公开(公告)号：US12143688B2

公开(公告)日：2024-11-12

申请号：US18353935

申请日：2023-07-18

Applicant: ROKU, INC.

Inventor： Rohit Mahto ,  Kelly Lee ,  Madhulika Taneja ,  Mehul Sanghavi

IPC: H04N21/81 ,  H04N21/431 ,  H04N21/458

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for utilizing a content recommendation system powering a streaming media publisher channel to enhance an ad creative being shown to the user via awareness or performance campaigns. This method allows the platform to present the most relevant Machine Language (ML) personalized in-channel content to the publisher platform users in endemic banners that run on the platform which then correspondingly helps drive user reach. An example embodiment operates by implementing personalized content banners that may act as a hook for channel users opening their streaming device, both active and lapsed, to enter back into the channel.

公开(公告)号：US12142300B2

公开(公告)日：2024-11-12

申请号：US18051568

申请日：2022-11-01

Applicant: Roku, Inc.

Inventor： Michael Cutter ,  Sunil Ramesh ,  Karina Levitian

IPC: G11B27/036 ,  G06V20/40

Abstract: In one aspect, an example method includes (i) obtaining, by a computing system, video data representing video content; (ii) analyzing, by the computing system, the video data to identify an event that is a subject of the video content; (iii) using, by the computing system, the identified event as a basis to select audio content; and (iv) performing, by the computing system, an operation that facilitates editing the video content to include the selected audio content.

公开(公告)号：US20240370968A1

公开(公告)日：2024-11-07

申请号：US18773156

申请日：2024-07-15

Applicant: Roku, Inc.

Inventor： Matthew James SOTTEK

IPC: G06T1/60 ,  G09G5/39

Abstract: Disclosed herein are system, method, and computer program product embodiments for modifying graphics rendering by transcoding a serialized command stream. An embodiment operates by receiving a command configured to instruct an API to render a graphics element. The embodiment further operates by generating, based on the command, a transcoded command configured to instruct the API to render a modified graphics element by applying a set of modification factors to a portion of the command. Subsequently, the embodiment operates by transmitting the transcoded command to the API.

公开(公告)号：US12137279B2

公开(公告)日：2024-11-05

申请号：US18480680

申请日：2023-10-04

Applicant: Roku, Inc.

Inventor： Sunil Ramesh ,  Michael Cutter ,  Charles Brian Pinkerton ,  Karina Levitian

IPC: H04N21/8358 ,  H04N21/431 ,  H04N21/84

Abstract: In one aspect, an example method includes (i) receiving, from a content-distribution system, video comprising a watermark; (ii) extracting the watermark from the video; (iii) based on the extracted watermark, determining a content-creation attribute of the video that indicates a process by which the video was created, wherein the determining comprises using the watermark to select the content-creation attribute from among a set of two or more content-creation attributes comprising organically-generated video and synthetically-generated video; and (iv) in response to determining the content-creation attribute of the video, causing a content-presentation device to perform an action.

公开(公告)号：US12136080B2

公开(公告)日：2024-11-05

申请号：US17968659

申请日：2022-10-18

Applicant: ROKU, INC.

Inventor： Neil Edward Johnson

IPC: G06Q30/0601 ,  G06K7/10 ,  G06Q20/08 ,  G06Q20/12 ,  G06Q20/20 ,  G06Q20/22 ,  G06Q20/32 ,  G06Q20/38 ,  H04W12/03 ,  H04W84/18

Abstract: Disclosed herein are a device, method, and system for dynamically activating a lightweight mobile point-of-sale (mPOS) within a remote control creating an ad-hoc payment system within a media system. When the lightweight mPOS is activated, remote control may operate as an ad-hoc lightweight mPOS that is capable of receiving contactless payment information for purchase of content provided by a media device. The lightweight mPOS may be controlled by the media device in response to a request to purchase the content.

公开(公告)号：US12132970B2

公开(公告)日：2024-10-29

申请号：US17726280

申请日：2022-04-21

Applicant: Roku, Inc.

Inventor： Mehul Sanghavi ,  Emily Jeanne Smith

IPC: H04N21/8355 ,  H04N21/24

CPC classification number: H04N21/8355 ,  H04N21/2407

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for distributing digital data. In some embodiments, a server receives a request to distribute digital data to be consumed by a plurality of users. The request indicates that the digital data is to be distributed based on a plurality of parameters and a plurality of resources. The digital data is associated with a digital file. The server identifies an opportunity to distribute the digital data based on a first parameter and a volume of installs of the digital file. Moreover, the server causes the digital data to be distributed such that the digital data is available to be output to the second set of devices using a set of resources based on a limit on resources for the opportunity and the first parameter.

