The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 11, 2019

Filed:

Feb. 27, 2017
Applicant:

Amazon Technologies, Inc., Reno, NV (US);

Inventors:

Alexander Watson, Seattle, WA (US);

Daniel Brim, Seattle, WA (US);

Christopher Simmons, Burnaby, CA;

Paul Radulovic, Seattle, WA (US);

Tyler Stuart Bray, San Diego, CA (US);

Jennifer Anne Brinkley, Portland, OR (US);

Eric Johnson, Seattle, WA (US);

Victor Chin, Bellevue, WA (US);

Jack Rasgaitis, San Diego, CA (US);

Nai Qin Cai, Seattle, WA (US);

Michael Gough, Seattle, WA (US);

Max Anger, Seattle, WA (US);

Assignee:

Amazon Technologies, Inc., Seattle, WA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
H04L 29/06 (2006.01); G06F 16/951 (2019.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01); G06F 21/55 (2013.01); G06N 5/00 (2006.01); G06N 5/04 (2006.01); G06N 7/00 (2006.01); G06Q 20/40 (2012.01); G06F 16/35 (2019.01);
U.S. Cl.
CPC ...
H04L 63/1416 (2013.01); G06F 16/35 (2019.01); G06F 16/951 (2019.01); G06F 21/554 (2013.01); G06N 3/0445 (2013.01); G06N 3/08 (2013.01); G06N 5/003 (2013.01); G06N 5/045 (2013.01); G06N 7/005 (2013.01); G06Q 20/4016 (2013.01); H04L 63/083 (2013.01); H04L 63/0861 (2013.01); H04L 63/101 (2013.01);
Abstract

A corpus of documents (and other data objects) stored for an entity can be analyzed to determine one or more topics for each document. Elements of the documents can be analyzed to also assign a risk score. The types of topics and security elements, and the associated risk scores, can be learned and adapted over time using, for example, a topic model and random forest regressor. Activity with respect to the documents is monitored, and expected behavior for a user determined using a trained recurrent neural network. Ongoing user activity is processed to determine whether the activity excessively deviates from the expected user activity. The activity can also be compared against the activity of user peers to determine whether the activity is also anomalous among the user peer group. For anomalous activity, risk scores of the accessed documents can be analyzed to determine whether to generate an alert.


Find Patent Forward Citations

Loading…