公开(公告)号：US20220123934A1

公开(公告)日：2022-04-21

申请号：US17071978

申请日：2020-10-15

Applicant: NETFLIX, INC.

Inventor： Andrew CHEN ,  Jonathan T. LOONEY

IPC: H04L9/32 ,  H04L29/06 ,  H04L9/08

Abstract: In various embodiments, servers in a server pool share a centrally-generated encryption key that is used to encrypt session keys in tickets that can be used by client applications to share secure communication sessions across different servers belonging to the same server pools. When the client application first establishes a secure communication session with a server in a server pool, the server returns a ticket that includes an encrypted version of a session key generated using an encryption key shared by servers in the server pool. Thereafter, the client application can present the ticket to other servers in the server pool to restore the secure communication session with the other servers. Associations between servers and server pools can be communicated to the client application in any technically feasible manner, such as part of information indicating servers from which content can be accessed or via the Domain Name System (DNS).

公开(公告)号：US20220115030A1

公开(公告)日：2022-04-14

申请号：US17555175

申请日：2021-12-17

Applicant: Netflix, Inc.

Inventor： Yadong Wang ,  Shilpa Jois Rao ,  Murthy Parthasarathi ,  Kyle Tacke

IPC: G10L25/51 ,  G10L15/00 ,  G10L15/22 ,  G10L25/81 ,  G10L25/84

Abstract: The disclosed computer-implemented method may include obtaining an audio sample from a content source, inputting the obtained audio sample into a trained machine learning model, obtaining the output of the trained machine learning model, wherein the output is a profile of an environment in which the input audio sample was recorded, obtaining an acoustic impulse response corresponding to the profile of the environment in which the input audio sample was recorded, obtaining a second audio sample, processing the obtained acoustic impulse response with the second audio sample, and inserting a result of processing the obtained acoustic impulse response and the second audio sample into an audio track. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US20220103869A1

公开(公告)日：2022-03-31

申请号：US17549793

申请日：2021-12-13

Applicant: NETFLIX, INC.

Inventor： Zhi LI

IPC: H04N19/86

Abstract: In various embodiments, a tunable VMAF application reduces an amount of influence that image enhancement operations have on perceptual video quality estimates. In operation, the tunable VMAF application computes a first value for a first visual quality metric based on reconstructed video content and a first enhancement gain limit. The tunable VMAF application computes a second value for a second visual quality metric based on the reconstructed video content and a second enhancement gain limit. Subsequently, the tunable VMAF application generates a feature value vector based on the first value for the first visual quality metric and the second value for the second visual quality metric. The tunable VMAF application executes a VMAF model based on the feature value vector to generate a tuned VMAF score that accounts, at least in part, for at least one image enhancement operation used to generate the reconstructed video content.

公开(公告)号：US20220060771A1

公开(公告)日：2022-02-24

申请号：US17001063

申请日：2020-08-24

Applicant: NETFLIX, INC.

Inventor： SEKWON CHOI ,  ANDREW CHEN

IPC: H04N21/258 ,  H04L29/12 ,  H04L29/06 ,  H04L29/08

Abstract: In various embodiments, a client application requests information relating to content servers from which particular content can be accessed, or a manifest server that maintains such information and is distinct from the Domain Name System (DNS) automatically determines that the client application is likely to request the content server information. The manifest server then transmits, to the client application, information specifying (1) hostnames associated with the content servers from which the particular content can be accessed, and (2) Internet Protocol (IP) addresses corresponding to the hostnames. Thereafter, the client application can use the IP addresses to connect to the content servers and validate certificates provided by the content servers, in order to establish secure communication channels with the content servers.

公开(公告)号：US20220038710A1

公开(公告)日：2022-02-03

申请号：US16945737

申请日：2020-07-31

Applicant: NETFLIX, INC.

Inventor： Zhi LI

IPC: H04N19/149 ,  H04N19/154 ,  H04L29/06

Abstract: In various embodiments, a data optimization application mitigates scoring inaccuracies in subjective quality experiments. In operation, the data optimization application generates a model that includes a first set of individual scores and a first set of parameters. The first set of parameters includes a first subjective score set and a first set of subjective factor sets. The data optimization application performs one or more optimization operations on the first set of parameters to generate a second set of parameters. The second set of parameters includes a second subjective score set and a second set of subjective factor sets, wherein the second subjective score set compensates for at least a first subjective factor set included in the second set of subjective factor sets. The data optimization application also computes a participant evaluation report based on at least a second subjective factor sets included in the second set of subjective factor sets

公开(公告)号：US11240156B2

公开(公告)日：2022-02-01

申请号：US16693180

申请日：2019-11-22

Applicant: NETFLIX, INC.

