Patent · US Active

Custom embedding model for semantic search

US12399918B1 · kind B1 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 27, 2024
Grant dateAug 26, 2025
Priority date
Expiry dateFeb 27, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F16/316
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

System, methods, apparatuses, and computer program products are disclosed for generating a field-specific embedding model and employing the generated field-specific embedding model for semantic search of a field-specific database. A plurality of field-specific documents stored in a field-specific database are analyzed to determine a first document and a second document that are relevant to each other. A training dataset including a first training pair is generated by pairing a first portion of the first document with a corresponding second portion of the second document based on determining that the first document and second document are relevant to each other. A field-specific embedding model is trained based on the training dataset. The plurality of field-specific documents are provided to the field-specific embedding model to generate index embedding vectors. The field-specific database storing the plurality of field-specific documents is indexed based on the generated index embedding vectors.

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