基于单层引文网络的技术演进路径研究——以机器学习领域为例

Researching on Technological Evolution Path Based on the Direct Patent Citation Network——A Case Study in the Field of the Machine Learning

科学地把握技术发展动态和了解技术发展脉络对企业和政府制定创新战略具有重要意义。本文提出了一种基于专利单层引文网络社区划分识别技术演进路径的方法,并以机器学习领域为例,构建五个时间段下的专利单层引文网络,通过分析网络结构,发现机器学习领域存在一定的技术壁垒;接着使用社区发现算法识别专利主题,利用德温特手工代码映射主题内容,依据相邻时间段引文网络社区之间的引用强度构建主题演化冲积图,最终识别出四条主要技术演进路径,验证了方法的有效性,表明本文提出的方法有望对现有技术演进路径的分析方法起到一定的补充作用。

It is of great significance for enterprises and governments to scientifically grasp the development trend of the technology. A method is proposed in this paper to track technological evolution paths by community detection in original direct citation network. After constructing five successive citation networks in the patent field of Machine Learning, the key topics in every period are identified through community detection algorithm and the topic content are represented by Derwent Manual Code. Then it is found that there are certain technical barriers in the field of machine learning through the analysis of network structure. Finally, four main technological evolution paths are tracked by detecting strong connections between communities in adjacent sliced time periods, which show that the method proposed in this paper is expected to supplement the existing approaches of tracking technological evolution paths.