Abstract

This paper reports on the construction of a new database – called TM-Link – that contains 12 million trade mark applications and registrations across six jurisdictions – Australia, Canada, New Zealand, the United States, the United Kingdom and the European Union. A new feature of the database is the identification of trade mark equivalents (or families) within and across national trade mark offices. Equivalent trade marks are two, or more, insignias for the same product applied for by the same company. For patents, equivalents can be easily identified as they are almost universally linked through a legal priority nominated in the application, but for trade marks legal priority is territorial, so the incentive to file for global priority is comparatively weak. To identify the number of true trade mark equivalents we therefore create synthetic links using a neural network-based machine learning algorithm.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call