公开(公告)号：US20200151546A1

公开(公告)日：2020-05-14

申请号：US16677161

申请日：2019-11-07

Applicant: Netflix, Inc.

Inventor： Dong Liu ,  Nagendra Kamath ,  Rohit Puri ,  Subhabrata Bhattacharya

IPC: G06N3/04 ,  G06K9/46 ,  G06N3/08 ,  G06K9/66 ,  G06T7/11 ,  G06K9/62

Abstract: The disclosed computer-implemented method may include generating a three-dimensional (3D) feature map for a digital image using a fully convolutional network (FCN). The 3D feature map may be configured to identify features of the digital image and identify an image region for each identified feature. The method may also include generating a region composition graph that includes the identified features and image regions. The region composition graph may be configured to model mutual dependencies between features of the 3D feature map. The method may further include performing a graph convolution on the region composition graph to determine a feature aesthetic value for each node according to the weightings in the node's weighted connecting segments, and calculating a weighted average for each node's feature aesthetic value to provide a combined level of aesthetic appeal for the digital image. Various other methods, systems, and computer-readable media are also disclosed.

公开(公告)号：US10572767B2

公开(公告)日：2020-02-25

申请号：US15486108

申请日：2017-04-12

Applicant: NETFLIX, Inc.

Inventor： Apurvakumar D. Kansara

IPC: G06K9/62 ,  H04N21/8549 ,  H04N21/84 ,  G06K9/00 ,  H04N21/845 ,  H04N21/234 ,  G06F16/738

Abstract: A method includes receiving, with a computing system, a video item. The method further includes identifying a first set of features within a first frame of the video item. The method further includes identifying, with the computing system, a second set of features within a second frame of the video item, the second frame being subsequent to the first frame. The method further includes determining, with the computing system, differences between the first set of features and the second set of features. The method further includes assigning a clip category to a clip extending between the first frame and the second frame based on the differences.

公开(公告)号：US10560506B2

公开(公告)日：2020-02-11

申请号：US15654657

申请日：2017-07-19

Applicant: NETFLIX Inc.

Inventor： Apurvakumar Dilipkumar Kansara

IPC: H04L29/06 ,  G06F3/0484

Abstract: A sequence analyzer compares different episodes of an episodic serial to identify portions of a current episode of the serial that have already been played back to a user. Those portions may include introductory material such as credits, or a recap section that includes content from previous episodes. The sequence analyzer parses previous episodes of the serial and selects a representative frame for each shot sequence. The sequence analyzer then generates a fingerprint for each shot sequence based on the associated representative frame. The sequence analyzer compares fingerprints associated with a current episode of the serial to fingerprints associated with one or more previous episodes of the serial to identify shot sequences that have already been played. The user may then skip those repeated sequences via a playback interface.

公开(公告)号：US20200029131A1

公开(公告)日：2020-01-23

申请号：US16040014

申请日：2018-07-19

Applicant: NETFLIX, INC.

Inventor： Aditya MAVLANKAR ,  Ioannis KATSAVOUNIDIS

IPC: H04N21/6587 ,  H04N21/2387 ,  H04N21/472 ,  G06F17/30 ,  H04N21/845

Abstract: A computer-implemented method includes receiving a request from a client computing device for a first shot included in a media title being streamed to the client computing device for playback; in response to the request, sending the first shot to the client computing device for playback; and sending a representative image for at least one of the first shot and a second shot included in the media title, wherein the first shot comprises a first sequence of video frames that is included in the media title and captured continuously from a first point of capture, and the second shot comprises a second sequence of video frames that is included in the media title and captured continuously from a second point of capture.

公开(公告)号：US20200028867A1

公开(公告)日：2020-01-23

申请号：US16514687

申请日：2019-07-17

Applicant: NETFLIX, INC.

Inventor： Forest MONSEN ,  Kevin GLISSON

IPC: H04L29/06 ,  G06N20/00 ,  G06F16/903 ,  G06N5/04

Abstract: In various embodiments, a forensic scoping application analyzes host instances in order to detect anomalies. The forensic scoping application acquires a snapshot for each host instance included in an instance group. Each snapshot represents a current operational state of the associated host instance. Subsequently, the forensic scoping application performs clustering operation(s) based on the snapshots to generate a set of clusters. The forensic scoping application determines that a first cluster in the set of clusters is associated with fewer host instances than at least a second cluster in the set of clusters. Based on the first cluster, the forensic scoping application determines that a first host instance included in the instance group is operating in an anomalous fashion. Advantageously, efficiently determining host instances that are operating in an anomalous fashion during a security attack can reduce the amount of damage caused by the security attack.

公开(公告)号：US10523732B2

公开(公告)日：2019-12-31

申请号：US14942084

申请日：2015-11-16

Applicant: Netflix, Inc.

