Abstract
In this study, we focus on utilizing the patent citation graph structure. We investigate the effect of using only one document feature which is patent class along citation graph for the classification task. We collect advantages of a kernel-based method and build kernel function to represent feature and citation associated information. We use k-step random walk paths algorithm to calculate kernel values of each patent pairwise and SVM classifier to do the classification task. We employ sub graph technique for a large patent graph to represent citation graph information. The method is based on the property of neighborhood in a graph. The evaluation of the k-step random walk paths kernel metrics on three datasets from the United States Patent and Trademark Office (USPTO) database shows that using patent citation graph structure with only one feature achieved better performance than previous studies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Abbas, A., Zhang, L., Khan, S.U.: A literature review on the state-of-the-art in patent analysis. World Pat. Inf. 37, 3–13 (2014)
Hall, B.H., Jaffe, A.B., Trajtenberg, M.: The NBER Patent Citations Data File: Lessons, Insight and Methodological Tools (2001)
Kumar, R., Math, S., Tripathi, R.C., Tiwari, M.D.: Patent classification of the new invention using PLSA. In: Proceedings of the First International Conference on Intelligent Interactive Technologies and Multimedia, pp. 222–225 (2010)
Nguyen, H.M., Phan, C.P., Nguyen, H.Q.: GeTCo: an ontology-based approach for patent classification search. In: iiWAS 2016 Proceedings of the 18th International Conference on Information Integration and Web-based Applications and Services, pp. 241–244 (2016)
Shih, M.J., Liu, D.R.: Patent classification using ontology-based patent network analysis. In: Proceedings Pacific Asia Conference on Information Systems PACIS 2010, Taipei, pp. 962–972 (2010)
Li, X., Chen, H., Zhang, Z., Li, J.: Automatic patent classification using citation network information: an experimental study in nanotechnology. In: Proceedings of the 7th ACM/IEEE Joint Conference on Digital Libraries - Building & Sustaining the Digital Environment, pp. 419–427 (2007)
Liu, D.R., Shih, M.J.: Hybrid-patent classification based on patent-network analysis. J. Am. Soc. Inform. Sci. Technol. 62(2), 246–256 (2011)
Stutzki, J., Schubert, M.: Geodata supported classification of patent applications. In: GeoRich 2016 Proceedings of the Third International ACM SIGMOD Workshop on Managing and Mining Enriched Geo-Spatial Data, pp. 4:1–4:6 (2016)
Zhang, L., Li, L., Li, T.: Patent mining: a survey. ACM SIGKDD Explor. Newsl. 16(2), 1–19 (2015)
Shalaby, W., Zadrozny, W.: Patent retrieval: a literature review. arXiv preprint, January 2017
Noh, H., Jo, Y., Lee, S.: Keyword selection and processing strategy for applying text mining to patent analysis. Expert Syst. Appl. 42(9), 4348–4360 (2015)
D’hondt, E., Verberne, S., Koster, C., Boves, L.: Text representations for patent classification. Comput. Linguist. 39(3), 755–775 (2013)
Fall, C.J., Torcsvari, A., Benzineb, K., Karetka, G.: Automated categorization in the international patent classification. ACM SIGIR Forum 37(1), 10–25 (2003)
Li, Y., Bontcheva, K.: Adapting support vector machines for F-term-based classification of patents. ACM Trans. Asian Lang. Inf. Process. 7(2), 1–19 (2008)
Wu, C.H., Ken, Y., Huang, T.: Patent classification system using a new hybrid genetic algorithm support vector machine. Appl. Soft Comput. 10(4), 1164–1177 (2010)
Csardi, G., Nepusz, T.: The igraph software package for complex network research. InterJ. Complex Syst. 1695, 1–9 (2006)
Diego, I.M.D., Muñoz, A., Moguerza, J.M.: Methods for the combination of kernel matrices within a support vector framework. Mach. Learn. 78(1–2), 137–174 (2010)
Sugiyama, M.: graphkernels: Graph Kernels. R package version 1.2 (2017)
Karatzoglou, A., Smola, A., Hornik, K., Zeileis, A.: kernlab - an S4 package for kernel methods in R. J. Stat. Softw. 11(9), 1–20 (2004)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Nugroho, B., Aritsugi, M. (2017). Application of k-Step Random Walk Paths to Graph Kernel for Automatic Patent Classification. In: Choemprayong, S., Crestani, F., Cunningham, S. (eds) Digital Libraries: Data, Information, and Knowledge for Digital Lives. ICADL 2017. Lecture Notes in Computer Science(), vol 10647. Springer, Cham. https://doi.org/10.1007/978-3-319-70232-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-70232-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70231-5
Online ISBN: 978-3-319-70232-2
eBook Packages: Computer ScienceComputer Science (R0)