公开(公告)号：US10225365B1

公开(公告)日：2019-03-05

申请号：US14578189

申请日：2014-12-19

Applicant: Amazon Technologies, Inc.

Inventor： Blair Livingstone Hotchkies ,  Bradley Scott Bowman ,  Paul Christopher Cerda ,  Min Chong ,  Anthony T. Chor ,  Leo Parker Dirac ,  Kevin Andrew Granade ,  Udip Pant ,  Sean Michael Scott

IPC: H04L29/06 ,  H04L29/08

Abstract: Systems and methods for managing content delivery functionalities based on machine learning models are provided. In one aspect, content requests are routed in accordance with clusters of historical content requests to optimize cache performance. In another aspect, content delivery strategies for responding to content requests are determined based on a model trained on data related to historical content requests. The model may also be used to determine above-the-fold configurations for rendering responses to content requests. In some embodiments, portions of the model can be executed on client computing devices.

公开(公告)号：US11457078B2

公开(公告)日：2022-09-27

申请号：US16201883

申请日：2018-11-27

Applicant: Amazon Technologies, Inc.

Inventor： Blair Livingstone Hotchkies ,  Bradley Scott Bowman ,  Paul Christopher Cerda ,  Min Chong ,  Anthony T. Chor ,  Leo Parker Dirac ,  Kevin Andrew Granade ,  Udip Pant ,  Sean Michael Scott

IPC: H04L29/06 ,  H04L29/08 ,  H04L67/63 ,  H04L67/568 ,  H04L67/01

Abstract: Systems and methods for managing content delivery functionalities based on machine learning models are provided. In one aspect, content requests are routed in accordance with clusters of historical content requests to optimize cache performance. In another aspect, content delivery strategies for responding to content requests are determined based on a model trained on data related to historical content requests. The model may also be used to determine above-the-fold configurations for rendering responses to content requests. In some embodiments, portions of the model can be executed on client computing devices.

公开(公告)号：US10311372B1

公开(公告)日：2019-06-04

申请号：US14578099

申请日：2014-12-19

Applicant: Amazon Technologies, Inc.

Inventor： Blair Livingstone Hotchkies ,  Bradley Scott Bowman ,  Paul Christopher Cerda ,  Min Chong ,  Anthony T. Chor ,  Leo Parker Dirac ,  Kevin Andrew Granade ,  Udip Pant ,  Sean Michael Scott

IPC: G06N20/00 ,  H04L29/08 ,  G06N5/04

Abstract: Systems and methods for managing content delivery functionalities based on machine learning models are provided. In one aspect, content requests are routed in accordance with clusters of historical content requests to optimize cache performance. In another aspect, content delivery strategies for responding to content requests are determined based on a model trained on data related to historical content requests. The model may also be used to determine above-the-fold configurations for rendering responses to content requests. In some embodiments, portions of the model can be executed on client computing devices.

公开(公告)号：US10311371B1

公开(公告)日：2019-06-04

申请号：US14578050

申请日：2014-12-19

Applicant: Amazon Technologies, Inc.

Inventor： Blair Livingstone Hotchkies ,  Bradley Scott Bowman ,  Paul Christopher Cerda ,  Min Chong ,  Anthony T. Chor ,  Leo Parker Dirac ,  Kevin Andrew Granade ,  Udip Pant ,  Sean Michael Scott ,  Aman Agarwal

IPC: G06N20/00 ,  G06N5/02 ,  H04L29/08

Abstract: Systems and methods for managing content delivery functionalities based on machine learning models are provided. In one aspect, content requests are routed in accordance with clusters of historical content requests to optimize cache performance. In another aspect, content delivery strategies for responding to content requests are determined based on a model trained on data related to historical content requests. The model may also be used to determine above-the-fold configurations for rendering responses to content requests. In some embodiments, portions of the model can be executed on client computing devices.

公开(公告)号：US20190109926A1

公开(公告)日：2019-04-11

申请号：US16201883

申请日：2018-11-27

Applicant: Amazon Technologies, Inc.

Inventor： Blair Livingstone Hotchkies ,  Bradley Scott Bowman ,  Paul Christopher Cerda ,  Min Chong ,  Anthony T. Chor ,  Leo Parker Dirac ,  Kevin Andrew Granade ,  Udip Pant ,  Sean Michael Scott

IPC: H04L29/08 ,  H04L29/06

Abstract: Systems and methods for managing content delivery functionalities based on machine learning models are provided. In one aspect, content requests are routed in accordance with clusters of historical content requests to optimize cache performance. In another aspect, content delivery strategies for responding to content requests are determined based on a model trained on data related to historical content requests. The model may also be used to determine above-the-fold configurations for rendering responses to content requests. In some embodiments, portions of the model can be executed on client computing devices.