公开(公告)号：US12177932B2

公开(公告)日：2024-12-24

申请号：US18157251

申请日：2023-01-20

Applicant: Verizon Patent and Licensing Inc.

Inventor： Violeta Cakulev ,  James Mathison ,  Lalit R. Kotecha

IPC: H04W4/60 ,  H04W4/24 ,  H04W4/50 ,  H04W8/18 ,  H04W60/00

Abstract: A network device may receive a request for determination of a first non-session management policy control decision for a UE, and may provide an account limits request to another network device based on the request. The network device may receive, from the other network device, account limits for the UE, and may determine a first non-session management policy control service for the UE based on the account limits. The network device may cause the UE to be provisioned with a service based on the first non-session management policy control service, and may receive a request for determination of a second non-session management policy control decision for the UE. The network device may determine a second non-session management policy control service for the UE based on the account limits, and may cause the UE to be provisioned with a service based on the second non-session management policy control service.

公开(公告)号：US20240420442A1

公开(公告)日：2024-12-19

申请号：US18815909

申请日：2024-08-27

Applicant: Verizon Patent and Licensing Inc.

Inventor： Prakash RANGANATHAN ,  Saurabh TAHILIANI

IPC: G06V10/20 ,  G06N3/045 ,  G06V10/25 ,  G06V10/774 ,  G06V10/82

Abstract: A device may receive unprocessed images to be labeled, and may utilize a first neural network model to identify objects of interest in the unprocessed images and bounding boxes for the objects of interest. The device may annotate the objects of interest to generate annotated objects of interest, and may utilize a second neural network model to group the annotated objects of interest into clusters. The device may utilize a third neural network model to determine labels for the clusters, and may request manually-generated labels for clusters for which labels are not determined. The device may receive the manually-generated labels, and may label the unprocessed images with the labels and the manually-generated labels to generate labeled images. The device may generate a training dataset based on the labeled images, and may train a computer vision model with the training dataset to generate a trained computer vision model.

公开(公告)号：US12171042B2

公开(公告)日：2024-12-17

申请号：US18432827

申请日：2024-02-05

Applicant: Verizon Patent and Licensing Inc.

Inventor： Susan Wu Sanders ,  Jin Yang ,  Xin Wang ,  Nischal Patel

IPC: H04W76/28 ,  H04W72/542

Abstract: A base station may include a processor configured to configure a default time period for periodic service requests for discontinuous reception (DRX) for user equipment (UE) devices serviced by the base station. The processor may be further configured to obtain a signal quality value for a UE device serviced by the base station; determine that the obtained signal quality value is less than a low signal quality threshold; and configure a longer time period for the periodic service requests for DRX for the UE device, in response to determining that the obtained signal quality value is less than the low signal quality threshold.

公开(公告)号：US12170961B2

公开(公告)日：2024-12-17

申请号：US17714431

申请日：2022-04-06

Applicant: Verizon Patent and Licensing Inc.

Inventor： Mark T. Watts ,  Donna L. Polehn ,  David Taft ,  Corey J. Christopherson

IPC: H04W52/02 ,  H04W72/1268 ,  H04W72/23 ,  H04W76/10 ,  H04W76/28

Abstract: A method, a device, and a non-transitory computer-readable storage medium are described in which an predictive discontinuous reception (DRX) bypass service is provided. The bypass service may provide flow control signaling that enables an uplink grant to be transmitted to an end device regardless of the DRX mode. The bypass service may provide for an immediate grant for uplink data and may improve latency. The bypass service may also provide flow control signaling for downlink data that may cause the end device to wake up from a DRX mode and receive downlink data. The bypass service also provides predictive scheduling that allows an external network, such as a multi-access edge computing network to establish a DRX-free downlink connection before completion of data processing. The flow control signaling may include a quality of service flow identifier value that correlates to the bypass service.

公开(公告)号：US20240412132A1

公开(公告)日：2024-12-12

申请号：US18332174

申请日：2023-06-09

Applicant: Verizon Patent and Licensing Inc.

Inventor： Qiao Yu ,  John S. Mccormick ,  Amritham N. Koduvayur

IPC: G06Q10/0631

Abstract: A method, a device, and a non-transitory storage medium are described in which a machine learning-based project evaluation, prediction, and recommendation service is provided. The service may include obtaining performance data pertaining to key performance indicators (KPIs) and groups of a project and calculating affinity propagation using the performance data. The service may further include calculating prospective target KPI values for groups that may have deficient current KPI values based on similar performance data associated with other groups. The service may also include calculating time periods allotted to attain the prospective target KPI values.

公开(公告)号：US12167438B2

公开(公告)日：2024-12-10

申请号：US17659101

申请日：2022-04-13

Applicant: Verizon Patent and Licensing Inc.

