公开(公告)号：US20230412760A1

公开(公告)日：2023-12-21

申请号：US17841564

申请日：2022-06-15

Applicant: Netflix, Inc.

Inventor： Yadong Wang ,  Shilpa Jois Rao

IPC: H04N5/93 ,  G10L15/00 ,  G10L15/04 ,  G10L15/26 ,  G10L25/57 ,  G10L25/81 ,  G10L15/22 ,  H04N5/278

CPC classification number: H04N5/9305 ,  G10L15/005 ,  G10L15/04 ,  G10L15/26 ,  G10L25/57 ,  G10L25/81 ,  G10L15/22 ,  H04N5/278

Abstract: The disclosed computer-implemented method may include systems and methods for automatically generating sound event subtitles for digital videos. For example, the systems and methods described herein can automatically generate subtitles for sound events within a digital video soundtrack that includes sounds other than speech. Additionally, the systems and methods described herein can automatically generate sound event subtitles as part of an automatic and comprehensive approach that generates subtitles for all sounds within a soundtrack of a digital video—thereby avoiding the need for any manual inputs as part of the subtitling process.

公开(公告)号：US20230396837A1

公开(公告)日：2023-12-07

申请号：US17834399

申请日：2022-06-07

Applicant: NETFLIX, INC.

Inventor： Mark WATSON ,  Christopher NEWTON

IPC: H04N21/4402 ,  H04N21/44

CPC classification number: H04N21/4402 ,  H04N21/44008

Abstract: In various embodiments, a localized video encoding application encodes localized videos. In operation, the localized video encoding application computes a prediction frame based on a target frame of a localized video and at least a portion of a reference frame of a decoded original video. The localized video encoding application computes a residual frame based on the prediction frame and the target frame of the localized video. The localized video encoding application performs one or more encoding operations on the residual frame to generate a frame of an encoded localization layer. The frame of the encoded localization layer and at least one frame of an encoded original video are subsequently transmitted to another device for decoding.

公开(公告)号：US20230388596A1

公开(公告)日：2023-11-30

申请号：US18325959

申请日：2023-05-30

Applicant: NETFLIX, INC.

Inventor： Moumita BHATTACHARYA ,  Sudarshan Dnyaneshwar LAMKHEDE ,  Christoph KOFLER ,  Kelley Jean ROBINSON ,  Yi ZHANG

IPC: H04N21/466 ,  H04N21/25 ,  H04N21/482

CPC classification number: H04N21/4668 ,  H04N21/251 ,  H04N21/4826

Abstract: In various embodiments, an in-session recommendation application generates recommendations for users during streaming sessions. The in-session recommendation application generates a set of feature values for a set of features associated with a trained machine learning model based on user interactions that have occurred via a graphical user interface (GUI) during a current streaming session. The in-session recommendation application executes the trained machine learning model on at least the set of feature values and a first feature value associated with a first item to generate a first score. The in-session recommendation application generates a recommendation based on the first score and at least a second score that is associated with both a second item and the user interactions. The in-session recommendation application displays the recommendation within the GUI.

公开(公告)号：US11830161B2

公开(公告)日：2023-11-28

申请号：US17700280

申请日：2022-03-21

Applicant: NETFLIX, INC.

Inventor： Apurvakumar Dilipkumar Kansara

IPC: G06T3/40 ,  H04N7/01 ,  H04N21/4402 ,  G06T7/13 ,  G06T3/00 ,  G06V40/16 ,  H04N5/262

CPC classification number: G06T3/40 ,  G06T3/0012 ,  G06T7/13 ,  G06V40/161 ,  H04N7/0122 ,  H04N21/440272 ,  H04N5/2628 ,  G06T3/40 ,  H04N7/0122 ,  H04N21/440272 ,  G06T7/13 ,  G06T3/0012 ,  G06V40/161 ,  H04N5/2628

Abstract: One embodiment of the present invention sets forth a technique for dynamically cropping image data transmitted to an endpoint device. The technique includes computing a first visual interest score for a first visual interest region within a digital image based on content included in the first visual interest region, computing a second visual interest score for a second visual interest region within the digital image based on content included in the second visual interest region, and determining that the first visual interest region is preferred over the second visual interest region based on the first visual interest score and the second visual interest score. The technique further includes setting a location within the first visual interest region as a point of visual interest and transmitting the digital image and the location of the point of visual interest to a computing device for displaying a portion of the digital image that includes the point of visual interest.

公开(公告)号：US11829500B2

公开(公告)日：2023-11-28

申请号：US17013288

申请日：2020-09-04

Applicant: NETFLIX, INC.

Inventor： Kishore Udayashankar Kasi ,  Shailesh Birari ,  Prudhviraj Karumanchi ,  Vikram Krishnamurthy ,  Ioannis Papapanagiotou

IPC: G06F21/62 ,  G06F21/31 ,  G06F16/182 ,  G06F16/16

CPC classification number: G06F21/6218 ,  G06F16/164 ,  G06F16/182 ,  G06F21/31 ,  G06F2221/2141

Abstract: Various embodiments of the present application set forth a computer-implemented method for accessing data comprising determining a manifest associated with a given user of an application, where the manifest identifies one or more assets that are accessible by the given user, for each of the one or more assets, one of a plurality of endpoint stores that stores data associated with the asset, and for each of the one or more assets, one of the plurality of endpoint stores that stores metadata associated with the asset, generating, based on the manifest, a user namespace that includes a unique reference for each of the one or more assets, and presenting the user namespace to the user.

