Selective network switching for dual connectivity

    公开(公告)号:US11950114B2

    公开(公告)日:2024-04-02

    申请号:US17490705

    申请日:2021-09-30

    Inventor: Haywood Peitzer

    CPC classification number: H04W24/08 H04L5/0055 H04W76/30 H04W88/06

    Abstract: An example method includes monitoring a status of a long term evolution network connection and a status of a fifth generation network connection over which a user endpoint device is simultaneously receiving data using an evolved-universal terrestrial radio access new radio dual connectivity configuration, detecting, based on the monitoring, that a performance metric of one of: the long term evolution network or the fifth generation network falls below a predefined threshold metric, and terminating, in response to the detecting, the long term evolution network connection or the fifth generation network connection to terminate the evolved-universal terrestrial radio access new radio dual connectivity configuration.

    Automatic connectivity for voice over WI-FI calls

    公开(公告)号:US11950098B2

    公开(公告)日:2024-04-02

    申请号:US17478778

    申请日:2021-09-17

    CPC classification number: H04W12/102 H04W12/66 H04W48/14 H04W48/16

    Abstract: A UE can enable a VoWIFI service, receive hidden SSID information, and register with a core network via a RAN. The UE can monitor a first signal strength of a first signal from the RAN. The UE can scan for a second signal from a WLAN, and when found, can measure a second signal strength of the second signal. The UE can determine whether the first signal strength is at or below a first threshold. If so, and if the WLAN is untrusted, the UE can probe it with the hidden SSID information. If the untrusted WLAN responds, the UE can send an access request to an untrusted WLAN access point. The UE can receive, via the untrusted WLAN access point, an authentication challenge from an ePDG. If the UE passes the authentication challenge, the UE can register with the core network via the untrusted WLAN and the ePDG.

    TRANSFER KNOWLEDGE FROM AUXILIARY DATA FOR MORE INCLUSIVE MACHINE LEARNING MODELS

    公开(公告)号:US20240104422A1

    公开(公告)日:2024-03-28

    申请号:US17935747

    申请日:2022-09-27

    CPC classification number: G06N20/00

    Abstract: Transfer knowledge from auxiliary data for more inclusive machine learning models is provided. A method can include generating a common feature space comprising first data features, wherein the first data features are present in training data used to train a first machine learning model, and wherein the first data features are present in auxiliary data that are independent of the training data; generating a combined learned feature representation, the combined learned feature representation being representative of the first data features of the common feature space and second data features that are unique to the training data; and training a second machine learning model based on the combined learned feature representation.

    Using a traffic monitoring service to detect traffic pattern shifts

    公开(公告)号:US11943126B1

    公开(公告)日:2024-03-26

    申请号:US17973946

    申请日:2022-10-26

    CPC classification number: H04L43/0876 H04L43/026 H04L43/062

    Abstract: Using a traffic monitoring service to detect traffic pattern shifts can include obtaining netflow data and routing data for core routers. Based on the netflow data and the routing data, an augmented traffic matrix can be generated. A router-level analysis can be performed on the augmented traffic matrix to identify a pair of core routers that are associated with a traffic pattern shift in the network. An entity-level analysis can be performed on the pair of core routers to identify an entity that is responsible for the traffic pattern shift in the network. Traffic shift data that identifies the pair of core routers and the entity that is responsible for the traffic pattern shift in the network can be output.

    INTELLIGENT MANAGEMENT OF ADAPTABLE AUDIO-VISUALS OF VIDEO CONFERENCING SESSIONS

    公开(公告)号:US20240097925A1

    公开(公告)日:2024-03-21

    申请号:US17932563

    申请日:2022-09-15

    Abstract: Techniques are described that facilitate intelligent management of adaptable audio-visuals of cloud-based video conferencing sessions. In one example embodiment, method comprises determining, by a system comprising a processor, capabilities of respective devices of participants of a video conferencing session provisioned via a communication network, the capabilities comprising audio-visual capabilities and connection capabilities of the respective devices related to communicating respective data streams of the video conferencing session via the communication network. The method further comprises determining, by the system, respective audio-visual settings of the video conferencing session applicable to the respective devices as a function of the capabilities of the respective devices, and controlling, by the system, performance of the video conferencing session at the respective devices in accordance with the respective audio-visual settings.

    Video curation service for personal streaming

    公开(公告)号:US11935565B2

    公开(公告)日:2024-03-19

    申请号:US17853411

    申请日:2022-06-29

    CPC classification number: G11B27/031 G06F16/438 G06V20/48

    Abstract: Aspects of the subject disclosure may include, for example, a device that includes a processing system with a processor, and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations such as receiving user input comprising a keyword identifying an object, monitoring a video recording during a generation of the video recording by a camera, wherein the monitoring includes detecting the object being captured by the camera, creating a video clip from the video recording, wherein the video clip comprises a start point and a stop point in the video recording determined by a machine learning algorithm, and sending a notification of the creating of the video clip. Other embodiments are disclosed.

    AUTOMATED EVENT WITNESS IDENTIFICATION
    200.
    发明公开

    公开(公告)号:US20240089697A1

    公开(公告)日:2024-03-14

    申请号:US17931375

    申请日:2022-09-12

    CPC classification number: H04W4/023 H04L67/52 H04W4/021

    Abstract: The disclosed technology is directed towards efficiently identifying a first entity (e.g., a user or sensor) as a potential witness to an event. A first dataset describing event time data and event location data of an event are obtained from a first device. A second dataset describing device time data and device location data are obtained via a device associated with a second entity, e.g., a user. By analyzing the first and second datasets, e.g., for time and location intersection, the second entity can be identified as a potential witness to the event, and notified of such. Factors such as line of sight, speed and direction, audio sensing range versus event volume, and the like of the second entity can be used in determining whether the second entity is a likely witness. A witness to a live event can be identified and asked to send in live (e.g., video) evidence.

Patent Agency Ranking