管理评论 ›› 2025, Vol. 37 ›› Issue (4): 98-112.

• 创新与创业管理 • 上一篇    

多层网络下企业技术创新能力影响因素及机理研究——以中国半导体行业上市公司为例

何喜军, 董颖, 武玉英, 杨娟   

  1. 北京工业大学经济与管理学院, 北京 100124
  • 收稿日期:2023-01-19 发布日期:2025-05-06
  • 作者简介:何喜军,北京工业大学经济与管理学院教授,博士生导师,博士;董颖(通讯作者),北京工业大学经济与管理学院博士研究生;武玉英,北京工业大学经济与管理学院副研究员,硕士生导师,博士;杨娟,北京工业大学经济与管理学院高级实验师,博士。
  • 基金资助:
    国家自然科学基金面上项目(71974009);国家自然科学基金项目(71774010);国际科研合作基金项目(2021B35);国家资助博士后研究人员计划C档(GZC20230184)。

Research on the Influencing Factors and Mechanism of Enterprises' Technological Innovation Capability under Multi-layer Network—Exemplified by Listed Companies in China's Semiconductor Industry

He Xijun, Dong Ying, Wu Yuying, Yang Juan   

  1. School of Economics and Management, Beijing University of Technology, Beijing 100124
  • Received:2023-01-19 Published:2025-05-06

摘要: 打通技术创新全链条中基础研究、应用研究、生产研究三个关键环节,构建企业间“知识-技术-生产”多层合作创新网络,考虑层内、层间多元关系交互作用,研究企业技术创新能力的影响因素及机理。基于负二项模型对中国半导体行业上市公司的实证研究发现:第一,PageRank中心性与企业技术创新能力呈倒U型关系;结构洞、关系广度和强度、网络嵌入水平与其正相关。第二,企业吸收能力和网络密度分别对上述关系起中介及调节作用。第三,产品复杂性指数能精确表征企业技术创新能力,并受网络嵌入水平的正向影响。第四,影响因素间形成的锁定效应、内外联动双循环效应及交互连通效应共同影响企业技术创新能力。本研究为半导体行业企业的技术创新能力提升提供决策支持。

关键词: 多层网络, 技术创新能力, 半导体, 多源异构数据, 研发合作

Abstract: This paper studies the factors that influence enterprises’ technological innovation capability by integrating the three key links of basic research, application research, and production research in the whole chain of technological innovation, building a multi-level cooperative innovation network of “knowledge-technology-production” among enterprises, and considering the interaction of multiple relationships within and between layers. Based on the empirical study of the listed companies in China’s semiconductor industry with the negative binomial model, we reach the following conclusions. First, the relationship between PageRank centrality and enterprises’ technological innovation capability takes on an inverted U shape. Structural holes, breadth and strength of relationships, and level of network embedding are positively correlated with enterprises’ technological innovation capability. Second, the absorptive capacity of enterprises and network density play a mediating and moderating role in the above relationship, respectively. Third, the product complexity index can accurately represent the technological innovation capability of enterprises. Fourth, the locking effect, internal and external linkage dual circulation effect, and interactive connectivity effect formed among the influencing factors jointly affect the technological innovation ability of enterprises. This study provides decision-making support for improving the technological innovation capabilities of enterprises in the semiconductor industry.

Key words: multilayer network, technological innovation capability, semiconductor, multi-source heterogeneous data, R&D cooperation