Adobe Inc. Patent for AI-Driven Digital Recommendations

ChangeBridge: Patent Grants - Business Methods (G06Q)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted Adobe Inc. a patent (US12586114B2) for a system that generates digital recommendations using AI, collaborative filtering, and reinforcement learning. The patent covers methods for monitoring user interactions and analyzing feedback to provide personalized content items.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has issued patent US12586114B2 to Adobe Inc. This patent details a system and method for generating digital recommendations by employing collaborative filtering, reinforcement learning with an actor-critic framework, and inclusive sets of negative feedback. The technology monitors user interactions with digital content to create item embeddings and uses a reinforcement learning model to determine additional content items to recommend, analyzing both positive and negative interactions and item embeddings.

This patent grant signifies a new intellectual property for Adobe in the AI and recommendation engine space. While it does not impose direct regulatory obligations on other entities, it highlights advancements in AI-driven personalization. Companies operating in e-commerce, digital content delivery, and advertising may need to consider this patented technology in their own development and competitive strategies, particularly concerning the use of collaborative filtering and reinforcement learning for user engagement.

Source document (simplified)

← USPTO Patent Grants

Generating digital recommendations utilizing collaborative filtering, reinforcement learning, and inclusive sets of negative feedback

Grant US12586114B2 Kind: B2 Mar 24, 2026

Assignee

Adobe Inc.

Inventors

Saayan Mitra, Xiang Chen, Vahid Azizi

Abstract

The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize collaborative filtering and a reinforcement learning model having an actor-critic framework to provide digital content items across client devices. In particular, in one or more embodiments, the disclosed systems monitor interactions of a client device with one or more digital content items to generate item embeddings (e.g., utilizing a collaborative filtering model). The disclosed systems further utilize a reinforcement learning model to generate a recommendation (e.g., determine one or more additional digital content items to provide to the client device) based on the user interactions. In some implementations, the disclosed systems utilize the reinforcement learning model to analyze every negative and positive interaction observed when generating the recommendation. Further, the disclosed systems utilize the reinforcement learning model to analyze item embeddings, which encode the relationships among the digital content items, when generating the recommendation.