eBay Hybrid Vector Database Patent Granted Apr 21
Summary
USPTO granted Patent US12608356B1 to eBay Inc. on April 21, 2026, covering a hybrid vector database system that combines mutable and immutable graph-based indexes for real-time vector data insertion and querying. The patent application (18991270) was filed on December 20, 2024, with 10 named inventors and 20 claims. Competitors developing vector database or AI/ML search systems should review the claims for potential infringement exposure.
“Periodically, the vector data is merged from the mutable index into one or more immutable graph-based indexes.”
About this source
GovPing monitors USPTO Patent Grants - AI & Computing (G06N) for new telecom & technology regulatory changes. Every update since tracking began is archived, classified, and available as free RSS or email alerts — 20 changes logged to date.
What changed
USPTO granted eBay Inc. a patent covering a hybrid vector database architecture that performs vector searches across both mutable indexes (supporting real-time indexing) and immutable graph-based indexes. The system merges vector data periodically from the mutable index into the immutable graph indexes. Competitors in the vector database, AI search, or machine learning infrastructure space should review the 20 granted claims to assess whether their products or services may require a license or design-around effort.
Archived snapshot
Apr 22, 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.
Hybrid vector database
Grant US12608356B1 Kind: B1 Apr 21, 2026
Assignee
eBay Inc.
Inventors
Hao Chen, Sami Ben Romdhane, Navaneetha Krishnan Thanka Nadar, Venkata R. Yella, Yuri L. Finkelstein, Viswa Prasad Vutharkar, Yongwei Lu, Erfan Zamanian Dolati, Mingda Sun, Souhaila Moalla
Abstract
In accordance with the described techniques, vector data to be inserted into a vector database is obtained. The vector data is indexed into a mutable index of the vector database that supports real-time vector indexing. Periodically, the vector data is merged from the mutable index into one or more immutable graph-based indexes. A query vector is received, and a vector search is performed in the mutable index and the one or more graph-based immutable indexes based on the query vector.
CPC Classifications
G06F 8/60 G06F 9/547 G06F 11/3433 G06F 16/215 G06F 12/128 G06F 17/18 G06F 8/20 G06F 40/106 G06F 40/143 G06F 40/166 G06F 16/245 G06F 16/172 G06F 16/28 G06F 16/285 G06F 16/13 G06F 2212/454 G06F 16/21 H04L 41/16 H04L 67/04 H04L 41/122 H04L 41/142 H04L 43/08 H04L 41/149 G06N 20/00 G06N 3/044 G06N 3/045 G06N 3/08 G06N 3/084 G06N 3/09
Filing Date
2024-12-20
Application No.
18991270
Claims
20
Mentioned entities
Parties
Related changes
Get daily alerts for USPTO Patent Grants - AI & Computing (G06N)
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 Grants - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.