文献类型：期刊文献

英文题名：Pioneering Technology Mining Research for New Technology Strategic Planning

作者：Li, Shugang[1];Li, Ziyi[1];Tang, Yixin[1];Zhao, Wenjing[1];Kang, Xiaoqi[1];Zheng, Lingling[1];Yu, Zhaoxu[2]

机构：[1]Shanghai Univ, Sch Management, Shanghai 200444, Peoples R China;[2]East China Univ Sci & Technol, Dept Automat, Shanghai 200237, Peoples R China

年份：2024

卷号：16

期号：15

外文期刊名：SUSTAINABILITY

收录：;WOS:【SSCI(收录号:WOS:001287026400001)，SCI-EXPANDED(收录号:WOS:001287026400001)】；

基金：This work is supported by grants from the National Natural Science Foundation of China (71871135 and 72271155).

语种：英文

外文关键词：pioneering technologies; original innovations; Multi-Dimensional Robust Stacking model; technological development matrix; new technology strategic planning

摘要：In today's increasingly competitive globalization, innovation is crucial to technological development, and original innovations have become the high horse in the fight for market dominance by enterprises and governments. However, extracting original innovative technologies from patent data faces challenges such as anomalous data and lengthy analysis cycles, making it difficult for traditional models to achieve high-precision identification. Therefore, we propose a Multi-Dimensional Robust Stacking (MDRS) model to deeply analyze patent data, extract leading indicators, and accurately identify cutting-edge technologies. The MDRS model is divided into four stages: single indicator construction, robust indicator mining, hyper-robust indicator construction, and the pioneering technology analysis phase. Based on this model, we construct a technological development matrix to analyze core 3D-printing technologies across the industry chain. The results show that the MDRS model significantly enhances the accuracy and robustness of technology forecasting, elucidates the mechanisms of technological leadership across different stages and application scenarios, and provides new methods for quantitative analysis of technological trends. This enhances the accuracy and robustness of traditional patent data analysis, aiding governments and enterprises in optimizing resource allocation and improving market competitiveness.