Inventor： Mark Watson ,  Bin Wang ,  Wei Wei

IPC: H04L29/06

Abstract: Techniques for transmitting a digital content stream through a network between a plurality of content servers and a content player. Network performance information for the plurality of content servers is retrieved. Embodiments then determine a mapping of the plurality of content servers to a plurality of portions of a content buffer on the content player, based on the retrieved network performance information. A request is transmitted to each of the plurality of content servers to transmit digital content associated with the corresponding portion of the content buffer.

公开(公告)号：US10475172B2

公开(公告)日：2019-11-12

申请号：US16017929

申请日：2018-06-25

Applicant: NETFLIX, INC.

Inventor： Anne Aaron ,  Dae Kim ,  Yu-Chieh Lin ,  David Ronca ,  Andy Schuler ,  Kuyen Tsao ,  Chi-Hao Wu

IPC: G06K9/00 ,  G06T7/00 ,  G06T9/00 ,  H04N21/466 ,  H04N19/154 ,  G06T7/20

Abstract: In one embodiment of the present invention, a quality trainer and quality calculator collaborate to establish a consistent perceptual quality metric via machine learning. In a training phase, the quality trainer leverages machine intelligence techniques to create a perceptual quality model that combines objective metrics to optimally track a subjective metric assigned during viewings of training videos. Subsequently, the quality calculator applies the perceptual quality model to values for the objective metrics for a target video, thereby generating a perceptual quality score for the target video. In this fashion, the perceptual quality model judiciously fuses the objective metrics for the target video based on the visual feedback processed during the training phase. Since the contribution of each objective metric to the perceptual quality score is determined based on empirical data, the perceptual quality score is a more accurate assessment of observed video quality than conventional objective metrics.

公开(公告)号：US10438335B2

公开(公告)日：2019-10-08

申请号：US16017929

申请日：2018-06-25

Applicant: NETFLIX, INC.

Inventor： Anne Aaron ,  Dae Kim ,  Yu-Chieh Lin ,  David Ronca ,  Andy Schuler ,  Kuyen Tsao ,  Chi-Hao Wu

IPC: G06K9/00 ,  G06T7/00 ,  G06T9/00 ,  H04N21/466 ,  H04N19/154 ,  G06T7/20

Abstract: In one embodiment of the present invention, a quality trainer and quality calculator collaborate to establish a consistent perceptual quality metric via machine learning. In a training phase, the quality trainer leverages machine intelligence techniques to create a perceptual quality model that combines objective metrics to optimally track a subjective metric assigned during viewings of training videos. Subsequently, the quality calculator applies the perceptual quality model to values for the objective metrics for a target video, thereby generating a perceptual quality score for the target video. In this fashion, the perceptual quality model judiciously fuses the objective metrics for the target video based on the visual feedback processed during the training phase. Since the contribution of each objective metric to the perceptual quality score is determined based on empirical data, the perceptual quality score is a more accurate assessment of observed video quality than conventional objective metrics.

公开(公告)号：US20190303234A1

公开(公告)日：2019-10-03

申请号：US16367069

申请日：2019-03-27

Applicant: NETFLIX, INC.

Inventor： Vinay CHELLA ,  Joseph LYNCH ,  Ajay UPADHYAY

IPC: G06F11/07

Abstract: Various embodiments of the invention disclosed herein provide techniques for performing distributed anti-entropy repair procedures across a plurality of nodes in a distributed database network. A node included in a plurality of nodes within the distributed database network determines, before all other nodes included in the plurality of nodes, that a first anti-entropy repair procedure has ended. The node determines that a second anti-entropy repair procedure is ready to begin. The node generates a schedule for executing one or more operations associated with the second anti-entropy repair procedure. The node writes the schedule to a shared repair schedule data structure to initiate the second anti-entropy repair procedure across multiple nodes included in the plurality of nodes. Each of the nodes included in the plurality of nodes then performs a node repair based on the schedule.

公开(公告)号：US10404566B2

公开(公告)日：2019-09-03

申请号：US15268131

申请日：2016-09-16

Applicant: NETFLIX, INC.

Inventor： Carlos A. Gomez-Uribe

IPC: H04L12/26 ,  H04L29/08 ,  G06Q30/02

Abstract: A system of assessing deployments in a network-based media system is provided herein. The system include a data storage system storing observation vectors, each observation vector being associated with an outcome indicator, and a processing device in communication with the data storage system to receive and store observation vectors and associated outcome indicators. The processing device performs operations including communicating with an endpoint device of a user to obtain information associated with the endpoint device; and transmitting an instance of a variable user interface to the endpoint device for presentation to the user via the endpoint device based on the stored observation vectors, the stored associated outcome indicators, and the obtained information associated with the endpoint device. Related systems and methods are also disclosed.