In this study, participants automated Trademark Infringement detection and legal relevant information extraction from past judgements using Machine Learning Tools thereby reducing time & manual effort in doing so.

An increase in E-commerce has led to an exponential rise in Trademark Infringement. Identifying and mitigating Trademark Infringement is critical to protecting an organization’s trademark. Trademark Infringement is the unauthorized use of a trademark in such a way that it causes confusion and leads to deception among customers. It can cost companies a loss of millions of dollars’ worth of revenue, resulting in inefficient, costlier, and time-consuming legal proceedings.

Traditionally, trademark infringement was and still is identified using manual methods. Participants, in this study, automated Trademark Infringement detection and legally relevant information extraction from past judgments. They aimed to reduce the manual effort & time taken by both the Legal research team and the Trademark Search using advanced Machine Learning Tools by deploying Logomark Similarity Search, Wordmark Infringement Detection, E-commerce Infringement Detection, and Past Judgement Analysis.

They built a one-stop model for wordmark infringement - ‘Ensemble Match’ that combined similarity algorithms. The team experimented with multiple Deep Learning and traditional approaches to retrieve similar logo marks. It connected them using a simple yet effective Inverse Rank Position approach for logomark similarity search. The team identified 15 matched past trademark infringement judgements using the latest state-of-the-art SBERT model for semantic search.

The project's business value was to provide a one-stop solution to look for Wordmark Infringement, which offers better potential infringement detection and a few more similarity searches that are not considered currently by WIPO but are considered infringing by the Indian courts. With this new and innovative solution, the manual effort and time involved in ‘Trademark Search’ will reduce considerably.

The researchers used the following techniques for the project: Search Wrapper, Infringement Classification, Rule-based Classification Model, Random Forest, Roberta, Glove, SBERT, Cosine Similarity distance metric, LexNLP Model, RegEx, LSTM decoder-encoder, Attention Model, Custom NER model.

References:

1) Kumar S., Boorugu A., Jalasutram N., Mittal N., Jethwani N., Jain T., ‘Trademark Infringement Lookout, Identification and Stoppage Automation using Machine Learning (TILSIM)