知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.012 秒)

    REINFORCEMENT LEARNING FOR GUARANTEED DELIVERY OF SUPPLEMENTAL CONTENT
    1.
    发明申请
    REINFORCEMENT LEARNING FOR GUARANTEED DELIVERY OF SUPPLEMENTAL CONTENT 有权

    公开(公告)号：US20220360854A1

    公开(公告)日：2022-11-10

    申请号：US17315107

    申请日：2021-05-07

    申请人： HULU, LLC

    发明人： Pengfei Gao ,  Dingming Wu ,  Chunyang Wei ,  Xiaohui Xie ,  Shulei Ma

    IPC分类号： H04N21/472 ,  H04N21/45 ,  H04N21/442 ,  H04N21/466 ,  G06Q30/02 ,  G06N20/00 ,  G06N5/04

    摘要： In some embodiments, a method receives a request for supplemental content to be provided in association with main content. The method selects an instance of supplemental content based on a long-term reward metric and a short-term reward metric. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and a delivery status for a delivery constraint of one instance of supplemental content. The short-term reward metric is based on feedback from delivery of the one instance of supplemental content. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and the short-term reward metric is based on feedback from delivery of one instance of supplemental content. The instance of supplemental content is provided to a client device.

    Reinforcement learning for guaranteed delivery of supplemental content
    2.
    发明授权
    Reinforcement learning for guaranteed delivery of supplemental content 有权

    公开(公告)号：US11546665B2

    公开(公告)日：2023-01-03

    申请号：US17315107

    申请日：2021-05-07

    申请人： HULU, LLC

    发明人： Pengfei Gao ,  Dingming Wu ,  Chunyang Wei ,  Xiaohui Xie ,  Shulei Ma

    IPC分类号： H04N21/442 ,  H04N21/472 ,  H04N21/45 ,  G06N5/04 ,  H04N21/466 ,  G06Q30/02 ,  G06N20/00

    摘要： In some embodiments, a method receives a request for supplemental content to be provided in association with main content. The method selects an instance of supplemental content based on a long-term reward metric and a short-term reward metric. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and a delivery status for a delivery constraint of one instance of supplemental content. The short-term reward metric is based on feedback from delivery of the one instance of supplemental content. The long-term reward metric is based on feedback from delivery of a plurality of instances of supplemental content and the short-term reward metric is based on feedback from delivery of one instance of supplemental content. The instance of supplemental content is provided to a client device.

    Training of multiple parts of a model to identify behavior to person prediction
    3.
    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

    申请人： HULU, LLC

    发明人： Dingming Wu ,  Changsheng Xiang ,  Wu Zhang ,  Chunyang Wei

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

    CPC分类号： H04N21/4667 ,  G06N7/01 ,  H04N21/44218 ,  H04N21/4532

    摘要： 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.

    Optimal supplemental content selection in content delivery
    5.
    发明授权
    Optimal supplemental content selection in content delivery 有权

    公开(公告)号：US11849188B2

    公开(公告)日：2023-12-19

    申请号：US17653422

    申请日：2022-03-03

    申请人： HULU, LLC

    发明人： Dingming Wu ,  Chunyang Wei ,  Changsheng Xiang ,  Shulei Ma

    IPC分类号： H04N21/4722 ,  H04N21/266 ,  H04N21/472

    CPC分类号： H04N21/4722 ,  H04N21/266 ,  H04N21/47202

    摘要： In some embodiments, a method receives information for a delivery of instances of supplemental content for a plurality of line items. A line item is associated with an instance of supplemental content that can be delivered and a pacing curve that describes a pace of delivery over time. The method updates a parameter for the line item to generate an updated parameter based on the delivery of the instances of supplemental content and a desired pacing behavior. The updated parameter is provided to a selection system that uses the updated parameter to select an instance for delivery. The delivery of instances of supplemental content for the line item is adjusted to meet the pacing curve based on a characteristic of the pacing behavior.

    Dynamic threshold calculation for video streaming
    6.
    发明授权
    Dynamic threshold calculation for video streaming 有权

    公开(公告)号：US11553220B1

    公开(公告)日：2023-01-10

    申请号：US17404645

    申请日：2021-08-17

    申请人： HULU, LLC

    发明人： Changsheng Xiang ,  Dingming Wu ,  Chunyang Wei

    IPC分类号： H04N7/10 ,  H04N21/234 ,  H04N21/431 ,  H04N21/466 ,  H04N21/25

    摘要： In some embodiments, a method receives an supplemental content placement and a context associated with a request for supplemental content to be displayed for the supplemental content placement. A first value is generated based on the context using a prediction network for a platform. The method determines probabilities for a plurality of types of request actions based on the context. Then, a threshold for the supplemental content placement is calculated based on the first value and the probabilities for the plurality of types of request actions. The method submits the threshold to a platform in a request for the platform to submit a second value for the supplemental content placement.

    SELECTION OF VIDEO ADVERTISEMENTS
    8.
    发明申请
    SELECTION OF VIDEO ADVERTISEMENTS 有权

    公开(公告)号：US20210158395A1

    公开(公告)日：2021-05-27

    申请号：US16698464

    申请日：2019-11-27

    申请人： HULU, LLC.

    发明人： Dingming Wu ,  Chunyang Wei

    IPC分类号： G06Q30/02

    摘要： In some embodiments, a method receives a request for an advertisement and selects a first advertisement deal from a first grouping of advertisement deals based on a first parameter value. The method determines a second parameter value for advertisement deals in the first grouping of advertisement deals. Then, the second parameter value of the advertisement deals in the first grouping of advertisement deals is compared to a second parameter value of a set of second advertisement deals from a second grouping of advertisement deals. The method selects one of a first category of the first grouping of advertisement deals and a second category of the second grouping of advertisement deals. The method selects a first advertisement deal from the first grouping of advertisement deals when the first category is selected and a second advertisement deal when the second category is selected for the request.