【摘要】 基于创新价值链视角，运用超效率SBM-Undesirable模型分别测算了中国30个省份技术研发和成果转化2个阶段的绿色创新效率；利用谱聚类算法将中国30个省份进行了绿色创新区域划分，并应用Kernel密度估计方法对各区域绿色创新效率的差异性进行了研究；构建了面板Tobit模型，探究影响因素对各区域绿色创新效率的影响机理.结果表明：从全国范围看，成果转化阶段绿色创新效率高于技术研发阶段，技术研发阶段仍然存在较大的提升空间；划分成的3个绿色创新区域绿色创新效率存在不均衡性，各区域绿色创新效率演变规律存在显著差异；不同阶段的影响因素对各区域绿色创新效率的影响程度和方向存在差异性.基于分析结论，从政府支持力度、环境规制等方面对不同区域提高绿色创新效率给出针对性建议.更多还原

【Abstract】 Based on the perspective of the innovation value chain, using the super efficiency SBM-Undesirable model, the green innovation efficiency values in the two stages of technology research and development and achievement transformation in 30 provinces in China were calculated; The spectral clustering algorithm was used to divide 30 provinces in China into green innovation regions, and the Kernel density estimation method was used to study the differences in the efficiency of green innovation in each region; Build a panel Tobit model to explore the impact mechanism of influencing factors on the efficiency of green innovation in various regions.The results show that, from a national perspective, the efficiency of green innovation in the achievement transformation stage is higher than that in the technology research and development stage, and there is still significant room for improvement in the technology research and development stage; The green innovation efficiency of the three green innovation regions is uneven, and there are significant differences in the evolution rules of green innovation efficiency among the regions; There are differences in the degree and direction of the impact of factors at different stages on the efficiency of green innovation in various regions.Based on the analysis conclusions, targeted suggestions are given to improve the efficiency of green innovation in different regions from aspects such as government support and environmental regulations.更多还原