MACHINE LEARNED BIOMETRIC TOKEN

Number of patents in Portfolio can not be more than 2000

United States of America Patent

APP PUB NO 20170358148A1
SERIAL NO

15286178

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

Embodiments of the invention(s) described herein enable a system that may rely on a biometric identifier entry validation system. The validation system “learns” the use pattern of a user. The validation system uses biometric methods such as facial recognition, palm veins, and thumb prints as an entry or passage token. When enough data has been collected, the validation system sends the user's biometric identifier to the use location within a bounded time frame when it expects a regular user to arrive at that location and within that time frame. In this manner the biometric identifier becomes a biometric token that replaces the need to use a form of fare media. Thus, the validation system becomes more efficient and recognizes a user faster after collecting data of a user for a short time. The validations system can record and interpret historic data. With this data, the validation system knows, on average, when to expect that passenger to arrive and where.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
CUBIC CORPORATION9333 BALBOA AVENUE SAN DIEGO CA 92123

International Classification(s)

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Kayhani, Niosha London, GB 15 41
Reymann, Steffen Surrey, GB 51 470

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation