Data-driven event detection for compressed video

    公开(公告)号:US11600070B2

    公开(公告)日:2023-03-07

    申请号:US17221947

    申请日:2021-04-05

    摘要: A system can obtain a labelled data set, including historic video data and labelled events. The system can divide the labelled data set into historic training/testing data sets. The system can determine, using the historic training data set, a plurality of different parameter configurations to be used by a video encoder to encode a video that includes a plurality of video frames. Each parameter configuration can include a group of pictures (“GOP”) size and a scenecut threshold. The system can calculate an accuracy of event detection (“ACC”) and a filtering rate (“FR”) for each parameter configuration. The system can calculate, for each parameter configuration of the plurality of different parameter configurations, a harmonic mean between the ACC and the FR. The system can then select a best parameter configuration of the plurality of different parameter configurations based upon the parameter configuration that has the highest harmonic mean.

    VOICE GATEWAY FOR FEDERATED VOICE SERVICES

    公开(公告)号:US20210304766A1

    公开(公告)日:2021-09-30

    申请号:US17347398

    申请日:2021-06-14

    IPC分类号: G10L15/22 G10L15/18 G10L15/30

    摘要: Devices, computer-readable media, and methods for submitting a modified voice input to a service based upon a user intent determined from a voice input in accordance with a voice interface of the service are disclosed. A processing system including at least one processor may obtain a voice input of a user, determine an intent from the voice input, identify a first service, from among a plurality of services, in accordance with the intent, and formulate a first modified voice input from the voice input in accordance with a voice interface of the first service, where each of the services is associated with one of a plurality of different voice interfaces. The processing system may further submit the first modified voice input to the first service, obtain a first voice response from the first service, and present a voice output to the user in accordance with the first voice response.

    RADIO ACCESS NETWORK INTELLIGENT CONTROLLER-BASED DYNAMIC TIME DIVISION DUPLEX COMMUNICATION IN A RADIO COMMUNICATION NETWORK

    公开(公告)号:US20210051522A1

    公开(公告)日:2021-02-18

    申请号:US16541690

    申请日:2019-08-15

    IPC分类号: H04W28/16 H04W24/10 H04W24/02

    摘要: Aspects of the subject disclosure may include, for example, a process or apparatus for receiving, by a processing system including a processor, cell traffic reports for cells of a radio communication network, performing a reconfiguration analysis to identify reconfiguration information to reconfigure the radio communication network according to changing network conditions, and communicating the reconfiguration information defining a new cell configuration for the cells of the radio communication network and communicating information defining a new reconfiguration time for the cells to substantially synchronously switch to communicating according to the reconfiguration information. The receiving the cell traffic reports, the performing the reconfiguration analysis and the communicating the reconfiguration information occur in substantially real time. Other embodiments are disclosed.