Inventor： Sergey Fedorov ,  Phelps Watson Williams ,  Niosha Behnam

IPC: H04L12/803 ,  H04L12/851 ,  G06F17/11 ,  H04L29/08 ,  H04N21/239 ,  H04L12/26 ,  H04L29/12 ,  H04L29/06

Abstract: In various embodiments, domain name system (DNS) servers are implemented on a content distribution network (CDN) infrastructure in order to facilitate centralized control of traffic steering. Each server appliance in the CDN infrastructure acts as both an authoritative DNS nameserver and a dynamic request proxy, and each such server appliance is assigned to one of multiple cloud computing system regions. The assignment of server appliances to cloud regions is based on latency measurements collected via client application probes and an optimization that minimizes an overall latency experienced by the client applications subject to constraints that the maximum traffic to each cloud region is less than a capacity constraint for that region, the maximum deviation of traffic to each cloud regions at any point in time is less than a given percentage, and the maximum deviation of traffic between direct and indirect paths is less than a given percentage.

公开(公告)号：US11212368B2

公开(公告)日：2021-12-28

申请号：US16416108

申请日：2019-05-17

Applicant: NETFLIX, INC.

Inventor： Antoine Jean Girbal

IPC: H04L29/06 ,  H04L29/08

Abstract: In various embodiments, a proxy application processes requests associated with a network-based service. In operation, the proxy application determines that a first request received from a client application indicates that a response to the first request can be offloaded from a server machine. Prior to transmitting the first request to the server machine, the proxy application transmits a response to the first request to the client application. The response indicates that the server machine has successfully processed the first request. Advantageously, upon receiving the response, the client application is able to initiate a second request irrespective of the server machine.

公开(公告)号：US20210400345A1

公开(公告)日：2021-12-23

申请号：US16904554

申请日：2020-06-17

Applicant: Netflix, Inc.

Inventor： Juha Turunen

IPC: H04N21/454 ,  H04N21/44 ,  H04N21/442

Abstract: The disclosed computer-implemented method includes determining that an image is to be blurred. The image has multiple pixels arranged along horizontal and/or vertical axes. The method next includes identifying a boundary size for a sliding window within which pixel values are to be sampled from the image and sampling, from pixels that lie on an axis that is diagonal relative to the horizontal/vertical axis of the image, various pixel values from within the boundary of the sliding window. The pixels sampled along the diagonal angle within the sliding window are selected according to a specified noise pattern. The method further includes performing an initial convolution pass on the pixels surrounding the sampled pixels to blur at least some of the pixels surrounding the sampled pixels, and then presenting the blurred image. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US20210390949A1

公开(公告)日：2021-12-16

申请号：US16903373

申请日：2020-06-16

Applicant: Netflix, Inc.

Inventor： Yadong Wang ,  Shilpa Jois Rao ,  Murthy Parthasarathi

IPC: G10L15/08 ,  G10L15/04 ,  G10L15/02 ,  G10L21/0232 ,  G06N20/00

Abstract: The disclosed computer-implemented method may include training a machine-learning algorithm to use look-ahead to improve effectiveness of identifying visemes corresponding to audio signals by, for one or more audio segments in a set of training audio signals, evaluating an audio segment, where the audio segment includes at least a portion of a phoneme, and a subsequent segment that includes contextual audio that comes after the audio segment and potentially contains context about a viseme that maps to the phoneme. The method may also include using the trained machine-learning algorithm to identify one or more probable visemes corresponding to speech in a target audio signal. Additionally, the method may include recording, as metadata of the target audio signal, where a probable viseme occurs within the target audio signal. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US20210390315A1

公开(公告)日：2021-12-16

申请号：US17344752

申请日：2021-06-10

Applicant: NETFLIX, INC.

Inventor： Shervin Ardeshir BEHROSTAGHI ,  Nagendra K. KAMATH

IPC: G06K9/00

Abstract: One embodiment of the present invention sets forth a technique for selecting a frame of video content that is representative of a media title. The technique includes applying an embedding model to a plurality of faces included in a set of frames of the video content to generate a plurality of face embeddings. The technique also includes aggregating the plurality of face embeddings into a plurality of clusters representing a plurality of characters included in the media title. The technique further includes computing a plurality of prominence scores for the plurality of characters based on one or more attributes of the plurality of clusters, and selecting, from the set of frames, a frame of video content as representative of the media title based on one or more prominence scores for one or more characters included in the frame.