Changeflow GovPing Banking & Finance USPTO Patent Grant: Product Recommendation Method
Routine Rule Added Final

USPTO Patent Grant: Product Recommendation Method

Favicon for changeflow.com ChangeBridge: Patent Grants - Business Methods (G06Q)
Published March 24th, 2026
Detected March 25th, 2026
Email

Summary

The USPTO has granted patent US12586116B2 for a product recommendation method using a Bayesian network. The patent, assigned to Luxottica Group S.P.A., details a system for matching products with ideal users and refining recommendations. The filing date was August 1, 2022.

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12586116B2 to Luxottica Group S.P.A. for a "Product recommendation method using Bayesian network indexing." This patent describes a method that utilizes a Bayesian network to identify ideal user characteristics for specific products within a catalog and includes a refining process to minimize errors in the network's predictions. The patent was filed on August 1, 2022, and officially granted on March 24, 2026.

This patent grant represents a new intellectual property right for a specific technological application in product recommendation systems. While it does not impose new regulatory obligations on businesses, it establishes exclusive rights for the assignee, Luxottica Group S.P.A., in the described technology. Companies operating in the e-commerce and retail sectors, particularly those developing or utilizing AI-driven recommendation engines, should be aware of this granted patent to avoid potential infringement issues and to understand the competitive landscape.

Source document (simplified)

← USPTO Patent Grants

Product recommendation method

Grant US12586116B2 Kind: B2 Mar 24, 2026

Assignee

LUXOTTICA GROUP S.P.A.

Inventors

Cristian Cascetta, Fabio Mazzarella, Luca Mazzocchi, Kamal Fahmy Salama, Filippo Bruno

Abstract

A product recommendation method includes an indexing step implementing a Bayesian network capable of creating direct matches between each respective product of a product catalog and an ideal user whose characteristics are the most likely to be suitable for the respective products. The indexing step includes inputting a first descriptor vector of a product into the Bayesian network to obtain the user-characteristics most likely to be suitable for the product. The product recommendation method further includes a refining process which identifies determinants associated with nodes and conditional probabilities of the Bayesian network to minimize errors at the nodes to which the arcs of the Bayesian network point.

CPC Classifications

G06Q 30/0631 G06Q 30/0601-0643 G06Q 30/08

Filing Date

2022-08-01

Application No.

17878404

Claims

11

View original document →

Named provisions

Product recommendation method

Classification

Agency
USPTO
Published
March 24th, 2026
Instrument
Rule
Legal weight
Binding
Stage
Final
Change scope
Minor
Document ID
US12586116B2

Who this affects

Applies to
Retailers E-commerce
Industry sector
4541 E-Commerce 4231 Wholesale Trade
Activity scope
Product Recommendation
Geographic scope
United States US

Taxonomy

Primary area
Intellectual Property
Operational domain
Legal
Topics
Artificial Intelligence E-commerce

Get Banking & Finance alerts

Weekly digest. AI-summarized, no noise.

Free. Unsubscribe anytime.

Get alerts for this source

We'll email you when ChangeBridge: Patent Grants - Business Methods (G06Q) publishes new changes.

Free. Unsubscribe anytime.