Jaipur, India

Prateek Agarwal

This inventor holds 1 USPTO granted patent. Top assignee: Adobe, Inc.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Prateek Agarwal. Retrieved from https://idiyas.com/inventor/prateek-agarwal-0v8ma9xl

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Prateek Agarwal: Inventor in Long-Range Event Relation Extraction

Introduction

Prateek Agarwal is an inventor based in Jaipur, India, whose patent work concerns methods for extracting relationships between events described across long stretches of text. His listed patent is associated with Adobe Inc.

Latest Patents

Agarwal is named on one patent, 1 patent: “Generating and Utilizing Models for Long-Range Event Relation Extraction.” The disclosure describes creating a dataset by adding synthetic sentences to a digital document containing an event pair. A generative language model can produce sentences that are inserted between the events to meet a long-range relation threshold. The resulting dataset can then be used to train an event relation extraction model to identify relationships between events that are separated in the text.

Career Highlights

The patent reflects work at the intersection of natural language processing and machine learning. Its approach uses generated text to expand training data and supports models designed to recognize event relationships beyond nearby passages.

Collaborations

The patent is associated with Adobe Inc., indicating a connection between Agarwal’s invention and the company’s research and development efforts.

Conclusion

Prateek Agarwal’s patent focuses on using synthetic sentences and machine learning to improve the extraction of long-range relationships between events in digital documents.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…