-
Patent Agency Ranking
公开(公告)号：US10740151B1
公开(公告)日：2020-08-11
申请号：US16113629
申请日：2018-08-27
Applicant: Amazon Technologies, Inc.
Inventor： Ryan Washington , Joe W. Pate , David Walker , Scott Conrad , Mikhail Sosonkin , Matthew Evans , Nathan Kevin McCarthy , Hugo Gabignon , Victor Chin , Joel Naomi Cornett , Joshua Stephen Du Lac
Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for parallelized forensic analysis using cloud-based servers. Example methods may include generating a first request for one or more notifications in a notification queue, where the one or more notifications include a first notification indicative of a first data input at a datastore, determining a first data type of the first data input, and generating a second notification indicative of the first data type. Some example methods may include determining that a first software component is subscribed to notifications for the first data type, sending the second notification to the first software component, determining a first output of the first software component, where the first output comprises a set of extracted data from the first data input, and sending the set of extracted data to the datastore.
-
公开(公告)号：US10320819B2
公开(公告)日：2019-06-11
申请号：US15443801
申请日：2017-02-27
Applicant: Amazon Technologies, Inc.
Inventor： Alexander Watson , Daniel Brim , Christopher Simmons , Paul Radulovic , Tyler Stuart Bray , Jennifer Anne Brinkley , Eric Johnson , Victor Chin , Jack Rasgaitis , Nai Qin Cai , Michael Gough , Max Anger
IPC: H04L29/06 , G06F16/951 , G06N3/04 , G06N3/08 , G06F21/55 , G06N5/00 , G06N5/04 , G06N7/00 , G06Q20/40 , G06F16/35
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.
-
公开(公告)号：US20180248895A1
公开(公告)日：2018-08-30
申请号：US15443801
申请日：2017-02-27
Applicant: Amazon Technologies, Inc.
Inventor： Alexander Watson , Daniel Brim , Christopher Simmons , Paul Radulovic , Tyler Stuart Bray , Jennifer Anne Brinkley , Eric Johnson , Victor Chin , Jack Rasgaitis , Nai Qin Cai , Michael Gough , Max Anger
CPC classification number: H04L63/1416 , G06F17/30705 , G06F17/30864 , G06F21/554 , G06N3/0445 , G06N3/08 , G06N5/003 , G06N5/045 , G06N7/005 , G06Q20/4016 , H04L63/083 , H04L63/0861 , H04L63/101
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.
-
公开(公告)号：US11102221B2
公开(公告)日：2021-08-24
申请号：US16426830
申请日：2019-05-30
Applicant: Amazon Technologies, Inc.
Inventor： Alexander Watson , Daniel Brim , Christopher Simmons , Paul Radulovic , Tyler Stuart Bray , Jennifer Anne Brinkley , Eric Johnson , Victor Chin , Jack Rasgaitis , Nai Qin Cai , Michael Gough , Max Anger
IPC: H04L29/06 , G06F16/951 , G06F21/55 , G06N5/00 , G06N5/04 , G06N7/00 , G06Q20/40 , G06F16/35 , G06N20/20 , G06N3/04 , G06N3/08
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.
-
公开(公告)号：US20190281076A1
公开(公告)日：2019-09-12
申请号：US16426830
申请日：2019-05-30
Applicant: Amazon Technologies, Inc.
Inventor： Alexander Watson , Daniel Brim , Christopher Simmons , Paul Radulovic , Tyler Stuart Bray , Jennifer Anne Brinkley , Eric Johnson , Victor Chin , Jack Rasgaitis , Nai Qin Cai , Michael Gough , Max Anger
IPC: H04L29/06 , G06N5/00 , G06Q20/40 , G06N7/00 , G06F16/35 , G06N3/08 , G06N3/04 , G06F21/55 , G06F16/951 , G06N5/04
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.
-
-
-
-
Search Results
5
records
(took 0.013 seconds)
