Retrieval-Augmented Item Attribute Generation via Latent Embeddings
Summary
USPTO published patent application US20260099876A1 assigned to eBay Inc., filed October 9, 2024 (Application No. 18911071). The application covers AI-driven techniques for generating item attributes in digital marketplaces using retrieval-augmented methods with latent space embeddings.
What changed
USPTO published patent application US20260099876A1 for eBay Inc. covering retrieval-augmented item attribute generation techniques. The system receives item input (title, image, or combination), generates latent space embeddings to identify similar items, extracts aspects from those items, and uses machine learning to generate name-value attribute pairs for marketplace listings.
Technology companies developing e-commerce AI systems should monitor this patent filing as it represents potential prior art in retrieval-augmented generation for automated product attribute extraction. No immediate compliance obligations arise from this publication of a patent application.
What to do next
- Monitor for updates
Archived snapshot
Apr 11, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Retrieval-Augmented Item Attribute Generation
Application US20260099876A1 Kind: A1 Apr 09, 2026
Assignee
eBay Inc.
Inventors
Jie Ren
Abstract
Retrieval-augmented item attribute generation techniques are described. An attribute generation system receives input describing a target item, such as a title of the target item, an image depicting the target item, or a combination thereof. Given the input, the attribute generation system generates a latent space embedding representation of the target item and identifies similar items based on the latent space embedding representation. The attribute generation system then identifies, for each similar item, one or more aspects that include information describing the similar item. Similar item aspects and the input describing the target item are used to generate a prompt that causes a machine learning system to generate name-value attribute pairs for the target item. The name-value attribute pairs are output for display in a user interface and selectable for inclusion in a digital marketplace listing for the target item.
CPC Classifications
G06Q 30/0643
Filing Date
2024-10-09
Application No.
18911071
Related changes
Get daily alerts for USPTO Patent Applications - Business Methods (G06Q)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - Business Methods (G06Q) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.