Benares, India

Sakshi Singh

This inventor holds 1 USPTO granted patent. Top assignee: L&t Technology Services Limited. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Sakshi Singh. Retrieved from https://idiyas.com/inventor/sakshi-singh-fxv4350c

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


% Patents Active = 100.0

Average Co-Inventor Count = 5.0

ph-index = 1


Company Filing History:


Years Active: 2026

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

Title: Sakshi Singh: Advancing Domain-Based OCR Error Correction.

Introduction

Sakshi Singh is an inventor associated with Benares, India, and L&T Technology Services Limited. Her patent work addresses ways to improve the accuracy of text recognized from document images.

Latest Patents

Singh is associated with 1 patent, titled “Method and System of Performing Domain-Based Error Correction After Optical Character Recognition.” The invention describes a method for correcting OCR errors by identifying text entities in document images and generating character, layout, and style embeddings for each entity. It combines these embeddings and uses an encoder-decoder model to produce corrected character embeddings, supporting context-aware text correction.

Career Highlights

Singh’s listed invention focuses on combining textual content with document layout and style information to improve OCR error correction. She is associated with L&T Technology Services Limited.

Collaborations

The provided information lists Mridul Balaraman and Madhusudan Singh as Singh’s coworkers. It does not specify their roles in the patent or the invention.

Conclusion

Sakshi Singh’s patent work explores how domain-based, context-aware correction can improve the reliability of text extracted from document images.

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…