公开(公告)号：US20250024114A1

公开(公告)日：2025-01-16

申请号：US18351434

申请日：2023-07-12

Applicant: Netflix, Inc.

Inventor： Allison Nicole Deal ,  Flavio Ribeiro Nogueira Barbosa ,  Xiaomei Liu ,  Katheryn Shi ,  Wei Wei ,  Christopher Newton

IPC: H04N21/6543 ,  H04N21/2187 ,  H04N21/239 ,  H04N21/472

Abstract: The disclosed computer-implemented methods and systems trigger actions by a client media player in response to determining that a live event has occurred during a live media broadcast. For example, the disclosed methods and systems determine that a live event has occurred during a live media broadcast and can generate instructions for various actions that the client media player should take in response to the live event. In one or more implementations, the disclosed methods and systems communicate these tailored instructions via the same dedicated communication channel that carries media content requests and responses. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US12192533B2

公开(公告)日：2025-01-07

申请号：US18166430

申请日：2023-02-08

Applicant: NETFLIX, INC.

Inventor： Andrey Norkin

IPC: H04N19/86 ,  H04N19/117 ,  H04N19/124 ,  H04N19/132 ,  H04N19/176 ,  H04N19/186 ,  H04N19/80

Abstract: One embodiment of the present invention sets forth a technique for deblocking video frames. The technique includes determining a filter length associated with a boundary between a first block and a second block included in the same video frame. The technique also includes computing a parameter value that minimizes a sum of squares of second derivatives associated with samples from the first block and second block that are adjacent to the boundary. The technique further includes determining a plurality of filter values based on the parameter value and the filter length, and applying a filter having the filter length and the filter values to additional samples within the first and second blocks to generate two filtered blocks corresponding to the first and second blocks. The technique additionally comprises generating a second video frame that includes the two filtered blocks.

公开(公告)号：US12181995B2

公开(公告)日：2024-12-31

申请号：US17683818

申请日：2022-03-01

Applicant: NETFLIX, INC.

Inventor： Varun Khaitan ,  Joseph Lynch ,  Rajiv Shringi

IPC: G06F16/00 ,  G06F9/54 ,  G06F11/30 ,  G06F40/284

Abstract: In various embodiments, a computer-implemented method comprises receiving, from a first endpoint device, a first event during a first time period, modifying an event log to include a record associated with the first event, causing a rollup queue to include a request to count a first count value associated with the first event, and generating, in a second time period subsequent to the first time period, a counter value associated with at least the first event based on the rollup queue and the event log.

公开(公告)号：US12166840B2

公开(公告)日：2024-12-10

申请号：US18355364

申请日：2023-07-19

Applicant: NETFLIX, INC.

Inventor： Christopher Newton

IPC: H04L67/568 ,  H04L67/1001 ,  H04L69/22 ,  H04L69/329

Abstract: Various embodiments of the present disclosure relate to a computer-implemented method of receiving a header associated with an object, where the header includes a limit value that specifies a quantity of times the object is to be served from a cache device before revalidation, and a current count value that specifies a number of times that the object has been served since a most-recent revalidation or load, receiving a request for the object from a requesting device, and upon determining that the current count value is below the limit value, serving the object to the requesting device from the cache device, or upon determining that the current count value matches the limit value, transmitting a request for revalidating the object.

公开(公告)号：US20240403713A1

公开(公告)日：2024-12-05

申请号：US18679215

申请日：2024-05-30

Applicant: Netflix, Inc.

Inventor： Ding Tong ,  Qifeng Qiao ,  Justin Derrick Basilico ,  Ting-Po Lee ,  James McInerney

IPC: G06N20/00

Abstract: A computer-implemented method includes identifying offline evaluation metrics that indicate, for a given feedback loop in a recommendation system, various feedback loop characteristics that are detrimental to the feedback loop. The method also includes generating a predictive machine learning (ML) model that correlates the identified offline evaluation metrics with indications of those feedback loop characteristics that are detrimental to the feedback loop. The method further includes instantiating the predictive ML model to predict, using the correlated offline evaluation metrics and the detrimental feedback loop characteristics, how the feedback loop will be negatively affected over time, and providing, to at least one entity, an indication of how the feedback loop will be negatively affected over time due to the detrimental feedback loop characteristics. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US20240388739A1

公开(公告)日：2024-11-21

申请号：US18441725

申请日：2024-02-14

Applicant: Netflix, Inc.

Inventor： Joel Sole Rojals

IPC: H04N19/86 ,  H04N19/167 ,  H04N19/182

Abstract: A computer-implemented method includes accessing a video frame that includes multiple pixels. The method also includes computing a local distribution for a specified region of the video frame that includes various pixels that are likely to include banding artifacts. This computing includes: defining a probability range for the local distribution that lies within a predefined interval, generating, using the defined probability range, a cumulative vector that includes a distribution of pixels values along a cumulative range of pixels that lie within the specified region of the video frame, and selecting a pseudorandom value within the cumulative range. The method further includes applying dithering at least to the specified region of the video frame using the selected pseudorandom values within the cumulative range. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US20240388615A1

公开(公告)日：2024-11-21

申请号：US18732122

申请日：2024-06-03

Applicant: NETFLIX, INC.

Inventor： Christopher Alan NEWTON

IPC: H04L65/60 ,  G06F8/71 ,  G06F16/955 ,  H04L67/568

Abstract: In various embodiments, a caching application streams segments of a downloadable to a client device. At a first point-in-time, the caching application receives a first request for a first segment of the downloadable from the client device. The caching application computes a cache key based on a request Uniform Resource Locator included in the first request and a version identifier associated with the downloadable. The caching application determines that no segment corresponding to the cache key is stored in a cache. The caching application transmits a second request for the first segment to a different server. Upon receiving a first version of the first segment from the different server, the caching server transmits a response that includes the first version of the first segment to the client device.

公开(公告)号：US20240259650A1

公开(公告)日：2024-08-01

申请号：US18160473

申请日：2023-01-27

Applicant: Baskar Odayarkoil ,  Akshay Garg

Inventor： Baskar Odayarkoil ,  Akshay Garg

IPC: H04N21/6543 ,  H04N21/442 ,  H04N21/472 ,  H04N21/845

CPC classification number: H04N21/6543 ,  H04N21/44204 ,  H04N21/47217 ,  H04N21/8455

Abstract: The disclosed computer-implemented methods and systems include pausing a digital content stream being provided to a display device in response to determining that the display device is powered off. For example, rather than utilizing signals related to the power status of the display device, the disclosed methods and systems utilize signals related to display protocols and interfaces utilized by the display device to determine its power status. In response to determining that a display device is powered off, the disclosed methods and systems can pause the digital content stream being provided to the display device. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US20240244224A1

公开(公告)日：2024-07-18

申请号：US18154680

申请日：2023-01-13

Applicant: NETFLIX, INC.

Inventor： Sagar Bharadwaj KALASIBAIL SEETHARAM ,  Te-Yuan HUANG ,  Renata Cruz TEIXEIRA ,  Xiaoqing ZHU

IPC: H04N19/146 ,  H04N19/105

CPC classification number: H04N19/146 ,  H04N19/105

Abstract: In various embodiments, an encoding ladder application generates encoding ladders that are used to stream media titles. The encoding ladder application generates an objective function based on a ladder configuration and a parameterized objective function. The parameterized objective function approximates a tradeoff between a quality of experience and a cost term associated with a candidate encoding ladder. The encoding ladder application generates constraints based on the ladder configuration and parameterized constraints. The encoding ladder application executes a constrained optimization algorithm on the objective function, the constraints, and encoding point metadata associated with a set of encoded videos to generate a first candidate encoding ladder for a media title.

公开(公告)号：US20240233076A1

公开(公告)日：2024-07-11

申请号：US18617162

申请日：2024-03-26

Applicant: NETFLIX, INC.

Inventor： Li-Heng CHEN ,  Christos G. BAMPIS ,  Zhi LI

IPC: G06T3/4046 ,  G06N3/084 ,  G06T9/00

CPC classification number: G06T3/4046 ,  G06N3/084 ,  G06T9/002

Abstract: In various embodiments, a training application trains a convolutional neural network to downsample images in a video encoding pipeline. The convolution neural network includes at least two residual blocks and is associated with a downsampling factor. The training application executes the convolutional neural network on a source image to generate a downsampled image. The training application then executes an upsampling algorithm on the downsampled image to generate a reconstructed image having the same resolution as the source image. The training application computes a reconstruction error based on the reconstructed image and the source image. The training application updates at least one parameter of the convolutional neural network based on the reconstruction error to generate a trained convolutional neural network. Advantageously, the trained convolution neural network can be implemented in a video encoding pipeline to mitigate visual quality reductions typically experienced with conventional video encoding pipelines that implement conventional downsampling techniques.