Patent · US Active

Numeric embeddings for entity-matching

US11615120B2 · kind B2 · utility

0Cited by

0References

20Claims

0Family size

Assignee

SAP SE · DE

Inventors

Stefan Klaus Baur · Heidelberg, DE
Matthias Frank · Oakland, US
Hoang-Vu Nguyen · Champaign, US

Key dates

Filing date	Jul 14, 2021
Grant date	Mar 28, 2023
Priority date	—
Expiry date	Jul 14, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/084
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Pairwise entity matching systems and methods are disclosed herein. A deep learning model may be used to match entities from separate data tables. Entities may be preprocessed to fuse textual and numeric data early in the neural network architecture. Numeric data may be represented as a vector of a geometrically progressing function. By fusing textual and numeric data, including dates, early in the neural network architecture the neural network may better learn the relationships between the numeric and textual data. Once preprocessed, the paired entities may be scored and matched using a neural network.

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