Evaluation of new quality productive forces in Henan province based on improved entropy weight-TOPSIS method and deep learning

基于改进熵权-TOPSIS方法和深度学习的河南省新型优质生产力评价

阅读:1

Abstract

This study constructs a comprehensive evaluation framework for new quality productive forces in Henan Province by integrating an improved entropy weight-TOPSIS method with deep learning techniques. The term "new quality productive forces" follows the official expression used in Chinese economic planning documents. A multi-dimensional indicator system encompassing innovation-driven development, digital transformation, green development, industrial integration, and factor coordination was established and optimized through deep learning-based feature extraction, achieving 35% indicator reduction while maintaining 94.6% information retention. Empirical analysis of 18 cities from 2018 to 2023 reveals significant spatial-temporal disparities in new quality productive forces development, characterized by a "core-periphery" structure and east-west development gradient. The improved methodology demonstrated superior performance in both accuracy (92.7%) and stability compared to traditional evaluation approaches. The findings indicate steady provincial progress with a 6.6% average annual growth rate, with digital transformation emerging as the fastest-growing dimension while innovation-driven development exhibits the highest regional disparity. Based on these results, targeted policy recommendations are proposed to promote balanced advancement of new quality productive forces across Henan Province.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。