USPTO Patent Grant US12585689B1 for Text Vector Retrieval

ChangeBridge: Patent Grants - Business Methods (G06Q)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted patent US12585689B1 to Dell Products L.P. for a multi-layered method of prefiltering and ranking for text-based vector retrieval. This patent covers a system for generating topics, filtering them, encoding documents into a vector database, and calculating similarity scores for queries.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12585689B1 to Dell Products L.P. The patent details a method, system, and non-transitory processor-readable storage medium for a text-based vector retrieval system. Key aspects include generating and filtering topics for documents, encoding documents into a vector database with metadata, grouping vectors into search clusters, and calculating similarity scores for query strings against these clusters.

This patent grant establishes intellectual property rights for Dell Products L.P. regarding specific technologies in text vector retrieval. While not a regulatory mandate for other entities, it signifies innovation in the field and may influence future product development or licensing strategies for companies operating in areas involving text analysis, search, and artificial intelligence. Compliance officers should note this as a development in the IP landscape relevant to their technology sector.

Source document (simplified)

← USPTO Patent Grants

Multi-layered method of prefiltering and ranking for text based vector retrieval

Grant US12585689B1 Kind: B1 Mar 24, 2026

Assignee

Dell Products L.P.

Inventors

Matthew Eaton, Shyam Singaraju, Anil Koluguri, David Sydow

Abstract

Methods, system, and non-transitory processor-readable storage medium for a text-based vector retrieval system are provided herein. An example method includes generating, by a text-based vector retrieval system, a set of topics Tx for a document set DX, generating for each document DN a set of topics TD, comparing the set of topics TD against the set of topics TX to generate a filtered set of topics TDFinal, comparing the topics TDFinal against final topics of all other documents to generate a set DNMatching, encoding each document from the document set into a vector database with corresponding DNMatching and TDFinal as metadata, grouping vectors into N search clusters, retrieving N topics from a query string to generate TQuery topics, comparing the TQuery topics against topics in each cluster to identify matching clusters having R matching topics, and calculating similarity scores for documents in the matching clusters.