Inventor： Jin Yang ,  Yuexin Dong ,  Frank Jager ,  Kristen Sydney Young

IPC: H04W72/56 ,  H04W28/02 ,  H04W28/10 ,  H04W48/02 ,  H04W64/00 ,  H04W72/54

Abstract: A system described herein may provide a technique for allocation and/or preemption of radio access network (“RAN”) resources in a wireless network based on Quality of Service (“QoS”)-related metrics associated with User Equipment (“UEs”) that are connected to, and/or are requesting connection to, a RAN. QoS-related metrics may include a network slice, a QoS Flow Identifier (“QFI”), other suitable metrics. A Slice-Based Priority (“SBP”) determine one or more priority (e.g., SBP) values for UEs connected to the one or more RANs, and/or for UEs requesting connection to such RANs. In addition to QoS-related metrics priority values may be determined based on RAN-related metrics, such as Allocation and Retention Priority (“ARP”) values associated with a UE. RANs may accordingly be able to allocate resources, accept or deny connection requests, and/or perform preemption based at least partly on slice-related QoS metrics, thus preserving end-to-end QoS parameters.

公开(公告)号：US20240403130A1

公开(公告)日：2024-12-05

申请号：US18203733

申请日：2023-05-31

Applicant: Verizon Patent and Licensing Inc.

Inventor： Myron E Bagwell ,  Kent S Gordon

IPC: G06F9/50 ,  G06F8/60

Abstract: One or more computing devices, systems, and/or methods are provided. In an embodiment, a method includes hosting a first application within a first container of a container hosting environment. A first peak resource usage for the first application is acquired. A first resource request is determined for the first application based on the first peak resource usage. A first resource limit for the first application is determined based on the first peak resource usage. An entity in the container hosting environment is redeployed based on the first resource request and the first resource limit.

公开(公告)号：US20240396966A1

公开(公告)日：2024-11-28

申请号：US18321112

申请日：2023-05-22

Applicant: Verizon Patent and Licensing Inc.

Inventor： Ahmed A. Khan ,  Abdul Raheem ,  David Szol ,  Mohammed Alsadi

IPC: H04L67/1095 ,  H04L67/1061

Abstract: A system described herein may receive ledger information based on contents of a distributed ledger maintained by a first set of nodes, receive communication information associated with the first set of nodes, and establish a second set of nodes. Establishing the second set of nodes may includes providing the ledger information to the second set of nodes, providing the communication information, associated with the first set of nodes, to the second set of nodes, and maintaining information that the second set of nodes are in a first state. After establishing the second set of nodes, the system may obtain sync information from the first set of nodes, provide the sync information to the second set of nodes, and based on providing the sync information to the second set of nodes, maintain information that the second set of nodes are in a second state.

公开(公告)号：US20240395081A1

公开(公告)日：2024-11-28

申请号：US18321580

申请日：2023-05-22

Applicant: Verizon Patent and Licensing Inc.

Inventor： Douglas COIMBRA DE ANDRADE ,  Leonardo SARTI ,  Tommaso BIANCONCINI ,  Lorenzo MOSCHI

IPC: G07C5/02 ,  G06N20/00 ,  G06V10/774 ,  G06V10/776 ,  G06V20/40 ,  G09B19/16

Abstract: A device may process video data, with a feature extraction model, to generate features, and may process a customer identifier, with an embedding layer, to generate an input. The device may optimize model weights for a classifier model and a customizer model, and may process the features, with the classifier model, to generate general predictions. The device may process the features, the input, and the general predictions, with the customizer model, to generate customer predictions, and may calculate first errors for the general predictions. The device may calculate second errors for the customer predictions, and may train the classifier model and the feature extraction model with the first errors and the optimized model weights. The device may train the customizer model and the embedding layer with the second errors and the optimized model weights. The device may implement the trained classifier model, feature extraction model, customizer model, and embedding layer.

公开(公告)号：US20240395038A1

公开(公告)日：2024-11-28

申请号：US18321589

申请日：2023-05-22

Applicant: Verizon Patent and Licensing Inc.

Inventor： Leonardo SARTI ,  Andrea BENERICETTI

IPC: G06V20/40 ,  G06V10/774 ,  G06V10/778

Abstract: A device may receive video data identifying videos, and may process the video data with a machine learning model, to determine classifications. The device may generate labels for the videos, and may calculate event severity scores and event severity labels. The device may calculate event severity incoherence scores, and may calculate user feedback scores of users associated with the device. The device may determine reviewer mistrust scores, and may calculate time review scores. The device may calculate reviewer bias scores, and may determine relabeling scores for the videos based on the event severity incoherence scores, the user feedback scores, the reviewer mistrust scores, the time review scores, and the reviewer bias scores. The device may generate new labels for one or more of the videos based on the relabeling scores, and may retrain the machine learning model, with the new labels, to generate a retrained machine learning model.