Patent · US Active

Method and device for abstracting a data record

US11487295B2 · kind B2 · utility

0Cited by

17References

19Claims

0Family size

Assignee

VOLKSWAGEN AKTIENGESELLSCHAFT · DE

Inventors

Peter Schlicht · Wolfsburg, DE
Fabian Hüger · Wolfenbüttel, DE

Key dates

Filing date	Oct 22, 2019
Grant date	Nov 1, 2022
Priority date	—
Expiry date	Jan 21, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG08G1/16
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

The invention relates to a method for abstracting a data record, wherein the data record is provided for machine learning at least one function, comprising the following steps: Training a complex neural network structure comprising different neural networks in the at least one function by way of machine learning based on the data record by means of a machine learning control apparatus, wherein the neural networks and the complex neural network structure are optimized with respect to maximum representativity of the data record, providing the trained complex neural network structure in the form of a data-record-specific knowledge module so that knowledge contained in the data record can be further used in a manner compliant with data protection. The invention further relates to an associated device.

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