中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

23 records (took 0.025 seconds)

    User device ad-hoc distributed caching of content
    11.
    发明授权
    User device ad-hoc distributed caching of content 有权

    公开(公告)号：US10382552B2

    公开(公告)日：2019-08-13

    申请号：US15375274

    申请日：2016-12-12

    Applicant: Verizon Patent and Licensing Inc.

    Inventor： Dante J. Pacella ,  Mani Tadayon ,  Ashish Sardesai ,  Saravanan Mallesan ,  Lee E. Sattler ,  Sonit Mahey ,  Venkata Josyula

    IPC: H04L29/08

    Abstract: A device receives a user election of participation in a distributed cache service, and receives user selection of one or more devices, that are each associated with the user, to register with the distributed cache service as participant nodes. The device determines an amount of available storage offered to the cache service for each of the one or more participant nodes, and determines an available bandwidth of a respective network connection associated with each of the one or more participant nodes. The device admits selected devices of the one or more participant nodes into the distributed cache service based on the available storage and the available bandwidth, and interleaves storage of multiple chunks of content across a subset of the participant nodes admitted into the distributed cache service. The device enables client access to the multiple chunks of content interleaved across the subset of the participant nodes.

    Systems and methods for secure authentication based on machine learning techniques
    12.
    发明授权
    Systems and methods for secure authentication based on machine learning techniques 有权

    公开(公告)号：US11488022B2

    公开(公告)日：2022-11-01

    申请号：US15930044

    申请日：2020-05-12

    Applicant: Verizon Patent and Licensing Inc.

    Inventor： Sumanth S. Mallya ,  Corbin Pierce Moline ,  Saravanan Mallesan

    IPC: G10L17/06 ,  G06N3/08 ,  G10L17/18 ,  G06N3/04 ,  G06F21/32 ,  G06V40/16 ,  G06V40/12

    Abstract: A system described herein may provide a technique for the use of machine learning techniques to perform authentication, such as biometrics-based user authentication. For example, user biometric information (e.g., facial features, fingerprints, voice, etc.) of a user may be used to train a machine learning model, in addition to a noise vector. A representation of the biometric information (e.g., an image file including a picture of the user's face, an encoded file with vectors or other representation of the user's fingerprint, a sound file including the user's voice, etc.) may be iteratively transformed until the transformed biometric information matches the noise vector, and the machine learning model may be trained based on the set of transformations that ultimately yield the noise vector, when given the biometric information.

    SYSTEMS AND METHODS FOR SECURE AUTHENTICATION BASED ON MACHINE LEARNING TECHNIQUES
    14.
    发明申请
    SYSTEMS AND METHODS FOR SECURE AUTHENTICATION BASED ON MACHINE LEARNING TECHNIQUES 有权

    公开(公告)号：US20210357761A1

    公开(公告)日：2021-11-18

    申请号：US15930044

    申请日：2020-05-12

    Applicant: Verizon Patent and Licensing Inc.

    Inventor： Sumanth S. Mallya ,  Corbin Pierce Moline ,  Saravanan Mallesan

    IPC: G06N3/08 ,  G10L17/06 ,  G10L17/18 ,  G06K9/00 ,  G06F21/32 ,  G06N3/04

    Abstract: A system described herein may provide a technique for the use of machine learning techniques to perform authentication, such as biometrics-based user authentication. For example, user biometric information (e.g., facial features, fingerprints, voice, etc.) of a user may be used to train a machine learning model, in addition to a noise vector. A representation of the biometric information (e.g., an image file including a picture of the user's face, an encoded file with vectors or other representation of the user's fingerprint, a sound file including the user's voice, etc.) may be iteratively transformed until the transformed biometric information matches the noise vector, and the machine learning model may be trained based on the set of transformations that ultimately yield the noise vector, when given the biometric information.

    SYSTEMS AND METHODS FOR SECURE AUTHENTICATION BASED ON MACHINE LEARNING TECHNIQUES
    18.
    发明申请
    SYSTEMS AND METHODS FOR SECURE AUTHENTICATION BASED ON MACHINE LEARNING TECHNIQUES 有权

    公开(公告)号：US20230009298A1

    公开(公告)日：2023-01-12

    申请号：US17934273

    申请日：2022-09-22

    Applicant: Verizon Patent and Licensing Inc.

    Inventor： Sumanth S. Mallya ,  Corbin Pierce Moline ,  Saravanan Mallesan

    IPC: G06N3/08 ,  G10L17/06 ,  G10L17/18 ,  G06N3/04 ,  G06F21/32 ,  G06V40/16 ,  G06V40/12

    Abstract: A system described herein may provide a technique for the use of machine learning techniques to perform authentication, such as biometrics-based user authentication. For example, user biometric information (e.g., facial features, fingerprints, voice, etc.) of a user may be used to train a machine learning model, in addition to a noise vector. A representation of the biometric information (e.g., an image file including a picture of the user's face, an encoded file with vectors or other representation of the user's fingerprint, a sound file including the user's voice, etc.) may be iteratively transformed until the transformed biometric information matches the noise vector, and the machine learning model may be trained based on the set of transformations that ultimately yield the noise vector, when given the biometric information.

Patent Agency Ranking