Abstract
This paper re-introduces the problem of patent classification with respect to the new Cooperative Patent Classification (CPC) system. CPC has replaced the U.S. Patent Classification (USPC) coding system as the official patent classification system in 2013. We frame patent classification as a multi-label text classification problem in which the prediction for a test document is a set of labels and success is measured based on the micro-F1 measure. We propose a supervised classification system that exploits the hierarchical taxonomy of CPC as well as the citation records of a test patent; we also propose various label ranking and cut-off (calibration) methods as part of the system pipeline. To evaluate the system, we conducted experiments on U.S. patents released in 2010 and 2011 for over 600 labels that correspond to the “subclasses” at the third level in the CPC hierarchy. The best variant of our model achieves \(\approx \)70% in micro-F1 score and the results are statistically significant. To the best of our knowledge, this is the first effort to reinitiate the automated patent classification task under the new CPC coding scheme.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See Patent No. 9,226,437, granted Jan. 5, 2016. Available at: http://pdfpiw.uspto.gov/.piw?Docid=09226437.
- 2.
- 3.
These are other older patents that appear in the References Cited section and are sometimes mentioned within the description of a new patent being considered for automated coding.
- 4.
- 5.
Although code assignment in reality is only done at the subgroup level, we can collapse such deeper codes to the subclass level by simply removing code components specific to the deeper nodes. In Table 1, code for resistors (row 3) can be obtained from the more specific subgroup code (row 5) by removing the “3/08” part. Typically, due to extremely high sparsity, code assignments are carried out at a higher level in preliminary studies including our current attempt and other automated PCS efforts.
- 6.
The product of d probabilities is significantly reduced in magnitude especially for large values of d. Here, use of the geometric mean is intended to restore the magnitude of the resulting product while ensuring that it remains in [0, 1]. This eases the interpretability of intermediate probability outputs while guarding against practical concerns such as floating point underflow.
References
Cameron, A.C., Trivedi, P.K.: Regression Analysis of Count Data, vol. 53. Cambridge University Press, Cambridge (2013)
Don, S., Min, D.: Feature selection for automatic categorization of patent documents. Indian J. Sci. Technol. 9(37), 1–17 (2016). Kindly check and confirm the edit made in Ref. [2]
Eisinger, D., Tsatsaronis, G., Bundschus, M., Wieneke, U., Schroeder, M.: Automated patent categorization and guided patent search using IPC as inspired by MeSH and PubMed. J. Biomed. Semant. 4(S1), 1–23 (2013)
Fall, C.J., Törcsvári, A., Benzineb, K., Karetka, G.: Automated categorization in the international patent classification. ACM SIGIR Forum 37(1), 10–25 (2003)
Gibaja, E., Ventura, S.: A tutorial on multilabel learning. ACM Comput. Surv. (CSUR) 47(3), 52 (2015)
Hsu, C.-W., Chang, C.-C., Lin, C.-J., et al.: A practical guide to support vector classification (2003). https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
Kavuluru, R., Rios, A., Lu, Y.: An empirical evaluation of supervised learning approaches in assigning diagnosis codes to electronic medical records. Artif. Intell. Med. 65(2), 155–166 (2015)
Kim, J.-H., Choi, K.-S.: Patent document categorization based on semantic structural information. Inf. Process. Manag. 43(5), 1200–1215 (2007)
Kotsiantis, S.B., Zaharakis, I., Pintelas, P.: Supervised machine learning: a review of classification techniques (2007)
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-CS Joint Conference on Digital Libraries, pp. 419–427. ACM (2007)
