Patent Citation Network Analysis: Ranking: From Web Pages to Patents

摘要

Ranking of nodes in a network of diverse number of connections (degree) is an extensively studied field. In the theory of social networks centrality measures were constructed to rank nodes of networks based on their (not unique) topological importance, Another family of measures is related to the spectral properties of the adjacency matrix , which takes into account the importance of the influence of a neighbor. Importance can be defined recursively. Brin and Page introduced a matching recursive centrality measure called PageRank. The relevance of this algorithm to citation networks was expressed by. By adopting a citation-based recursive ranking method for patents the evolution of new field of technologies can be traced. Specifically, the laser/inkjet printer technology emerged from the recombination of existing technologies, such as sequential printing and static image production. The dynamics of the citations coming from the different precursor classes illuminate the mechanism of the emergence of new fields and give the possibility to make predictions about future technological development. The combination of using clustering algorithms with ranking algorithms give more insight about the dynamics of the patent citation network.