Assessment of Patent Legal Value by Regression and Back-Propagation Neural Network

Authors

  • Hui-Chung Che Gainia Intellectual Asset Services, Inc.
  • Yi-Hsuan Lai, Szu-Yi Wang Institute of Technology Management, Chung Hua University

DOI:

https://doi.org/10.6977/IJoSI.201001_1(1).0003

Abstract

This study aimed at the basis of patent law and proposed a revolutionary valuation model for the monetary legal value of patents. The damage award of a patent infringement lawsuit was deemed to be the legal value of a patent. 65 Effective samples of infringement lawsuits were extracted from 4,289 patent related lawsuits which were retrieved in U.S. district courts of Delaware, California and Texas. 17 patent indicators were summarized to quantitatively describe dimensions of patents. The linear regression analysis was applied to discuss the linear relationship between each patent indicator and the damage award; finally 7 significant patent indicators were derived. The Back-Propagation Neural Network was then applied to construct the nonlinear valuation model of patent legal value, wherein the 7 significant patent indicators were the input variables and the damage award was the output variable. The proposed patent valuation model was validated to have the predictive power by error analysis. It accommodated to valuate the possible damage award or to negotiate the settlement fee for disputing patent infringement lawsuits. 

Author Biographies

Hui-Chung Che, Gainia Intellectual Asset Services, Inc.

Chief Technology Officer & Vice President

Yi-Hsuan Lai, Szu-Yi Wang, Institute of Technology Management, Chung Hua University

Assistant professor

Published

2010-01-07