公开(公告)号：US20240296730A1

公开(公告)日：2024-09-05

申请号：US18664758

申请日：2024-05-15

Applicant: Roku, Inc.

Inventor： Sunil Ramesh ,  Charles Brian Pinkerton ,  Mark Robins ,  Anthony Wood

IPC: G08B21/10 ,  H04L12/28

CPC classification number: G08B21/10 ,  H04L12/2825 ,  H04L12/2834

Abstract: A method and system for collecting context information in response to prediction of an emergency event. A cloud-based computing system could determine that an emergency event is predicted to impact a customer premises at an upcoming time. Responsive to that determination, and before the upcoming time, the cloud-based computing system could then cause or more on-premises computing devices at the customer premises to collect and report context information, such as a count of people present at the customer premises and/or an operational state of one or more utilities or other systems at the customer premises, that may assist in responding to the emergency event. Further, the cloud-based computing system could select a given such device at the customer premises to function as a coordinating device to work with one or more other devices at the customer premises to collect and report the context information.

公开(公告)号：US20240296641A1

公开(公告)日：2024-09-05

申请号：US18449789

申请日：2023-08-15

Applicant: Roku, Inc.

Inventor： Sunil Ramesh ,  Michael Cutter ,  Karina Levitian

IPC: G06T19/20 ,  G06T15/10 ,  G06T15/50 ,  G06V10/70 ,  G06V20/40

CPC classification number: G06T19/20 ,  G06T15/10 ,  G06T15/503 ,  G06V10/70 ,  G06V20/41 ,  G06T2219/2016 ,  G06V2201/10

Abstract: In one aspect, an example method includes (i) obtaining video that depicts an area across multiple frames of the video, wherein the area is part of a scene of the video, and wherein the area is suitable for having an object inserted therein; (ii) detecting the area within the obtained video and determining area characteristic data associated with the detected area; (iii) determining scene attribute data associated with the scene; (iv) using at least the determined area characteristic data and the determined scene attribute data as a basis to select an object from among a set of multiple candidate objects; (v) inserting into the detected area the selected object to generate video that is a modified version of the obtained video; and (vi) outputting for presentation the generated video.

公开(公告)号：US20240259752A1

公开(公告)日：2024-08-01

申请号：US18163207

申请日：2023-02-01

Applicant: ROKU, INC.

Inventor： Yu-Cheng Lin ,  Brian James Hetherman ,  Sunil Ramesh ,  Michael Cutter ,  Karina Levitian

IPC: H04S7/00 ,  H04R5/02 ,  H04R5/04

CPC classification number: H04S7/303 ,  H04R5/02 ,  H04R5/04 ,  H04S7/301 ,  H04S2400/11 ,  H04S2400/13

Abstract: In one aspect, an example method for use in connection with an audio system that is configured to present audio within a listening area includes (i) detecting, by a computing system, a position of a user located within the listening area; (ii) using, by the computing system, at least the detected position of the user to identify, from among multiple candidate reference positons, a reference positon that most closely matches the detected position of the user; (iii) using, by the computing system, at least the identified reference position as a basis to select a set of audio settings that corresponds to the identified reference position; and (iv) configuring, by the computing system, the audio system based on the selected set of audio settings.

公开(公告)号：US11936948B1

公开(公告)日：2024-03-19

申请号：US18158546

申请日：2023-01-24

Applicant: Roku, Inc.

Inventor： Ronica Jethwa ,  Sunil Ramesh ,  Michael Cutter ,  Karina Levitian

IPC: H04N21/442 ,  G06V10/764 ,  G06V40/16 ,  G06V40/20 ,  H04N21/81 ,  H04N21/854

CPC classification number: H04N21/44218 ,  G06V10/764 ,  G06V40/176 ,  G06V40/23 ,  H04N21/8146 ,  H04N21/854

Abstract: In one aspect, an example method in connection with a shared content viewing session in which multiple users are receiving and viewing respective instances of the same media content in a synchronized manner is disclosed. The example method includes (i) detecting that each of the multiple users respectively exhibits a threshold extent of physical reaction around the same time; (ii) responsive to the detecting, for each of the multiple users, generating and/or storing respective visual content representing that user's physical reaction; (iii) generating a visual content composition that includes at least the generated and/or stored visual content for each of the multiple users; and (iv) outputting for presentation, the generated visual content composition.

公开(公告)号：US11763656B1

公开(公告)日：2023-09-19

申请号：US17860649

申请日：2022-07-08

Applicant: Roku, Inc.

Inventor： Sunil Ramesh ,  Charles Brian Pinkerton ,  Mark Robins ,  Anthony Wood

IPC: G08B21/10 ,  H04L12/28

CPC classification number: G08B21/10 ,  H04L12/2825 ,  H04L12/2834

Abstract: A method and system for collecting context information in response to prediction of an emergency event. A cloud-based computing system could determine that an emergency event is predicted to impact a customer premises at an upcoming time. Responsive to that determination, and before the upcoming time, the cloud-based computing system could then cause or more on-premises computing devices at the customer premises to collect and report context information, such as a count of people present at the customer premises and/or an operational state of one or more utilities or other systems at the customer premises, that may assist in responding to the emergency event. Further, the cloud-based computing system could select a given such device at the customer premises to function as a coordinating device to work with one or more other devices at the customer premises to collect and report the context information.

