This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Intuit, Inc.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Nandakumar Ramani and Guided Large Language Model Transaction Matching.
Introduction
Nandakumar Ramani is an inventor based in San Jose, California, and works at Intuit, Inc. His patent describes applying large language models to help match financial transactions.
Latest Patents
Ramani is associated with 1 patent: “Guided Large Language Model Transaction Matching.” The invention uses a transformer model to convert an unstructured financial institution transaction record into a structured record. It then identifies potential matching entities, selects relevant user transaction records, and prompts a large language model to find a matching transaction. The resulting match can be displayed in a user interface alongside the original financial institution record.
Career Highlights
Ramani’s patent work addresses the challenge of reconciling financial transactions by combining structured data processing with large language model assistance. This approach is designed to narrow the records considered and present a relevant match to the user.
Collaborations
His listed coworkers include Pushparaj Shanmugam and Balachandra Maddina.
Conclusion
Nandakumar Ramani’s patent reflects an application of transformer models and large language models to financial transaction matching, with the goal of helping users identify corresponding records.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile