Using IPC-Based Clustering and Link Analysis to Observe the Technological Directions

摘要

To explore the technological directions of an industry is essential for companies and stakeholders to anticipate the future situations and R&D activities. Patent data contains plentiful technical information, which is appropriate to be used in technological analysis in order to find out the technical topics and possible directions. Due to the complex nature of patent data, two data mining methods: IPC-based clustering and link analysis, are used to figure out the potential tendencies on thin-film solar cell. An IPC-based clustering algorithm will be proposed and utilized to generate the significant categories via the IPC and Abstract fields, while the link analysis will be adopted to draw a link diagram for the whole dataset via the Abstract, Issue Date, and Assignee Country fields. During experiment, the technical categories will be identified using the IPC-based clustering, and the technological directions will be found through the link analysis. Finally, the recognized technical categories and technological directions will be provided to the managers and stakeholders for assisting their decision making.