# US 2026/0087082 A1 · Recommendation system using retrieval-augmented generation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0087082 A1
- Document ID: US20260087082A1
- Status: Published application
- Kind: A1
- Application number: 19/399,395
- Filed: 2025-11-24
- Published: 2026-03-26
- Earliest claimed: 2024-01-09
- Assignees: NVIDIA Corporation
- Applicants: NVIDIA Corporation
- Inventors: Tanay VARSHNEY; Kari Ann BRISKI; George Joseph CONWAY; Davide Marco ONOFRIO; Annie Prasanna SURLA; Shashank VERMA
- Web page: https://patentgrep.com/patent/US20260087082A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/3347: {using vector based model}
- G06F 16/9532: Query formulation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

In various examples, a technique for recommending items is disclosed that includes receiving a request to recommend an item. The technique further includes generating, based on the request, one or more query tags, the one or more query tags including one or more preferred tags, at least one of the preferred tags specifying an item of interest. The technique also includes generating one or more subqueries based on the one or more query tags. The technique still further includes generating, based on the one or more subqueries, a query vector in an embedding space of the vector database. The technique further includes identifying, in the vector database and using the query vector, a plurality of candidate items. The technique still further includes selecting a recommended item from the plurality of candidate items based on the request.

## Claims

### Claim 1

A method, comprising:
receiving, at a computing device, a request to recommend an item;
generating, based at least on the request, one or more query tags, the one or more query tags including one or more preferred tags, at least one of the preferred tags specifying an item of interest;
generating one or more subqueries based at least on the one or more query tags, at least one of the subqueries being generated further based at least on one or more attributes of the item of interest, the one or more attributes being retrieved from a vector database;
generating, based at least on the one or more subqueries, a query vector in an embedding space of the vector database;
identifying, in the vector database, a plurality of candidate items by querying the vector database using the query vector; and
selecting a recommended item from the plurality of candidate items based at least on the request and further based at least on the one or more attributes of the item.