Liu, D.-R., Shih, M.-J.: Hybrid-patent classification based on patent-network analysis. J. Assoc. Inf. Sci. Technol. 62(2), 246–256 (2011)
Liu, K., Peng, S., Wu, J., Zhai, C., Mamitsuka, H., Zhu, S.: MeSHLabeler: improving the accuracy of large-scale MeSH indexing by integrating diverse evidence. Bioinformatics 31(12), i339–i347 (2015)
Nam, J., Kim, J., Loza Mencía, E., Gurevych, I., Fürnkranz, J.: Large-scale multi-label text classification — revisiting neural networks. In: Calders, T., Esposito, F., Hüllermeier, E., Meo, R. (eds.) ECML PKDD 2014. LNCS (LNAI), vol. 8725, pp. 437–452. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44851-9_28
Richter, G., MacFarlane, A.: The impact of metadata on the accuracy of automated patent classification. World Pat. Inf. 27(1), 13–26 (2005)
Rios, A., Kavuluru, R.: Analyzing the moving parts of a large-scale multi-label text classification pipeline: experiences in indexing biomedical articles. In: 2015 International Conference on Healthcare Informatics (ICHI), pp. 1–7. IEEE (2015)
Salton, G., McGill, M.J.: Introduction to Modern Information Retrieval. McGraw-Hill, New York (1986)
Silla, C.N., Freitas, A.A.: A survey of hierarchical classification across different application domains. Data Min. Knowl. Discov. 22(1–2), 31–72 (2011)
Simmons, H.J.: Categorizing the useful arts: part, present, and future development of patent classification in the United States. Law Libr. J. 106, 563 (2014)
Sokolova, M., Lapalme, G.: A systematic analysis of performance measures for classification tasks. Inf. Process. Manag. 45(4), 427–437 (2009)
Tong, X., Frame, J.D.: Measuring national technological performance with patent claims data. Res. Policy 23(2), 133–141 (1994)
Tsoumakas, G., Katakis, I., Vlahavas, I.: Mining multi-label data. In: Maimon, O., Rokach, L. (eds.) Data Mining and Knowledge Discovery Handbook, pp. 667–685. Springer, Boston (2010). https://doi.org/10.1007/978-0-387-09823-4_34
U.S. Patent and Trademark Office: U.S. Patent Statistics Chart. https://www.uspto.gov/web/offices/ac/ido/oeip/taf/us_stat.htm (2016). Accessed 30 Nov 2016
U.S. Patent and Trademark Office and European Patent Office: Cooperative Patent Classification Scheme in Bulk. http://www.cooperativepatentclassification.org/cpcSchemeAndDefinitions/Bulk.html (2015). Accessed 01 Feb 2015
U.S. Patent and Trademark Office and European Patent Office: Guide to the CPC. http://www.cooperativepatentclassification.org/publications/GuideToTheCPC.pdf (2015). Accessed 30 Nov 2016
Wallace, B.C., Small, K., Brodley, C.E., Trikalinos, T.A.: Class imbalance, redux. In: 2011 IEEE 11th International Conference on Data Mining (ICDM), pp. 754–763. IEEE (2011)
Wolter, B.: It takes all kinds to make a world-some thoughts on the use of classification in patent searching. World Pat. Inf. 34(1), 8–18 (2012)
World Intellectual Property Organization: Guide to the IPC. http://www.wipo.int/export/sites/www/classifications/ipc/en/guide/guide_ipc.pdf (2016). Accessed 30 Nov 2016
Zhang, M.-L., Zhou, Z.-H.: A review on multi-label learning algorithms. IEEE Trans. Knowl. Data Eng. 26(8), 1819–1837 (2014)
Acknowledgements
We thank anonymous reviewers for their honest and constructive comments that helped improve our paper’s presentation. Our work is primarily supported by the National Library of Medicine through grant R21LM012274. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Tran, T., Kavuluru, R. (2017). Supervised Approaches to Assign Cooperative Patent Classification (CPC) Codes to Patents. In: Ghosh, A., Pal, R., Prasath, R. (eds) Mining Intelligence and Knowledge Exploration. MIKE 2017. Lecture Notes in Computer Science(), vol 10682. Springer, Cham. https://doi.org/10.1007/978-3-319-71928-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-71928-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-71927-6
Online ISBN: 978-3-319-71928-3
eBook Packages: Computer ScienceComputer Science (R0)