知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.018 seconds)

    PERSONA/INDIVIDUAL BASED ACTIONS BASED ON COMMUNITY SPECIFIC TRIGGER
    2.
    发明申请
    PERSONA/INDIVIDUAL BASED ACTIONS BASED ON COMMUNITY SPECIFIC TRIGGER 审中-公开

    公开(公告)号：US20200067776A1

    公开(公告)日：2020-02-27

    申请号：US16113355

    申请日：2018-08-27

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

    Inventor： Robert F. WILLIAMS ,  Eric ZAVESKY ,  James PRATT

    IPC: H04L12/24 ,  H04L29/08

    Abstract: Systems and methods herein spawn action sets for networked communities which are executed based on detected triggers. A method that spawns action sets can include selecting a community including member devices. The member devices are associated with a distributed job. The method can also include identifying a trigger related to the distributed job and spawning an automated action set related to the trigger. The automated action set includes at least one of automated action by the member devices or automated action by a remote device communicatively coupled to at least one of the member devices.

    DATA AND CONTEXT BASED ROLE MEMBERSHIP SYSTEM
    7.
    发明申请
    DATA AND CONTEXT BASED ROLE MEMBERSHIP SYSTEM 审中-公开

    公开(公告)号：US20190387000A1

    公开(公告)日：2019-12-19

    申请号：US16011780

    申请日：2018-06-19

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

    Inventor： Eric ZAVESKY ,  James PRATT ,  Robert GRATZ ,  Jason DECUIR

    IPC: H04L29/06 ,  H04L29/08 ,  H04L12/24

    Abstract: A data and context based role management system comprising: a community, the community including at least one data source having plural roles stored therein, the plural roles including an identity including at least one of a credential, a function, a capability, and a historic response data; a discovery module configured to identify an alert associated with an event requiring a response, the discovery module being further configured to search the community for a responder based on the event, wherein the discovery module is configured to compare a criteria based on the event to the identity associated with each of the plural roles to identify the responder; and when the responder is identified, the community promotes the responder to transform at least one device of the responder to provide at least access to data associated with the event.

    EDGE SHARING ORCHESTRATION SYSTEM
    8.
    发明申请
    EDGE SHARING ORCHESTRATION SYSTEM 审中-公开

    公开(公告)号：US20190379734A1

    公开(公告)日：2019-12-12

    申请号：US16002579

    申请日：2018-06-07

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

    Inventor： Eric ZAVESKY ,  Nigel BRADLEY ,  David Crawford GIBBON ,  James PRATT ,  Timothy INNES

    IPC: H04L29/08

    Abstract: An edge share orchestration system comprising: an opportunistic capability listener in communication with at least one customer device and at least one additional device; the opportunistic capability listener is configured to pool the at least one customer device and the at least one additional device based on at least one of a capability and a function; an edge share balancer configured to integrate the at least one customer device with the at least one additional device to transform the capability or function of the at least one customer device to provide at least one of a novel service and an augmented service.

    AUGMENTED MULTI-TIER CLASSIFIER FOR MULTI-MODAL VOICE ACTIVITY DETECTION
    9.
    发明申请
    AUGMENTED MULTI-TIER CLASSIFIER FOR MULTI-MODAL VOICE ACTIVITY DETECTION 有权

    公开(公告)号：US20210074315A1

    公开(公告)日：2021-03-11

    申请号：US17101048

    申请日：2020-11-23

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

    Inventor： Dimitrios DIMITRIADIS ,  Eric ZAVESKY ,  Matthew BURLICK

    IPC: G10L25/78 ,  G10L25/84

    Abstract: Voice activity in a media signal is detected in an augmented, multi-tier classifier architecture. For instance, a first voice activity indicator, detected in a first modality for a human subject, is received from a first classifier. 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 then concatenates, 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