Keyword-based patent citation prediction via information theory

Farshad Madani, Martin Zwick, Tugrul Daim
2018 International Journal of General Systems  
Patent citation shows how a technology impacts other inventions, so the number of patent citations (backward citations) is used in many technology prediction studies. Current prediction methods use patent citations, but since it may take a long time till a patent is cited by other inventors, identifying impactful patents based on their citations is not an effective way. The offered prediction method in this article predicts patent citations based on the content of patents. In this research,
more » ... nstructability Analysis (RA), which is based on information theory and graph theory, is applied to predict patent citations based on keywords extracted from the abstracts of selected patents. After applying three classes of RA (variable-based analysis without and with loops and statebased analysis), nine specific IV states of a predicting model are extracted. These states involve the four keywords of 'chamber', 'hous', 'main', and 'return'. Lastly, the abstracts of the patents are examined to identify the technical subjects relevant to smart building technologies for which these keywords are proxies.
doi:10.1080/03081079.2018.1524892 fatcat:436ccf45avgzpfpswehle7pnzy