USPTO Patent Grant: Item Recommendation System

ChangeBridge: Patent Grants - Business Methods (G06Q)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted patent US12586117B2 to Target Brands, Inc. for an item recommendation system using graph neural networks. The system processes user item selections to recommend additional items, enhancing online retail experiences.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has issued patent US12586117B2, titled 'Methods and system for automatic population of item recommendations in retail website in response to item selections,' to Target Brands, Inc. The patent describes a recommendation system that utilizes graph neural networks to analyze sequences of user-selected items and suggest further items, thereby improving online retail personalization.

This patent grant is primarily an intellectual property matter and does not impose new regulatory obligations on businesses. However, companies developing or utilizing similar recommendation technologies should be aware of this granted patent, as it may impact their freedom to operate or necessitate licensing agreements if their systems infringe upon the patented claims. The filing date for this patent was July 24, 2023, and the grant date is March 24, 2026.

Source document (simplified)

← USPTO Patent Grants

Methods and system for automatic population of item recommendations in retail website in response to item selections

Grant US12586117B2 Kind: B2 Mar 24, 2026

Assignee

Target Brands, Inc.

Inventors

Bhavtosh Rath, Amit Pande

Abstract

A recommendation system is disclosed. The recommendation system may receive a sequence of items selected by a user. Based on the sequence of items, the recommendation system may recommend one or more items. To do so, the recommendation system may apply a graph neural network. The recommendation system may receive a second sequence of items that includes the first sequence of items plus one or more items. Based on the second sequence of items, the recommendation system may recommend one or more different items by applying the graph neural network.