公开(公告)号：US20230376761A1

公开(公告)日：2023-11-23

申请号：US18319146

申请日：2023-05-17

Applicant: NETFLIX, INC.

Inventor： James Edward MCINERNEY ,  Nathan KALLUS

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: One or more embodiments include a computer-implemented method that includes receiving a data set generated by a machine learning model, wherein the data set comprises a plurality of data samples that are independent of each other, performing two or more fitting operations to fit the data set to a regularized maximum likelihood estimators (MLEs), determining a variance associated with the data set based on a derivative associated with the regularized MLEs, and performing one or more operations associated with the machine learning model based on the variance.

公开(公告)号：US20230345088A1

公开(公告)日：2023-10-26

申请号：US18343695

申请日：2023-06-28

Applicant: NETFLIX, INC.

Inventor： Maxine CHEUNG ,  Mark WATSON ,  Carla Christine FISHER ,  Kevin Pei-Wen LEE ,  Yves RAIMOND

IPC: H04N21/8541 ,  H04N21/234 ,  H04N21/442 ,  H04N21/475 ,  H04N21/8545

CPC classification number: H04N21/8541 ,  H04N21/23406 ,  H04N21/44222 ,  H04N21/4758 ,  H04N21/8545

Abstract: A playback application is configured to dynamically generate topology for an interactive media title. The playback application obtains an initial topology and also collects various data associated with a user interacting with the feature. The playback application then modifies the initial topology, based on the collected data, to generate a dynamic topology tailored to the user. The dynamic topology describes the set of choices available to the user during playback as well as which options can be selected by the user when making a given choice. In addition, the playback application also selectively buffers different portions of the interactive media title, based on the collected data, in anticipation of the user selecting particular options for available choices.

公开(公告)号：US20230336809A1

公开(公告)日：2023-10-19

申请号：US18338186

申请日：2023-06-20

Applicant: NETFLIX, INC.

Inventor： Mark WATSON

IPC: H04N21/43 ,  G06F16/783 ,  H04N21/439 ,  G06V20/40

CPC classification number: H04N21/4307 ,  G06F16/7834 ,  H04N21/4394 ,  G06V20/46 ,  G06V20/49

Abstract: A playback application is configured to analyze audio frames associated with transitions between segments within a media title to identify one or more portions of extraneous audio. The playback application is configured to analyze the one or more portions of extraneous audio and then determine which of the one or more corresponding audio frames should be dropped. In doing so, the playback application can analyze a topology associated with the media title to determine whether any specific portions of extraneous audio are to be played outside of a logical ordering of audio samples set forth in the topology. These specific portions of extraneous audio are preferentially removed.

公开(公告)号：US11778010B2

公开(公告)日：2023-10-03

申请号：US17164523

申请日：2021-02-01

Applicant: NETFLIX, INC.

Inventor： Zhi Li ,  Te-Yuan Huang

IPC: H04L65/70 ,  H04L65/80 ,  H04L65/613

CPC classification number: H04L65/70 ,  H04L65/613 ,  H04L65/80

Abstract: In various embodiments, a hindsight application computes a hindsight metric value for evaluation of a video rate selection algorithm. The hindsight application determines a first encoding option associated with a source chunk of a media title based on a network throughput trace and a buffer trellis. The hindsight application determines that the first encoding option is associated with a buffered duration range. The buffered duration range is also associated with a second encoding option that is stored in the buffer trellis. After determining that the first encoding option is associated with a higher visual quality than the second encoding option, the hindsight application stores the first encoding option instead of the second encoding option in the buffer trellis to generate a modified buffer trellis. Finally, the hindsight application computes a hindsight metric value associated with a sequence of encoded chunks of the media title based on the modified buffer trellis.

公开(公告)号：US11747983B2

公开(公告)日：2023-09-05

申请号：US15725259

申请日：2017-10-04

Applicant: NETFLIX, INC.

Inventor： John Andrew Koszewnik

IPC: G06F3/06 ,  G06F16/738 ,  G06F11/14

CPC classification number: G06F3/0611 ,  G06F3/065 ,  G06F3/068 ,  G06F3/0619 ,  G06F3/0641 ,  G06F3/0685 ,  G06F11/1451 ,  G06F16/739 ,  G06F2201/84

Abstract: In various embodiments, a write state application generates a snapshot that includes one or more data values associated with a source dataset. In operation, the write state application performs one or more compression operations on the source dataset to generate a first compressed record. The write state application then serializes the first compressed record and a second compressed record to generate a first compressed record list. Finally, the write state application generates the snapshot based on the first compressed record list. When the data values are accessed from the first snapshot, the size of the snapshot is maintained. Advantageously, because the size of the snapshot is smaller than the size of the source dataset, some consumers that are unable to store the entire source dataset in random access memory (RAM) are able to store the entire snapshot in RAM.