中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

862 records (took 0.045 seconds)

    Generating a pre-caching schedule based on forecasted content requests
    141.
    发明授权
    Generating a pre-caching schedule based on forecasted content requests 有权

    公开(公告)号：US10117058B2

    公开(公告)日：2018-10-30

    申请号：US15078867

    申请日：2016-03-23

    Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

    Inventor： Lee Begeja ,  David Crawford Gibbon ,  Raghuraman Gopalan ,  Zhu Liu ,  Yadong Mu ,  Bernard S. Renger ,  Behzad Shahraray ,  Eric Zavesky

    IPC: H04J3/00 ,  G06F15/167 ,  G06F15/16 ,  H04W4/02 ,  H04L29/06

    Abstract: A method includes accessing information identifying user devices, and accessing media consumption data indicating content requests corresponding to the user devices. The method also includes determining expected locations of the user devices based on the information, and determining forecasted content requests based on the media consumption data. The method further includes generating a pre-caching schedule based on the forecasted content requests and the expected locations, and determining that the pre-caching schedule indicates that particular media data is to be provided via a multicast transmission to a first user device and to a second user device. The method also includes sending an instruction to the first user device directing the first user device to store the particular media data. The method includes sending, responsive to a request from the second user device, the particular media data via the multicast transmission to the first user device and to the second user device.

    Dynamic image recognition model updates
    142.
    发明授权
    Dynamic image recognition model updates 有权

    公开(公告)号：US10115185B2

    公开(公告)日：2018-10-30

    申请号：US14561353

    申请日：2014-12-05

    Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

    Inventor： David Crawford Gibbon ,  Benjamin J. Stern ,  Zhu Liu ,  Eric Zavesky

    IPC: G06K9/46 ,  G06T5/00 ,  G06K9/00 ,  G06K9/62

    Abstract: A method includes receiving first image data at an electronic device, and performing a first image recognition operation on the first image data based on a first image recognition model stored in a memory of the electronic device. The method may include sending an image recognition model update request from the electronic device to a server, in response to determining that a result of the first image recognition operation fails to satisfy a confidence threshold. The method includes receiving image recognition model update information from the server and updating the first image recognition model based on the image recognition model update information to generate a second image recognition model. The method further includes performing a second image recognition operation based on the second image recognition model.

    Audio adjustment and profile system
    145.
    发明授权
    Audio adjustment and profile system 有权

    公开(公告)号：US09980076B1

    公开(公告)日：2018-05-22

    申请号：US15438701

    申请日：2017-02-21

    Applicant: AT&T INTELLECTUAL PROPERTY I, L.P. ,  AT&T Mobility II LLC

    Inventor： James Pratt ,  Eric Zavesky ,  Yupeng Jia

    IPC: H04R5/02 ,  H04S7/00

    CPC classification number: H04S7/303 ,  H04S7/301 ,  H04S2400/11 ,  H04S2400/13

    Abstract: An audio adjustment and profile system is provided that can track individuals and speaker locations in an area to dynamically calibrate speakers to provide a uniform listening experience. The system can generate an acoustic model of a room and further calibrate speakers using the acoustic model. The audio adjustment and profile system can also use profile information associated with the listener to customize the listening experience based on the preference information in the profile information. The preference information can comprise mood preferences that emphasize certain frequencies and tones while limiting others.

    Augmented multi-tier classifier for multi-modal voice activity detection
    146.
    发明授权
    Augmented multi-tier classifier for multi-modal voice activity detection 有权

    公开(公告)号：US09892745B2

    公开(公告)日：2018-02-13

    申请号：US13974453

    申请日：2013-08-23

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

    Inventor： Dimitrios Dimitriadis ,  Eric Zavesky ,  Matthew Burlick

    IPC: G10L15/24 ,  G10L25/78 ,  G10L25/84 ,  G06K9/00

    CPC classification number: G10L25/78 ,  G06K9/00335 ,  G10L15/24 ,  G10L25/84

    Abstract: Disclosed herein are systems, methods, and computer-readable storage media for detecting voice activity in a media signal in an augmented, multi-tier classifier architecture. A system configured to practice the method can receive, from a first classifier, a first voice activity indicator detected in a first modality for a human subject. Then, the system can receive, from a second classifier, a second voice activity indicator detected in a second modality for the human subject, wherein the first voice activity indicator and the second voice activity indicators are based on the human subject at a same time, and wherein the first modality and the second modality are different. The system can concatenate, via a third classifier, the first voice activity indicator and the second voice activity indicator with original features of the human subject, to yield a classifier output, and determine voice activity based on the classifier output.

Patent Agency Ranking