中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

260 records (took 0.03 seconds)

    METHODS, SYSTEMS AND DEVICES FOR SELECTING ADVERTISEMENTS BASED ON MEDIA PROFILES AND ADVERTISEMENT PROFILES
    152.
    发明申请
    METHODS, SYSTEMS AND DEVICES FOR SELECTING ADVERTISEMENTS BASED ON MEDIA PROFILES AND ADVERTISEMENT PROFILES 有权

    公开(公告)号：US20220237663A1

    公开(公告)日：2022-07-28

    申请号：US17723654

    申请日：2022-04-19

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Eric Zavesky ,  Behzad Shahraray ,  Bernard S. Renger ,  Raghuraman Gopalan ,  Tan Xu

    IPC: G06Q30/02

    Abstract: Aspects of the subject disclosure may include, for example, embodiments for determining a media profile for media content. The media profile comprises a media metric for each of a plurality of portions of the media content. Further, embodiments include determining a price for advertising associated with the media content. In addition, embodiments include identifying an advertisement profile for each of a plurality of advertisements. The advertisement profile comprises an ad metric for each of a plurality of portions of an advertisement. Also, embodiments include selecting a first advertisement associated with a first advertisement profile from the plurality of advertisements according to the media profile, the first advertisement profile, and the price for the advertising associated with the media content. Further, embodiments include providing the first advertisement to be presented with the media content at a playback device. Other embodiments are disclosed.

    ACTIVATION OF EXTENDED REALITY ACTUATORS BASED ON CONTENT ANALYSIS
    153.
    发明申请
    ACTIVATION OF EXTENDED REALITY ACTUATORS BASED ON CONTENT ANALYSIS 有权

    公开(公告)号：US20220215637A1

    公开(公告)日：2022-07-07

    申请号：US17700365

    申请日：2022-03-21

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Behzad Shahraray ,  Eric Zavesky ,  David Crawford Gibbon ,  Tan Xu ,  Zhu Liu

    IPC: G06T19/00 ,  G06T19/20 ,  G06F3/01 ,  G02B27/01

    Abstract: In one example, a method performed by a processing system in a telecommunications network includes acquiring the media stream and identifying an anchor in a scene of the media stream. The anchor is a presence in the scene that has a physical effect on the scene. A type and a magnitude of the physical effect of the anchor on the scene is estimated. An actuator in a vicinity of the user endpoint device that is capable of producing a physical effect in the real world to match the physical effect of the anchor on the scene is identified. A signal is sent to the actuator. The signal controls the actuator to produce the physical effect in the real world when the physical effect of the anchor on the scene occurs in the media stream.

    DIRECTING USER FOCUS IN 360 VIDEO CONSUMPTION
    154.
    发明申请
    DIRECTING USER FOCUS IN 360 VIDEO CONSUMPTION 有权

    公开(公告)号：US20220086516A1

    公开(公告)日：2022-03-17

    申请号：US17533654

    申请日：2021-11-23

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Raghuraman Gopalan ,  Zhu Liu ,  Behzad Shahraray ,  Eric Zavesky ,  Tan Xu

    IPC: H04N21/258 ,  H04N21/462

    Abstract: Aspects of the subject disclosure may include, for example, a method including obtaining media content and an identification of a plurality of points of interest in the media content, receiving a request from a user to view the media content, obtaining information about the user, identifying one or more highlight and/or degrade points based on the information about the user, modifying the media content to create highlighted content, the highlighted content being the media content modified to attract attention of the user to the highlight point and drive the attention of the user away from the degrade point, presenting the highlighted content to the user, and monitoring the user's consumption of the content. Other embodiments are disclosed.

    OBJECT MODELING WITH ADVERSARIAL LEARNING
    155.
    发明申请
    OBJECT MODELING WITH ADVERSARIAL LEARNING 有权

    公开(公告)号：US20220026905A1

    公开(公告)日：2022-01-27

    申请号：US17493770

    申请日：2021-10-04

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Eric Zavesky ,  Raghuraman Gopalan ,  Behzad Shahraray ,  David Crawford Gibbon ,  Bernard S. Renger ,  Paul Triantafyllou

    IPC: G05D1/00 ,  G06N5/02 ,  B60W30/095 ,  G06K9/00 ,  G06K9/62

    Abstract: Methods, computer-readable media, and devices are disclosed for improving an object model based upon measurements of physical properties of an object via an unmanned vehicle using adversarial examples. For example, a method may include a processing system capturing measurements of physical properties of an object via at least one unmanned vehicle, updating an object model for the object to include the measurements of the physical properties of the object, where the object model is associated with a feature space, and generating an example from the feature space, where the example comprises an adversarial example. The processing system may further apply the object model to the example to generate a prediction, capture additional measurements of the physical properties of the object via the at least one unmanned vehicle when the prediction fails to identify that the example is an adversarial example, and update the object model to include the additional measurements.

    Deviations from workflows associated with physical items
    159.
    发明授权
    Deviations from workflows associated with physical items 有权

    公开(公告)号：US11157845B2

    公开(公告)日：2021-10-26

    申请号：US15941415

    申请日：2018-03-30

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Eric Zavesky ,  Lee Begeja ,  Zhu Liu ,  Behzad Shahraray ,  Bernard S. Renger

    IPC: G06Q10/06 ,  G06F16/9535

    Abstract: Devices, computer-readable media, and methods for detecting a deviation from a workflow associated with a physical item. For example, a method may include a processing system having at least one processor for capturing a plurality of images of at least one physical item during a performance of a workflow comprising a plurality of tasks relating to the at least one physical item, tracking a progression of the performance of the workflow, and detecting, from at least a first image of the plurality of images, a deviation from the workflow. The processing system may then present a notification of the deviation from the workflow and confirm an action in response to the notification.

    Object modeling with adversarial learning
    160.
    发明授权
    Object modeling with adversarial learning 有权

    公开(公告)号：US11137761B2

    公开(公告)日：2021-10-05

    申请号：US15818495

    申请日：2017-11-20

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Eric Zavesky ,  Raghuraman Gopalan ,  Behzad Shahraray ,  David Crawford Gibbon ,  Bernard S. Renger ,  Paul Triantafyllou

    IPC: G06N5/02 ,  G05D1/00 ,  B60W30/095 ,  G06K9/00 ,  G06K9/62 ,  B60W30/09 ,  G05D1/02

    Abstract: Methods, computer-readable media, and devices are disclosed for improving an object model based upon measurements of physical properties of an object via an unmanned vehicle using adversarial examples. For example, a method may include a processing system capturing measurements of physical properties of an object via at least one unmanned vehicle, updating an object model for the object to include the measurements of the physical properties of the object, where the object model is associated with a feature space, and generating an example from the feature space, where the example comprises an adversarial example. The processing system may further apply the object model to the example to generate a prediction, capture additional measurements of the physical properties of the object via the at least one unmanned vehicle when the prediction fails to identify that the example is an adversarial example, and update the object model to include the additional measurements.

Patent Agency Ranking