New York, NY, United States of America

Jiankun Song

This inventor holds 1 USPTO granted patent and 3 published patent applications. Top assignee: Maplebear Inc.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Jiankun Song. Retrieved from https://idiyas.com/inventor/jiankun-song

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

Calculating rank
USPTO Granted Patents = 1 

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

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

Title: Jiankun Song and Hybrid AI Chat Systems.

Introduction

Jiankun Song is an inventor based in New York, New York. His work includes a patent for a hybrid artificial intelligence chat system that routes user queries between language models and decision-tree flows.

Latest Patents

Song is named on 1 patent: “Hybrid artificial intelligence chat system with contextual routing between language model and decision tree flows.” The invention describes a system in which a routing large language model identifies a user’s intent using the query and its context, then selects an appropriate response model from predefined decision-tree flows or large language model chatbots. The selected model generates a response that is delivered to the user’s device.

Career Highlights

Song is associated with Maplebear Inc. His patented work focuses on combining structured decision-tree processes with conversational AI, allowing a system to choose a response approach based on the user’s intent and context.

Collaborations

Song’s listed coworkers include Riddhima Sejpal and Jatin Jain.

Conclusion

Jiankun Song’s patent presents a contextual routing approach that brings together decision-tree flows and large language models to support flexible AI conversations.

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…