公开(公告)号：US20180300869A1

公开(公告)日：2018-10-18

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: G06T7/00 ,  H04N19/154 ,  H04N21/466 ,  G06T9/00 ,  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：US20180300554A1

公开(公告)日：2018-10-18

申请号：US15486108

申请日：2017-04-12

Applicant: NETFLIX, Inc.

Inventor： Apurvakumar D. Kansara

IPC: G06K9/00 ,  H04N21/8549 ,  H04N21/84 ,  G06K9/62

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：US09998354B2

公开(公告)日：2018-06-12

申请号：US14289552

申请日：2014-05-28

Applicant: Netflix, Inc.

Inventor： Christopher Brand ,  David Fullagar

IPC: G06F15/16 ,  H04L12/733 ,  H04L29/06 ,  H04L29/08

CPC classification number: H04L45/126 ,  H04L65/4084 ,  H04L65/80 ,  H04L67/10 ,  H04L67/101 ,  H04L67/1021 ,  H04L67/18 ,  H04L67/42

Abstract: In an embodiment, a method comprises receiving a first routing table of a first server computer; receiving a second routing table of a second server computer; receiving a request, from a client computer, for information about content servers that hold a media item title, wherein the request includes a client internet protocol address of the client computer; estimating that the first server computer is closer to the client computer than the second server computer is to the client computer based, at least in part, on the client internet protocol address, the first routing table, and the second routing table; sending, to the client computer, a first address to the client computer based, at least in part, on estimating that the first server computer is closer to the client computer than the second server computer, wherein the first address identifies the media item title stored on the first server computer.

公开(公告)号：US20180143786A1

公开(公告)日：2018-05-24

申请号：US15820407

申请日：2017-11-21

Applicant: NETFLIX, INC.

Inventor： John Andrew KOSZEWNIK

IPC: G06F3/06

CPC classification number: G06F3/0659 ,  G06F3/0604 ,  G06F3/0631 ,  G06F3/0673 ,  G06F9/5016 ,  G06F12/00 ,  G06F13/14

Abstract: In various embodiments, a memory pool application implements composite arrays via a memory pool that includes a first slab and a second slab. First, the memory pool application assigns the first slab and the second slab to a composite array. The memory pool application then modifies a final data word included in the first slab to store a first portion of a specified value and a leading data word included in the second slab to store a second portion of the specified value. The memory pool application copies the second data word to a duplicate data word included in the first slab. Subsequently, the memory pool application performs an unaligned read operation on the first slab based on a specified offset to retrieve a first word stored in memory and extracts the specified value from the first word based on the specified offset and a specified number of bits.

公开(公告)号：US09954822B2

公开(公告)日：2018-04-24

申请号：US15471254

申请日：2017-03-28

Applicant: Netflix, Inc.

Inventor： Jason Chan ,  Poornaprajna Udupi ,  Shashi Madappa

IPC: H04L29/06 ,  H04L29/08

CPC classification number: H04L63/0245 ,  G06F17/30312 ,  H04L63/0218 ,  H04L63/0227 ,  H04L63/1408 ,  H04L63/20 ,  H04L67/10

Abstract: Approaches, techniques, and mechanisms are disclosed for implementing a distributed firewall. In an embodiment, many different computer assets police incoming messages based on local policy data. This local policy data is synchronized with global policy data. The global policy data is generated by one or more separate analyzers. Each analyzer has access to message logs, or information derived therefrom, for groups of computer assets, and is thus able to generate policies based on intelligence from an entire group as opposed to an isolated asset. Among other effects, some of the approaches, techniques, and mechanisms may be effective even in computing environments with limited supervision over the attack surface, and/or computing environments in which assets may need to make independent decisions with respect to how incoming messages should be handled, on account of latency and/or unreliability in connections to other system components.

公开(公告)号：US09953173B2

公开(公告)日：2018-04-24

申请号：US14703862

申请日：2015-05-04

Applicant: NETFLIX, INC.

Inventor： Ariel Tseitlin ,  Roy Rapoport ,  Jason Chan

IPC: H04L29/06 ,  G06F21/60 ,  H04L12/26 ,  G06F17/30

CPC classification number: G06F21/604 ,  G06F9/50 ,  G06F11/302 ,  G06F11/3051 ,  G06F17/30598 ,  G06F21/00 ,  G06F21/45 ,  G06F21/577 ,  G06F2209/504 ,  G06F2221/034 ,  G06F2221/2141 ,  H04L9/3268 ,  H04L41/12 ,  H04L43/16 ,  H04L63/101 ,  H04L63/1408 ,  H04L63/1433 ,  H04L67/10 ,  Y02D10/22

Abstract: A security application manages security and reliability of networked applications executing collection of interacting computing elements within a distributed computing architecture. The security application monitors various classes of resources utilized by the collection of nodes within the distributed computing architecture and determine whether utilization of a class of resources is approaching a pre-determined maximum limit. The security application performs a vulnerability scan of a networked application to determine whether the networked application is prone to a risk of intentional or inadvertent breach by an external application. The security application scans a distributed computing architecture for the existence of access control lists (ACLs), and stores ACL configurations and configuration changes in a database. The security application scans a distributed computing architecture for the existence of security certificates, places newly discovered security certificates in a database, and deletes outdated security certificates. Advantageously, security and reliability are improved in a distributed computing architecture.

