能力比较体系中各指标的权重是基础和核心。首先,根据文献分析法及创新成果产出的特征,选取比较指标。其次,采用因子分析法对数据进行降维处理,再利用变异系数法、熵权法及主成分分析法,结合最小鉴别信息原理构建组合赋权模型对GDP达万亿元的国内城市的创新能力进行实证分析。结果表明,影响这类城市创新能力的主要因素为创新效率、创新实现、创新提升3个因子;这类城市整体创新能力一般,创新能力较强的城市有北京、深圳、上海、广州;不同地区的城市的创新能力有显著差异,东部地区城市的创新能力强于中西部地区城市。最后,结合重要影响因素,对如何提高生产总值万亿元级城市创新能力提出对策建议。
In order to objectively and accurately compare the innovation capability of trillion GDP cities,it is crucial to determine the weight of each indicator in the urban innovation capability comparison system.First of all,using the literature analysis method and the characteristics of innovation output,the paper selects the comparison index.Secondly,the factor analysis method is used to reduce the dimension of the data,and then the coefficient of variation method,entropy weight method and principal component analysis method are combined with the principle of minimum discriminant information to construct a combination weighting model to empirically analyze the innovation ability of trillion GDP cities.The results show that the main factors affecting urban innovation capability are innovation efficiency,innovation realization and innovation improvement;the overall innovation ability of trillion GDP city is not outstanding;cities with strong innovation ability are Beijing,Shenzhen,Shanghai,Guangzhou;there are significant differences in the innovation ability of different cities,and the innovation ability of the eastern region is stronger than that of the central and western regions.Finally,combined with important influencing factors,suggestions on how to improve urban innovation capability are put forward.
作者
周子钰
柳炳祥
付振康
Zhou Ziyu;Liu Bingxiang;Fu Zhenkang(Graduate School,Jingdezhen Ceramic University,Jingdezhen 333403,China;School of Information Engineering,Jingdezhen Ceramic University,Jingdezhen 333403,China)
出处
《科技管理研究》
CSSCI
北大核心
2022年第17期9-15,共7页
Science and Technology Management Research
基金
江西省研究生创新专项资金项目“高校专利质量评价指标体系构建实证研究”(YC2021-S532)。
关键词
创新能力
最小鉴别信息
组合赋权
专利
innovation ability
minimum identification information
combination weighting
patent
