Patent · US Active

Searching a data source using embeddings of a vector space

US12099533B2 · kind B2 · utility

1Cited by

5References

20Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Richard Obinna Osuala · Munich, DE
Dominik Stein · Göttingen, DE
Andrea Giovannini · La Spezia, IT

Key dates

Filing date	Sep 23, 2022
Grant date	Sep 24, 2024
Priority date	—
Expiry date	Sep 23, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06F40/284
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

In several aspects for querying a data source represented by data object embeddings in a vector space, a processor inputs, to a trained embedding generation model, a received query and at least one token for receiving from the trained embedding generation model a set of embeddings of the vector space. The set of embeddings comprises an embedding of the received query and at least one embedding of the at least one token respectively, wherein the embedding of each token is a prediction of an embedding of a supplement of the query. The data object embeddings may be searched for data object embeddings that match the set of embeddings. This may result in search result embeddings of the set of embeddings. Data objects that are represented by the search result embeddings may be determined. At least part of the determined data objects may be provided.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.