公开(公告)号：US20250030907A1

公开(公告)日：2025-01-23

申请号：US18907109

申请日：2024-10-04

Applicant: ROKU, INC.

Inventor： Amit PALIWAL ,  Andrey MARSAVIN ,  Govind VAIDYA ,  Wim MICHIELS ,  Beth Teresa LOGAN ,  Zheng HAN ,  Tapan OZA ,  Vijay Anand RAGHAVAN

IPC: H04N21/2662 ,  G06N5/01 ,  G06N20/00 ,  G06N20/20 ,  H04N21/24 ,  H04N21/25 ,  H04N21/44 ,  H04N21/442 ,  H04N21/845

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for modifying one or more parameters of a data streaming bitrate selection algorithm based on machine learning. An example embodiment operates by training and operating a first machine learning model to predict a sustainable network bandwidth. A second machine learning model is trained to receive the sustainable network bandwidth and predict a likelihood that this network bandwidth will not empty a data buffer of streaming data. A bitrate is selected based on the likelihood being below a threshold percentage, such as 50%.

公开(公告)号：US20230133880A1

公开(公告)日：2023-05-04

申请号：US17515225

申请日：2021-10-29

Applicant: Roku, Inc.

Inventor： Amit PALIWAL ,  Andrey MARSAVIN ,  Govind VAIDYA ,  Wim MICHIELS ,  Beth Teresa LOGAN ,  Zheng HAN ,  Tapan OZA ,  Vijay Anand RAGHAVAN

IPC: H04N21/2662 ,  H04N21/25 ,  G06N20/00 ,  H04N21/24

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for modifying one or more parameters of a data streaming bitrate selection algorithm based on machine learning. An example embodiment operates by training and operating a first machine learning model to predict a sustainable network bandwidth. A second machine learning model is trained to receive the sustainable network bandwidth and predict a likelihood that this network bandwidth will not empty a data buffer of streaming data. A bitrate is selected based on the likelihood being below a threshold percentage, such as 50%.

公开(公告)号：US20220076299A1

公开(公告)日：2022-03-10

申请号：US17527595

申请日：2021-11-16

Applicant: ROKU, INC.

Inventor： Charith Srian PERIS ,  Saket Subhash MENGLE ,  Beth Teresa LOGAN ,  Willard Lennox SIMMONS

IPC: G06Q30/02 ,  G06N5/04 ,  G06N20/00

Abstract: Described herein are various embodiments for intelligent advertisement generation and distribution. An embodiment operates by determining website history information about a plurality of consumers and an ad history information about the plurality of consumers. The advertisement is provided for display on a computing device for each consumer of at least a subset of consumers of the plurality of consumers responsive to a first bid opportunity for the advertisement to be displayed. Website actions of the subset of consumers to whom the advertisement was provided for display are tracked. A predictive model that the bid opportunity lead to a conversion is generated based on the website history, ad history, and the tracking of website actions. A price to bid for a second bid opportunity is generated. The generated price to bid is submitted for the second bid opportunity to display the advertisement to a marketplace.