Patent Maintenance Recommendation with Patent Information Network Model

Patents are of crucial importance for businesses, because they provide legal protection for the invented techniques, processes or products. A patent can be held for up to 20 years. However, large maintenance fees need to be paid to keep it enforceable. If the patent is deemed not valuable, the owner may decide to abandon it by stopping paying the maintenance fees to reduce the cost. For large companies or organizations, making such decisions is difficult because too many patents need to be investigated. In this paper, we introduce the new patent mining problem of automatic patent maintenance prediction, and propose a systematic solution to analyze patents for recommending patent maintenance decision. We model the patents as a heterogeneous time-evolving information network and propose new patent features to build model for a ranked prediction on whether to maintain or abandon a patent. In addition, a network-based refinement approach is proposed to further improve the performance. We have conducted experiments on the large scale United States Patent and Trademark Office (USPTO) database which contains over four million granted patents. The results show that our technique can achieve high performance.

[1]  R. Polk Wagner,et al.  Understanding Patent Quality Mechanisms , 2009 .

[2]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[3]  Helmut Berger,et al.  Towards a patent taxonomy integration and interaction framework , 2008, PaIR '08.

[4]  Yan Liu,et al.  Latent graphical models for quantifying and predicting patent quality , 2011, KDD.

[5]  Jay F. Nunamaker,et al.  Managing Knowledge in Light of Its Evolution Process: An Empirical Study on Citation Network-Based Patent Classification , 2009, J. Manag. Inf. Syst..

[6]  Lipika Dey,et al.  A feature selection technique for classificatory analysis , 2005, Pattern Recognit. Lett..

[7]  Hendrik Blockeel,et al.  Web mining research: a survey , 2000, SKDD.

[8]  A. Törcsvári,et al.  Automated categorization in the international patent classification , 2003, SIGF.

[9]  Jon M. Kleinberg,et al.  Automatic Resource Compilation by Analyzing Hyperlink Structure and Associated Text , 1998, Comput. Networks.

[10]  Andreas Rauber,et al.  Improving Retrievability of Patents in Prior-Art Search , 2010, ECIR.

[11]  Amit Singhal,et al.  Pivoted document length normalization , 1996, SIGIR 1996.

[12]  April Kontostathis,et al.  Experiments in First Story Detection , 2005 .

[13]  Martin F. Porter,et al.  An algorithm for suffix stripping , 1997, Program.

[14]  Ichiro Sakata,et al.  Predictive Modeling of Patent Quality by Using Text Mining , 2010 .

[15]  Ronald J. Mann,et al.  A New Look at Patent Quality: Relating Patent Prosecution to Validity , 2010 .

[16]  Vernon J. Richardson,et al.  Valuation effects of patent quality: A comparison for Japanese and U.S. firms , 2001 .

[17]  W. Scott Spangler,et al.  SIMPLE: A Strategic Information Mining Platform for Licensing and Execution , 2009, 2009 IEEE International Conference on Data Mining Workshops.

[18]  Stephen E. Robertson,et al.  Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval , 1994, SIGIR '94.

[19]  Gerard Salton,et al.  A vector space model for automatic indexing , 1975, CACM.

[20]  Ellis Horowitz,et al.  FindCite: automatically finding prior art patents , 2009 .

[21]  W. Scott Spangler,et al.  COA: finding novel patents through text analysis , 2009, KDD.

[22]  W. Bruce Croft,et al.  A language modeling approach to information retrieval , 1998, SIGIR '98.

[23]  W. Scott Spangler,et al.  Assessing patent value through advanced text analysis , 2007, ICAIL.