Ranchi, India

Piush Kumar Singh

This inventor holds 1 USPTO granted patent. Top assignee: Fmr Corp.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Piush Kumar Singh. Retrieved from https://idiyas.com/inventor/piush-kumar-singh

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: Piush Kumar Singh: Inventor in Document Processing

Introduction

Piush Kumar Singh is an inventor associated with Ranchi, India, and Fmr Corp. His listed patent focuses on representing the positions of textual objects in document images for use in machine-learning systems. Singh is credited with 1 patent in the information provided.

Latest Patents

Singh’s listed patent is “Method for Adaptively Encoding Positions of Textual Objects in a Document.” It describes a computer-implemented method that receives an image of a document and identifies the absolute position of a textual object within it. The system normalizes that position to obtain a relative position, calculates a bin size for dividing at least one image axis into evenly spaced bins, and discretizes the relative position using those bins. The resulting discretized position and the object’s textual content are then provided as input to a machine-learning model.

Career Highlights

The patent reflects work at the intersection of document-image processing and machine learning. Its adaptive position encoding method is designed to convert the location of text in a document into a structured representation that a model can process.

Collaborations

The supplied information lists Chen Lin and Mathew James Pazaris as Singh’s coworkers. It does not specify their roles in the patent or describe particular collaborative contributions.

Conclusion

Piush Kumar Singh’s listed invention addresses how textual positions in document images can be discretized and supplied to machine-learning models, highlighting a focused contribution to document processing.

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…