San Jose, CA, United States of America

Cheng Jia

This inventor holds 1 USPTO granted patent and 2 published patent applications. Top assignee: Maplebear Inc.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Cheng Jia. Retrieved from https://idiyas.com/inventor/cheng-jia-ik0xw25b

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

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: Cheng Jia: Inventor in Recommendation Systems.

Introduction

Cheng Jia is an inventor based in San Jose, California, and works at Maplebear Inc. His patent work addresses how online systems can provide recommendations quickly while accounting for both a user’s longer-term characteristics and activity during a current session.

Latest Patents

Jia is associated with 1 patent: “Using Long-Term Features and Short-Term Features to Filter Content Before a Selection Process to Reduce Latency of a Content Distribution System.” The invention describes an online system that identifies candidate recommendations in response to a request, retrieves long-term features for each candidate, and determines session-based short-term features. A scoring model uses both types of features to rank the candidates and select a subset for a subsequent selector. This approach is designed to help deliver a recommendation before the request’s latency period expires.

Career Highlights

Jia’s listed patent reflects work on recommendation systems and content distribution, with a focus on reducing the time required to serve recommendations. His professional affiliation is Maplebear Inc.

Collaborations

Jia’s listed coworkers include Aakarsh Madhavan and Karuna Ahuja. Their shared professional context is Maplebear Inc.

Conclusion

Cheng Jia’s patent focuses on combining long-term and session-specific information to streamline recommendation selection and reduce latency in content distribution systems.

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…