Patent · US Active

Systems, methods, and techniques for training neural networks and utilizing the neural networks to detect non-compliant content

US11568172B2 · kind B2 · utility

0Cited by

18References

20Claims

0Family size

Assignee

Walmart Apollo, LLC · US

Inventors

Shreyansh Prakash Gandhi · Milpitas, US
Alessandro Magnani · Menlo Park, US
Abhinandan Krishnan · Sunnyvale, US
Abon Chaudhuri · Sunnyvale, US
Samrat Kokkula · Santa Clara, US
Venkatesh Kandaswamy · San Ramon, US

Key dates

Filing date	Feb 12, 2021
Grant date	Jan 31, 2023
Priority date	—
Expiry date	Feb 12, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06V2201/09
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A system can include one or more processors and one or more non-transitory computer-readable storage media storing computing instructions configured to run on the one or more processors and perform: generating a training dataset for training a neural network detection model; identifying, using the neural network detection model, as trained, the non-compliant content in the synthetic training images; receiving, at the neural network detection model, at least one image; and utilizing the neural network detection model to determine whether the at least one image comprises the non-compliant content. Other embodiments are disclosed herein.

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