The spatio-temporal pattern driving factors of high-skilled talent distribution in Shandong Province and their impact on urban innovative development

Talent is the first resource to drive scientific and technological innovation, and its optimal allocation is directly related to the healthy development of the region and the effectiveness of the innovative national strategy, which is crucial to promoting the development of new quality productivity. Based on the data from the fifth, sixth and seventh national censuses of China, this paper analyzes the spatio-temporal characteristics and driving factors of the distribution of highly skilled talents in Shandong Province by using spatial statistical analysis and geographic detectors. Meanwhile, a fixed panel effect Poisson model is constructed to explore the impact of highly skilled talents on urban innovative development. The main findings are as follows: ①The scale of highly skilled talents in Shandong Province is generally on the rise, but it shows an unbalanced distribution pattern of "strong in Jiaodong region and central Shandong region, weak in southern Shandong and Northwest Shandong".②The distribution of high skilled talents in Shandong Province showed significant positive spatial autocorrelation in 2000 and 2010, but no significant local agglomeration or discrete distribution pattern in 2020; ③The aggregation of highly skilled talents in Shandong Province is the result of the joint drive of multiple factors, and there is a significant two-factor enhancing effect among the vast majority of driving factors. ④High skilled talents play a significant role in promoting urban innovation in Shandong Province, but their average marginal effect is weakening. Based on this, by integrating advanced concepts and practices from various countries, countermeasures and suggestions for optimizing the distribution pattern of high-skilled talents in Shandong Province are proposed to further promote the province's efforts to build a talent highland and achieve innovative development.