公开(公告)号：US11748568B1

公开(公告)日：2023-09-05

申请号：US16988153

申请日：2020-08-07

Applicant: Amazon Technologies, Inc.

Inventor： Umut Orhan ,  Harshad Vasant Kulkarni ,  Jasmeet Chhabra ,  Vikas Dharia

IPC: G06F40/289 ,  G06F40/284 ,  H04L41/16 ,  H04L43/16 ,  H04L43/024

CPC classification number: G06F40/284 ,  H04L41/16 ,  H04L43/16 ,  H04L43/024

Abstract: A plurality of metrics records, including some records indicating metrics for which anomaly analysis has been performed, is obtained. Using a training data set which includes the metrics records, a machine learning model is trained to predict an anomaly analysis relevance score for an input record which indicates a metric name. Collection of a particular metric of an application is initiated based at least in part on an anomaly analysis relevance score obtained for the particular metric using a trained version of the model.

公开(公告)号：US12073182B2

公开(公告)日：2024-08-27

申请号：US18353164

申请日：2023-07-17

Applicant: Amazon Technologies, Inc.

Inventor： Umut Orhan ,  Harshad Vasant Kulkarni ,  Jasmeet Chhabra ,  Vikas Dharia

IPC: G06F40/284 ,  H04L41/16 ,  H04L43/16 ,  H04L43/024

CPC classification number: G06F40/284 ,  H04L41/16 ,  H04L43/16 ,  H04L43/024

Abstract: A plurality of metrics records, including some records indicating metrics for which anomaly analysis has been performed, is obtained. Using a training data set which includes the metrics records, a machine learning model is trained to predict an anomaly analysis relevance score for an input record which indicates a metric name. Collection of a particular metric of an application is initiated based at least in part on an anomaly analysis relevance score obtained for the particular metric using a trained version of the model.

公开(公告)号：US20240028830A1

公开(公告)日：2024-01-25

申请号：US18353164

申请日：2023-07-17

Applicant: Amazon Technologies, Inc.

Inventor： Umut Orhan ,  Harshad Vasant Kulkarni ,  Jasmeet Chhabra ,  Vikas Dharia

IPC: G06F40/284 ,  H04L41/16 ,  H04L43/16

CPC classification number: G06F40/284 ,  H04L41/16 ,  H04L43/16 ,  H04L43/024

Abstract: A plurality of metrics records, including some records indicating metrics for which anomaly analysis has been performed, is obtained. Using a training data set which includes the metrics records, a machine learning model is trained to predict an anomaly analysis relevance score for an input record which indicates a metric name. Collection of a particular metric of an application is initiated based at least in part on an anomaly analysis relevance score obtained for the particular metric using a trained version of the model.

公开(公告)号：US11593669B1

公开(公告)日：2023-02-28

申请号：US17105979

申请日：2020-11-27

Applicant: Amazon Technologies, Inc.

Inventor： Jasmeet Chhabra ,  Zaid Radi Abu Ziad ,  Vikas Dharia ,  Harshad Vasant Kulkarni ,  Khaled Salah Sedky ,  Scott Michael Wiltamuth ,  Douglas Allen Walter

IPC: G06F11/00 ,  G06N5/022 ,  G06F11/30 ,  G06F11/07 ,  G06N5/045 ,  G06F11/22

Abstract: Techniques for determining insight are described. An exemplary method includes receiving a request to provide insight into potential abnormal behavior; receiving one or more of anomaly information and event information associated with the potential abnormal behavior; evaluating the received one or more of the anomaly information and event information associated with the abnormal behavior to determine there is insight as to what is causing the potential abnormal behavior and to add to an insight at least two of an indication of a metric involved in the abnormal behavior, a severity for the insight indication, an indication of a relevant event involved in the abnormal behavior, and a recommendation on how to cure the potential abnormal behavior; and providing an insight indication for the generated insight.