RESOURCE ORCHESTRATION FOR MICROSERVICES-BASED 5G APPLICATIONS

    公开(公告)号:US20230035024A1

    公开(公告)日:2023-02-02

    申请号:US17863685

    申请日:2022-07-13

    Abstract: A method for performing resource orchestration for microservices-based 5G applications in a dynamic, heterogenous, multi-tiered compute and network environment is presented. The method includes managing compute requirements and network requirements of a microservices-based application jointly by positioning computing nodes distributed across multiple layers, across edges and at a central cloud, identifying and modeling coupling relationships between compute and network resources for a plurality of microservices, when only application-level requirements are provided, to build coupling functions, solving a multi-objective optimization problem to identify how each of the plurality of microservices are deployed in the dynamic, heterogenous, multi-tiered compute and network environment by employing the coupling functions to jointly optimize resource usage of the compute and network resources across different compute and network slices, and deriving optimal joint network and compute resource allocation and function placement decisions.

    DYNAMIC, CONTEXTUALIZED AI MODELS
    84.
    发明申请

    公开(公告)号:US20220230421A1

    公开(公告)日:2022-07-21

    申请号:US17577664

    申请日:2022-01-18

    Abstract: A method for employing a semi-supervised learning approach to improve accuracy of a small model on an edge device is presented. The method includes collecting a plurality of frames from a plurality of video streams generated from a plurality of cameras, each camera associated with a respective small model, each small model deployed in the edge device, sampling the plurality of frames to define sampled frames, performing inference to the sampled frames by using a big model, the big model shared by all of the plurality of cameras and deployed in a cloud or cloud edge, using the big model to generate labels for each of the sampled frames to generate training data, and training each of the small models with the training data to generate updated small models on the edge device.

    FACE CLUSTERING IN VIDEO STREAMS
    85.
    发明申请

    公开(公告)号:US20210319226A1

    公开(公告)日:2021-10-14

    申请号:US17194911

    申请日:2021-03-08

    Abstract: Methods and systems for video analysis and response include detecting face images within video streams. Noisy images are filtered from the detected face images. Batches of the remaining detected face images are clustered to generate mini-clusters, constrained by temporal locality. The mini-clusters are globally clustered to generate merged clusters formed of face images for respective people, using camera-chain information to constrain a set of the video streams being considered. Analytics are performed on the merged clusters to identify a tracked individual's movements through an environment. A response is performed to the tracked individual's movements.

    EFFICIENT WATCHLIST SEARCHING WITH NORMALIZED SIMILARITY

    公开(公告)号:US20210319212A1

    公开(公告)日:2021-10-14

    申请号:US17197431

    申请日:2021-03-10

    Abstract: Methods and systems for face recognition and response include extracting a face image from a video stream. A pre-processed index is searched for a watchlist image that matches the face image, based on a similarity distance that is computed from a normalized similarity score to satisfy metric properties. The index of the watchlist includes similarity distances between face images stored in the watchlist. An action is performed responsive to a determination that the extracted face image matches the watchlist image.

    COMBINED LIGHT AND HEAVY MODELS FOR IMAGE FILTERING

    公开(公告)号:US20210264138A1

    公开(公告)日:2021-08-26

    申请号:US17181735

    申请日:2021-02-22

    Abstract: Systems and methods for demographic determination using image recognition. The method includes analyzing an image with a pre-trained lightweight neural network model, where the lightweight neural network model generates a confidence value, and comparing the confidence value to a threshold value to determine if the pre-trained lightweight neural network model is sufficiently accurate. The method further includes analyzing the image with a pre-trained heavyweight neural network model for the confidence value below the threshold value, wherein the pre-trained heavyweight neural network model has above about one million trainable parameters and the pre-trained lightweight neural network model has a number of trainable parameters below one tenth the heavyweight model, and displaying demographic data to a user on a user interface, wherein the user modifies store inventory based on the demographic data.

    COMBINED PERSON DETECTION AND FACE RECOGNITION FOR PHYSICAL ACCESS CONTROL

    公开(公告)号:US20210264137A1

    公开(公告)日:2021-08-26

    申请号:US17178444

    申请日:2021-02-18

    Abstract: Methods and systems for managing access include detecting a person within a region of interest in a video stream. It is determined that a clear image of the person's face is not available within the region of interest. Tracking information of the person is matched to historical face tracking information for the person in a previously captured frame. The person's face from the previously captured video frame is matched to an authentication list, responsive to detecting the person within the region of interest, to determine that the detected person is unauthorized for access. A response to the determination that the detected person is unauthorized for access is performed.

    MANAGING APPLICATIONS FOR SENSORS
    90.
    发明申请

    公开(公告)号:US20210263752A1

    公开(公告)日:2021-08-26

    申请号:US17177998

    申请日:2021-02-17

    Abstract: A method is provided for managing applications for sensors. In one embodiment, the method includes loading a plurality of applications and links for communicating with a plurality of sensors on a platform having an interface for entry of a requested use case; and copying a configuration from a grouping of application instances being applied to a first sensor performing in a function comprising of the requested use case. The method may further include applying the configuration for the grouping of application instances to a second set of sensors to automatically conform the plurality of sensors on the platform to perform the requested use case.

Patent Agency Ranking