公开(公告)号：US20240346084A1

公开(公告)日：2024-10-17

申请号：US18398495

申请日：2023-12-28

Applicant: Roku, Inc.

Inventor： Kapil Kumar ,  Abhishek Majumdar ,  Danish Shaikh ,  Nitish Aggarwal ,  Srimaruti Manoj Nimmagadda ,  Aniruddha Das

IPC: G06F16/9035 ,  G06F16/9038 ,  G06F40/40

CPC classification number: G06F16/9035 ,  G06F16/9038 ,  G06F40/40

Abstract: Disclosed are system, method and/or computer program product embodiments that retrieve items for a user based on a query using a two-tower deep machine learning model. An example embodiment provides input to a context tower, wherein the input includes the query and one or more of a query embedding corresponding to the query or a graph user embedding corresponding to the user. The context tower generates a context embedding in a vector space based on the input. The model determines a measure of similarity between the context embedding and each of a plurality of item embeddings in the vector space that are generated by an item tower and represent a plurality of candidate items. A relevancy score is calculated for each candidate item based on the measure of similarity between the context embedding and the corresponding item embedding. The relevancy scores are used for item retrieval and/or ranking.

公开(公告)号：US20240333991A1

公开(公告)日：2024-10-03

申请号：US18742516

申请日：2024-06-13

Applicant: Roku, Inc.

Inventor： Cameron ESFAHANI ,  Brian King ,  Mark Young ,  Alex Bishop

IPC: H04N21/258 ,  H04N21/422 ,  H04N21/443 ,  H04N21/6377 ,  H04W76/10

CPC classification number: H04N21/25816 ,  H04N21/25875 ,  H04N21/4222 ,  H04N21/443 ,  H04N21/63775 ,  H04W76/10

Abstract: The present disclosure is directed to embodiments for securely reconfiguring a media playback device. For example, a method may include determining whether a media playback device is being controlled by a user. In response to determining that the media playback device is not being controlled by the user, the method may further include: causing display of a pictograph that includes an encrypted payload with information for wirelessly connecting to the media playback device and is configured to be scanned by a client device; determining whether a request from the client device to wirelessly connect to the media playback device is a valid request; in response to the request being valid, wirelessly connecting the client device to the media playback device via a soft access point; and receiving, at the media playback device, information for reconfiguring the media playback device.

公开(公告)号：US12101531B2

公开(公告)日：2024-09-24

申请号：US17459632

申请日：2021-08-27

Applicant: Roku, Inc.

Inventor： Jan Neerbek ,  Rafal Krzysztof Malewski ,  Brian Thoft Moth Møller ,  Paul Nangeroni ,  Amalavoyal Narasimha Chari

IPC: H04N21/442 ,  G06N3/08 ,  H04N21/45 ,  H04N21/454 ,  H04N21/466

CPC classification number: H04N21/44218 ,  G06N3/08 ,  H04N21/4524 ,  H04N21/454 ,  H04N21/4666

Abstract: Disclosed herein are system, method, and computer program product embodiments for detecting human presence in front of a plurality of sensors, such as speaker sensors, and a device with a processor, such as a television. An example method includes varying, during a collection routine, a respective signal strength of one or more of a plurality of transmitters. The example method further includes receiving results of the collection routine in a form of raw data from a plurality of sensors. The example method further includes determining, by at least one processor, a respective geographical position of one or more humans present within a predetermined geographical range of the at least one processor based on the raw data from the plurality of sensors. Subsequently, the example method includes executing an action based on the respective geographical position of the one or more humans.

公开(公告)号：US20240304219A1

公开(公告)日：2024-09-12

申请号：US18666243

申请日：2024-05-16

Applicant: Roku, Inc.

Inventor： Sunil Ramesh ,  Michael Cutter ,  Karina Levitian

IPC: G11B27/036 ,  G06T7/70

CPC classification number: G11B27/036 ,  G06T7/70 ,  G06T2207/10016 ,  G06T2207/30196

Abstract: In one aspect, an example method includes (i) estimating, using a skeletal detection model, a pose of an original actor for each of multiple frames of a video; (ii) obtaining, for each of a plurality of the estimated poses, a respective image of a replacement actor; (iii) obtaining replacement speech in the replacement actor's voice that corresponds to speech of the original actor in the video; (iv) generating, using the estimated poses, the images of the replacement actor, and the replacement speech, synthetic frames corresponding to the multiple frames of the video that depict the replacement actor in place of the original actor, with the synthetic frames including facial expressions for the replacement actor that temporally align with the replacement speech; and (iv) combining the synthetic frames and the replacement speech so as to obtain a synthetic video that replaces the original actor with the replacement actor.