公开(公告)号：US09948601B2

公开(公告)日：2018-04-17

申请号：US14031689

申请日：2013-09-19

Applicant: Netflix, Inc.

Inventor： Jafar Husain

IPC: H04L29/12 ,  G06F17/30 ,  H04N21/472 ,  G06F12/0811 ,  G06F12/0817 ,  H04L12/701

CPC classification number: H04L61/2596 ,  G06F12/0811 ,  G06F12/0817 ,  G06F17/30831 ,  G06F17/30858 ,  H04L43/0876 ,  H04L45/00 ,  H04N21/47202

Abstract: Embodiments of the invention generally provide a method, a computing system, and a computer-readable medium configured to respond to requests for payload data and provide unique cache keys for caching the payload data. The computer-implemented method includes accepting a first request for translation that specifies a first path configured to identify first payload data associated with a graph object. The computer-implemented method further includes determining that the graph object includes a first translation node associated with a first portion of the first path. The computer-implemented method also includes obtaining, from the graph object, a second path that is associated with the first translation node. The computer-implemented method further includes replacing the first portion of the first path with the second path to generate a first translated path. The computer-implemented method also includes obtaining, from the graph object, the first payload data, based on the first translated path.

公开(公告)号：US20180101312A1

公开(公告)日：2018-04-12

申请号：US15725261

申请日：2017-10-04

Applicant: NETFLIX, INC.

Inventor： John Andrew KOSZEWNIK

IPC: G06F3/06 ,  G06F11/14

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

Abstract: In various embodiments, a consumer generates and operates with an in-memory dataset. In operation, a read state application copies a snapshot associated with a source dataset from a file store to a random access memory (RAM) to generate an in-memory dataset. Notably, the source dataset has a first size, and the in-memory dataset has a second size that is smaller than the first size. The read state application then performs a read-only operation on the in-memory dataset to access one or more data values that are stored in the in-memory dataset and associated with the source dataset. When the one or more data values are accessed, the second data size of the in-memory dataset is maintained. Advantageously, some consumers that are unable to store the entire source dataset in are able to store the entire snapshot in RAM.

公开(公告)号：US20180089011A1

公开(公告)日：2018-03-29

申请号：US15393183

申请日：2016-12-28

Applicant: NETFLIX, INC.

Inventor： Ali BASIRI ,  Aaron BLOHOWIAK ,  Lorin HOCHSTEIN ,  Casey ROSENTHAL

IPC: G06F11/07 ,  H04L29/08 ,  H04L12/26

CPC classification number: G06F11/079 ,  G06F9/5077 ,  G06F11/0709 ,  G06F11/0751 ,  G06F11/3006 ,  H04L43/50 ,  H04L67/025 ,  H04L67/10

Abstract: One embodiment of the present invention sets forth a technique for testing microservices in distributed computing systems. The technique includes routing a first traffic sample associated with request traffic from one or more client devices to a first instance of a first service implemented in a distributed computing system, wherein the first instance generates a first plurality of request responses in response to a first plurality of data requests included in the first traffic sample and transmits the first plurality of request responses to a second service included in the sequence of services, and routing a second traffic sample associated with the request traffic to a second instance of the first service, wherein the second instance generates a second plurality of request responses in response to a second plurality of data requests included in the second traffic sample and transmits the second plurality of request responses to the second service.

公开(公告)号：US20180048925A1

公开(公告)日：2018-02-15

申请号：US15791392

申请日：2017-10-23

Applicant: NETFLIX, INC.

Inventor： ANGADH SINGH ,  CARLOS GOMEZ-URIBE

IPC: H04N21/25 ,  H04N21/2668 ,  H04N21/262 ,  H04N21/258 ,  H04N21/61 ,  H04N21/482

CPC classification number: H04N21/252 ,  H04N21/251 ,  H04N21/25891 ,  H04N21/26258 ,  H04N21/2668 ,  H04N21/4825 ,  H04N21/4826 ,  H04N21/6125

Abstract: In an approach, a method comprises using a server computer in a media content delivery system that is configured to selectively deliver a particular media title from among a library of titles, for a source title, generating title data that specifies an order of a plurality of titles that are related to the source title based on a plurality of stored probability values; wherein each probability value in the plurality of probability values represents, for each particular title of the plurality of titles, a likelihood of selecting the particular title after playing the source title; using the server computer, receiving title impression data, wherein the title impression data specifies a plurality of browsed titles that were browsed from among the plurality of titles but may have not been selected for interaction; using the server computer, receiving title interaction data, wherein the title interaction data specifies a plurality of selected titles that were selected for interaction from the plurality of browsed titles; based on the title interaction data, the title impression data and a statistical model, re-calculating the plurality of probabilities.