公开(公告)号：US20250165678A1

公开(公告)日：2025-05-22

申请号：US18511873

申请日：2023-11-16

Applicant: Roku, Inc.

Inventor： Gak Wee Low ,  Sunil Ramesh ,  Michael Patrick Cutter ,  Andrew Peter Fogg ,  Michael Richard Sanders

IPC: G06F30/27

Abstract: Conducting user research with human users is time consuming and expensive. Provided with quality training data that represents human users having different personae, models can be trained to offer responses that can emulate different human users. The models may offer synthetic users that can extract information from and respond to inputs to the models. The inputs can include prompts and responses can include answers to the prompts. In some cases, data about human users can be used to build different synthetic user memories, which may be used to generate different prompt chains corresponding to different users. The prompt chain can be used to prompt a model to respond based on the contextual information in the synthetic user memory.

公开(公告)号：US20250156919A1

公开(公告)日：2025-05-15

申请号：US18505398

申请日：2023-11-09

Applicant: Roku, Inc.

Inventor： Andrew Peter Fogg ,  Charles Brian Pinkerton ,  Sunil Ramesh ,  Michael Patrick Cutter ,  David Lee Stern ,  Ronica Jethwa

IPC: H04N21/25 ,  G06T19/00 ,  H04N21/442

Abstract: A method is described and includes presenting a stimulus to a user, wherein the stimulus comprises at least a portion of a first item of content and includes audio, video, or both; detecting at least one non-verbal reaction of the user to the stimulus; processing the detected at least one non-verbal reaction to determine a response of the user to the stimulus; providing to the user a list of recommendations based on the determined response of the user to the stimulus, wherein the list of recommendations comprises at least one second item of content selected from a content database; and prompting the user to select an item of content from the list of recommendations.

公开(公告)号：US20250039489A1

公开(公告)日：2025-01-30

申请号：US18918740

申请日：2024-10-17

Applicant: Roku, Inc.

Inventor： Hugo du Plooy ,  Kenny Wu ,  Erwin Bellers ,  Sunil Ramesh ,  Michael Cutter

IPC: H04N21/41 ,  H04N21/422 ,  H05B47/165

Abstract: In one aspect, a method includes receiving video content comprising a first data portion comprising parameters that control a visual appearance of frames of video content presented by a content-presentation device. The content-presentation device is communicatively coupled to a light unit that is (i) present in a viewing area of the content-presentation device and (ii) configured to provide ambient light in the viewing area. The method also includes extracting, from the received video content, a second data portion, separate from the first data portion, specifying one or more light control parameters that a controller associated with the light unit is configured to interpret as instructions for controlling the light unit. The method also includes transmitting the extracted second data portion to the controller to facilitate the controller controlling the light unit according to the specified one or more light control parameters.

公开(公告)号：US12199790B2

公开(公告)日：2025-01-14

申请号：US18542199

申请日：2023-12-15

Applicant: Roku, Inc.

Inventor： Anthony Wood ,  David Stern ,  Sunil Ramesh

IPC: H04L12/28

Abstract: A method for provisioning a group of devices with control-group data defining one or more functional interrelationships between the devices. The method includes providing a GUI defining an online application marketplace, the GUI specifying multiple applications available for download, each application including a different respective set of control-group data defining a different respective set of one or more functional interrelationships. Further, the method includes receiving user input selecting a given one of the applications, the selected application defining given control-group data defining a given set of one or more functional interrelationships. And the method includes responsively (i) downloading the selected application and (ii) provisioning the devices of the group with the given set of control-group data, the provisioning establishing the given set of one or more functional interrelationships between the devices of the group.

公开(公告)号：US20240406521A1

公开(公告)日：2024-12-05

申请号：US18328560

申请日：2023-06-02

Applicant: Roku, Inc.

Inventor： Sunil Ramesh ,  Michael Cutter ,  Karina Levitian

IPC: H04N21/8549 ,  H04N21/235 ,  H04N21/845

Abstract: In one aspect, an example method includes (i) obtaining first media content; (ii) obtaining plot data associated with the obtained first media content; (iii) obtaining user profile data associated with a user; (iv) identifying from the obtained first media content, a first set of segments; (v) using at least the obtained plot data, the obtained user profile data, and segment data associated with each segment, to determine segment relevance data for each such segment; (vi) using at least the determined segment relevance data for the segments as a basis to select, from among the identified first set of segments, a second set of segments; (vii) using at least the selected second set of segments to generate second media content, wherein the generated second media content is shorter in duration than the obtained first media content; and (viii) outputting for presentation the generated second media content.