中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

81 records (took 0.026 seconds)

    Control of wireless fidelity access for 5G or other next generation network
    3.
    发明授权
    Control of wireless fidelity access for 5G or other next generation network 有权

    公开(公告)号：US11160001B2

    公开(公告)日：2021-10-26

    申请号：US16890423

    申请日：2020-06-02

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

    Inventor： Sheldon Meredith ,  Mark Austin ,  Rick Tipton

    IPC: H04W36/22 ,  H04W36/30 ,  H04W28/08 ,  H04W72/08 ,  H04W72/04 ,  H04W36/24 ,  H04W48/20 ,  G01S19/04

    Abstract: Techniques for facilitating cellular or wireless fidelity access point selection are provided. In one example herein a method is provided comprising receiving, by a mobile device comprising a processor, first radio load data associated with a predicted radio load of a first channel of a first wireless device. Based on a first condition associated with the first radio load being determined to have been satisfied, the method can facilitate, by the mobile device, receiving second radio load data, indicative of a current radio load, from a second wireless device. Additionally, in response to a second condition associated with the current radio load being determined to have been satisfied, the method can utilize, by the mobile device, a second channel of the second wireless device for a communication.

    System, Method, and Platform for Auto Machine Learning Via Optimal Hybrid AI Formulation from Crowd
    6.
    发明申请
    System, Method, and Platform for Auto Machine Learning Via Optimal Hybrid AI Formulation from Crowd 有权

    公开(公告)号：US20210174130A1

    公开(公告)日：2021-06-10

    申请号：US16703430

    申请日：2019-12-04

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

    Inventor： Mark Austin ,  ABHAY DABHOLKAR ,  VIJAYAN NAGARAJAN ,  Lauren Savage ,  Joshua Whitney

    IPC: G06K9/62 ,  G06N20/20

    Abstract: Aspects of the subject disclosure may include, for example, receiving a plurality of proposed machine learning solutions to a machine learning problem including receiving, for each respective proposed machine learning solution of the plurality of proposed machine learning solutions, one or more of a machine learning model, a dataset and a data pipeline output; automatically determining hybrid solutions to the machine learning problem, including combining, by the processing system, at least one of a first component from a first proposed machine learning solution with at least one of a second component from a second proposed machine learning solution; and ranking the hybrid solutions including determining a log loss score for each hybrid solution and sorting the hybrid solutions according to the log loss score for each hybrid solution. Other embodiments are disclosed.

    Velocity-weighted analysis of user equipment location data
    7.
    发明授权
    Velocity-weighted analysis of user equipment location data 有权

    公开(公告)号：US10405142B2

    公开(公告)日：2019-09-03

    申请号：US16239519

    申请日：2019-01-03

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

    Inventor： Kuang-Chi Tung ,  Mark Austin ,  Sheldon Meredith

    IPC: H04W4/02 ,  H04W4/029

    Abstract: Velocity-weighted analysis of UE location data is disclosed. UE velocity can be determined from the change in position and time. UE dwell can also be determined from the change in position and time. UE dwell and UE velocity can be inversely related. UE dwell an UE velocity can be correlated to a likelihood that an event occurrence related to a point of interest affects UE travel between a first and second location. A location of the point of interest can be determined to be in a region corresponding to a path between the first and second location. The region can be associated with the UE dwell and/or UE velocity, such that a probability of interaction can be determined for the event occurrence for the point of interest. The region can comprise a probable UE path based on historical UE data.

Patent Agency Ranking