公开(公告)号：US20220103985A1

公开(公告)日：2022-03-31

申请号：US17035939

申请日：2020-09-29

Applicant: Verizon Patent and Licensing Inc.

Inventor： Bhumip Khasnabish ,  Rohit Shirish Saraf

IPC: H04W4/40 ,  H04W48/18 ,  H04W76/10 ,  H04W4/50

Abstract: Systems and methods provide an intelligent vehicle to everything (iV2X) service that ensures robust communication of teleoperations and other data. An edge slice proxy system is used to incorporate edge platforms into network slicing considerations. A network device may receive a request for a connection from an end device, such as a vehicle requiring the iV2X service, via wireless signals. The network device may detect that the request is a request for an iV2X service and assign the end device to a network slice that supports stateful and robust iV2X services. The network slice may include one of the virtual network functions executed on the edge platform.

公开(公告)号：US20210409516A1

公开(公告)日：2021-12-30

申请号：US16917227

申请日：2020-06-30

Applicant: Verizon Patent and Licensing Inc.

Inventor： Rohit Shirish Saraf ,  Bhumip Khasnabish

IPC: H04L29/06 ,  G06T13/40 ,  H04L29/08

Abstract: Systems and methods provide an adaptive avatar-based real-time holographic communication service. End devices implement a customized avatar for holographic communications. With the assistance of a network edge platform, a user's facial motions and gestures are extracted in real time and applied to the customized avatar in the form of an augmented-reality-based or virtual-reality-based holographic entity. When a connection to the network edge platform is interrupted or not available, a master holographic entity provides a graceful fallback to a less resource-intensive avatar presentation using, for example, a user's prerecorded motions as a basis for rendering avatar movement. The customized avatar may be automatically adjusted/altered depending on with whom a user is communicating (e.g., a friend vs. a business associate) or a purpose for the communication (e.g., a professional meeting vs. a social activity).

公开(公告)号：US11617090B2

公开(公告)日：2023-03-28

申请号：US17674358

申请日：2022-02-17

Applicant: Verizon Patent and Licensing Inc.

Inventor： Bhumip Khasnabish ,  Rohit Shirish Saraf

IPC: H04W16/14 ,  H04W16/10 ,  H04W24/02 ,  H04W72/04 ,  H04W48/18 ,  H04W72/0453

Abstract: Provided are systems and methods for performing dynamic spectrum allocation and state shifting in order to provide high quality stateful services to user equipment (“UE”) that access the stateful services from different network locations. The dynamic spectrum allocation and state shifting may include tracking mobility of a UE accessing a stateful service using a first allocation of spectrum from a first Radio Access Network (“RAN”), predicting continued stateful service access via a second RAN, determining latency requirements of the stateful service, selecting a second allocation of spectrum at the second RAN with a frequency range that provides a first amount of latency, transferring the stateful service state to a Multi-Access Edge Computing (“MEC”) location that provides a second amount of latency for services accessed via the second RAN such that the first and second amounts of latency satisfy the performance requirements of the stateful service.

公开(公告)号：US20220038534A1

公开(公告)日：2022-02-03

申请号：US16944737

申请日：2020-07-31

Applicant: Verizon Patent and Licensing Inc.

Inventor： Rohit Shirish Saraf ,  Bhumip Khasnabish ,  John Aceron

IPC: H04L29/08 ,  G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Systems and methods described herein perform computer vision (CV) model training in a distributed edge network. Regional Multi-access Edge Compute (MEC) clusters are provided with a local copy of a CV model and a local synthetic training data generator. A MEC cluster receives client data requiring computer vision and applies the local copy of the CV model to the client data. The MEC cluster detects an exception to the local copy of the CV model and generates local synthetic training data for the exception. The MEC cluster updates, based on the local synthetic training data, the local copy of the CV model to form an updated local CV model. The MEC cluster sends the local synthetic training data and the updated local CV model to a central network. The central network uses the local synthetic training data to update a master CV model and any other interconnected CV models.