San Jose, CA, United States of America

Shiv Kumar Saini

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

IDiyas Innovation Intelligence. (2026). Inventor Profile: Shiv Kumar Saini. Retrieved from https://idiyas.com/inventor/shiv-kumar-saini-zeh3adj7

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


Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

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

Title: Shiv Kumar Saini: Inventor in Natural Language Processing

Introduction

Shiv Kumar Saini is an inventor based in San Jose, California, and works at Adobe, Inc. His patent work includes an approach to translating natural-language queries into graph queries with the help of large language models.

Latest Patents

Saini is associated with 1 patent, titled “Translating Natural Language Input Using Large Language Models.” The invention describes a system in which a large language model generates a graph query from a natural-language query. A validation module checks the query and identifies errors, which are sent back to the model so it can provide a modified query. After the modified query is validated, the system executes it against a knowledge graph and returns the result as a response to the original query.

Career Highlights

Saini’s patent highlights work on improving the reliability of language-model-generated queries. By combining model-generated queries with validation and revision, the described approach aims to help translate natural-language requests into queries that can be executed against knowledge graphs.

Collaborations

Saini’s listed coworkers include Ramasuri Narayanam and Chetan Sharma.

Conclusion

Shiv Kumar Saini’s patent describes a validation-and-revision process for using large language models to translate natural-language input into graph queries, reflecting his work at Adobe, Inc.

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…