公开(公告)号：US20210406671A1

公开(公告)日：2021-12-30

申请号：US16912312

申请日：2020-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Jan Gasthaus ,  Mohamed El Fadhel Ayed ,  Lorenzo Stella ,  Tim Januschowski

IPC: G06N3/08 ,  G06F16/23 ,  G06N3/04 ,  G06F40/20

Abstract: Techniques for anomaly detection are described. An exemplary method includes receiving a request to monitor for anomalies from one or more data sources; analyzing time-series data from the one or more data sources; generating a recommendation for handling the determined anomaly, the recommendation generated by performing one or more of a root cause analysis, a heuristic analysis, and an incident similarity analysis; and reporting the anomaly and recommendation

公开(公告)号：US11675646B2

公开(公告)日：2023-06-13

申请号：US16912312

申请日：2020-06-25

Applicant: Amazon Technologies, Inc.

Inventor： Jan Gasthaus ,  Mohamed El Fadhel Ayed ,  Lorenzo Stella ,  Tim Januschowski

IPC: G06F11/07 ,  G06F16/23 ,  G06F40/20 ,  G06F11/22

CPC classification number: G06F11/079 ,  G06F11/0793 ,  G06F11/2263 ,  G06F16/2379 ,  G06F40/20

Abstract: Techniques for anomaly detection are described. An exemplary method includes receiving a request to monitor for anomalies from one or more data sources; analyzing time-series data from the one or more data sources; generating a recommendation for handling the determined anomaly, the recommendation generated by performing one or more of a root cause analysis, a heuristic analysis, and an incident similarity analysis; and reporting the anomaly and recommendation.

公开(公告)号：US11281969B1

公开(公告)日：2022-03-22

申请号：US16116631

申请日：2018-08-29

Applicant: Amazon Technologies, Inc.

Inventor： Syama Rangapuram ,  Jan Alexander Gasthaus ,  Tim Januschowski ,  Matthias Seeger ,  Lorenzo Stella

IPC: G06N3/08 ,  G06N7/00 ,  G06Q10/04 ,  G06F17/13 ,  G06K9/62

Abstract: A composite time series forecasting model comprising a neural network sub-model and one or more state space sub-models corresponding to individual time series is trained. During training, output of the neural network sub-model is used to determine parameters of the state space sub-models, and a loss function is computed using the values of the time series and probabilistic values generated as output by the state space sub-models. A trained version of the composite model is stored.