中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

394 records (took 0.065 seconds)

    MACHINE LEARNING ANOMALY DETECTION ON QUALITY OF SERVICE NETWORKING METRICS
    1.
    发明申请
    MACHINE LEARNING ANOMALY DETECTION ON QUALITY OF SERVICE NETWORKING METRICS 有权

    公开(公告)号：US20240406088A1

    公开(公告)日：2024-12-05

    申请号：US18327579

    申请日：2023-06-01

    Applicant: HULU, LLC

    Inventor： Tuo Li ,  Vahidreza Arbab

    IPC: H04L43/0823 ,  G06N20/00 ,  H04L41/16

    Abstract: In some embodiments, a method receives a first instance of data for anomaly detection. The first instance of data includes values from multiple variables. The first instance of data is stored in a queue. The method weights instances of data in the queue based on data changing over time and projects the instances of the data in the queue into a space. A point in the space represents a correlation of the values for the multiple variables for a respective instance of data. A boundary is generated based on the points in the space. Then, the method determines a point in the space that is considered an anomaly based on the boundary.

    Modeless interaction model for video interface
    2.
    发明授权
    Modeless interaction model for video interface 有权

    公开(公告)号：US11960716B2

    公开(公告)日：2024-04-16

    申请号：US17383211

    申请日：2021-07-22

    Applicant: HULU, LLC

    Inventor： Nathanael Smith

    IPC: G06F3/04886 ,  G06F3/04815 ,  G06F3/0482 ,  G06F3/0483 ,  H04N21/431

    CPC classification number: G06F3/04886 ,  G06F3/04815 ,  G06F3/0482 ,  G06F3/0483 ,  H04N21/4316

    Abstract: In some embodiments, a method applies a priority to a plurality of surfaces where the plurality of surfaces each include content. Content is displayed from a first portion of a first surface in the interface based on a priority that is applied to the first surface. A second portion of a second surface is obscured by the first surface. The method maintains operation of the second portion of the second surface and receives an interaction from the interface. The display of the interface is adjusted by displaying the second portion of the second surface in the interface in a state based on the maintaining of the operation.

    Pushing content in time windows based on different positions
    4.
    发明授权
    Pushing content in time windows based on different positions 有权

    公开(公告)号：US11811890B2

    公开(公告)日：2023-11-07

    申请号：US17507196

    申请日：2021-10-21

    Applicant: HULU, LLC

    Inventor： Shenglan Huang ,  Lan Xie ,  Wenhao Zhang

    IPC: H04L67/55 ,  H04L67/02 ,  H04L65/75 ,  H04L65/613

    CPC classification number: H04L67/55 ,  H04L65/613 ,  H04L65/75 ,  H04L67/02

    Abstract: In some embodiments, a method receives a first request for a first time window and a first position. A first message is sent to indicate a computing device will push content to a client in a stream for a video for a first one or more time windows other than the first time window. The method pushes content for the first time window based on the first position. A second request is received to change from the first position to a second position. The method pushes content for a second time window to the client based on the first position. A second message is sent to indicate the computing device will push content to the client in the stream for a second one or more time windows other than the second time window. The method pushes content for a third time window to the client based on the second position.

    Generation of unique presentation of media content
    5.
    发明授权
    Generation of unique presentation of media content 有权

    公开(公告)号：US11811838B1

    公开(公告)日：2023-11-07

    申请号：US17938297

    申请日：2022-10-05

    Applicant: HULU, LLC

    Inventor： Nicholas Brookins

    IPC: H04L65/80 ,  H04L65/60

    CPC classification number: H04L65/60 ,  H04L65/80

    Abstract: In some embodiments, a method receives a characteristic for media content. A number of entropy slots is determined that is based on the characteristic for the media content. An entropy slot in the media content is where a segment from a first version of the media content or a second version of the media content can be delivered. The method creates the first version of the media content having a first number of segments and creates the second version of the media content having a second number of segments based on the number of entropy slots. The second number of segments that correspond to the number of entropy slots is less than the first number of segments. The first version of the media content and the second version of the media content is output to create different sequences of segments that are attributable to different requests.

    Client based storage of remote element resolutions
    7.
    发明授权
    Client based storage of remote element resolutions 有权

    公开(公告)号：US11765421B2

    公开(公告)日：2023-09-19

    申请号：US17188151

    申请日：2021-03-01

    Applicant: HULU, LLC

    Inventor： Zachary McKeel Cava

    IPC: H04N21/431 ,  H04N21/84 ,  H04N21/81 ,  H04N21/435

    CPC classification number: H04N21/4316 ,  H04N21/4356 ,  H04N21/812 ,  H04N21/84

    Abstract: In some embodiments, a method receives a manifest presentation description for a media presentation. The manifest presentation description includes an opportunity that requires resolution to determine supplemental content for the opportunity. A request to resolve the opportunity is sent where information for the supplemental content that is received from the request is inserted in an instance of the media presentation description. The method stores the information for the supplemental content in association with an identifier for the opportunity. An update to the manifest presentation description is received where the update includes the opportunity. The method retrieves the information for the supplemental content that was stored in association with the identifier for the opportunity and inserts the information for the supplemental content into the instance of the update to the manifest presentation description.

    Training of multiple parts of a model to identify behavior to person prediction
    8.
    发明授权
    Training of multiple parts of a model to identify behavior to person prediction 有权

    公开(公告)号：US11671668B2

    公开(公告)日：2023-06-06

    申请号：US17318215

    申请日：2021-05-12

    Applicant: HULU, LLC

    Inventor： Dingming Wu ,  Changsheng Xiang ,  Wu Zhang ,  Chunyang Wei

    IPC: H04N21/466 ,  H04N21/45 ,  H04N21/442 ,  G06N7/01

    CPC classification number: H04N21/4667 ,  G06N7/01 ,  H04N21/44218 ,  H04N21/4532

    Abstract: In some embodiments, a method receives a first set of probabilities mapping a behavior to a user for a set of behaviors in a video delivery system. A first part of a model is used to predict the first set of probabilities. The method receives a second set of probabilities mapping a user to a behavior for a set of users that are using an account on the video delivery system. A second part of the model is used to predict the second set of probabilities. A combined probability is calculated for the set of behaviors and the set of users based on the first set of probabilities and the second set of probabilities. The method updates a second parameter of the second part of the model while keeping a first parameter of the first part of the model fixed and outputs the second parameter of the second part of the model upon determining the training of the model is finished.

Patent Agency Ranking